Merge tag 'nfsd-5.4' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - Add a new knfsd file cache, so that we don't have to open and close
     on each (NFSv2/v3) READ or WRITE. This can speed up read and write
     in some cases. It also replaces our readahead cache.

   - Prevent silent data loss on write errors, by treating write errors
     like server reboots for the purposes of write caching, thus forcing
     clients to resend their writes.

   - Tweak the code that allocates sessions to be more forgiving, so
     that NFSv4.1 mounts are less likely to hang when a server already
     has a lot of clients.

   - Eliminate an arbitrary limit on NFSv4 ACL sizes; they should now be
     limited only by the backend filesystem and the maximum RPC size.

   - Allow the server to enforce use of the correct kerberos credentials
     when a client reclaims state after a reboot.

  And some miscellaneous smaller bugfixes and cleanup"

* tag 'nfsd-5.4' of git://linux-nfs.org/~bfields/linux: (34 commits)
  sunrpc: clean up indentation issue
  nfsd: fix nfs read eof detection
  nfsd: Make nfsd_reset_boot_verifier_locked static
  nfsd: degraded slot-count more gracefully as allocation nears exhaustion.
  nfsd: handle drc over-allocation gracefully.
  nfsd: add support for upcall version 2
  nfsd: add a "GetVersion" upcall for nfsdcld
  nfsd: Reset the boot verifier on all write I/O errors
  nfsd: Don't garbage collect files that might contain write errors
  nfsd: Support the server resetting the boot verifier
  nfsd: nfsd_file cache entries should be per net namespace
  nfsd: eliminate an unnecessary acl size limit
  Deprecate nfsd fault injection
  nfsd: remove duplicated include from filecache.c
  nfsd: Fix the documentation for svcxdr_tmpalloc()
  nfsd: Fix up some unused variable warnings
  nfsd: close cached files prior to a REMOVE or RENAME that would replace target
  nfsd: rip out the raparms cache
  nfsd: have nfsd_test_lock use the nfsd_file cache
  nfsd: hook up nfs4_preprocess_stateid_op to the nfsd_file cache
  ...

fs/file_table.c

@@ -327,6 +327,7 @@ void flush_delayed_fput(void)
 {
 	delayed_fput(NULL);
 }
+EXPORT_SYMBOL_GPL(flush_delayed_fput);
 
 static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 

fs/locks.c

@@ -212,6 +212,7 @@ struct file_lock_list_struct {
 static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list);
 DEFINE_STATIC_PERCPU_RWSEM(file_rwsem);
 
+
 /*
  * The blocked_hash is used to find POSIX lock loops for deadlock detection.
  * It is protected by blocked_lock_lock.
@@ -1991,6 +1992,64 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 }
 EXPORT_SYMBOL(generic_setlease);
 
+#if IS_ENABLED(CONFIG_SRCU)
+/*
+ * Kernel subsystems can register to be notified on any attempt to set
+ * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd
+ * to close files that it may have cached when there is an attempt to set a
+ * conflicting lease.
+ */
+static struct srcu_notifier_head lease_notifier_chain;
+
+static inline void
+lease_notifier_chain_init(void)
+{
+	srcu_init_notifier_head(&lease_notifier_chain);
+}
+
+static inline void
+setlease_notifier(long arg, struct file_lock *lease)
+{
+	if (arg != F_UNLCK)
+		srcu_notifier_call_chain(&lease_notifier_chain, arg, lease);
+}
+
+int lease_register_notifier(struct notifier_block *nb)
+{
+	return srcu_notifier_chain_register(&lease_notifier_chain, nb);
+}
+EXPORT_SYMBOL_GPL(lease_register_notifier);
+
+void lease_unregister_notifier(struct notifier_block *nb)
+{
+	srcu_notifier_chain_unregister(&lease_notifier_chain, nb);
+}
+EXPORT_SYMBOL_GPL(lease_unregister_notifier);
+
+#else /* !IS_ENABLED(CONFIG_SRCU) */
+static inline void
+lease_notifier_chain_init(void)
+{
+}
+
+static inline void
+setlease_notifier(long arg, struct file_lock *lease)
+{
+}
+
+int lease_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(lease_register_notifier);
+
+void lease_unregister_notifier(struct notifier_block *nb)
+{
+}
+EXPORT_SYMBOL_GPL(lease_unregister_notifier);
+
+#endif /* IS_ENABLED(CONFIG_SRCU) */
+
 /**
  * vfs_setlease        -       sets a lease on an open file
  * @filp:	file pointer
@@ -2011,6 +2070,8 @@ EXPORT_SYMBOL(generic_setlease);
 int
 vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
+	if (lease)
+		setlease_notifier(arg, *lease);
 	if (filp->f_op->setlease)
 		return filp->f_op->setlease(filp, arg, lease, priv);
 	else
@@ -2924,6 +2985,7 @@ static int __init filelock_init(void)
 		INIT_HLIST_HEAD(&fll->hlist);
 	}
 
+	lease_notifier_chain_init();
 	return 0;
 }
 core_initcall(filelock_init);

fs/nfsd/Kconfig

@@ -3,6 +3,7 @@ config NFSD
 	tristate "NFS server support"
 	depends on INET
 	depends on FILE_LOCKING
+	depends on FSNOTIFY
 	select LOCKD
 	select SUNRPC
 	select EXPORTFS
@@ -147,7 +148,7 @@ config NFSD_V4_SECURITY_LABEL
 
 config NFSD_FAULT_INJECTION
 	bool "NFS server manual fault injection"
-	depends on NFSD_V4 && DEBUG_KERNEL && DEBUG_FS
+	depends on NFSD_V4 && DEBUG_KERNEL && DEBUG_FS && BROKEN
 	help
 	  This option enables support for manually injecting faults
 	  into the NFS server.  This is intended to be used for

fs/nfsd/Makefile

@@ -11,7 +11,8 @@ obj-$(CONFIG_NFSD)	+= nfsd.o
 nfsd-y			+= trace.o
 
 nfsd-y 			+= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
-			   export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o
+			   export.o auth.o lockd.o nfscache.o nfsxdr.o \
+			   stats.o filecache.o
 nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
 nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o

fs/nfsd/acl.h

@@ -39,14 +39,6 @@ struct nfs4_acl;
 struct svc_fh;
 struct svc_rqst;
 
-/*
- * Maximum ACL we'll accept from a client; chosen (somewhat
- * arbitrarily) so that kmalloc'ing the ACL shouldn't require a
- * high-order allocation.  This allows 204 ACEs on x86_64:
- */
-#define NFS4_ACL_MAX ((PAGE_SIZE - sizeof(struct nfs4_acl)) \
-			/ sizeof(struct nfs4_ace))
-
 int nfs4_acl_bytes(int entries);
 int nfs4_acl_get_whotype(char *, u32);
 __be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who);

fs/nfsd/blocklayout.c

@@ -15,6 +15,7 @@
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_PNFS
 
@@ -404,7 +405,7 @@ static void
 nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls)
 {
 	struct nfs4_client *clp = ls->ls_stid.sc_client;
-	struct block_device *bdev = ls->ls_file->f_path.mnt->mnt_sb->s_bdev;
+	struct block_device *bdev = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_bdev;
 
 	bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
 			nfsd4_scsi_pr_key(clp), 0, true);

fs/nfsd/export.c

@@ -22,6 +22,7 @@
 #include "nfsfh.h"
 #include "netns.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -232,6 +233,17 @@ static struct cache_head *expkey_alloc(void)
 		return NULL;
 }
 
