Merge tag 'nfsd-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "This release completes the SunRPC thread scheduler work that was begun
  in v6.6. The scheduler can now find an svc thread to wake in constant
  time and without a list walk. Thanks again to Neil Brown for this
  overhaul.

  Lorenzo Bianconi contributed infrastructure for a netlink-based NFSD
  control plane. The long-term plan is to provide the same functionality
  as found in /proc/fs/nfsd, plus some interesting additions, and then
  migrate the NFSD user space utilities to netlink.

  A long series to overhaul NFSD's NFSv4 operation encoding was applied
  in this release. The goals are to bring this family of encoding
  functions in line with the matching NFSv4 decoding functions and with
  the NFSv2 and NFSv3 XDR functions, preparing the way for better memory
  safety and maintainability.

  A further improvement to NFSD's write delegation support was
  contributed by Dai Ngo. This adds a CB_GETATTR callback, enabling the
  server to retrieve cached size and mtime data from clients holding
  write delegations. If the server can retrieve this information, it
  does not have to recall the delegation in some cases.

  The usual panoply of bug fixes and minor improvements round out this
  release. As always I am grateful to all contributors, reviewers, and
  testers"

* tag 'nfsd-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (127 commits)
  svcrdma: Fix tracepoint printk format
  svcrdma: Drop connection after an RDMA Read error
  NFSD: clean up alloc_init_deleg()
  NFSD: Fix frame size warning in svc_export_parse()
  NFSD: Rewrite synopsis of nfsd_percpu_counters_init()
  nfsd: Clean up errors in nfs3proc.c
  nfsd: Clean up errors in nfs4state.c
  NFSD: Clean up errors in stats.c
  NFSD: simplify error paths in nfsd_svc()
  NFSD: Clean up nfsd4_encode_seek()
  NFSD: Clean up nfsd4_encode_offset_status()
  NFSD: Clean up nfsd4_encode_copy_notify()
  NFSD: Clean up nfsd4_encode_copy()
  NFSD: Clean up nfsd4_encode_test_stateid()
  NFSD: Clean up nfsd4_encode_exchange_id()
  NFSD: Clean up nfsd4_do_encode_secinfo()
  NFSD: Clean up nfsd4_encode_access()
  NFSD: Clean up nfsd4_encode_readdir()
  NFSD: Clean up nfsd4_encode_entry4()
  NFSD: Add an nfsd4_encode_nfs_cookie4() helper
  ...

Documentation/filesystems/nfs/exporting.rst

@@ -241,3 +241,10 @@ following flags are defined:
     all of an inode's dirty data on last close. Exports that behave this
     way should set EXPORT_OP_FLUSH_ON_CLOSE so that NFSD knows to skip
     waiting for writeback when closing such files.
+
+  EXPORT_OP_ASYNC_LOCK - Indicates a capable filesystem to do async lock
+    requests from lockd. Only set EXPORT_OP_ASYNC_LOCK if the filesystem has
+    it's own ->lock() functionality as core posix_lock_file() implementation
+    has no async lock request handling yet. For more information about how to
+    indicate an async lock request from a ->lock() file_operations struct, see
+    fs/locks.c and comment for the function vfs_lock_file().

Documentation/netlink/specs/nfsd.yaml

+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: nfsd
+protocol: genetlink
+uapi-header: linux/nfsd_netlink.h
+
+doc: NFSD configuration over generic netlink.
+
+attribute-sets:
+  -
+    name: rpc-status
+    attributes:
+      -
+        name: xid
+        type: u32
+        byte-order: big-endian
+      -
+        name: flags
+        type: u32
+      -
+        name: prog
+        type: u32
+      -
+        name: version
+        type: u8
+      -
+        name: proc
+        type: u32
+      -
+        name: service_time
+        type: s64
+      -
+        name: pad
+        type: pad
+      -
+        name: saddr4
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: daddr4
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: saddr6
+        type: binary
+        display-hint: ipv6
+      -
+        name: daddr6
+        type: binary
+        display-hint: ipv6
+      -
+        name: sport
+        type: u16
+        byte-order: big-endian
+      -
+        name: dport
+        type: u16
+        byte-order: big-endian
+      -
+        name: compound-ops
+        type: u32
+        multi-attr: true
+
+operations:
+  list:
+    -
+      name: rpc-status-get
+      doc: dump pending nfsd rpc
+      attribute-set: rpc-status
+      dump:
+        pre: nfsd-nl-rpc-status-get-start
+        post: nfsd-nl-rpc-status-get-done
+        reply:
+          attributes:
+            - xid
+            - flags
+            - prog
+            - version
+            - proc
+            - service_time
+            - saddr4
+            - daddr4
+            - saddr6
+            - daddr6
+            - sport
+            - dport
+            - compound-ops

fs/lockd/svc.c

@@ -24,7 +24,6 @@
 #include <linux/uio.h>
 #include <linux/smp.h>
 #include <linux/mutex.h>
-#include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/inetdevice.h>
 
@@ -135,11 +134,11 @@ lockd(void *vrqstp)
 	 * The main request loop. We don't terminate until the last
 	 * NFS mount or NFS daemon has gone away.
 	 */
-	while (!kthread_should_stop()) {
+	while (!svc_thread_should_stop(rqstp)) {
 		/* update sv_maxconn if it has changed */
 		rqstp->rq_server->sv_maxconn = nlm_max_connections;
 
-		nlmsvc_retry_blocked();
+		nlmsvc_retry_blocked(rqstp);
 		svc_recv(rqstp);
 	}
 	if (nlmsvc_ops)
@@ -373,7 +372,9 @@ static void lockd_put(void)
 	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
 #endif
 
+	svc_get(nlmsvc_serv);
 	svc_set_num_threads(nlmsvc_serv, NULL, 0);
+	svc_put(nlmsvc_serv);
 	timer_delete_sync(&nlmsvc_retry);
 	nlmsvc_serv = NULL;
 	dprintk("lockd_down: service destroyed\n");

fs/lockd/svclock.c

@@ -30,7 +30,6 @@
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/lockd/nlm.h>
 #include <linux/lockd/lockd.h>
-#include <linux/kthread.h>
 #include <linux/exportfs.h>
 
 #define NLMDBG_FACILITY		NLMDBG_SVCLOCK
@@ -481,9 +480,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	    struct nlm_host *host, struct nlm_lock *lock, int wait,
 	    struct nlm_cookie *cookie, int reclaim)
 {
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct inode		*inode = nlmsvc_file_inode(file);
-#endif
 	struct nlm_block	*block = NULL;
 	int			error;
 	int			mode;
@@ -497,7 +494,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_end,
 				wait);
 
