if (key->gc)
__set_bit(NFSD_FILE_GC, &nf->nf_flags);
nf->nf_inode = key->inode;
- /* nf_ref is pre-incremented for hash table */
- refcount_set(&nf->nf_ref, 2);
+ refcount_set(&nf->nf_ref, 1);
nf->nf_may = key->need;
nf->nf_mark = NULL;
}
return false;
}
-static bool
+static void
nfsd_file_free(struct nfsd_file *nf)
{
s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime));
- bool flush = false;
trace_nfsd_file_free(nf);
this_cpu_inc(nfsd_file_releases);
this_cpu_add(nfsd_file_total_age, age);
+ nfsd_file_unhash(nf);
+
+ /*
+ * We call fsync here in order to catch writeback errors. It's not
+ * strictly required by the protocol, but an nfsd_file could get
+ * evicted from the cache before a COMMIT comes in. If another
+ * task were to open that file in the interim and scrape the error,
+ * then the client may never see it. By calling fsync here, we ensure
+ * that writeback happens before the entry is freed, and that any
+ * errors reported result in the write verifier changing.
+ */
+ nfsd_file_fsync(nf);
+
if (nf->nf_mark)
nfsd_file_mark_put(nf->nf_mark);
if (nf->nf_file) {
get_file(nf->nf_file);
filp_close(nf->nf_file, NULL);
fput(nf->nf_file);
- flush = true;
}
/*
* WARN and leak it to preserve system stability.
*/
if (WARN_ON_ONCE(!list_empty(&nf->nf_lru)))
- return flush;
+ return;
call_rcu(&nf->nf_rcu, nfsd_file_slab_free);
- return flush;
}
static bool
mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
}
-static void nfsd_file_lru_add(struct nfsd_file *nf)
+static bool nfsd_file_lru_add(struct nfsd_file *nf)
{
set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
- if (list_lru_add(&nfsd_file_lru, &nf->nf_lru))
+ if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) {
trace_nfsd_file_lru_add(nf);
+ return true;
+ }
+ return false;
}
-static void nfsd_file_lru_remove(struct nfsd_file *nf)
+static bool nfsd_file_lru_remove(struct nfsd_file *nf)
{
- if (list_lru_del(&nfsd_file_lru, &nf->nf_lru))
+ if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) {
trace_nfsd_file_lru_del(nf);
+ return true;
+ }
+ return false;
}
struct nfsd_file *
return NULL;
}
-static void
-nfsd_file_unhash_and_queue(struct nfsd_file *nf, struct list_head *dispose)
-{
- trace_nfsd_file_unhash_and_queue(nf);
- if (nfsd_file_unhash(nf)) {
- /* caller must call nfsd_file_dispose_list() later */
- nfsd_file_lru_remove(nf);
- list_add(&nf->nf_lru, dispose);
- }
-}
-
-static void
-nfsd_file_put_noref(struct nfsd_file *nf)
-{
- trace_nfsd_file_put(nf);
-
- if (refcount_dec_and_test(&nf->nf_ref)) {
- WARN_ON(test_bit(NFSD_FILE_HASHED, &nf->nf_flags));
- nfsd_file_lru_remove(nf);
- nfsd_file_free(nf);
- }
-}
-
-static void
-nfsd_file_unhash_and_put(struct nfsd_file *nf)
-{
- if (nfsd_file_unhash(nf))
- nfsd_file_put_noref(nf);
-}
-
+/**
+ * nfsd_file_put - put the reference to a nfsd_file
+ * @nf: nfsd_file of which to put the reference
+ *
+ * Put a reference to a nfsd_file. In the non-GC case, we just put the
+ * reference immediately. In the GC case, if the reference would be
+ * the last one, the put it on the LRU instead to be cleaned up later.
+ */
void
nfsd_file_put(struct nfsd_file *nf)
{
might_sleep();
+ trace_nfsd_file_put(nf);
- if (test_bit(NFSD_FILE_GC, &nf->nf_flags))
- nfsd_file_lru_add(nf);
- else if (refcount_read(&nf->nf_ref) == 2)
- nfsd_file_unhash_and_put(nf);
-
- if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
- nfsd_file_fsync(nf);
- nfsd_file_put_noref(nf);
- } else if (nf->nf_file && test_bit(NFSD_FILE_GC, &nf->nf_flags)) {
- nfsd_file_put_noref(nf);
- nfsd_file_schedule_laundrette();
- } else
- nfsd_file_put_noref(nf);
-}
-
-static void
-nfsd_file_dispose_list(struct list_head *dispose)
-{
- struct nfsd_file *nf;
+ if (test_bit(NFSD_FILE_GC, &nf->nf_flags) &&
+ test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+ /*
+ * If this is the last reference (nf_ref == 1), then try to
+ * transfer it to the LRU.
