1 files changed, 177 insertions, 79 deletions

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 9cb7f0c33df5..fb9b1656a287 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -39,6 +39,7 @@
 #include <linux/fsnotify.h>
 #include <linux/seq_file.h>
 #include <linux/rhashtable.h>
+#include <linux/nfslocalio.h>
 
 #include "vfs.h"
 #include "nfsd.h"
@@ -52,22 +53,20 @@
 #define NFSD_FILE_CACHE_UP		     (0)
 
 /* We only care about NFSD_MAY_READ/WRITE for this cache */
-#define NFSD_FILE_MAY_MASK	(NFSD_MAY_READ|NFSD_MAY_WRITE)
+#define NFSD_FILE_MAY_MASK	(NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO)
 
 static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
+static DEFINE_PER_CPU(unsigned long, nfsd_file_allocations);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_releases);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions);
 
 struct nfsd_fcache_disposal {
-	struct work_struct work;
 	spinlock_t lock;
 	struct list_head freeme;
 };
 
-static struct workqueue_struct *nfsd_filecache_wq __read_mostly;
-
 static struct kmem_cache		*nfsd_file_slab;
 static struct kmem_cache		*nfsd_file_mark_slab;
 static struct list_lru			nfsd_file_lru;
@@ -114,7 +113,7 @@ static void
 nfsd_file_schedule_laundrette(void)
 {
 	if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags))
-		queue_delayed_work(system_wq, &nfsd_filecache_laundrette,
+		queue_delayed_work(system_unbound_wq, &nfsd_filecache_laundrette,
 				   NFSD_LAUNDRETTE_DELAY);
 }
 
@@ -154,7 +153,7 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm)
 }
 
 static struct nfsd_file_mark *
-nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode)
+nfsd_file_mark_find_or_create(struct inode *inode)
 {
 	int			err;
 	struct fsnotify_mark	*mark;
@@ -162,8 +161,8 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode)
 
 	do {
 		fsnotify_group_lock(nfsd_file_fsnotify_group);
-		mark = fsnotify_find_mark(&inode->i_fsnotify_marks,
-					  nfsd_file_fsnotify_group);
+		mark = fsnotify_find_inode_mark(inode,
+						nfsd_file_fsnotify_group);
 		if (mark) {
 			nfm = nfsd_file_mark_get(container_of(mark,
 						 struct nfsd_file_mark,
@@ -218,7 +217,9 @@ nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,
 	if (unlikely(!nf))
 		return NULL;
 
+	this_cpu_inc(nfsd_file_allocations);
 	INIT_LIST_HEAD(&nf->nf_lru);
+	INIT_LIST_HEAD(&nf->nf_gc);
 	nf->nf_birthtime = ktime_get();
 	nf->nf_file = NULL;
 	nf->nf_cred = get_current_cred();
@@ -283,7 +284,7 @@ nfsd_file_free(struct nfsd_file *nf)
 		nfsd_file_mark_put(nf->nf_mark);
 	if (nf->nf_file) {
 		nfsd_file_check_write_error(nf);
-		filp_close(nf->nf_file, NULL);
+		nfsd_filp_close(nf->nf_file);
 	}
 
 	/*
@@ -390,14 +391,42 @@ nfsd_file_put(struct nfsd_file *nf)
 		nfsd_file_free(nf);
 }
 
+/**
+ * nfsd_file_put_local - put nfsd_file reference and arm nfsd_net_put in caller
+ * @nf: nfsd_file of which to put the reference
+ *
+ * First save the associated net to return to caller, then put
+ * the reference of the nfsd_file.
+ */
+struct net *
+nfsd_file_put_local(struct nfsd_file *nf)
+{
+	struct net *net = nf->nf_net;
+
+	nfsd_file_put(nf);
+	return net;
+}
+
+/**
+ * nfsd_file_file - get the backing file of an nfsd_file
+ * @nf: nfsd_file of which to access the backing file.
+ *
+ * Return backing file for @nf.
+ */
+struct file *
+nfsd_file_file(struct nfsd_file *nf)
+{
+	return nf->nf_file;
+}
+
 static void
 nfsd_file_dispose_list(struct list_head *dispose)
 {
 	struct nfsd_file *nf;
 