-	if (nlmsvc_file_file(file)->f_op->lock) {
+	if (!exportfs_lock_op_is_async(inode->i_sb->s_export_op)) {
 		async_block = wait;
 		wait = 0;
 	}
@@ -543,6 +540,25 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
+	spin_lock(&nlm_blocked_lock);
+	/*
+	 * If this is a lock request for an already pending
+	 * lock request we return nlm_lck_blocked without calling
+	 * vfs_lock_file() again. Otherwise we have two pending
+	 * requests on the underlaying ->lock() implementation but
+	 * only one nlm_block to being granted by lm_grant().
+	 */
+	if (exportfs_lock_op_is_async(inode->i_sb->s_export_op) &&
+	    !list_empty(&block->b_list)) {
+		spin_unlock(&nlm_blocked_lock);
+		ret = nlm_lck_blocked;
+		goto out;
+	}
+
+	/* Append to list of blocked */
+	nlmsvc_insert_block_locked(block, NLM_NEVER);
+	spin_unlock(&nlm_blocked_lock);
+
 	if (!wait)
 		lock->fl.fl_flags &= ~FL_SLEEP;
 	mode = lock_to_openmode(&lock->fl);
@@ -552,16 +568,12 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	dprintk("lockd: vfs_lock_file returned %d\n", error);
 	switch (error) {
 		case 0:
+			nlmsvc_remove_block(block);
 			ret = nlm_granted;
 			goto out;
 		case -EAGAIN:
-			/*
-			 * If this is a blocking request for an
-			 * already pending lock request then we need
-			 * to put it back on lockd's block list
-			 */
-			if (wait)
-				break;
+			if (!wait)
+				nlmsvc_remove_block(block);
 			ret = async_block ? nlm_lck_blocked : nlm_lck_denied;
 			goto out;
 		case FILE_LOCK_DEFERRED:
@@ -572,17 +584,16 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 			ret = nlmsvc_defer_lock_rqst(rqstp, block);
 			goto out;
 		case -EDEADLK:
+			nlmsvc_remove_block(block);
 			ret = nlm_deadlock;
 			goto out;
 		default:			/* includes ENOLCK */
+			nlmsvc_remove_block(block);
 			ret = nlm_lck_denied_nolocks;
 			goto out;
 	}
 
 	ret = nlm_lck_blocked;
-
-	/* Append to list of blocked */
-	nlmsvc_insert_block(block, NLM_NEVER);
 out:
 	mutex_unlock(&file->f_mutex);
 	nlmsvc_release_block(block);
@@ -1020,13 +1031,13 @@ retry_deferred_block(struct nlm_block *block)
  * be retransmitted.
  */
 void
-nlmsvc_retry_blocked(void)
+nlmsvc_retry_blocked(struct svc_rqst *rqstp)
 {
 	unsigned long	timeout = MAX_SCHEDULE_TIMEOUT;
 	struct nlm_block *block;
 
 	spin_lock(&nlm_blocked_lock);
-	while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
+	while (!list_empty(&nlm_blocked) && !svc_thread_should_stop(rqstp)) {
 		block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
 
 		if (block->b_when == NLM_NEVER)

fs/locks.c

@@ -2264,11 +2264,13 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
  * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX
  * locks, the ->lock() interface may return asynchronously, before the lock has
  * been granted or denied by the underlying filesystem, if (and only if)
- * lm_grant is set. Callers expecting ->lock() to return asynchronously
- * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if)
- * the request is for a blocking lock. When ->lock() does return asynchronously,
- * it must return FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock
- * request completes.
+ * lm_grant is set. Additionally EXPORT_OP_ASYNC_LOCK in export_operations
+ * flags need to be set.
+ *
+ * Callers expecting ->lock() to return asynchronously will only use F_SETLK,
+ * not F_SETLKW; they will set FL_SLEEP if (and only if) the request is for a
+ * blocking lock. When ->lock() does return asynchronously, it must return
+ * FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock request completes.
  * If the request is for non-blocking lock the file system should return
  * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine
  * with the result. If the request timed out the callback routine will return a

fs/nfs/callback.c

@@ -78,7 +78,7 @@ nfs4_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	while (!kthread_freezable_should_stop(NULL))
+	while (!svc_thread_should_stop(rqstp))
 		svc_recv(rqstp);
 
 	svc_exit_thread(rqstp);
@@ -86,45 +86,6 @@ nfs4_callback_svc(void *vrqstp)
 }
 
 #if defined(CONFIG_NFS_V4_1)
-/*
- * The callback service for NFSv4.1 callbacks
- */
-static int
-nfs41_callback_svc(void *vrqstp)
-{
-	struct svc_rqst *rqstp = vrqstp;
-	struct svc_serv *serv = rqstp->rq_server;
-	struct rpc_rqst *req;
-	int error;
-	DEFINE_WAIT(wq);
-
-	set_freezable();
-
-	while (!kthread_freezable_should_stop(NULL)) {
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_IDLE);
-		spin_lock_bh(&serv->sv_cb_lock);
-		if (!list_empty(&serv->sv_cb_list)) {
-			req = list_first_entry(&serv->sv_cb_list,
-					struct rpc_rqst, rq_bc_list);
-			list_del(&req->rq_bc_list);
-			spin_unlock_bh(&serv->sv_cb_lock);
-			finish_wait(&serv->sv_cb_waitq, &wq);
-			dprintk("Invoking bc_svc_process()\n");
-			error = bc_svc_process(serv, req, rqstp);
-			dprintk("bc_svc_process() returned w/ error code= %d\n",
-				error);
-		} else {
-			spin_unlock_bh(&serv->sv_cb_lock);
-			if (!kthread_should_stop())
-				schedule();
-			finish_wait(&serv->sv_cb_waitq, &wq);
-		}
-	}
-
-	svc_exit_thread(rqstp);
-	return 0;
-}
-
 static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
 		struct svc_serv *serv)
 {
@@ -237,10 +198,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 			cb_info->users);
 
 	threadfn = nfs4_callback_svc;
-#if defined(CONFIG_NFS_V4_1)
-	if (minorversion)
-		threadfn = nfs41_callback_svc;
-#else
+#if !defined(CONFIG_NFS_V4_1)
 	if (minorversion)
 		return ERR_PTR(-ENOTSUPP);
 #endif

fs/nfsd/Makefile

@@ -12,7 +12,8 @@ nfsd-y			+= trace.o
 
 nfsd-y 			+= nfssvc.o nfsctl.o nfsfh.o vfs.o \
 			   export.o auth.o lockd.o nfscache.o \
-			   stats.o filecache.o nfs3proc.o nfs3xdr.o
+			   stats.o filecache.o nfs3proc.o nfs3xdr.o \
+			   netlink.o
 nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o

fs/nfsd/blocklayoutxdr.c

@@ -16,9 +16,9 @@
 
 __be32
 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
-		struct nfsd4_layoutget *lgp)
+		const struct nfsd4_layoutget *lgp)
 {
-	struct pnfs_block_extent *b = lgp->lg_content;
+	const struct pnfs_block_extent *b = lgp->lg_content;
 	int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32);
 	__be32 *p;
 
