summaryrefslogtreecommitdiff
path: root/fs/nfsd
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfsd')
-rw-r--r--fs/nfsd/filecache.c367
-rw-r--r--fs/nfsd/filecache.h5
-rw-r--r--fs/nfsd/netns.h2
-rw-r--r--fs/nfsd/nfs4callback.c6
-rw-r--r--fs/nfsd/nfs4proc.c28
-rw-r--r--fs/nfsd/nfs4state.c46
-rw-r--r--fs/nfsd/nfs4xdr.c13
-rw-r--r--fs/nfsd/nfsctl.c7
-rw-r--r--fs/nfsd/nfsd.h6
-rw-r--r--fs/nfsd/nfsproc.c4
-rw-r--r--fs/nfsd/nfssvc.c2
-rw-r--r--fs/nfsd/trace.h95
12 files changed, 284 insertions, 297 deletions
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 1998b4d5f692..c0950edb26b0 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -324,8 +324,7 @@ nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may)
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;
}
@@ -377,24 +376,35 @@ nfsd_file_unhash(struct nfsd_file *nf)
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;
}
/*
@@ -402,10 +412,9 @@ nfsd_file_free(struct nfsd_file *nf)
* 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
@@ -421,17 +430,23 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
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 *
@@ -442,86 +457,60 @@ nfsd_file_get(struct nfsd_file *nf)
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
@@ -591,21 +580,8 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
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
@@ -616,40 +592,30 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
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)
{
@@ -659,7 +625,7 @@ 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
@@ -685,7 +651,7 @@ nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc)
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;
}
@@ -695,18 +661,62 @@ static struct shrinker nfsd_file_shrinker = {
.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_cond_queue - conditionally unhash and queue a nfsd_file
+ * @nf: nfsd_file to attempt to queue
+ * @dispose: private list to queue successfully-put objects
+ *
+ * Unhash an nfsd_file, try to get a reference to it, and then put that
+ * reference. If it's the last reference, queue it to the dispose list.
+ */
+static void
+nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose)
+ __must_hold(RCU)
+{
+ int decrement = 1;
+
+ /* If we raced with someone else unhashing, ignore it */
+ if (!nfsd_file_unhash(nf))
+ return;
+
+ /* If we can't get a reference, ignore it */
+ if (!nfsd_file_get(nf))
+ return;
+
+ /* 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);
+ }
+}
+
+/**
+ * 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();
@@ -715,52 +725,61 @@ __nfsd_file_close_inode(struct inode *inode, struct list_head *dispose)
nfsd_file_rhash_params);
if (!nf)
break;
- nfsd_file_unhash_and_queue(nf, dispose);
- count++;
+ nfsd_file_cond_queue(nf, dispose);
} 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
@@ -782,7 +801,7 @@ nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg,
/* 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;
}
@@ -903,6 +922,13 @@ out_err:
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)
{
@@ -917,7 +943,7 @@ __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);
+ nfsd_file_cond_queue(nf, &dispose);
nf = rhashtable_walk_next(&iter);
}
@@ -1056,8 +1082,8 @@ nfsd_file_is_cached(struct inode *inode)
static __be32
nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf,
- bool open, bool want_gc)
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf, bool want_gc)
{
struct nfsd_file_lookup_key key = {
.type = NFSD_FILE_KEY_FULL,
@@ -1084,8 +1110,12 @@ retry:
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) {
@@ -1118,48 +1148,53 @@ wait_for_construction:
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));
out:
if (status == nfs_ok) {
- if (open)
- this_cpu_inc(nfsd_file_acquisitions);
+ 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;
}
out_status:
put_cred(key.cred);
- if (open)
- trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
+ trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
return status;
open_file:
trace_nfsd_file_alloc(nf);
nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode);
if (nf->nf_mark) {
- if (open) {
+ if (file) {
+ get_file(file);
+ nf->nf_file = file;
+ status = nfs_ok;
+ trace_nfsd_file_opened(nf, status);
+ } else {
status = nfsd_open_verified(rqstp, fhp, may_flags,
&nf->nf_file);
trace_nfsd_file_open(nf, status);
- } else
- status = nfs_ok;
+ }
} else
status = nfserr_jukebox;
/*
* 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);
@@ -1185,7 +1220,7 @@ __be32
nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true);
}
/**
@@ -1206,28 +1241,30 @@ __be32
nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false);
}
/**
- * nfsd_file_create - Get a struct nfsd_file, do not open
+ * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file
* @rqstp: the RPC transaction being executed
* @fhp: the NFS filehandle of the file just created
* @may_flags: NFSD_MAY_ settings for the file
+ * @file: cached, already-open file (may be NULL)
* @pnf: OUT: new or found "struct nfsd_file" object
*
- * The nfsd_file_object returned by this API is reference-counted
- * but not garbage-collected. The object is released immediately
- * one RCU grace period after the final nfsd_file_put().
+ * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist,
+ * and @file is non-NULL, use it to instantiate a new nfsd_file instead of
+ * opening a new one.
*
* Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
* network byte order is returned.
*/
__be32
-nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf)
+nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false);
}
/*
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index b7efb2c3ddb1..41516a4263ea 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -60,7 +60,8 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **nfp);
__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **nfp);
-__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **nfp);
int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
#endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 8c854ba3285b..51a4b7885cae 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -195,7 +195,7 @@ struct nfsd_net {
atomic_t nfsd_courtesy_clients;
struct shrinker nfsd_client_shrinker;
- struct delayed_work nfsd_shrinker_work;
+ struct work_struct nfsd_shrinker_work;
};
/* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 1b57f2c2f0bb..2a815f5a52c4 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -942,7 +942,7 @@ static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct r
} else {
struct cred *kcred;
- kcred = prepare_kernel_cred(NULL);
+ kcred = prepare_kernel_cred(&init_task);
if (!kcred)
return NULL;
@@ -988,7 +988,6 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
} else {
if (!conn->cb_xprt)
return -EINVAL;
- clp->cl_cb_conn.cb_xprt = conn->cb_xprt;
clp->cl_cb_session = ses;
args.bc_xprt = conn->cb_xprt;
args.prognumber = clp->cl_cb_session->se_cb_prog;
@@ -1008,6 +1007,9 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
rpc_shutdown_client(client);
return -ENOMEM;
}
+
+ if (clp->cl_minorversion != 0)
+ clp->cl_cb_conn.cb_xprt = conn->cb_xprt;
clp->cl_cb_client = client;
clp->cl_cb_cred = cred;
rcu_read_lock();
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 73ed32ad23a2..f189ba7995f5 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -937,7 +937,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* the client wants us to do more in this compound:
*/
if (!nfsd4_last_compound_op(rqstp))
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
@@ -1318,6 +1318,7 @@ try_again:
/* allow 20secs for mount/unmount for now - revisit */
if (signal_pending(current) ||
(schedule_timeout(20*HZ) == 0)) {
+ finish_wait(&nn->nfsd_ssc_waitq, &wait);
kfree(work);
return nfserr_eagain;
}
@@ -1461,13 +1462,6 @@ out_err:
return status;
}
-static void
-nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
-{
- nfs_do_sb_deactive(ss_mnt->mnt_sb);
- mntput(ss_mnt);
-}
-
/*
* Verify COPY destination stateid.
*
@@ -1570,11 +1564,6 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp,
{
}
-static void
-nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
-{
-}
-
static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
struct nfs_fh *src_fh,
nfs4_stateid *stateid)
@@ -1770,7 +1759,7 @@ static int nfsd4_do_async_copy(void *data)
default:
nfserr = nfserr_offload_denied;
}
- nfsd4_interssc_disconnect(copy->ss_mnt);
+ /* ss_mnt will be unmounted by the laundromat */
goto do_callback;
}
nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file,
@@ -1851,8 +1840,10 @@ out_err:
if (async_copy)
cleanup_async_copy(async_copy);
status = nfserrno(-ENOMEM);
- if (nfsd4_ssc_is_inter(copy))
- nfsd4_interssc_disconnect(copy->ss_mnt);
+ /*
+ * source's vfsmount of inter-copy will be unmounted
+ * by the laundromat
+ */
goto out;
}
@@ -2617,12 +2608,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
cstate->minorversion = args->minorversion;
fh_init(current_fh, NFS4_FHSIZE);
fh_init(save_fh, NFS4_FHSIZE);
-
/*
* Don't use the deferral mechanism for NFSv4; compounds make it
* too hard to avoid non-idempotency problems.