+static void expkey_flush(void)
+{
+	/*
+	 * Take the nfsd_mutex here to ensure that the file cache is not
+	 * destroyed while we're in the middle of flushing.
+	 */
+	mutex_lock(&nfsd_mutex);
+	nfsd_file_cache_purge(current->nsproxy->net_ns);
+	mutex_unlock(&nfsd_mutex);
+}
+
 static const struct cache_detail svc_expkey_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= EXPKEY_HASHMAX,
@@ -244,6 +256,7 @@ static const struct cache_detail svc_expkey_cache_template = {
 	.init		= expkey_init,
 	.update       	= expkey_update,
 	.alloc		= expkey_alloc,
+	.flush		= expkey_flush,
 };
 
 static int

fs/nfsd/filecache.h

+#ifndef _FS_NFSD_FILECACHE_H
+#define _FS_NFSD_FILECACHE_H
+
+#include <linux/fsnotify_backend.h>
+
+/*
+ * This is the fsnotify_mark container that nfsd attaches to the files that it
+ * is holding open. Note that we have a separate refcount here aside from the
+ * one in the fsnotify_mark. We only want a single fsnotify_mark attached to
+ * the inode, and for each nfsd_file to hold a reference to it.
+ *
+ * The fsnotify_mark is itself refcounted, but that's not sufficient to tell us
+ * how to put that reference. If there are still outstanding nfsd_files that
+ * reference the mark, then we would want to call fsnotify_put_mark on it.
+ * If there were not, then we'd need to call fsnotify_destroy_mark. Since we
+ * can't really tell the difference, we use the nfm_mark to keep track of how
+ * many nfsd_files hold references to the mark. When that counter goes to zero
+ * then we know to call fsnotify_destroy_mark on it.
+ */
+struct nfsd_file_mark {
+	struct fsnotify_mark	nfm_mark;
+	atomic_t		nfm_ref;
+};
+
+/*
+ * A representation of a file that has been opened by knfsd. These are hashed
+ * in the hashtable by inode pointer value. Note that this object doesn't
+ * hold a reference to the inode by itself, so the nf_inode pointer should
+ * never be dereferenced, only used for comparison.
+ */
+struct nfsd_file {
+	struct hlist_node	nf_node;
+	struct list_head	nf_lru;
+	struct rcu_head		nf_rcu;
+	struct file		*nf_file;
+	const struct cred	*nf_cred;
+	struct net		*nf_net;
+#define NFSD_FILE_HASHED	(0)
+#define NFSD_FILE_PENDING	(1)
+#define NFSD_FILE_BREAK_READ	(2)
+#define NFSD_FILE_BREAK_WRITE	(3)
+#define NFSD_FILE_REFERENCED	(4)
+	unsigned long		nf_flags;
+	struct inode		*nf_inode;
+	unsigned int		nf_hashval;
+	atomic_t		nf_ref;
+	unsigned char		nf_may;
+	struct nfsd_file_mark	*nf_mark;
+};
+
+int nfsd_file_cache_init(void);
+void nfsd_file_cache_purge(struct net *);
+void nfsd_file_cache_shutdown(void);
+void nfsd_file_put(struct nfsd_file *nf);
+struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
+void nfsd_file_close_inode_sync(struct inode *inode);
+bool nfsd_file_is_cached(struct inode *inode);
+__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
+int	nfsd_file_cache_stats_open(struct inode *, struct file *);
+#endif /* _FS_NFSD_FILECACHE_H */

fs/nfsd/netns.h

@@ -104,6 +104,7 @@ struct nfsd_net {
 
 	/* Time of server startup */
 	struct timespec64 nfssvc_boot;
+	seqlock_t boot_lock;
 
 	/*
 	 * Max number of connections this nfsd container will allow. Defaults
@@ -179,4 +180,7 @@ struct nfsd_net {
 extern void nfsd_netns_free_versions(struct nfsd_net *nn);
 
 extern unsigned int nfsd_net_id;
+
+void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn);
+void nfsd_reset_boot_verifier(struct nfsd_net *nn);
 #endif /* __NFSD_NETNS_H__ */

fs/nfsd/nfs3proc.c

@@ -172,13 +172,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
 	nfserr = nfsd_read(rqstp, &resp->fh,
 				  argp->offset,
 			   	  rqstp->rq_vec, argp->vlen,
-				  &resp->count);
-	if (nfserr == 0) {
-		struct inode	*inode = d_inode(resp->fh.fh_dentry);
-		resp->eof = nfsd_eof_on_read(cnt, resp->count, argp->offset,
-							inode->i_size);
-	}
-
+				  &resp->count,
+				  &resp->eof);
 	RETURN_STATUS(nfserr);
 }
 

fs/nfsd/nfs3xdr.c

@@ -27,6 +27,7 @@ static u32	nfs3_ftypes[] = {
 	NF3SOCK, NF3BAD,  NF3LNK, NF3BAD,
 };
 
+
 /*
  * XDR functions for basic NFS types
  */
@@ -751,14 +752,16 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	__be32 verf[2];
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
 		*p++ = htonl(resp->committed);
 		/* unique identifier, y2038 overflow can be ignored */
-		*p++ = htonl((u32)nn->nfssvc_boot.tv_sec);
-		*p++ = htonl(nn->nfssvc_boot.tv_nsec);
+		nfsd_copy_boot_verifier(verf, nn);
+		*p++ = verf[0];
+		*p++ = verf[1];
 	}
 	return xdr_ressize_check(rqstp, p);
 }
@@ -1125,13 +1128,15 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	__be32 verf[2];
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	/* Write verifier */
 	if (resp->status == 0) {
 		/* unique identifier, y2038 overflow can be ignored */
-		*p++ = htonl((u32)nn->nfssvc_boot.tv_sec);
-		*p++ = htonl(nn->nfssvc_boot.tv_nsec);
+		nfsd_copy_boot_verifier(verf, nn);
+		*p++ = verf[0];
+		*p++ = verf[1];
 	}
 	return xdr_ressize_check(rqstp, p);
 }

fs/nfsd/nfs4callback.c

@@ -512,11 +512,9 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 	if (unlikely(status))
 		return status;
 
-	if (cb != NULL) {
-		status = decode_cb_sequence4res(xdr, cb);
-		if (unlikely(status || cb->cb_seq_status))
-			return status;
-	}
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
 
 	return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status);
 }
@@ -604,11 +602,10 @@ static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
 	if (unlikely(status))
 		return status;
 