+ */
+ if (refcount_dec_not_one(&nf->nf_ref))
+ return;
+
+ /* Try to add it to the LRU. If that fails, decrement. */
+ if (nfsd_file_lru_add(nf)) {
+ /* If it's still hashed, we're done */
+ if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+ nfsd_file_schedule_laundrette();
+ return;
+ }
- while(!list_empty(dispose)) {
- nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
- list_del_init(&nf->nf_lru);
- nfsd_file_fsync(nf);
- nfsd_file_put_noref(nf);
+ /*
+ * We're racing with unhashing, so try to remove it from
+ * the LRU. If removal fails, then someone else already
+ * has our reference.
+ */
+ if (!nfsd_file_lru_remove(nf))
+ return;
+ }
}
+ if (refcount_dec_and_test(&nf->nf_ref))
+ nfsd_file_free(nf);
}
static void
-nfsd_file_dispose_list_sync(struct list_head *dispose)
+nfsd_file_dispose_list(struct list_head *dispose)
{
- bool flush = false;
struct nfsd_file *nf;
- while(!list_empty(dispose)) {
+ while (!list_empty(dispose)) {
nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
list_del_init(&nf->nf_lru);
- nfsd_file_fsync(nf);
- if (!refcount_dec_and_test(&nf->nf_ref))
- continue;
- if (nfsd_file_free(nf))
- flush = true;
+ nfsd_file_free(nf);
}
- if (flush)
- flush_delayed_fput();
}
static void
struct list_head *head = arg;
struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru);
- /*
- * Do a lockless refcount check. The hashtable holds one reference, so
- * we look to see if anything else has a reference, or if any have
- * been put since the shrinker last ran. Those don't get unhashed and
- * released.
- *
- * Note that in the put path, we set the flag and then decrement the
- * counter. Here we check the counter and then test and clear the flag.
- * That order is deliberate to ensure that we can do this locklessly.
- */
- if (refcount_read(&nf->nf_ref) > 1) {
- list_lru_isolate(lru, &nf->nf_lru);
- trace_nfsd_file_gc_in_use(nf);
- return LRU_REMOVED;
- }
+ /* We should only be dealing with GC entries here */
+ WARN_ON_ONCE(!test_bit(NFSD_FILE_GC, &nf->nf_flags));
/*
* Don't throw out files that are still undergoing I/O or
return LRU_SKIP;
}
+ /* If it was recently added to the list, skip it */
if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags)) {
trace_nfsd_file_gc_referenced(nf);
return LRU_ROTATE;
}
- if (!test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
- trace_nfsd_file_gc_hashed(nf);
- return LRU_SKIP;
+ /*
+ * Put the reference held on behalf of the LRU. If it wasn't the last
+ * one, then just remove it from the LRU and ignore it.
+ */
+ if (!refcount_dec_and_test(&nf->nf_ref)) {
+ trace_nfsd_file_gc_in_use(nf);
+ list_lru_isolate(lru, &nf->nf_lru);
+ return LRU_REMOVED;
}
+ /* Refcount went to zero. Unhash it and queue it to the dispose list */
+ nfsd_file_unhash(nf);
list_lru_isolate_move(lru, &nf->nf_lru, head);
this_cpu_inc(nfsd_file_evictions);
trace_nfsd_file_gc_disposed(nf);
return LRU_REMOVED;
}
-/*
- * Unhash items on @dispose immediately, then queue them on the
- * disposal workqueue to finish releasing them in the background.
- *
- * cel: Note that between the time list_lru_shrink_walk runs and
- * now, these items are in the hash table but marked unhashed.
- * Why release these outside of lru_cb ? There's no lock ordering
- * problem since lru_cb currently takes no lock.
- */
-static void nfsd_file_gc_dispose_list(struct list_head *dispose)
-{
- struct nfsd_file *nf;
-
- list_for_each_entry(nf, dispose, nf_lru)
- nfsd_file_hash_remove(nf);
- nfsd_file_dispose_list_delayed(dispose);
-}
-
static void
nfsd_file_gc(void)
{
ret = list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb,
&dispose, list_lru_count(&nfsd_file_lru));
trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru));
- nfsd_file_gc_dispose_list(&dispose);
+ nfsd_file_dispose_list_delayed(&dispose);
}
static void
ret = list_lru_shrink_walk(&nfsd_file_lru, sc,
nfsd_file_lru_cb, &dispose);
trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru));
- nfsd_file_gc_dispose_list(&dispose);
+ nfsd_file_dispose_list_delayed(&dispose);
return ret;
}
.seeks = 1,
};
-/*
- * Find all cache items across all net namespaces that match @inode and
- * move them to @dispose. The lookup is atomic wrt nfsd_file_acquire().