 	while (!list_empty(dispose)) {
-		nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
-		list_del_init(&nf->nf_lru);
+		nf = list_first_entry(dispose, struct nfsd_file, nf_gc);
+		list_del_init(&nf->nf_gc);
 		nfsd_file_free(nf);
 	}
 }
@@ -414,14 +443,53 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
 {
 	while(!list_empty(dispose)) {
 		struct nfsd_file *nf = list_first_entry(dispose,
-						struct nfsd_file, nf_lru);
+						struct nfsd_file, nf_gc);
 		struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
 		struct nfsd_fcache_disposal *l = nn->fcache_disposal;
+		struct svc_serv *serv;
 
 		spin_lock(&l->lock);
-		list_move_tail(&nf->nf_lru, &l->freeme);
+		list_move_tail(&nf->nf_gc, &l->freeme);
 		spin_unlock(&l->lock);
-		queue_work(nfsd_filecache_wq, &l->work);
+
+		/*
+		 * The filecache laundrette is shut down after the
+		 * nn->nfsd_serv pointer is cleared, but before the
+		 * svc_serv is freed.
+		 */
+		serv = nn->nfsd_serv;
+		if (serv)
+			svc_wake_up(serv);
+	}
+}
+
+/**
+ * nfsd_file_net_dispose - deal with nfsd_files waiting to be disposed.
+ * @nn: nfsd_net in which to find files to be disposed.
+ *
+ * When files held open for nfsv3 are removed from the filecache, whether
+ * due to memory pressure or garbage collection, they are queued to
+ * a per-net-ns queue.  This function completes the disposal, either
+ * directly or by waking another nfsd thread to help with the work.
+ */
+void nfsd_file_net_dispose(struct nfsd_net *nn)
+{
+	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
+
+	if (!list_empty(&l->freeme)) {
+		LIST_HEAD(dispose);
+		int i;
+
+		spin_lock(&l->lock);
+		for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
+			list_move(l->freeme.next, &dispose);
+		spin_unlock(&l->lock);
+		if (!list_empty(&l->freeme))
+			/* Wake up another thread to share the work
+			 * *before* doing any actual disposing.
+			 */
+			svc_wake_up(nn->nfsd_serv);
+		nfsd_file_dispose_list(&dispose);
 	}
 }
 
@@ -429,7 +497,6 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
  * nfsd_file_lru_cb - Examine an entry on the LRU list
  * @item: LRU entry to examine
  * @lru: controlling LRU
- * @lock: LRU list lock (unused)
  * @arg: dispose list
  *
  * Return values:
@@ -439,9 +506,7 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
  */
 static enum lru_status
 nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
-		 spinlock_t *lock, void *arg)
-	__releases(lock)
-	__acquires(lock)
+		 void *arg)
 {
 	struct list_head *head = arg;
 	struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru);
@@ -476,7 +541,8 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
 
 	/* 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);
+	list_lru_isolate(lru, &nf->nf_lru);
+	list_add(&nf->nf_gc, head);
 	this_cpu_inc(nfsd_file_evictions);
 	trace_nfsd_file_gc_disposed(nf);
 	return LRU_REMOVED;
@@ -551,7 +617,7 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose)
 
 	/* 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);
+		list_add(&nf->nf_gc, dispose);
 		trace_nfsd_file_closing(nf);
 	}
 }
@@ -627,43 +693,21 @@ nfsd_file_close_inode_sync(struct inode *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);
+		nf = list_first_entry(&dispose, struct nfsd_file, nf_gc);
+		list_del_init(&nf->nf_gc);
 		nfsd_file_free(nf);
 	}
-	flush_delayed_fput();
-}
-
-/**
- * nfsd_file_delayed_close - close unused nfsd_files
- * @work: dummy
- *
- * Scrape the freeme list for this nfsd_net, and then dispose of them
- * all.
- */
-static void
-nfsd_file_delayed_close(struct work_struct *work)
-{
-	LIST_HEAD(head);
-	struct nfsd_fcache_disposal *l = container_of(work,
-			struct nfsd_fcache_disposal, work);
-
-	spin_lock(&l->lock);
-	list_splice_init(&l->freeme, &head);
-	spin_unlock(&l->lock);
-
-	nfsd_file_dispose_list(&head);
 }
 
 static int
 nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg,
 			    void *data)
 {
-	struct file_lock *fl = data;
+	struct file_lease *fl = data;
 