-	if (cb) {
-		status = decode_cb_sequence4res(xdr, cb);
-		if (unlikely(status || cb->cb_seq_status))
-			return status;
-	}
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+
 	return decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &cb->cb_status);
 }
 #endif /* CONFIG_NFSD_PNFS */
@@ -663,11 +660,10 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
 	if (unlikely(status))
 		return status;
 
-	if (cb) {
-		status = decode_cb_sequence4res(xdr, cb);
-		if (unlikely(status || cb->cb_seq_status))
-			return status;
-	}
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+
 	return decode_cb_op_status(xdr, OP_CB_NOTIFY_LOCK, &cb->cb_status);
 }
 
@@ -759,11 +755,10 @@ static int nfs4_xdr_dec_cb_offload(struct rpc_rqst *rqstp,
 	if (unlikely(status))
 		return status;
 
-	if (cb) {
-		status = decode_cb_sequence4res(xdr, cb);
-		if (unlikely(status || cb->cb_seq_status))
-			return status;
-	}
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+
 	return decode_cb_op_status(xdr, OP_CB_OFFLOAD, &cb->cb_status);
 }
 /*

fs/nfsd/nfs4layouts.c

@@ -169,8 +169,8 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 	spin_unlock(&fp->fi_lock);
 
 	if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
-		vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
-	fput(ls->ls_file);
+		vfs_setlease(ls->ls_file->nf_file, F_UNLCK, NULL, (void **)&ls);
+	nfsd_file_put(ls->ls_file);
 
 	if (ls->ls_recalled)
 		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);
@@ -197,7 +197,7 @@ nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
 	fl->fl_end = OFFSET_MAX;
 	fl->fl_owner = ls;
 	fl->fl_pid = current->tgid;
-	fl->fl_file = ls->ls_file;
+	fl->fl_file = ls->ls_file->nf_file;
 
 	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
 	if (status) {
@@ -236,13 +236,13 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 			NFSPROC4_CLNT_CB_LAYOUT);
 
 	if (parent->sc_type == NFS4_DELEG_STID)
-		ls->ls_file = get_file(fp->fi_deleg_file);
+		ls->ls_file = nfsd_file_get(fp->fi_deleg_file);
 	else
 		ls->ls_file = find_any_file(fp);
 	BUG_ON(!ls->ls_file);
 
 	if (nfsd4_layout_setlease(ls)) {
-		fput(ls->ls_file);
+		nfsd_file_put(ls->ls_file);
 		put_nfs4_file(fp);
 		kmem_cache_free(nfs4_layout_stateid_cache, ls);
 		return NULL;
@@ -626,7 +626,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
 	argv[0] = (char *)nfsd_recall_failed;
 	argv[1] = addr_str;
-	argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id;
+	argv[2] = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_id;
 	argv[3] = NULL;
 
 	error = call_usermodehelper(nfsd_recall_failed, argv, envp,

fs/nfsd/nfs4proc.c

@@ -568,17 +568,11 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
 {
-	__be32 verf[2];
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	__be32 *verf = (__be32 *)verifier->data;
 
-	/*
-	 * This is opaque to client, so no need to byte-swap. Use
-	 * __force to keep sparse happy. y2038 time_t overflow is
-	 * irrelevant in this usage.
-	 */
-	verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec;
-	verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec;
-	memcpy(verifier->data, verf, sizeof(verifier->data));
+	BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data));
+
+	nfsd_copy_boot_verifier(verf, net_generic(net, nfsd_net_id));
 }
 
 static __be32
@@ -761,7 +755,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfsd4_read *read = &u->read;
 	__be32 status;
 
-	read->rd_filp = NULL;
+	read->rd_nf = NULL;
 	if (read->rd_offset >= OFFSET_MAX)
 		return nfserr_inval;
 
@@ -782,7 +776,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	/* check stateid */
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					&read->rd_stateid, RD_STATE,
-					&read->rd_filp, &read->rd_tmp_file);
+					&read->rd_nf);
 	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
@@ -798,8 +792,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 static void
 nfsd4_read_release(union nfsd4_op_u *u)
 {
-	if (u->read.rd_filp)
-		fput(u->read.rd_filp);
+	if (u->read.rd_nf)
+		nfsd_file_put(u->read.rd_nf);
 	trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp,
 			     u->read.rd_offset, u->read.rd_length);
 }
@@ -954,7 +948,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
 				&cstate->current_fh, &setattr->sa_stateid,
-				WR_STATE, NULL, NULL);
+				WR_STATE, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -993,7 +987,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	struct nfsd4_write *write = &u->write;
 	stateid_t *stateid = &write->wr_stateid;
-	struct file *filp = NULL;
+	struct nfsd_file *nf = NULL;
 	__be32 status = nfs_ok;
 	unsigned long cnt;
 	int nvecs;
@@ -1005,7 +999,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	trace_nfsd_write_start(rqstp, &cstate->current_fh,
 			       write->wr_offset, cnt);
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
-						stateid, WR_STATE, &filp, NULL);
+						stateid, WR_STATE, &nf);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
@@ -1018,10 +1012,10 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				      &write->wr_head, write->wr_buflen);
 	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
-	status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp,
+	status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf->nf_file,
 				write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
 				write->wr_how_written);
-	fput(filp);
+	nfsd_file_put(nf);
 
 	write->wr_bytes_written = cnt;
 	trace_nfsd_write_done(rqstp, &cstate->current_fh,
@@ -1031,8 +1025,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		  stateid_t *src_stateid, struct file **src,
-		  stateid_t *dst_stateid, struct file **dst)
+		  stateid_t *src_stateid, struct nfsd_file **src,
+		  stateid_t *dst_stateid, struct nfsd_file **dst)
 {
 	__be32 status;
 
@@ -1040,22 +1034,22 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_nofilehandle;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
-					    src_stateid, RD_STATE, src, NULL);
+					    src_stateid, RD_STATE, src);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
 		goto out;
 	}
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
-					    dst_stateid, WR_STATE, dst, NULL);
+					    dst_stateid, WR_STATE, dst);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
 		goto out_put_src;
 	}
 
 	/* fix up for NFS-specific error code */
-	if (!S_ISREG(file_inode(*src)->i_mode) ||
-	    !S_ISREG(file_inode(*dst)->i_mode)) {
+	if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) ||
+	    !S_ISREG(file_inode((*dst)->nf_file)->i_mode)) {
 		status = nfserr_wrong_type;
 		goto out_put_dst;
 	}
@@ -1063,9 +1057,9 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 out:
 	return status;
 out_put_dst:
-	fput(*dst);
+	nfsd_file_put(*dst);
 out_put_src:
-	fput(*src);
+	nfsd_file_put(*src);
 	goto out;
 }
 
@@ -1074,7 +1068,7 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		union nfsd4_op_u *u)
 {
 	struct nfsd4_clone *clone = &u->clone;
-	struct file *src, *dst;
+	struct nfsd_file *src, *dst;
 	__be32 status;
 
 	status = nfsd4_verify_copy(rqstp, cstate, &clone->cl_src_stateid, &src,
@@ -1082,11 +1076,11 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out;
 