+/**
+ * nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode
+ * @inode: inode on which to close out nfsd_files
+ * @dispose: list on which to gather nfsd_files to close out
+ *
+ * An nfsd_file represents a struct file being held open on behalf of nfsd. An
+ * open file however can block other activity (such as leases), or cause
+ * undesirable behavior (e.g. spurious silly-renames when reexporting NFS).
+ *
+ * This function is intended to find open nfsd_files when this sort of
+ * conflicting access occurs and then attempt to close those files out.
+ *
+ * Populates the dispose list with entries that have already had their
+ * refcounts go to zero. The actual free of an nfsd_file can be expensive,
+ * so we leave it up to the caller whether it wants to wait or not.
*/
-static unsigned int
-__nfsd_file_close_inode(struct inode *inode, struct list_head *dispose)
+static void
+nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose)
{
struct nfsd_file_lookup_key key = {
.type = NFSD_FILE_KEY_INODE,
.inode = inode,
};
- unsigned int count = 0;
struct nfsd_file *nf;
rcu_read_lock();
do {
+ int decrement = 1;
+
nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key,
nfsd_file_rhash_params);
if (!nf)
break;
- nfsd_file_unhash_and_queue(nf, dispose);
- count++;
+
+ /* If we raced with someone else unhashing, ignore it */
+ if (!nfsd_file_unhash(nf))
+ continue;
+
+ /* If we can't get a reference, ignore it */
+ if (!nfsd_file_get(nf))
+ continue;
+
+ /* Extra decrement if we remove from the LRU */
+ if (nfsd_file_lru_remove(nf))
+ ++decrement;
+
+ /* If refcount goes to 0, then put on the dispose list */
+ if (refcount_sub_and_test(decrement, &nf->nf_ref)) {
+ list_add(&nf->nf_lru, dispose);
+ trace_nfsd_file_closing(nf);
+ }
} while (1);
rcu_read_unlock();
- return count;
}
/**
- * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file
+ * nfsd_file_close_inode - attempt a delayed close of a nfsd_file
* @inode: inode of the file to attempt to remove
*
- * Unhash and put, then flush and fput all cache items associated with @inode.
+ * Close out any open nfsd_files that can be reaped for @inode. The
+ * actual freeing is deferred to the dispose_list_delayed infrastructure.
+ *
+ * This is used by the fsnotify callbacks and setlease notifier.
*/
-void
-nfsd_file_close_inode_sync(struct inode *inode)
+static void
+nfsd_file_close_inode(struct inode *inode)
{
LIST_HEAD(dispose);
- unsigned int count;
- count = __nfsd_file_close_inode(inode, &dispose);
- trace_nfsd_file_close_inode_sync(inode, count);
- nfsd_file_dispose_list_sync(&dispose);
+ nfsd_file_queue_for_close(inode, &dispose);
+ nfsd_file_dispose_list_delayed(&dispose);
}
/**
- * nfsd_file_close_inode - attempt a delayed close of a nfsd_file
+ * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file
* @inode: inode of the file to attempt to remove
*
- * Unhash and put all cache item associated with @inode.
+ * Close out any open nfsd_files that can be reaped for @inode. The
+ * nfsd_files are closed out synchronously.
+ *
+ * This is called from nfsd_rename and nfsd_unlink to avoid silly-renames
+ * when reexporting NFS.
*/
-static void
-nfsd_file_close_inode(struct inode *inode)
+void
+nfsd_file_close_inode_sync(struct inode *inode)
{
+ struct nfsd_file *nf;
LIST_HEAD(dispose);
- unsigned int count;
- count = __nfsd_file_close_inode(inode, &dispose);
- trace_nfsd_file_close_inode(inode, count);
- nfsd_file_dispose_list_delayed(&dispose);
+ trace_nfsd_file_close(inode);
+
+ nfsd_file_queue_for_close(inode, &dispose);
+ while (!list_empty(&dispose)) {
+ nf = list_first_entry(&dispose, struct nfsd_file, nf_lru);
+ list_del_init(&nf->nf_lru);
+ nfsd_file_free(nf);
+ }
+ flush_delayed_fput();
}
/**
* nfsd_file_delayed_close - close unused nfsd_files
* @work: dummy
*
- * Walk the LRU list and close any entries that have not been used since
+ * Walk the LRU list and destroy any entries that have not been used since
* the last scan.