*/
- __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
/*
* According to RFC3010, this takes precedence over all other errors.
@@ -2744,7 +2734,7 @@ encode_op:
out:
cstate->status = status;
/* Reset deferral mechanism for RPC deferrals */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
return rpc_success;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7b2ee535ade8..4ef529379065 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4411,7 +4411,7 @@ nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc)
if (!count)
count = atomic_long_read(&num_delegations);
if (count)
- mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+ queue_work(laundry_wq, &nn->nfsd_shrinker_work);
return (unsigned long)count;
}
@@ -4421,7 +4421,7 @@ nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc)
return SHRINK_STOP;
}
-int
+void
nfsd4_init_leases_net(struct nfsd_net *nn)
{
struct sysinfo si;
@@ -4443,16 +4443,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn)
nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
atomic_set(&nn->nfsd_courtesy_clients, 0);
- nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
- nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
- nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
- return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
-}
-
-void
-nfsd4_leases_net_shutdown(struct nfsd_net *nn)
-{
- unregister_shrinker(&nn->nfsd_client_shrinker);
}
static void init_nfs4_replay(struct nfs4_replay *rp)
@@ -5262,18 +5252,10 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
if (!fp->fi_fds[oflag]) {
spin_unlock(&fp->fi_lock);
- if (!open->op_filp) {
- status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- } else {
- status = nfsd_file_create(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- nf->nf_file = open->op_filp;
- open->op_filp = NULL;
- trace_nfsd_file_create(rqstp, access, nf);
- }
+ status = nfsd_file_acquire_opened(rqstp, cur_fh, access,
+ open->op_filp, &nf);
+ if (status != nfs_ok)
+ goto out_put_access;
spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
@@ -6243,8 +6225,7 @@ deleg_reaper(struct nfsd_net *nn)
static void
nfsd4_state_shrinker_worker(struct work_struct *work)
{
- struct delayed_work *dwork = to_delayed_work(work);
- struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ struct nfsd_net *nn = container_of(work, struct nfsd_net,
nfsd_shrinker_work);
courtesy_client_reaper(nn);
@@ -8074,11 +8055,20 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->blocked_locks_lru);
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
- INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
+ INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
get_net(net);
+ nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
+ nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
+ nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+
+ if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"))
+ goto err_shrinker;
return 0;
+err_shrinker:
+ put_net(net);
+ kfree(nn->sessionid_hashtbl);
err_sessionid:
kfree(nn->unconf_id_hashtbl);
err_unconf_id:
@@ -8171,6 +8161,8 @@ nfs4_state_shutdown_net(struct net *net)
struct list_head *pos, *next, reaplist;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ unregister_shrinker(&nn->nfsd_client_shrinker);
+ cancel_work(&nn->nfsd_shrinker_work);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2b4ae858c89b..97edb32be77f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2523,7 +2523,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
- __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
return true;
}
@@ -3629,6 +3629,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
case nfserr_noent:
xdr_truncate_encode(xdr, start_offset);
goto skip_entry;
+ case nfserr_jukebox:
+ /*
+ * The pseudoroot should only display dentries that lead to
+ * exports. If we get EJUKEBOX here, then we can't tell whether
+ * this entry should be included. Just fail the whole READDIR
+ * with NFS4ERR_DELAY in that case, and hope that the situation
+ * will resolve itself by the client's next attempt.