-	status = nfsd4_clone_file_range(src, clone->cl_src_pos,
-			dst, clone->cl_dst_pos, clone->cl_count);
+	status = nfsd4_clone_file_range(src->nf_file, clone->cl_src_pos,
+			dst->nf_file, clone->cl_dst_pos, clone->cl_count);
 
-	fput(dst);
-	fput(src);
+	nfsd_file_put(dst);
+	nfsd_file_put(src);
 out:
 	return status;
 }
@@ -1176,8 +1170,9 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
 	do {
 		if (kthread_should_stop())
 			break;
-		bytes_copied = nfsd_copy_file_range(copy->file_src, src_pos,
-				copy->file_dst, dst_pos, bytes_total);
+		bytes_copied = nfsd_copy_file_range(copy->nf_src->nf_file,
+				src_pos, copy->nf_dst->nf_file, dst_pos,
+				bytes_total);
 		if (bytes_copied <= 0)
 			break;
 		bytes_total -= bytes_copied;
@@ -1204,8 +1199,8 @@ static __be32 nfsd4_do_copy(struct nfsd4_copy *copy, bool sync)
 		status = nfs_ok;
 	}
 
-	fput(copy->file_src);
-	fput(copy->file_dst);
+	nfsd_file_put(copy->nf_src);
+	nfsd_file_put(copy->nf_dst);
 	return status;
 }
 
@@ -1218,16 +1213,16 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
 	memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res));
 	memcpy(&dst->fh, &src->fh, sizeof(src->fh));
 	dst->cp_clp = src->cp_clp;
-	dst->file_dst = get_file(src->file_dst);
-	dst->file_src = get_file(src->file_src);
+	dst->nf_dst = nfsd_file_get(src->nf_dst);
+	dst->nf_src = nfsd_file_get(src->nf_src);
 	memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid));
 }
 
 static void cleanup_async_copy(struct nfsd4_copy *copy)
 {
 	nfs4_free_cp_state(copy);
-	fput(copy->file_dst);
-	fput(copy->file_src);
+	nfsd_file_put(copy->nf_dst);
+	nfsd_file_put(copy->nf_src);
 	spin_lock(&copy->cp_clp->async_lock);
 	list_del(&copy->copies);
 	spin_unlock(&copy->cp_clp->async_lock);
@@ -1264,8 +1259,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfsd4_copy *async_copy = NULL;
 
 	status = nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
-				   &copy->file_src, &copy->cp_dst_stateid,
-				   &copy->file_dst);
+				   &copy->nf_src, &copy->cp_dst_stateid,
+				   &copy->nf_dst);
 	if (status)
 		goto out;
 
@@ -1347,21 +1342,21 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
 {
 	__be32 status;
-	struct file *file;
+	struct nfsd_file *nf;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &fallocate->falloc_stateid,
-					    WR_STATE, &file, NULL);
+					    WR_STATE, &nf);
 	if (status != nfs_ok) {
 		dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
 		return status;
 	}
 
-	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file,
+	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file,
 				     fallocate->falloc_offset,
 				     fallocate->falloc_length,
 				     flags);
-	fput(file);
+	nfsd_file_put(nf);
 	return status;
 }
 static __be32
@@ -1406,11 +1401,11 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfsd4_seek *seek = &u->seek;
 	int whence;
 	__be32 status;
-	struct file *file;
+	struct nfsd_file *nf;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &seek->seek_stateid,
-					    RD_STATE, &file, NULL);
+					    RD_STATE, &nf);
 	if (status) {
 		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
 		return status;
@@ -1432,14 +1427,14 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * Note:  This call does change file->f_pos, but nothing in NFSD
 	 *        should ever file->f_pos.
 	 */
-	seek->seek_pos = vfs_llseek(file, seek->seek_offset, whence);
+	seek->seek_pos = vfs_llseek(nf->nf_file, seek->seek_offset, whence);
 	if (seek->seek_pos < 0)
 		status = nfserrno(seek->seek_pos);
-	else if (seek->seek_pos >= i_size_read(file_inode(file)))
+	else if (seek->seek_pos >= i_size_read(file_inode(nf->nf_file)))
 		seek->seek_eof = true;
 
 out:
-	fput(file);
+	nfsd_file_put(nf);
 	return status;
 }
 

fs/nfsd/nfs4xdr.c

@@ -49,6 +49,7 @@
 #include "cache.h"
 #include "netns.h"
 #include "pnfs.h"
+#include "filecache.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -203,6 +204,13 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
 	return p;
 }
 
+static unsigned int compoundargs_bytes_left(struct nfsd4_compoundargs *argp)
+{
+	unsigned int this = (char *)argp->end - (char *)argp->p;
+
+	return this + argp->pagelen;
+}
+
 static int zero_clientid(clientid_t *clid)
 {
 	return (clid->cl_boot == 0) && (clid->cl_id == 0);
@@ -211,10 +219,10 @@ static int zero_clientid(clientid_t *clid)
 /**
  * svcxdr_tmpalloc - allocate memory to be freed after compound processing
  * @argp: NFSv4 compound argument structure
- * @p: pointer to be freed (with kfree())
+ * @len: length of buffer to allocate
  *
- * Marks @p to be freed when processing the compound operation
- * described in @argp finishes.
+ * Allocates a buffer of size @len to be freed when processing the compound
+ * operation described in @argp finishes.
  */
 static void *
 svcxdr_tmpalloc(struct nfsd4_compoundargs *argp, u32 len)
@@ -347,7 +355,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		READ_BUF(4); len += 4;
 		nace = be32_to_cpup(p++);
 
-		if (nace > NFS4_ACL_MAX)
+		if (nace > compoundargs_bytes_left(argp)/20)
+			/*
+			 * Even with 4-byte names there wouldn't be
+			 * space for that many aces; something fishy is
+			 * going on:
+			 */
 			return nfserr_fbig;
 
 		*acl = svcxdr_tmpalloc(argp, nfs4_acl_bytes(nace));
@@ -1418,7 +1431,6 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 			    struct nfsd4_create_session *sess)
 {
 	DECODE_HEAD;
-	u32 dummy;
 
 	READ_BUF(16);
 	COPYMEM(&sess->clientid, 8);
@@ -1427,7 +1439,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 
 	/* Fore channel attrs */
 	READ_BUF(28);
-	dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */
+	p++; /* headerpadsz is always 0 */
 	sess->fore_channel.maxreq_sz = be32_to_cpup(p++);
 	sess->fore_channel.maxresp_sz = be32_to_cpup(p++);
 	sess->fore_channel.maxresp_cached = be32_to_cpup(p++);
@@ -1444,7 +1456,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 
 	/* Back channel attrs */
 	READ_BUF(28);
-	dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */
+	p++; /* headerpadsz is always 0 */
 	sess->back_channel.maxreq_sz = be32_to_cpup(p++);
 	sess->back_channel.maxresp_sz = be32_to_cpup(p++);
 	sess->back_channel.maxresp_cached = be32_to_cpup(p++);
@@ -1736,7 +1748,6 @@ static __be32
 nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
 {
 	DECODE_HEAD;
-	unsigned int tmp;
 
 	status = nfsd4_decode_stateid(argp, &copy->cp_src_stateid);
 	if (status)
@@ -1751,7 +1762,7 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)
 	p = xdr_decode_hyper(p, &copy->cp_count);
 	p++; /* ca_consecutive: we always do consecutive copies */
 	copy->cp_synchronous = be32_to_cpup(p++);
-	tmp = be32_to_cpup(p); /* Source server list not supported */
+	/* tmp = be32_to_cpup(p); Source server list not supported */
 