*/
static void
/* Only close files for F_SETLEASE leases */
if (fl->fl_flags & FL_LEASE)
- nfsd_file_close_inode_sync(file_inode(fl->fl_file));
+ nfsd_file_close_inode(file_inode(fl->fl_file));
return 0;
}
goto out;
}
+/**
+ * __nfsd_file_cache_purge: clean out the cache for shutdown
+ * @net: net-namespace to shut down the cache (may be NULL)
+ *
+ * Walk the nfsd_file cache and close out any that match @net. If @net is NULL,
+ * then close out everything. Called when an nfsd instance is being shut down.
+ */
static void
__nfsd_file_cache_purge(struct net *net)
{
nf = rhashtable_walk_next(&iter);
while (!IS_ERR_OR_NULL(nf)) {
- if (!net || nf->nf_net == net)
- nfsd_file_unhash_and_queue(nf, &dispose);
+ if (!net || nf->nf_net == net) {
+ nfsd_file_unhash(nf);
+ nfsd_file_lru_remove(nf);
+ list_add(&nf->nf_lru, &dispose);
+ }
nf = rhashtable_walk_next(&iter);
}
if (nf)
nf = nfsd_file_get(nf);
rcu_read_unlock();
- if (nf)
+
+ if (nf) {
+ if (nfsd_file_lru_remove(nf))
+ WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref));
goto wait_for_construction;
+ }
nf = nfsd_file_alloc(&key, may_flags);
if (!nf) {
goto out;
}
open_retry = false;
- nfsd_file_put_noref(nf);
+ if (refcount_dec_and_test(&nf->nf_ref))
+ nfsd_file_free(nf);
goto retry;
}
- nfsd_file_lru_remove(nf);
this_cpu_inc(nfsd_file_cache_hits);
status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags));
this_cpu_inc(nfsd_file_acquisitions);
*pnf = nf;
} else {
- nfsd_file_put(nf);
+ if (refcount_dec_and_test(&nf->nf_ref))
+ nfsd_file_free(nf);
nf = NULL;
}
* If construction failed, or we raced with a call to unlink()
* then unhash.
*/
- if (status != nfs_ok || key.inode->i_nlink == 0)
- nfsd_file_unhash_and_put(nf);
+ if (status == nfs_ok && key.inode->i_nlink == 0)
+ status = nfserr_jukebox;
+ if (status != nfs_ok)
+ nfsd_file_unhash(nf);
clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags);
smp_mb__after_atomic();
wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING);
__print_flags(val, "|", \
{ 1 << NFSD_FILE_HASHED, "HASHED" }, \
{ 1 << NFSD_FILE_PENDING, "PENDING" }, \
- { 1 << NFSD_FILE_REFERENCED, "REFERENCED"}, \
- { 1 << NFSD_FILE_GC, "GC"})
+ { 1 << NFSD_FILE_REFERENCED, "REFERENCED" }, \
+ { 1 << NFSD_FILE_GC, "GC" })
DECLARE_EVENT_CLASS(nfsd_file_class,
TP_PROTO(struct nfsd_file *nf),
DEFINE_NFSD_FILE_EVENT(nfsd_file_free);
DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash);
DEFINE_NFSD_FILE_EVENT(nfsd_file_put);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_closing);
DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_queue);
TRACE_EVENT(nfsd_file_alloc,
__entry->nf_file)
)
-DECLARE_EVENT_CLASS(nfsd_file_search_class,
- TP_PROTO(
- const struct inode *inode,
- unsigned int count
- ),
- TP_ARGS(inode, count),
- TP_STRUCT__entry(
- __field(const struct inode *, inode)
- __field(unsigned int, count)
- ),
- TP_fast_assign(
- __entry->inode = inode;
- __entry->count = count;
- ),
- TP_printk("inode=%p count=%u",
- __entry->inode, __entry->count)
-);
-
-#define DEFINE_NFSD_FILE_SEARCH_EVENT(name) \
-DEFINE_EVENT(nfsd_file_search_class, name, \
- TP_PROTO( \
- const struct inode *inode, \
- unsigned int count \
- ), \
- TP_ARGS(inode, count))
-
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync);
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode);
-
TRACE_EVENT(nfsd_file_is_cached,
TP_PROTO(
const struct inode *inode,
DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use);
DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback);
DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced);
-DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_hashed);
DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed);
DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class,
DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed);
DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed);
+TRACE_EVENT(nfsd_file_close,
+ TP_PROTO(
+ const struct inode *inode
+ ),
+ TP_ARGS(inode),
+ TP_STRUCT__entry(
+ __field(const void *, inode)
+ ),
+ TP_fast_assign(
+ __entry->inode = inode;
+ ),
+ TP_printk("inode=%p",
+ __entry->inode
+ )
+);
+
TRACE_EVENT(nfsd_file_fsync,
TP_PROTO(
const struct nfsd_file *nf,
projects / users / hch / xfs.git / commitdiff