@@ -77,7 +77,7 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 
 __be32
 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
-		struct nfsd4_getdeviceinfo *gdp)
+		const struct nfsd4_getdeviceinfo *gdp)
 {
 	struct pnfs_block_deviceaddr *dev = gdp->gd_device;
 	int len = sizeof(__be32), ret, i;

fs/nfsd/blocklayoutxdr.h

@@ -51,9 +51,9 @@ struct pnfs_block_deviceaddr {
 };
 
 __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
-		struct nfsd4_getdeviceinfo *gdp);
+		const struct nfsd4_getdeviceinfo *gdp);
 __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
-		struct nfsd4_layoutget *lgp);
+		const struct nfsd4_layoutget *lgp);
 int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
 		u32 block_size);
 int nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,

fs/nfsd/export.c

@@ -339,12 +339,16 @@ static int export_stats_init(struct export_stats *stats)
 
 static void export_stats_reset(struct export_stats *stats)
 {
-	nfsd_percpu_counters_reset(stats->counter, EXP_STATS_COUNTERS_NUM);
+	if (stats)
+		nfsd_percpu_counters_reset(stats->counter,
+					   EXP_STATS_COUNTERS_NUM);
 }
 
 static void export_stats_destroy(struct export_stats *stats)
 {
-	nfsd_percpu_counters_destroy(stats->counter, EXP_STATS_COUNTERS_NUM);
+	if (stats)
+		nfsd_percpu_counters_destroy(stats->counter,
+					     EXP_STATS_COUNTERS_NUM);
 }
 
 static void svc_export_put(struct kref *ref)
@@ -353,7 +357,8 @@ static void svc_export_put(struct kref *ref)
 	path_put(&exp->ex_path);
 	auth_domain_put(exp->ex_client);
 	nfsd4_fslocs_free(&exp->ex_fslocs);
-	export_stats_destroy(&exp->ex_stats);
+	export_stats_destroy(exp->ex_stats);
+	kfree(exp->ex_stats);
 	kfree(exp->ex_uuid);
 	kfree_rcu(exp, ex_rcu);
 }
@@ -767,13 +772,15 @@ static int svc_export_show(struct seq_file *m,
 	seq_putc(m, '\t');
 	seq_escape(m, exp->ex_client->name, " \t\n\\");
 	if (export_stats) {
-		seq_printf(m, "\t%lld\n", exp->ex_stats.start_time);
+		struct percpu_counter *counter = exp->ex_stats->counter;
+
+		seq_printf(m, "\t%lld\n", exp->ex_stats->start_time);
 		seq_printf(m, "\tfh_stale: %lld\n",
-			   percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_FH_STALE]));
+			   percpu_counter_sum_positive(&counter[EXP_STATS_FH_STALE]));
 		seq_printf(m, "\tio_read: %lld\n",
-			   percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_READ]));
+			   percpu_counter_sum_positive(&counter[EXP_STATS_IO_READ]));
 		seq_printf(m, "\tio_write: %lld\n",
-			   percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_WRITE]));
+			   percpu_counter_sum_positive(&counter[EXP_STATS_IO_WRITE]));
 		seq_putc(m, '\n');
 		return 0;
 	}
@@ -819,7 +826,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_layout_types = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
-	export_stats_reset(&new->ex_stats);
+	export_stats_reset(new->ex_stats);
 }
 
 static void export_update(struct cache_head *cnew, struct cache_head *citem)
@@ -856,7 +863,14 @@ static struct cache_head *svc_export_alloc(void)
 	if (!i)
 		return NULL;
 
-	if (export_stats_init(&i->ex_stats)) {
+	i->ex_stats = kmalloc(sizeof(*(i->ex_stats)), GFP_KERNEL);
+	if (!i->ex_stats) {
+		kfree(i);
+		return NULL;
+	}
+
+	if (export_stats_init(i->ex_stats)) {
+		kfree(i->ex_stats);
 		kfree(i);
 		return NULL;
 	}

fs/nfsd/export.h

@@ -64,10 +64,10 @@ struct svc_export {
 	struct cache_head	h;
 	struct auth_domain *	ex_client;
 	int			ex_flags;
+	int			ex_fsid;
 	struct path		ex_path;
 	kuid_t			ex_anon_uid;
 	kgid_t			ex_anon_gid;
-	int			ex_fsid;
 	unsigned char *		ex_uuid; /* 16 byte fsid */
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
@@ -76,8 +76,8 @@ struct svc_export {
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 	struct rcu_head		ex_rcu;
-	struct export_stats	ex_stats;
 	unsigned long		ex_xprtsec_modes;
+	struct export_stats	*ex_stats;
 };
 
 /* an "export key" (expkey) maps a filehandlefragement to an

fs/nfsd/filecache.c

@@ -989,22 +989,21 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_file *new, *nf;
-	const struct cred *cred;
+	bool stale_retry = true;
 	bool open_retry = true;
 	struct inode *inode;
 	__be32 status;
 	int ret;
 
+retry:
 	status = fh_verify(rqstp, fhp, S_IFREG,
 				may_flags|NFSD_MAY_OWNER_OVERRIDE);
 	if (status != nfs_ok)
 		return status;
 	inode = d_inode(fhp->fh_dentry);
-	cred = get_current_cred();
 
-retry:
 	rcu_read_lock();
-	nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc);
+	nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc);
 	rcu_read_unlock();
 
 	if (nf) {
@@ -1026,7 +1025,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 	rcu_read_lock();
 	spin_lock(&inode->i_lock);
-	nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc);
+	nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc);
 	if (unlikely(nf)) {
 		spin_unlock(&inode->i_lock);
 		rcu_read_unlock();
@@ -1058,6 +1057,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			goto construction_err;
 		}
 		open_retry = false;
+		fh_put(fhp);
 		goto retry;
 	}
 	this_cpu_inc(nfsd_file_cache_hits);
@@ -1074,7 +1074,6 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		nfsd_file_check_write_error(nf);
 		*pnf = nf;
 	}
-	put_cred(cred);
 	trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status);
 	return status;
 
@@ -1088,8 +1087,20 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			status = nfs_ok;
 			trace_nfsd_file_opened(nf, status);
 		} else {
-			status = nfsd_open_verified(rqstp, fhp, may_flags,
-						    &nf->nf_file);
+			ret = nfsd_open_verified(rqstp, fhp, may_flags,
+						 &nf->nf_file);
+			if (ret == -EOPENSTALE && stale_retry) {
+				stale_retry = false;
+				nfsd_file_unhash(nf);
+				clear_and_wake_up_bit(NFSD_FILE_PENDING,
+						      &nf->nf_flags);
+				if (refcount_dec_and_test(&nf->nf_ref))
+					nfsd_file_free(nf);
+				nf = NULL;
+				fh_put(fhp);
+				goto retry;
+			}
+			status = nfserrno(ret);
 			trace_nfsd_file_open(nf, status);
 		}
 	} else

fs/nfsd/flexfilelayoutxdr.c

@@ -17,9 +17,9 @@ struct ff_idmap {
 
 __be32
 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
-		struct nfsd4_layoutget *lgp)
+		const struct nfsd4_layoutget *lgp)
 {
-	struct pnfs_ff_layout *fl = lgp->lg_content;
+	const struct pnfs_ff_layout *fl = lgp->lg_content;
 	int len, mirror_len, ds_len, fh_len;
 	__be32 *p;
 