 	DECODE_TAIL;
 }
@@ -3217,9 +3228,8 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 	if (!p)
 		return nfserr_resource;
 	encode_cinfo(p, &create->cr_cinfo);
-	nfserr = nfsd4_encode_bitmap(xdr, create->cr_bmval[0],
+	return nfsd4_encode_bitmap(xdr, create->cr_bmval[0],
 			create->cr_bmval[1], create->cr_bmval[2]);
-	return 0;
 }
 
 static __be32
@@ -3462,7 +3472,7 @@ static __be32 nfsd4_encode_splice_read(
 
 	len = maxcount;
 	nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp,
-				  file, read->rd_offset, &maxcount);
+				  file, read->rd_offset, &maxcount, &eof);
 	read->rd_length = maxcount;
 	if (nfserr) {
 		/*
@@ -3474,9 +3484,6 @@ static __be32 nfsd4_encode_splice_read(
 		return nfserr;
 	}
 
-	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
-				d_inode(read->rd_fhp->fh_dentry)->i_size);
-
 	*(p++) = htonl(eof);
 	*(p++) = htonl(maxcount);
 
@@ -3547,15 +3554,13 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 
 	len = maxcount;
 	nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset,
-			    resp->rqstp->rq_vec, read->rd_vlen, &maxcount);
+			    resp->rqstp->rq_vec, read->rd_vlen, &maxcount,
+			    &eof);
 	read->rd_length = maxcount;
 	if (nfserr)
 		return nfserr;
 	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
 
-	eof = nfsd_eof_on_read(len, maxcount, read->rd_offset,
-				d_inode(read->rd_fhp->fh_dentry)->i_size);
-
 	tmp = htonl(eof);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len    , &tmp, 4);
 	tmp = htonl(maxcount);
@@ -3574,11 +3579,14 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 {
 	unsigned long maxcount;
 	struct xdr_stream *xdr = &resp->xdr;
-	struct file *file = read->rd_filp;
+	struct file *file;
 	int starting_len = xdr->buf->len;
-	struct raparms *ra = NULL;
 	__be32 *p;
 
+	if (nfserr)
+		return nfserr;
+	file = read->rd_nf->nf_file;
+
 	p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
 	if (!p) {
 		WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));
@@ -3596,18 +3604,12 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 			 (xdr->buf->buflen - xdr->buf->len));
 	maxcount = min_t(unsigned long, maxcount, read->rd_length);
 
-	if (read->rd_tmp_file)
-		ra = nfsd_init_raparms(file);
-
 	if (file->f_op->splice_read &&
 	    test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags))
 		nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount);
 	else
 		nfserr = nfsd4_encode_readv(resp, read, file, maxcount);
 
-	if (ra)
-		nfsd_put_raparams(file, ra);
-
 	if (nfserr)
 		xdr_truncate_encode(xdr, starting_len);
 

fs/nfsd/nfsctl.c

@@ -1476,6 +1476,7 @@ static __net_init int nfsd_init_net(struct net *net)
 
 	atomic_set(&nn->ntf_refcnt, 0);
 	init_waitqueue_head(&nn->ntf_wq);
+	seqlock_init(&nn->boot_lock);
 
 	mnt =  vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
 	if (IS_ERR(mnt)) {

fs/nfsd/nfsproc.c

@@ -172,6 +172,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
 	struct nfsd_readargs *argp = rqstp->rq_argp;
 	struct nfsd_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
+	u32 eof;
 
 	dprintk("nfsd: READ    %s %d bytes at %d\n",
 		SVCFH_fmt(&argp->fh),
@@ -195,7 +196,8 @@ nfsd_proc_read(struct svc_rqst *rqstp)
 	nfserr = nfsd_read(rqstp, fh_copy(&resp->fh, &argp->fh),
 				  argp->offset,
 			   	  rqstp->rq_vec, argp->vlen,
-				  &resp->count);
+				  &resp->count,
+				  &eof);
 
 	if (nfserr) return nfserr;
 	return fh_getattr(&resp->fh, &resp->stat);

fs/nfsd/nfssvc.c

@@ -27,6 +27,7 @@
 #include "cache.h"
 #include "vfs.h"
 #include "netns.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
@@ -313,22 +314,17 @@ static int nfsd_startup_generic(int nrservs)
 	if (nfsd_users++)
 		return 0;
 
-	/*
-	 * Readahead param cache - will no-op if it already exists.
-	 * (Note therefore results will be suboptimal if number of
-	 * threads is modified after nfsd start.)
-	 */
-	ret = nfsd_racache_init(2*nrservs);
+	ret = nfsd_file_cache_init();
 	if (ret)
 		goto dec_users;
 
 	ret = nfs4_state_start();
 	if (ret)
-		goto out_racache;
+		goto out_file_cache;
 	return 0;
 
-out_racache:
-	nfsd_racache_shutdown();
+out_file_cache:
+	nfsd_file_cache_shutdown();
 dec_users:
 	nfsd_users--;
 	return ret;
@@ -340,7 +336,7 @@ static void nfsd_shutdown_generic(void)
 		return;
 
 	nfs4_state_shutdown();
-	nfsd_racache_shutdown();
+	nfsd_file_cache_shutdown();
 }
 
 static bool nfsd_needs_lockd(struct nfsd_net *nn)
@@ -348,6 +344,35 @@ static bool nfsd_needs_lockd(struct nfsd_net *nn)
 	return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST);
 }
 