 	/* Only close files for F_SETLEASE leases */
-	if (fl->fl_flags & FL_LEASE)
-		nfsd_file_close_inode(file_inode(fl->fl_file));
+	if (fl->c.flc_flags & FL_LEASE)
+		nfsd_file_close_inode(file_inode(fl->c.flc_file));
 	return 0;
 }
 
@@ -714,28 +758,21 @@ nfsd_file_cache_init(void)
 
 	ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params);
 	if (ret)
-		return ret;
-
-	ret = -ENOMEM;
-	nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", WQ_UNBOUND, 0);
-	if (!nfsd_filecache_wq)
 		goto out;
 
-	nfsd_file_slab = kmem_cache_create("nfsd_file",
-				sizeof(struct nfsd_file), 0, 0, NULL);
+	ret = -ENOMEM;
+	nfsd_file_slab = KMEM_CACHE(nfsd_file, 0);
 	if (!nfsd_file_slab) {
 		pr_err("nfsd: unable to create nfsd_file_slab\n");
 		goto out_err;
 	}
 
-	nfsd_file_mark_slab = kmem_cache_create("nfsd_file_mark",
-					sizeof(struct nfsd_file_mark), 0, 0, NULL);
+	nfsd_file_mark_slab = KMEM_CACHE(nfsd_file_mark, 0);
 	if (!nfsd_file_mark_slab) {
 		pr_err("nfsd: unable to create nfsd_file_mark_slab\n");
 		goto out_err;
 	}
 
-
 	ret = list_lru_init(&nfsd_file_lru);
 	if (ret) {
 		pr_err("nfsd: failed to init nfsd_file_lru: %d\n", ret);
@@ -762,7 +799,7 @@ nfsd_file_cache_init(void)
 	}
 
 	nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops,
-							FSNOTIFY_GROUP_NOFS);
+							0);
 	if (IS_ERR(nfsd_file_fsnotify_group)) {
 		pr_err("nfsd: unable to create fsnotify group: %ld\n",
 			PTR_ERR(nfsd_file_fsnotify_group));
@@ -773,6 +810,8 @@ nfsd_file_cache_init(void)
 
 	INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker);
 out:
+	if (ret)
+		clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags);
 	return ret;
 out_notifier:
 	lease_unregister_notifier(&nfsd_file_lease_notifier);
@@ -785,8 +824,6 @@ out_err:
 	nfsd_file_slab = NULL;
 	kmem_cache_destroy(nfsd_file_mark_slab);
 	nfsd_file_mark_slab = NULL;
-	destroy_workqueue(nfsd_filecache_wq);
-	nfsd_filecache_wq = NULL;
 	rhltable_destroy(&nfsd_file_rhltable);
 	goto out;
 }
@@ -806,6 +843,14 @@ __nfsd_file_cache_purge(struct net *net)
 	struct nfsd_file *nf;
 	LIST_HEAD(dispose);
 