@@ -77,7 +77,7 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
 
 __be32
 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
-		struct nfsd4_getdeviceinfo *gdp)
+		const struct nfsd4_getdeviceinfo *gdp)
 {
 	struct pnfs_ff_device_addr *da = gdp->gd_device;
 	int len;

fs/nfsd/flexfilelayoutxdr.h

@@ -43,8 +43,8 @@ struct pnfs_ff_layout {
 };
 
 __be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
-		struct nfsd4_getdeviceinfo *gdp);
+		const struct nfsd4_getdeviceinfo *gdp);
 __be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
-		struct nfsd4_layoutget *lgp);
+		const struct nfsd4_layoutget *lgp);
 
 #endif /* _NFSD_FLEXFILELAYOUTXDR_H */

fs/nfsd/netlink.c

+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/nfsd.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netlink.h"
+
+#include <uapi/linux/nfsd_netlink.h>
+
+/* Ops table for nfsd */
+static const struct genl_split_ops nfsd_nl_ops[] = {
+	{
+		.cmd	= NFSD_CMD_RPC_STATUS_GET,
+		.start	= nfsd_nl_rpc_status_get_start,
+		.dumpit	= nfsd_nl_rpc_status_get_dumpit,
+		.done	= nfsd_nl_rpc_status_get_done,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+};
+
+struct genl_family nfsd_nl_family __ro_after_init = {
+	.name		= NFSD_FAMILY_NAME,
+	.version	= NFSD_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= nfsd_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(nfsd_nl_ops),
+};

fs/nfsd/netlink.h

+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/nfsd.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_NFSD_GEN_H
+#define _LINUX_NFSD_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/nfsd_netlink.h>
+
+int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb);
+int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb);
+
+int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+
+extern struct genl_family nfsd_nl_family;
+
+#endif /* _LINUX_NFSD_GEN_H */

fs/nfsd/nfs3proc.c

@@ -171,7 +171,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
 	 * + 1 (xdr opaque byte count) = 26
 	 */
 	resp->count = argp->count;
-	svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4);
+	svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3) << 2) +
+			 resp->count + 4);
 
 	fh_copy(&resp->fh, &argp->fh);
 	resp->status = nfsd_read(rqstp, &resp->fh, argp->offset,
@@ -194,7 +195,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
 				SVCFH_fmt(&argp->fh),
 				argp->len,
 				(unsigned long long) argp->offset,
-				argp->stable? " stable" : "");
+				argp->stable ? " stable" : "");
 
 	resp->status = nfserr_fbig;
 	if (argp->offset > (u64)OFFSET_MAX ||

fs/nfsd/nfs4callback.c

@@ -84,7 +84,21 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n)
 static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
 			   size_t len)
 {
-	WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
+	xdr_stream_encode_uint32_array(xdr, bitmap, len);
+}
+
+static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap,
+				struct nfs4_cb_fattr *fattr)
+{
+	fattr->ncf_cb_change = 0;
+	fattr->ncf_cb_fsize = 0;
+	if (bitmap[0] & FATTR4_WORD0_CHANGE)
+		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0)
+			return -NFSERR_BAD_XDR;
+	if (bitmap[0] & FATTR4_WORD0_SIZE)
+		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0)
+			return -NFSERR_BAD_XDR;
+	return 0;
 }
 
 /*
@@ -357,6 +371,30 @@ encode_cb_recallany4args(struct xdr_stream *xdr,
 	hdr->nops++;
 }
 
+/*
+ * CB_GETATTR4args
+ *	struct CB_GETATTR4args {
+ *	   nfs_fh4 fh;
+ *	   bitmap4 attr_request;
+ *	};
+ *
+ * The size and change attributes are the only one
+ * guaranteed to be serviced by the client.
+ */
+static void
+encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
+			struct nfs4_cb_fattr *fattr)
+{
+	struct nfs4_delegation *dp =
+		container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
+	struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
+
+	encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
+	encode_nfs_fh4(xdr, fh);
+	encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
+	hdr->nops++;
+}
+
 /*
  * CB_SEQUENCE4args
  *
@@ -492,6 +530,26 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 	xdr_reserve_space(xdr, 0);
 }
 
+/*
+ * 20.1.  Operation 3: CB_GETATTR - Get Attributes
+ */
+static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req,
+		struct xdr_stream *xdr, const void *data)
+{
+	const struct nfsd4_callback *cb = data;
+	struct nfs4_cb_fattr *ncf =
+		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = cb->cb_clp->cl_cb_ident,
+		.minorversion = cb->cb_clp->cl_minorversion,
+	};
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+	encode_cb_getattr4args(xdr, &hdr, ncf);
+	encode_cb_nops(&hdr);
+}
+
 /*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
@@ -547,6 +605,42 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 	return 0;
 }
 
+/*
+ * 20.1.  Operation 3: CB_GETATTR - Get Attributes
+ */
+static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfsd4_callback *cb = data;
+	struct nfs4_cb_compound_hdr hdr;
+	int status;
+	u32 bitmap[3] = {0};
+	u32 attrlen;
+	struct nfs4_cb_fattr *ncf =
+		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		return status;
+
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+
+	status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status);
+	if (status)
+		return status;
+	if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0)
+		return -NFSERR_BAD_XDR;
+	if (xdr_stream_decode_u32(xdr, &attrlen) < 0)
+		return -NFSERR_BAD_XDR;
+	if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize)))
+		return -NFSERR_BAD_XDR;
+	status = decode_cb_fattr4(xdr, bitmap, ncf);
+	return status;
+}
+
 /*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
@@ -855,6 +949,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 	PROC(CB_OFFLOAD,	COMPOUND,	cb_offload,	cb_offload),
 	PROC(CB_RECALL_ANY,	COMPOUND,	cb_recall_any,	cb_recall_any),
+	PROC(CB_GETATTR,	COMPOUND,	cb_getattr,	cb_getattr),
 };
 
 static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];

fs/nfsd/nfs4layouts.c

@@ -515,11 +515,11 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
 	if (!list_empty(&ls->ls_layouts)) {
 		if (found)
 			nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid);
-		lrp->lrs_present = 1;
+		lrp->lrs_present = true;
 	} else {
 		trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid);
 		nfs4_unhash_stid(&ls->ls_stid);
-		lrp->lrs_present = 0;
+		lrp->lrs_present = false;
 	}
 	spin_unlock(&ls->ls_lock);
 
@@ -539,7 +539,7 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp,
 	struct nfs4_layout *lp, *t;
 	LIST_HEAD(reaplist);
 