+ */
+ if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT)
+ goto fail;
+ fallthrough;
default:
/*
* If the client requested the RDATTR_ERROR attribute,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index d1e581a60480..c2577ee7ffb2 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1457,9 +1457,7 @@ static __net_init int nfsd_init_net(struct net *net)
goto out_idmap_error;
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
- retval = nfsd4_init_leases_net(nn);
- if (retval)
- goto out_drc_error;
+ nfsd4_init_leases_net(nn);
retval = nfsd_reply_cache_init(nn);
if (retval)
goto out_cache_error;
@@ -1469,8 +1467,6 @@ static __net_init int nfsd_init_net(struct net *net)
return 0;
out_cache_error:
- nfsd4_leases_net_shutdown(nn);
-out_drc_error:
nfsd_idmap_shutdown(net);
out_idmap_error:
nfsd_export_shutdown(net);
@@ -1486,7 +1482,6 @@ static __net_exit void nfsd_exit_net(struct net *net)
nfsd_idmap_shutdown(net);
nfsd_export_shutdown(net);
nfsd_netns_free_versions(net_generic(net, nfsd_net_id));
- nfsd4_leases_net_shutdown(nn);
}
static struct pernet_operations nfsd_net_ops = {
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 93b42ef9ed91..fa0144a74267 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -504,8 +504,7 @@ extern void unregister_cld_notifier(void);
extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
#endif
-extern int nfsd4_init_leases_net(struct nfsd_net *nn);
-extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn);
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
#else /* CONFIG_NFSD_V4 */
static inline int nfsd4_is_junction(struct dentry *dentry)
@@ -513,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry)
return 0;
}
-static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; };
-static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {};
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };
#define register_cld_notifier() 0
#define unregister_cld_notifier() do { } while(0)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a5570cf75f3f..9744443c3965 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
@@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp)
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 56fba1cba3af..325d3d3f1211 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -453,8 +453,8 @@ static void nfsd_shutdown_net(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- nfsd_file_cache_shutdown_net(net);
nfs4_state_shutdown_net(net);
+ nfsd_file_cache_shutdown_net(net);
if (nn->lockd_up) {
lockd_down(net);
nn->lockd_up = false;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 46b8f68a2497..8f9c82d9e075 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -876,8 +876,8 @@ DEFINE_CLID_EVENT(confirmed_r);
__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),
@@ -912,6 +912,7 @@ DEFINE_EVENT(nfsd_file_class, name, \
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,
@@ -980,43 +981,6 @@ TRACE_EVENT(nfsd_file_acquire,
)
);
-TRACE_EVENT(nfsd_file_create,
- TP_PROTO(
- const struct svc_rqst *rqstp,
- unsigned int may_flags,
- const struct nfsd_file *nf
- ),
-
- TP_ARGS(rqstp, may_flags, nf),
-
- TP_STRUCT__entry(
- __field(const void *, nf_inode)
- __field(const void *, nf_file)
- __field(unsigned long, may_flags)
- __field(unsigned long, nf_flags)
- __field(unsigned long, nf_may)
- __field(unsigned int, nf_ref)
- __field(u32, xid)
- ),
-
- TP_fast_assign(
- __entry->nf_inode = nf->nf_inode;
- __entry->nf_file = nf->nf_file;
- __entry->may_flags = may_flags;
- __entry->nf_flags = nf->nf_flags;
- __entry->nf_may = nf->nf_may;
- __entry->nf_ref = refcount_read(&nf->nf_ref);
- __entry->xid = be32_to_cpu(rqstp->rq_xid);
- ),
-
- TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p",
- __entry->xid, __entry->nf_inode,
- show_nfsd_may_flags(__entry->may_flags),
- __entry->nf_ref, show_nf_flags(__entry->nf_flags),
- show_nfsd_may_flags(__entry->nf_may), __entry->nf_file
- )
-);
-
TRACE_EVENT(nfsd_file_insert_err,
TP_PROTO(
const struct svc_rqst *rqstp,
@@ -1078,8 +1042,8 @@ TRACE_EVENT(nfsd_file_cons_err,
)
);
-TRACE_EVENT(nfsd_file_open,
- TP_PROTO(struct nfsd_file *nf, __be32 status),
+DECLARE_EVENT_CLASS(nfsd_file_open_class,
+ TP_PROTO(const struct nfsd_file *nf, __be32 status),
TP_ARGS(nf, status),
TP_STRUCT__entry(
__field(void *, nf_inode) /* cannot be dereferenced */
@@ -1103,34 +1067,16 @@ TRACE_EVENT(nfsd_file_open,
__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, \
+#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \
+DEFINE_EVENT(nfsd_file_open_class, name, \
TP_PROTO( \
- const struct inode *inode, \
- unsigned int count \
+ const struct nfsd_file *nf, \
+ __be32 status \
), \
- TP_ARGS(inode, count))
+ TP_ARGS(nf, status))
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync);
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode);
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open);
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened);
TRACE_EVENT(nfsd_file_is_cached,
TP_PROTO(
@@ -1209,7 +1155,6 @@ DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed);
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,
@@ -1241,6 +1186,22 @@ DEFINE_EVENT(nfsd_file_lruwalk_class, name, \
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,