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	if (net) {
+		struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+		nfs_localio_invalidate_clients(&nn->local_clients,
+					       &nn->local_clients_lock);
+	}
+#endif
+
 	rhltable_walk_enter(&nfsd_file_rhltable, &iter);
 	do {
 		rhashtable_walk_start(&iter);
@@ -832,7 +877,6 @@ nfsd_alloc_fcache_disposal(void)
 	l = kmalloc(sizeof(*l), GFP_KERNEL);
 	if (!l)
 		return NULL;
-	INIT_WORK(&l->work, nfsd_file_delayed_close);
 	spin_lock_init(&l->lock);
 	INIT_LIST_HEAD(&l->freeme);
 	return l;
@@ -841,7 +885,6 @@ nfsd_alloc_fcache_disposal(void)
 static void
 nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l)
 {
-	cancel_work_sync(&l->work);
 	nfsd_file_dispose_list(&l->freeme);
 	kfree(l);
 }
@@ -910,13 +953,12 @@ nfsd_file_cache_shutdown(void)
 	fsnotify_wait_marks_destroyed();
 	kmem_cache_destroy(nfsd_file_mark_slab);
 	nfsd_file_mark_slab = NULL;
-	destroy_workqueue(nfsd_filecache_wq);
-	nfsd_filecache_wq = NULL;
 	rhltable_destroy(&nfsd_file_rhltable);
 
 	for_each_possible_cpu(i) {
 		per_cpu(nfsd_file_cache_hits, i) = 0;
 		per_cpu(nfsd_file_acquisitions, i) = 0;
+		per_cpu(nfsd_file_allocations, i) = 0;
 		per_cpu(nfsd_file_releases, i) = 0;
 		per_cpu(nfsd_file_total_age, i) = 0;
 		per_cpu(nfsd_file_evictions, i) = 0;
@@ -985,12 +1027,14 @@ nfsd_file_is_cached(struct inode *inode)
 }
 
 static __be32
-nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
+		     struct svc_cred *cred,
+		     struct auth_domain *client,
+		     struct svc_fh *fhp,
 		     unsigned int may_flags, struct file *file,
 		     struct nfsd_file **pnf, bool want_gc)
 {
 	unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
-	struct net *net = SVC_NET(rqstp);
 	struct nfsd_file *new, *nf;
 	bool stale_retry = true;
 	bool open_retry = true;
@@ -999,8 +1043,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int ret;
 
 retry:
-	status = fh_verify(rqstp, fhp, S_IFREG,
-				may_flags|NFSD_MAY_OWNER_OVERRIDE);
+	if (rqstp) {
+		status = fh_verify(rqstp, fhp, S_IFREG,
+				   may_flags|NFSD_MAY_OWNER_OVERRIDE);
+	} else {
+		status = fh_verify_local(net, cred, client, fhp, S_IFREG,
+					 may_flags|NFSD_MAY_OWNER_OVERRIDE);
+	}
 	if (status != nfs_ok)
 		return status;
 	inode = d_inode(fhp->fh_dentry);
@@ -1016,7 +1065,7 @@ retry:
 		 * the last one however, since we should hold another.
 		 */
 		if (nfsd_file_lru_remove(nf))
-			WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref));
+			refcount_dec(&nf->nf_ref);
 		goto wait_for_construction;
 	}
 
@@ -1032,7 +1081,7 @@ retry:
 	if (unlikely(nf)) {
 		spin_unlock(&inode->i_lock);
 		rcu_read_unlock();
-		nfsd_file_slab_free(&new->nf_rcu);
+		nfsd_file_free(new);
 		goto wait_for_construction;
 	}
 	nf = new;
@@ -1043,8 +1092,6 @@ retry:
 	if (likely(ret == 0))
 		goto open_file;
 
-	if (ret == -EEXIST)
-		goto retry;
 	trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret);
 	status = nfserr_jukebox;
 	goto construction_err;
@@ -1059,6 +1106,7 @@ wait_for_construction:
 			status = nfserr_jukebox;
 			goto construction_err;
 		}
+		nfsd_file_put(nf);
 		open_retry = false;
 		fh_put(fhp);
 		goto retry;
@@ -1082,7 +1130,7 @@ out:
 