-	lrp->lrs_present = 0;
+	lrp->lrs_present = false;
 
 	spin_lock(&clp->cl_lock);
 	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {

fs/nfsd/nfs4proc.c

@@ -1329,7 +1329,8 @@ extern void nfs_sb_deactive(struct super_block *sb);
  * setup a work entry in the ssc delayed unmount list.
  */
 static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
-				  struct nfsd4_ssc_umount_item **nsui)
+				  struct nfsd4_ssc_umount_item **nsui,
+				  struct svc_rqst *rqstp)
 {
 	struct nfsd4_ssc_umount_item *ni = NULL;
 	struct nfsd4_ssc_umount_item *work = NULL;
@@ -1351,7 +1352,7 @@ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
 			spin_unlock(&nn->nfsd_ssc_lock);
 
 			/* allow 20secs for mount/unmount for now - revisit */
-			if (kthread_should_stop() ||
+			if (svc_thread_should_stop(rqstp) ||
 					(schedule_timeout(20*HZ) == 0)) {
 				finish_wait(&nn->nfsd_ssc_waitq, &wait);
 				kfree(work);
@@ -1467,7 +1468,7 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp,
 		goto out_free_rawdata;
 	snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep);
 
-	status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui);
+	status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui, rqstp);
 	if (status)
 		goto out_free_devname;
 	if ((*nsui)->nsui_vfsmount)
@@ -1642,6 +1643,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy,
 	if (bytes_total == 0)
 		bytes_total = ULLONG_MAX;
 	do {
+		/* Only async copies can be stopped here */
 		if (kthread_should_stop())
 			break;
 		bytes_copied = nfsd_copy_file_range(src, src_pos, dst, dst_pos,
@@ -1760,6 +1762,7 @@ static int nfsd4_do_async_copy(void *data)
 	struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
 	__be32 nfserr;
 
+	trace_nfsd_copy_do_async(copy);
 	if (nfsd4_ssc_is_inter(copy)) {
 		struct file *filp;
 
@@ -1798,21 +1801,27 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	__be32 status;
 	struct nfsd4_copy *async_copy = NULL;
 
+	copy->cp_clp = cstate->clp;
 	if (nfsd4_ssc_is_inter(copy)) {
+		trace_nfsd_copy_inter(copy);
 		if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) {
 			status = nfserr_notsupp;
 			goto out;
 		}
 		status = nfsd4_setup_inter_ssc(rqstp, cstate, copy);
-		if (status)
+		if (status) {
+			trace_nfsd_copy_done(copy, status);
 			return nfserr_offload_denied;
+		}
 	} else {
+		trace_nfsd_copy_intra(copy);
 		status = nfsd4_setup_intra_ssc(rqstp, cstate, copy);
-		if (status)
+		if (status) {
+			trace_nfsd_copy_done(copy, status);
 			return status;
+		}
 	}
 
-	copy->cp_clp = cstate->clp;
 	memcpy(&copy->fh, &cstate->current_fh.fh_handle,
 		sizeof(struct knfsd_fh));
 	if (nfsd4_copy_is_async(copy)) {
@@ -1847,6 +1856,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				       copy->nf_dst->nf_file, true);
 	}
 out:
+	trace_nfsd_copy_done(copy, status);
 	release_copy_files(copy);
 	return status;
 out_err:
@@ -1929,8 +1939,8 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		return status;
 
-	cn->cpn_sec = nn->nfsd4_lease;
-	cn->cpn_nsec = 0;
+	cn->cpn_lease_time.tv_sec = nn->nfsd4_lease;
+	cn->cpn_lease_time.tv_nsec = 0;
 
 	status = nfserrno(-ENOMEM);
 	cps = nfs4_alloc_init_cpntf_state(nn, stid);
@@ -2347,10 +2357,10 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
 	mutex_unlock(&ls->ls_mutex);
 
 	if (new_size > i_size_read(inode)) {
-		lcp->lc_size_chg = 1;
+		lcp->lc_size_chg = true;
 		lcp->lc_newsize = new_size;
 	} else {
-		lcp->lc_size_chg = 0;
+		lcp->lc_size_chg = false;
 	}
 
 	nfserr = ops->proc_layoutcommit(inode, lcp);
@@ -3200,6 +3210,7 @@ static const struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_LOCK] = {
 		.op_func = nfsd4_lock,
+		.op_release = nfsd4_lock_release,
 		.op_flags = OP_MODIFIES_SOMETHING |
 				OP_NONTRIVIAL_ERROR_ENCODE,
 		.op_name = "OP_LOCK",
@@ -3208,6 +3219,7 @@ static const struct nfsd4_operation nfsd4_ops[] = {
 	},
 	[OP_LOCKT] = {
 		.op_func = nfsd4_lockt,
+		.op_release = nfsd4_lockt_release,
 		.op_flags = OP_NONTRIVIAL_ERROR_ENCODE,
 		.op_name = "OP_LOCKT",
 		.op_rsize_bop = nfsd4_lock_rsize,

fs/nfsd/nfsctl.c

@@ -26,6 +26,7 @@
 #include "pnfs.h"
 #include "filecache.h"
 #include "trace.h"
+#include "netlink.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1495,6 +1496,203 @@ static int create_proc_exports_entry(void)
 
 unsigned int nfsd_net_id;
 