+void nfsd_copy_boot_verifier(__be32 verf[2], struct nfsd_net *nn)
+{
+	int seq = 0;
+
+	do {
+		read_seqbegin_or_lock(&nn->boot_lock, &seq);
+		/*
+		 * This is opaque to client, so no need to byte-swap. Use
+		 * __force to keep sparse happy. y2038 time_t overflow is
+		 * irrelevant in this usage
+		 */
+		verf[0] = (__force __be32)nn->nfssvc_boot.tv_sec;
+		verf[1] = (__force __be32)nn->nfssvc_boot.tv_nsec;
+	} while (need_seqretry(&nn->boot_lock, seq));
+	done_seqretry(&nn->boot_lock, seq);
+}
+
+static void nfsd_reset_boot_verifier_locked(struct nfsd_net *nn)
+{
+	ktime_get_real_ts64(&nn->nfssvc_boot);
+}
+
+void nfsd_reset_boot_verifier(struct nfsd_net *nn)
+{
+	write_seqlock(&nn->boot_lock);
+	nfsd_reset_boot_verifier_locked(nn);
+	write_sequnlock(&nn->boot_lock);
+}
+
 static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cred)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -391,6 +416,7 @@ static void nfsd_shutdown_net(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
+	nfsd_file_cache_purge(net);
 	nfs4_state_shutdown_net(net);
 	if (nn->lockd_up) {
 		lockd_down(net);
@@ -599,7 +625,7 @@ int nfsd_create_serv(struct net *net)
 #endif
 	}
 	atomic_inc(&nn->ntf_refcnt);
-	ktime_get_real_ts64(&nn->nfssvc_boot); /* record boot time */
+	nfsd_reset_boot_verifier(nn);
 	return 0;
 }
 

fs/nfsd/state.h

@@ -378,6 +378,7 @@ struct nfs4_client_reclaim {
 	struct list_head	cr_strhash;	/* hash by cr_name */
 	struct nfs4_client	*cr_clp;	/* pointer to associated clp */
 	struct xdr_netobj	cr_name;	/* recovery dir name */
+	struct xdr_netobj	cr_princhash;
 };
 
 /* A reasonable value for REPLAY_ISIZE was estimated as follows:  
@@ -506,7 +507,7 @@ struct nfs4_file {
 	};
 	struct list_head	fi_clnt_odstate;
 	/* One each for O_RDONLY, O_WRONLY, O_RDWR: */
-	struct file *		fi_fds[3];
+	struct nfsd_file	*fi_fds[3];
 	/*
 	 * Each open or lock stateid contributes 0-4 to the counts
 	 * below depending on which bits are set in st_access_bitmap:
@@ -516,7 +517,7 @@ struct nfs4_file {
 	 */
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
-	struct file		*fi_deleg_file;
+	struct nfsd_file	*fi_deleg_file;
 	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
@@ -565,7 +566,7 @@ struct nfs4_layout_stateid {
 	spinlock_t			ls_lock;
 	struct list_head		ls_layouts;
 	u32				ls_layout_type;
-	struct file			*ls_file;
+	struct nfsd_file		*ls_file;
 	struct nfsd4_callback		ls_recall;
 	stateid_t			ls_recall_sid;
 	bool				ls_recalled;
@@ -616,7 +617,7 @@ struct nfsd4_copy;
 
 extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
-		stateid_t *stateid, int flags, struct file **filp, bool *tmp_file);
+		stateid_t *stateid, int flags, struct nfsd_file **filp);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
@@ -645,7 +646,7 @@ extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfsd4_shutdown_copy(struct nfs4_client *clp);
 extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
 extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
-							struct nfsd_net *nn);
+				struct xdr_netobj princhash, struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
 
 struct nfs4_file *find_file(struct knfsd_fh *fh);
@@ -657,7 +658,7 @@ static inline void get_nfs4_file(struct nfs4_file *fi)
 {
 	refcount_inc(&fi->fi_ref);
 }
-struct file *find_any_file(struct nfs4_file *f);
+struct nfsd_file *find_any_file(struct nfs4_file *f);
 
 /* grace period management */
 void nfsd4_end_grace(struct nfsd_net *nn);

fs/nfsd/trace.h

@@ -126,6 +126,8 @@ DEFINE_NFSD_ERR_EVENT(read_err);
 DEFINE_NFSD_ERR_EVENT(write_err);
 
 #include "state.h"
+#include "filecache.h"
+#include "vfs.h"
 
 DECLARE_EVENT_CLASS(nfsd_stateid_class,
 	TP_PROTO(stateid_t *stp),
@@ -164,6 +166,144 @@ DEFINE_STATEID_EVENT(layout_recall_done);
 DEFINE_STATEID_EVENT(layout_recall_fail);
 DEFINE_STATEID_EVENT(layout_recall_release);
 
+#define show_nf_flags(val)						\
+	__print_flags(val, "|",						\
+		{ 1 << NFSD_FILE_HASHED,	"HASHED" },		\
+		{ 1 << NFSD_FILE_PENDING,	"PENDING" },		\
+		{ 1 << NFSD_FILE_BREAK_READ,	"BREAK_READ" },		\
+		{ 1 << NFSD_FILE_BREAK_WRITE,	"BREAK_WRITE" },	\
+		{ 1 << NFSD_FILE_REFERENCED,	"REFERENCED"})
+
+/* FIXME: This should probably be fleshed out in the future. */
+#define show_nf_may(val)						\
+	__print_flags(val, "|",						\
+		{ NFSD_MAY_READ,		"READ" },		\
+		{ NFSD_MAY_WRITE,		"WRITE" },		\
+		{ NFSD_MAY_NOT_BREAK_LEASE,	"NOT_BREAK_LEASE" })
+
+DECLARE_EVENT_CLASS(nfsd_file_class,
+	TP_PROTO(struct nfsd_file *nf),
+	TP_ARGS(nf),
+	TP_STRUCT__entry(
+		__field(unsigned int, nf_hashval)
+		__field(void *, nf_inode)
+		__field(int, nf_ref)
+		__field(unsigned long, nf_flags)
+		__field(unsigned char, nf_may)
+		__field(struct file *, nf_file)
+	),
+	TP_fast_assign(
+		__entry->nf_hashval = nf->nf_hashval;
+		__entry->nf_inode = nf->nf_inode;
+		__entry->nf_ref = atomic_read(&nf->nf_ref);
+		__entry->nf_flags = nf->nf_flags;
+		__entry->nf_may = nf->nf_may;
+		__entry->nf_file = nf->nf_file;
+	),
+	TP_printk("hash=0x%x inode=0x%p ref=%d flags=%s may=%s file=%p",
+		__entry->nf_hashval,
+		__entry->nf_inode,
+		__entry->nf_ref,
+		show_nf_flags(__entry->nf_flags),
+		show_nf_may(__entry->nf_may),
+		__entry->nf_file)
+)
+
+#define DEFINE_NFSD_FILE_EVENT(name) \
+DEFINE_EVENT(nfsd_file_class, name, \
+	TP_PROTO(struct nfsd_file *nf), \
+	TP_ARGS(nf))
+
+DEFINE_NFSD_FILE_EVENT(nfsd_file_alloc);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_put_final);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_put);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_release_locked);
+
+TRACE_EVENT(nfsd_file_acquire,
+	TP_PROTO(struct svc_rqst *rqstp, unsigned int hash,
+		 struct inode *inode, unsigned int may_flags,
+		 struct nfsd_file *nf, __be32 status),
+
+	TP_ARGS(rqstp, hash, inode, may_flags, nf, status),
+
+	TP_STRUCT__entry(
+		__field(__be32, xid)
+		__field(unsigned int, hash)
+		__field(void *, inode)
+		__field(unsigned int, may_flags)
+		__field(int, nf_ref)
+		__field(unsigned long, nf_flags)
+		__field(unsigned char, nf_may)
+		__field(struct file *, nf_file)
+		__field(__be32, status)
+	),
+
+	TP_fast_assign(
+		__entry->xid = rqstp->rq_xid;
+		__entry->hash = hash;
+		__entry->inode = inode;
+		__entry->may_flags = may_flags;
+		__entry->nf_ref = nf ? atomic_read(&nf->nf_ref) : 0;
+		__entry->nf_flags = nf ? nf->nf_flags : 0;
+		__entry->nf_may = nf ? nf->nf_may : 0;
+		__entry->nf_file = nf ? nf->nf_file : NULL;
+		__entry->status = status;
+	),
+
+	TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u",
+			be32_to_cpu(__entry->xid), __entry->hash, __entry->inode,
+			show_nf_may(__entry->may_flags), __entry->nf_ref,
+			show_nf_flags(__entry->nf_flags),
+			show_nf_may(__entry->nf_may), __entry->nf_file,
+			be32_to_cpu(__entry->status))
+);
+
+DECLARE_EVENT_CLASS(nfsd_file_search_class,
+	TP_PROTO(struct inode *inode, unsigned int hash, int found),
+	TP_ARGS(inode, hash, found),
+	TP_STRUCT__entry(
+		__field(struct inode *, inode)
+		__field(unsigned int, hash)
+		__field(int, found)
+	),
+	TP_fast_assign(
+		__entry->inode = inode;
+		__entry->hash = hash;
+		__entry->found = found;
+	),
+	TP_printk("hash=0x%x inode=0x%p found=%d", __entry->hash,
+			__entry->inode, __entry->found)
+);
+
+#define DEFINE_NFSD_FILE_SEARCH_EVENT(name)				\
+DEFINE_EVENT(nfsd_file_search_class, name,				\
+	TP_PROTO(struct inode *inode, unsigned int hash, int found),	\
+	TP_ARGS(inode, hash, found))
+
+DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync);
+DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode);
+DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_is_cached);
+
+TRACE_EVENT(nfsd_file_fsnotify_handle_event,
+	TP_PROTO(struct inode *inode, u32 mask),
+	TP_ARGS(inode, mask),
+	TP_STRUCT__entry(
+		__field(struct inode *, inode)
+		__field(unsigned int, nlink)
+		__field(umode_t, mode)
+		__field(u32, mask)
+	),
+	TP_fast_assign(
+		__entry->inode = inode;
+		__entry->nlink = inode->i_nlink;
+		__entry->mode = inode->i_mode;
+		__entry->mask = mask;
+	),
+	TP_printk("inode=0x%p nlink=%u mode=0%ho mask=0x%x", __entry->inode,
+			__entry->nlink, __entry->mode, __entry->mask)
+);
+
 #endif /* _NFSD_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH

fs/nfsd/vfs.h

@@ -40,8 +40,6 @@
 typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
 
 /* nfsd/vfs.c */
-int		nfsd_racache_init(int);
-void		nfsd_racache_shutdown(void);
 int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 		                struct svc_export **expp);
 __be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,
@@ -75,18 +73,23 @@ __be32		do_nfsd_create(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
 				loff_t, unsigned long);
 #endif /* CONFIG_NFSD_V3 */
+int 		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
-struct raparms;
+__be32		nfsd_open_verified(struct svc_rqst *, struct svc_fh *, umode_t,
+				int, struct file **);
 __be32		nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
-				unsigned long *count);
+				unsigned long *count,
+				u32 *eof);
 __be32		nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
 				struct kvec *vec, int vlen,
-				unsigned long *count);
+				unsigned long *count,
+				u32 *eof);
 __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *,
-				loff_t, struct kvec *, int, unsigned long *);
+				loff_t, struct kvec *, int, unsigned long *,
+				u32 *eof);
 __be32 		nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t,
 				struct kvec *, int, unsigned long *, int);
 __be32		nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -115,9 +118,6 @@ __be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd_permission(struct svc_rqst *, struct svc_export *,
 				struct dentry *, int);
 
-struct raparms *nfsd_init_raparms(struct file *file);
-void		nfsd_put_raparams(struct file *file, struct raparms *ra);
-
 static inline int fh_want_write(struct svc_fh *fh)
 {
 	int ret;
@@ -152,23 +152,4 @@ static inline int nfsd_create_is_exclusive(int createmode)
 	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
 }
 
-static inline bool nfsd_eof_on_read(long requested, long read,
-				loff_t offset, loff_t size)
-{
-	/* We assume a short read means eof: */
-	if (requested > read)
-		return true;
-	/*
-	 * A non-short read might also reach end of file.  The spec
-	 * still requires us to set eof in that case.
-	 *
-	 * Further operations may have modified the file size since
-	 * the read, so the following check is not atomic with the read.
-	 * We've only seen that cause a problem for a client in the case
-	 * where the read returned a count of 0 without setting eof.
-	 * That case was fixed by the addition of the above check.
-	 */
-	return (offset + read >= size);
-}
-
 #endif /* LINUX_NFSD_VFS_H */

fs/nfsd/xdr3.h

@@ -151,7 +151,7 @@ struct nfsd3_readres {
 	__be32			status;
 	struct svc_fh		fh;
 	unsigned long		count;
-	int			eof;
+	__u32			eof;
 };
 
 struct nfsd3_writeres {

fs/nfsd/xdr4.h

@@ -273,15 +273,14 @@ struct nfsd4_open_downgrade {
 
 
 struct nfsd4_read {
-	stateid_t	rd_stateid;         /* request */
-	u64		rd_offset;          /* request */
-	u32		rd_length;          /* request */
-	int		rd_vlen;
-	struct file     *rd_filp;
-	bool		rd_tmp_file;
+	stateid_t		rd_stateid;         /* request */
+	u64			rd_offset;          /* request */
+	u32			rd_length;          /* request */
+	int			rd_vlen;
+	struct nfsd_file	*rd_nf;
 	
-	struct svc_rqst *rd_rqstp;          /* response */
-	struct svc_fh * rd_fhp;             /* response */
+	struct svc_rqst		*rd_rqstp;          /* response */
+	struct svc_fh		*rd_fhp;             /* response */
 };
 
 struct nfsd4_readdir {
@@ -538,8 +537,8 @@ struct nfsd4_copy {
 
 	struct nfs4_client      *cp_clp;
 
-	struct file             *file_src;
-	struct file             *file_dst;
+	struct nfsd_file        *nf_src;
+	struct nfsd_file        *nf_dst;
 
 	stateid_t		cp_stateid;
 

fs/notify/fsnotify.h

@@ -54,8 +54,6 @@ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
 {
 	fsnotify_destroy_marks(&sb->s_fsnotify_marks);
 }
-/* Wait until all marks queued for destruction are destroyed */
-extern void fsnotify_wait_marks_destroyed(void);
 
 /*
  * update the dentry->d_flags of all of inode's children to indicate if inode cares

fs/notify/group.c

@@ -108,6 +108,7 @@ void fsnotify_put_group(struct fsnotify_group *group)
 	if (refcount_dec_and_test(&group->refcnt))
 		fsnotify_final_destroy_group(group);
 }
+EXPORT_SYMBOL_GPL(fsnotify_put_group);
 