 open_file:
 	trace_nfsd_file_alloc(nf);
-	nf->nf_mark = nfsd_file_mark_find_or_create(nf, inode);
+	nf->nf_mark = nfsd_file_mark_find_or_create(inode);
 	if (nf->nf_mark) {
 		if (file) {
 			get_file(file);
@@ -1090,8 +1138,7 @@ open_file:
 			status = nfs_ok;
 			trace_nfsd_file_opened(nf, status);
 		} else {
-			ret = nfsd_open_verified(rqstp, fhp, may_flags,
-						 &nf->nf_file);
+			ret = nfsd_open_verified(fhp, may_flags, &nf->nf_file);
 			if (ret == -EOPENSTALE && stale_retry) {
 				stale_retry = false;
 				nfsd_file_unhash(nf);
@@ -1147,7 +1194,8 @@ __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, NULL, pnf, true);
+	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
+				    fhp, may_flags, NULL, pnf, true);
 }
 
 /**
@@ -1171,7 +1219,54 @@ __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, NULL, pnf, false);
+	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
+				    fhp, may_flags, NULL, pnf, false);
+}
+
+/**
+ * nfsd_file_acquire_local - Get a struct nfsd_file with an open file for localio
+ * @net: The network namespace in which to perform a lookup
+ * @cred: the user credential with which to validate access
+ * @client: the auth_domain for LOCALIO lookup
+ * @fhp: the NFS filehandle of the file to be opened
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * This file lookup interface provide access to a file given the
+ * filehandle and credential.  No connection-based authorisation
+ * is performed and in that way it is quite different to other
+ * file access mediated by nfsd.  It allows a kernel module such as the NFS
+ * client to reach across network and filesystem namespaces to access
+ * a file.  The security implications of this should be carefully
+ * considered before use.
+ *
+ * The nfsd_file_object returned by this API is reference-counted
+ * but not garbage-collected. The object is unhashed after the
+ * final nfsd_file_put().
+ *
+ * Return values:
+ *   %nfs_ok - @pnf points to an nfsd_file with its reference
+ *   count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
+ */
+__be32
+nfsd_file_acquire_local(struct net *net, struct svc_cred *cred,
+			struct auth_domain *client, struct svc_fh *fhp,
+			unsigned int may_flags, struct nfsd_file **pnf)
+{
+	/*
+	 * Save creds before calling nfsd_file_do_acquire() (which calls
+	 * nfsd_setuser). Important because caller (LOCALIO) is from
+	 * client context.
+	 */
+	const struct cred *save_cred = get_current_cred();
+	__be32 beres;
+
+	beres = nfsd_file_do_acquire(NULL, net, cred, client,
+				     fhp, may_flags, NULL, pnf, false);
+	put_cred(revert_creds(save_cred));
+	return beres;
 }
 
 /**
@@ -1197,7 +1292,8 @@ 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, file, pnf, false);
+	return nfsd_file_do_acquire(rqstp, SVC_NET(rqstp), NULL, NULL,
+				    fhp, may_flags, file, pnf, false);
 }
 
 /*
@@ -1207,7 +1303,7 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
  */
 int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 {
-	unsigned long releases = 0, evictions = 0;
+	unsigned long allocations = 0, releases = 0, evictions = 0;
 	unsigned long hits = 0, acquisitions = 0;
 	unsigned int i, count = 0, buckets = 0;
 	unsigned long lru = 0, total_age = 0;
@@ -1232,6 +1328,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 	for_each_possible_cpu(i) {
 		hits += per_cpu(nfsd_file_cache_hits, i);
 		acquisitions += per_cpu(nfsd_file_acquisitions, i);
+		allocations += per_cpu(nfsd_file_allocations, i);
 		releases += per_cpu(nfsd_file_releases, i);
 		total_age += per_cpu(nfsd_file_total_age, i);
 		evictions += per_cpu(nfsd_file_evictions, i);
@@ -1242,6 +1339,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "lru entries:   %lu\n", lru);
 	seq_printf(m, "cache hits:    %lu\n", hits);
 	seq_printf(m, "acquisitions:  %lu\n", acquisitions);
+	seq_printf(m, "allocations:   %lu\n", allocations);
 	seq_printf(m, "releases:      %lu\n", releases);
 	seq_printf(m, "evictions:     %lu\n", evictions);
 	if (releases)