+/**
+ * nfsd_nl_rpc_status_get_start - Prepare rpc_status_get dumpit
+ * @cb: netlink metadata and command arguments
+ *
+ * Return values:
+ *   %0: The rpc_status_get command may proceed
+ *   %-ENODEV: There is no NFSD running in this namespace
+ */
+int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb)
+{
+	struct nfsd_net *nn = net_generic(sock_net(cb->skb->sk), nfsd_net_id);
+	int ret = -ENODEV;
+
+	mutex_lock(&nfsd_mutex);
+	if (nn->nfsd_serv) {
+		svc_get(nn->nfsd_serv);
+		ret = 0;
+	}
+	mutex_unlock(&nfsd_mutex);
+
+	return ret;
+}
+
+static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb,
+					    struct netlink_callback *cb,
+					    struct nfsd_genl_rqstp *rqstp)
+{
+	void *hdr;
+	u32 i;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &nfsd_nl_family, 0, NFSD_CMD_RPC_STATUS_GET);
+	if (!hdr)
+		return -ENOBUFS;
+
+	if (nla_put_be32(skb, NFSD_A_RPC_STATUS_XID, rqstp->rq_xid) ||
+	    nla_put_u32(skb, NFSD_A_RPC_STATUS_FLAGS, rqstp->rq_flags) ||
+	    nla_put_u32(skb, NFSD_A_RPC_STATUS_PROG, rqstp->rq_prog) ||
+	    nla_put_u32(skb, NFSD_A_RPC_STATUS_PROC, rqstp->rq_proc) ||
+	    nla_put_u8(skb, NFSD_A_RPC_STATUS_VERSION, rqstp->rq_vers) ||
+	    nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME,
+			ktime_to_us(rqstp->rq_stime),
+			NFSD_A_RPC_STATUS_PAD))
+		return -ENOBUFS;
+
+	switch (rqstp->rq_saddr.sa_family) {
+	case AF_INET: {
+		const struct sockaddr_in *s_in, *d_in;
+
+		s_in = (const struct sockaddr_in *)&rqstp->rq_saddr;
+		d_in = (const struct sockaddr_in *)&rqstp->rq_daddr;
+		if (nla_put_in_addr(skb, NFSD_A_RPC_STATUS_SADDR4,
+				    s_in->sin_addr.s_addr) ||
+		    nla_put_in_addr(skb, NFSD_A_RPC_STATUS_DADDR4,
+				    d_in->sin_addr.s_addr) ||
+		    nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT,
+				 s_in->sin_port) ||
+		    nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT,
+				 d_in->sin_port))
+			return -ENOBUFS;
+		break;
+	}
+	case AF_INET6: {
+		const struct sockaddr_in6 *s_in, *d_in;
+
+		s_in = (const struct sockaddr_in6 *)&rqstp->rq_saddr;
+		d_in = (const struct sockaddr_in6 *)&rqstp->rq_daddr;
+		if (nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_SADDR6,
+				     &s_in->sin6_addr) ||
+		    nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_DADDR6,
+				     &d_in->sin6_addr) ||
+		    nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT,
+				 s_in->sin6_port) ||
+		    nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT,
+				 d_in->sin6_port))
+			return -ENOBUFS;
+		break;
+	}
+	}
+
+	for (i = 0; i < rqstp->rq_opcnt; i++)
+		if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS,
+				rqstp->rq_opnum[i]))
+			return -ENOBUFS;
+
+	genlmsg_end(skb, hdr);
+	return 0;
+}
+
+/**
+ * nfsd_nl_rpc_status_get_dumpit - Handle rpc_status_get dumpit
+ * @skb: reply buffer
+ * @cb: netlink metadata and command arguments
+ *
+ * Returns the size of the reply or a negative errno.
+ */
+int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id);
+	int i, ret, rqstp_index = 0;
+
+	rcu_read_lock();
+
+	for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
+		struct svc_rqst *rqstp;
+
+		if (i < cb->args[0]) /* already consumed */
+			continue;
+
+		rqstp_index = 0;
+		list_for_each_entry_rcu(rqstp,
+				&nn->nfsd_serv->sv_pools[i].sp_all_threads,
+				rq_all) {
+			struct nfsd_genl_rqstp genl_rqstp;
+			unsigned int status_counter;
+
+			if (rqstp_index++ < cb->args[1]) /* already consumed */
+				continue;
+			/*
+			 * Acquire rq_status_counter before parsing the rqst
+			 * fields. rq_status_counter is set to an odd value in
+			 * order to notify the consumers the rqstp fields are
+			 * meaningful.
+			 */
+			status_counter =
+				smp_load_acquire(&rqstp->rq_status_counter);
+			if (!(status_counter & 1))
+				continue;
+
+			genl_rqstp.rq_xid = rqstp->rq_xid;
+			genl_rqstp.rq_flags = rqstp->rq_flags;
+			genl_rqstp.rq_vers = rqstp->rq_vers;
+			genl_rqstp.rq_prog = rqstp->rq_prog;
+			genl_rqstp.rq_proc = rqstp->rq_proc;
+			genl_rqstp.rq_stime = rqstp->rq_stime;
+			genl_rqstp.rq_opcnt = 0;
+			memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp),
+			       sizeof(struct sockaddr));
+			memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp),
+			       sizeof(struct sockaddr));
+
+#ifdef CONFIG_NFSD_V4
+			if (rqstp->rq_vers == NFS4_VERSION &&
+			    rqstp->rq_proc == NFSPROC4_COMPOUND) {
+				/* NFSv4 compound */
+				struct nfsd4_compoundargs *args;
+				int j;
+
+				args = rqstp->rq_argp;
+				genl_rqstp.rq_opcnt = args->opcnt;
+				for (j = 0; j < genl_rqstp.rq_opcnt; j++)
+					genl_rqstp.rq_opnum[j] =
+						args->ops[j].opnum;
+			}
+#endif /* CONFIG_NFSD_V4 */
+
+			/*
+			 * Acquire rq_status_counter before reporting the rqst
+			 * fields to the user.
+			 */
+			if (smp_load_acquire(&rqstp->rq_status_counter) !=
+			    status_counter)
+				continue;
+
+			ret = nfsd_genl_rpc_status_compose_msg(skb, cb,
+							       &genl_rqstp);
+			if (ret)
+				goto out;
+		}
+	}
+
+	cb->args[0] = i;
+	cb->args[1] = rqstp_index;
+	ret = skb->len;
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * nfsd_nl_rpc_status_get_done - rpc_status_get dumpit post-processing
+ * @cb: netlink metadata and command arguments
+ *
+ * Return values:
+ *   %0: Success
+ */
+int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb)
+{
+	mutex_lock(&nfsd_mutex);
+	nfsd_put(sock_net(cb->skb->sk));
+	mutex_unlock(&nfsd_mutex);
+
+	return 0;
+}
+
 /**
  * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace
  * @net: a freshly-created network namespace
@@ -1589,6 +1787,10 @@ static int __init init_nfsd(void)
 	retval = register_filesystem(&nfsd_fs_type);
 	if (retval)
 		goto out_free_all;
+	retval = genl_register_family(&nfsd_nl_family);
+	if (retval)
+		goto out_free_all;
+
 	return 0;
 out_free_all:
 	nfsd4_destroy_laundry_wq();
@@ -1613,6 +1815,7 @@ static int __init init_nfsd(void)
 
 static void __exit exit_nfsd(void)
 {
+	genl_unregister_family(&nfsd_nl_family);
 	unregister_filesystem(&nfsd_fs_type);
 	nfsd4_destroy_laundry_wq();
 	unregister_cld_notifier();

fs/nfsd/nfsd.h

@@ -62,6 +62,23 @@ struct readdir_cd {
 	__be32			err;	/* 0, nfserr, or nfserr_eof */
 };
 
+/* Maximum number of operations per session compound */
+#define NFSD_MAX_OPS_PER_COMPOUND	50
+
+struct nfsd_genl_rqstp {
+	struct sockaddr		rq_daddr;
+	struct sockaddr		rq_saddr;
+	unsigned long		rq_flags;
+	ktime_t			rq_stime;
+	__be32			rq_xid;
+	u32			rq_vers;
+	u32			rq_prog;
+	u32			rq_proc;
+
+	/* NFSv4 compound */
+	u32			rq_opcnt;
+	u32			rq_opnum[NFSD_MAX_OPS_PER_COMPOUND];
+};
 
 extern struct svc_program	nfsd_program;
 extern const struct svc_version	nfsd_version2, nfsd_version3, nfsd_version4;

fs/nfsd/nfsfh.c

@@ -771,7 +771,7 @@ enum fsid_source fsid_source(const struct svc_fh *fhp)
  * assume that the new change attr is always logged to stable storage in some
  * fashion before the results can be seen.
  */
-u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode)
+u64 nfsd4_change_attribute(const struct kstat *stat, const struct inode *inode)
 {
 	u64 chattr;
 

fs/nfsd/nfsfh.h

@@ -293,7 +293,8 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
 	fhp->fh_pre_saved = false;
 }
 
-u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode);
+u64 nfsd4_change_attribute(const struct kstat *stat,
+			   const struct inode *inode);
 __be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp);
 __be32 fh_fill_post_attrs(struct svc_fh *fhp);
 __be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp);

fs/nfsd/nfssvc.c

@@ -572,7 +572,6 @@ static void nfsd_last_thread(struct net *net)
 		return;
 
 	nfsd_shutdown_net(net);
-	pr_info("nfsd: last server has exited, flushing export cache\n");
 	nfsd_export_flush(net);
 }
 
@@ -713,14 +712,13 @@ int nfsd_nrpools(struct net *net)
 
 int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 {
-	int i = 0;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv = nn->nfsd_serv;
+	int i;
 
-	if (nn->nfsd_serv != NULL) {
-		for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++)
-			nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads;
-	}
-
+	if (serv)
+		for (i = 0; i < serv->sv_nrpools && i < n; i++)
+			nthreads[i] = atomic_read(&serv->sv_pools[i].sp_nrthreads);
 	return 0;
 }
 
@@ -787,7 +785,6 @@ int
 nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 {
 	int	error;
-	bool	nfsd_up_before;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_serv *serv;
 
@@ -807,8 +804,6 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 	error = nfsd_create_serv(net);
 	if (error)
 		goto out;
-
-	nfsd_up_before = nn->nfsd_net_up;
 	serv = nn->nfsd_serv;
 
 	error = nfsd_startup_net(net, cred);
@@ -816,17 +811,15 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 		goto out_put;
 	error = svc_set_num_threads(serv, NULL, nrservs);
 	if (error)
-		goto out_shutdown;
+		goto out_put;
 	error = serv->sv_nrthreads;
-	if (error == 0)
-		nfsd_last_thread(net);
-out_shutdown:
-	if (error < 0 && !nfsd_up_before)
-		nfsd_shutdown_net(net);
 out_put:
 	/* Threads now hold service active */
 	if (xchg(&nn->keep_active, 0))
 		svc_put(serv);
+
+	if (serv->sv_nrthreads == 0)
+		nfsd_last_thread(net);
 	svc_put(serv);
 out:
 	mutex_unlock(&nfsd_mutex);
@@ -957,7 +950,7 @@ nfsd(void *vrqstp)
 	/*
 	 * The main request loop
 	 */
-	while (!kthread_should_stop()) {
+	while (!svc_thread_should_stop(rqstp)) {
 		/* Update sv_maxconn if it has changed */
 		rqstp->rq_server->sv_maxconn = nn->max_connections;
 
@@ -998,6 +991,15 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream))
 		goto out_decode_err;
 
+	/*
+	 * Release rq_status_counter setting it to an odd value after the rpc
+	 * request has been properly parsed. rq_status_counter is used to
+	 * notify the consumers if the rqstp fields are stable
+	 * (rq_status_counter is odd) or not meaningful (rq_status_counter
+	 * is even).
+	 */
+	smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1);
+
 	rp = NULL;
 	switch (nfsd_cache_lookup(rqstp, &rp)) {
 	case RC_DOIT:
@@ -1015,6 +1017,12 @@ int nfsd_dispatch(struct svc_rqst *rqstp)
 	if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream))
 		goto out_encode_err;
 
+	/*
+	 * Release rq_status_counter setting it to an even value after the rpc
+	 * request has been properly processed.
+	 */
+	smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1);
+
 	nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1);
 out_cached_reply:
 	return 1;

fs/nfsd/pnfs.h

@@ -27,12 +27,12 @@ struct nfsd4_layout_ops {
 			struct nfs4_client *clp,
 			struct nfsd4_getdeviceinfo *gdevp);
 	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
-			struct nfsd4_getdeviceinfo *gdevp);
+			const struct nfsd4_getdeviceinfo *gdevp);
 
 	__be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
 			struct nfsd4_layoutget *lgp);
-	__be32 (*encode_layoutget)(struct xdr_stream *,
-			struct nfsd4_layoutget *lgp);
+	__be32 (*encode_layoutget)(struct xdr_stream *xdr,
+			const struct nfsd4_layoutget *lgp);
 
 	__be32 (*proc_layoutcommit)(struct inode *inode,
 			struct nfsd4_layoutcommit *lcp);

fs/nfsd/state.h

@@ -117,6 +117,24 @@ struct nfs4_cpntf_state {
 	time64_t		cpntf_time;	/* last time stateid used */
 };
 
+struct nfs4_cb_fattr {
+	struct nfsd4_callback ncf_getattr;
+	u32 ncf_cb_status;
+	u32 ncf_cb_bmap[1];
+
+	/* from CB_GETATTR reply */
+	u64 ncf_cb_change;
+	u64 ncf_cb_fsize;
+
+	unsigned long ncf_cb_flags;
+	bool ncf_file_modified;
+	u64 ncf_initial_cinfo;
+	u64 ncf_cur_fsize;
+};
+
+/* bits for ncf_cb_flags */
+#define	CB_GETATTR_BUSY		0
+
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -150,6 +168,9 @@ struct nfs4_delegation {
 	int			dl_retries;
 	struct nfsd4_callback	dl_recall;
 	bool			dl_recalled;
+
+	/* for CB_GETATTR */
+	struct nfs4_cb_fattr    dl_cb_fattr;
 };
 
 #define cb_to_delegation(cb) \
@@ -174,8 +195,6 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
 
 /* Maximum number of slots per session. 160 is useful for long haul TCP */
 #define NFSD_MAX_SLOTS_PER_SESSION     160
-/* Maximum number of operations per session compound */
-#define NFSD_MAX_OPS_PER_COMPOUND	50
 /* Maximum  session per slot cache size */
 #define NFSD_SLOT_CACHE_SIZE		2048
 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
@@ -642,6 +661,7 @@ enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_SEQUENCE,
 	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
 	NFSPROC4_CLNT_CB_RECALL_ANY,
+	NFSPROC4_CLNT_CB_GETATTR,
 };
 
 /* Returns true iff a is later than b: */
@@ -734,5 +754,6 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
 }
 
 extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
-				struct inode *inode);
+		struct inode *inode, bool *file_modified, u64 *size);
+extern void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf);
 #endif   /* NFSD4_STATE_H */

fs/nfsd/stats.c

@@ -60,7 +60,7 @@ static int nfsd_show(struct seq_file *seq, void *v)
 #ifdef CONFIG_NFSD_V4
 	/* Show count for individual nfsv4 operations */
 	/* Writing operation numbers 0 1 2 also for maintaining uniformity */
-	seq_printf(seq,"proc4ops %u", LAST_NFS4_OP + 1);
+	seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1);
 	for (i = 0; i <= LAST_NFS4_OP; i++) {
 		seq_printf(seq, " %lld",
 			   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)]));
@@ -76,7 +76,7 @@ static int nfsd_show(struct seq_file *seq, void *v)
 
 DEFINE_PROC_SHOW_ATTRIBUTE(nfsd);
 
-int nfsd_percpu_counters_init(struct percpu_counter counters[], int num)
+int nfsd_percpu_counters_init(struct percpu_counter *counters, int num)
 {
 	int i, err = 0;
 

fs/nfsd/stats.h

@@ -37,9 +37,9 @@ extern struct nfsd_stats	nfsdstats;
 
 extern struct svc_stat		nfsd_svcstats;
 
-int nfsd_percpu_counters_init(struct percpu_counter counters[], int num);
-void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num);
-void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num);
+int nfsd_percpu_counters_init(struct percpu_counter *counters, int num);
+void nfsd_percpu_counters_reset(struct percpu_counter *counters, int num);
+void nfsd_percpu_counters_destroy(struct percpu_counter *counters, int num);
 int nfsd_stat_init(void);
 void nfsd_stat_shutdown(void);
 
@@ -61,22 +61,22 @@ static inline void nfsd_stats_rc_nocache_inc(void)
 static inline void nfsd_stats_fh_stale_inc(struct svc_export *exp)
 {
 	percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_FH_STALE]);
-	if (exp)
-		percpu_counter_inc(&exp->ex_stats.counter[EXP_STATS_FH_STALE]);
+	if (exp && exp->ex_stats)
+		percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]);
 }
 
 static inline void nfsd_stats_io_read_add(struct svc_export *exp, s64 amount)
 {
 	percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_READ], amount);
-	if (exp)
-		percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_READ], amount);
+	if (exp && exp->ex_stats)
+		percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_READ], amount);
 }
 
 static inline void nfsd_stats_io_write_add(struct svc_export *exp, s64 amount)
 {
 	percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_WRITE], amount);
-	if (exp)
-		percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_WRITE], amount);
+	if (exp && exp->ex_stats)
+		percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_WRITE], amount);
 }
 
 static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn)

fs/nfsd/trace.h

@@ -1863,6 +1863,93 @@ TRACE_EVENT(nfsd_end_grace,
 	)
 );
 
+DECLARE_EVENT_CLASS(nfsd_copy_class,
+	TP_PROTO(
+		const struct nfsd4_copy *copy
+	),
+	TP_ARGS(copy),
+	TP_STRUCT__entry(
+		__field(bool, intra)
+		__field(bool, async)
+		__field(u32, src_cl_boot)
+		__field(u32, src_cl_id)
+		__field(u32, src_so_id)
+		__field(u32, src_si_generation)
+		__field(u32, dst_cl_boot)
+		__field(u32, dst_cl_id)
+		__field(u32, dst_so_id)
+		__field(u32, dst_si_generation)
+		__field(u64, src_cp_pos)
+		__field(u64, dst_cp_pos)
+		__field(u64, cp_count)
+		__sockaddr(addr, sizeof(struct sockaddr_in6))
+	),
+	TP_fast_assign(
+		const stateid_t *src_stp = &copy->cp_src_stateid;
+		const stateid_t *dst_stp = &copy->cp_dst_stateid;
+
+		__entry->intra = test_bit(NFSD4_COPY_F_INTRA, &copy->cp_flags);
+		__entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, &copy->cp_flags);
+		__entry->src_cl_boot = src_stp->si_opaque.so_clid.cl_boot;
+		__entry->src_cl_id = src_stp->si_opaque.so_clid.cl_id;
+		__entry->src_so_id = src_stp->si_opaque.so_id;
+		__entry->src_si_generation = src_stp->si_generation;
+		__entry->dst_cl_boot = dst_stp->si_opaque.so_clid.cl_boot;
+		__entry->dst_cl_id = dst_stp->si_opaque.so_clid.cl_id;
+		__entry->dst_so_id = dst_stp->si_opaque.so_id;
+		__entry->dst_si_generation = dst_stp->si_generation;
+		__entry->src_cp_pos = copy->cp_src_pos;
+		__entry->dst_cp_pos = copy->cp_dst_pos;
+		__entry->cp_count = copy->cp_count;
+		__assign_sockaddr(addr, &copy->cp_clp->cl_addr,
+				sizeof(struct sockaddr_in6));
+	),
+	TP_printk("client=%pISpc intra=%d async=%d "
+		"src_stateid[si_generation:0x%x cl_boot:0x%x cl_id:0x%x so_id:0x%x] "
+		"dst_stateid[si_generation:0x%x cl_boot:0x%x cl_id:0x%x so_id:0x%x] "
+		"cp_src_pos=%llu cp_dst_pos=%llu cp_count=%llu",
+		__get_sockaddr(addr), __entry->intra, __entry->async,
+		__entry->src_si_generation, __entry->src_cl_boot,
+		__entry->src_cl_id, __entry->src_so_id,
+		__entry->dst_si_generation, __entry->dst_cl_boot,
+		__entry->dst_cl_id, __entry->dst_so_id,
+		__entry->src_cp_pos, __entry->dst_cp_pos, __entry->cp_count
+	)
+);
+
+#define DEFINE_COPY_EVENT(name)				\
+DEFINE_EVENT(nfsd_copy_class, nfsd_copy_##name,	\
+	TP_PROTO(const struct nfsd4_copy *copy),	\
+	TP_ARGS(copy))
+
+DEFINE_COPY_EVENT(inter);
+DEFINE_COPY_EVENT(intra);
+DEFINE_COPY_EVENT(do_async);
+
+TRACE_EVENT(nfsd_copy_done,
+	TP_PROTO(
+		const struct nfsd4_copy *copy,
+		__be32 status
+	),
+	TP_ARGS(copy, status),
+	TP_STRUCT__entry(
+		__field(int, status)
+		__field(bool, intra)
+		__field(bool, async)
+		__sockaddr(addr, sizeof(struct sockaddr_in6))
+	),
+	TP_fast_assign(
+		__entry->status = be32_to_cpu(status);
+		__entry->intra = test_bit(NFSD4_COPY_F_INTRA, &copy->cp_flags);
+		__entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, &copy->cp_flags);
+		__assign_sockaddr(addr, &copy->cp_clp->cl_addr,
+				sizeof(struct sockaddr_in6));
+	),
+	TP_printk("addr=%pISpc status=%d intra=%d async=%d ",
+		__get_sockaddr(addr), __entry->status, __entry->intra, __entry->async
+	)
+);
+
 #endif /* _NFSD_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH

fs/nfsd/vfs.h

@@ -104,8 +104,8 @@ __be32		nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 int 		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
-__be32		nfsd_open_verified(struct svc_rqst *, struct svc_fh *,
-				int, struct file **);
+int		nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				   int may_flags, struct file **filp);
 __be32		nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
 				unsigned long *count,