 /*
  * Create a new fsnotify_group and hold a reference for the group returned.
@@ -137,6 +138,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 
 	return group;
 }
+EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
 
 int fsnotify_fasync(int fd, struct file *file, int on)
 {

fs/notify/mark.c

@@ -276,6 +276,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	queue_delayed_work(system_unbound_wq, &reaper_work,
 			   FSNOTIFY_REAPER_DELAY);
 }
+EXPORT_SYMBOL_GPL(fsnotify_put_mark);
 
 /*
  * Get mark reference when we found the mark via lockless traversal of object
@@ -430,6 +431,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	mutex_unlock(&group->mark_mutex);
 	fsnotify_free_mark(mark);
 }
+EXPORT_SYMBOL_GPL(fsnotify_destroy_mark);
 
 /*
  * Sorting function for lists of fsnotify marks.
@@ -685,6 +687,7 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
 	mutex_unlock(&group->mark_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(fsnotify_add_mark);
 
 /*
  * Given a list of marks, find the mark associated with given group. If found
@@ -711,6 +714,7 @@ struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
 	spin_unlock(&conn->lock);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(fsnotify_find_mark);
 
 /* Clear any marks in a group with given type mask */
 void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
@@ -809,6 +813,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	mark->group = group;
 	WRITE_ONCE(mark->connector, NULL);
 }
+EXPORT_SYMBOL_GPL(fsnotify_init_mark);
 
 /*
  * Destroy all marks in destroy_list, waits for SRCU period to finish before
@@ -837,3 +842,4 @@ void fsnotify_wait_marks_destroyed(void)
 {
 	flush_delayed_work(&reaper_work);
 }
+EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed);

include/linux/fs.h

@@ -1168,6 +1168,11 @@ extern void lease_get_mtime(struct inode *, struct timespec64 *time);
 extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
 extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
 extern int lease_modify(struct file_lock *, int, struct list_head *);
+
+struct notifier_block;
+extern int lease_register_notifier(struct notifier_block *);
+extern void lease_unregister_notifier(struct notifier_block *);
+
 struct files_struct;
 extern void show_fd_locks(struct seq_file *f,
 			 struct file *filp, struct files_struct *files);

include/linux/fsnotify_backend.h

@@ -475,6 +475,8 @@ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 extern void fsnotify_detach_mark(struct fsnotify_mark *mark);
 /* free mark */
 extern void fsnotify_free_mark(struct fsnotify_mark *mark);
+/* Wait until all marks queued for destruction are destroyed */
+extern void fsnotify_wait_marks_destroyed(void);
 /* run all the marks in a group, and clear all of the marks attached to given object type */
 extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type);
 /* run all the marks in a group, and clear all of the vfsmount marks */

include/linux/sunrpc/cache.h

@@ -87,6 +87,7 @@ struct cache_detail {
 					      int has_died);
 
 	struct cache_head *	(*alloc)(void);
+	void			(*flush)(void);
 	int			(*match)(struct cache_head *orig, struct cache_head *new);
 	void			(*init)(struct cache_head *orig, struct cache_head *new);
 	void			(*update)(struct cache_head *orig, struct cache_head *new);
@@ -107,9 +108,9 @@ struct cache_detail {
 	/* fields for communication over channel */
 	struct list_head	queue;
 
-	atomic_t		readers;		/* how many time is /chennel open */
-	time_t			last_close;		/* if no readers, when did last close */
-	time_t			last_warn;		/* when we last warned about no readers */
+	atomic_t		writers;		/* how many time is /channel open */
+	time_t			last_close;		/* if no writers, when did last close */
+	time_t			last_warn;		/* when we last warned about no writers */
 
 	union {
 		struct proc_dir_entry	*procfs;

include/linux/sunrpc/svc_rdma.h

@@ -42,6 +42,7 @@
 
 #ifndef SVC_RDMA_H
 #define SVC_RDMA_H
+#include <linux/llist.h>
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/rpc_rdma.h>
@@ -107,8 +108,7 @@ struct svcxprt_rdma {
 	struct list_head     sc_read_complete_q;
 	struct work_struct   sc_work;
 
-	spinlock_t	     sc_recv_lock;
-	struct list_head     sc_recv_ctxts;
+	struct llist_head    sc_recv_ctxts;
 };
 /* sc_flags */
 #define RDMAXPRT_CONN_PENDING	3
@@ -125,6 +125,7 @@ enum {
 #define RPCSVC_MAXPAYLOAD_RDMA	RPCSVC_MAXPAYLOAD
 
 struct svc_rdma_recv_ctxt {
+	struct llist_node	rc_node;
 	struct list_head	rc_list;
 	struct ib_recv_wr	rc_recv_wr;
 	struct ib_cqe		rc_cqe;
@@ -200,7 +201,6 @@ extern struct svc_xprt_class svc_rdma_bc_class;
 #endif
 
 /* svc_rdma.c */
-extern struct workqueue_struct *svc_rdma_wq;
 extern int svc_rdma_init(void);
 extern void svc_rdma_cleanup(void);
 

include/uapi/linux/nfsd/cld.h

@@ -26,17 +26,22 @@
 #include <linux/types.h>
 
 /* latest upcall version available */
-#define CLD_UPCALL_VERSION 1
+#define CLD_UPCALL_VERSION 2
 
 /* defined by RFC3530 */
 #define NFS4_OPAQUE_LIMIT 1024
 
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
 enum cld_command {
 	Cld_Create,		/* create a record for this cm_id */
 	Cld_Remove,		/* remove record of this cm_id */
 	Cld_Check,		/* is this cm_id allowed? */
 	Cld_GraceDone,		/* grace period is complete */
-	Cld_GraceStart,
+	Cld_GraceStart,		/* grace start (upload client records) */
+	Cld_GetVersion,		/* query max supported upcall version */
 };
 
 /* representation of long-form NFSv4 client ID */
@@ -45,6 +50,17 @@ struct cld_name {
 	unsigned char	cn_id[NFS4_OPAQUE_LIMIT];	/* client-provided */
 } __attribute__((packed));
 
+/* sha256 hash of the kerberos principal */
+struct cld_princhash {
+	__u8		cp_len;				/* length of cp_data */
+	unsigned char	cp_data[SHA256_DIGEST_SIZE];	/* hash of principal */
+} __attribute__((packed));
+
+struct cld_clntinfo {
+	struct cld_name		cc_name;
+	struct cld_princhash	cc_princhash;
+} __attribute__((packed));
+
 /* message struct for communication with userspace */
 struct cld_msg {
 	__u8		cm_vers;		/* upcall version */
@@ -54,7 +70,28 @@ struct cld_msg {
 	union {
 		__s64		cm_gracetime;	/* grace period start time */
 		struct cld_name	cm_name;
+		__u8		cm_version;	/* for getting max version */
+	} __attribute__((packed)) cm_u;
+} __attribute__((packed));
+
+/* version 2 message can include hash of kerberos principal */
+struct cld_msg_v2 {
+	__u8		cm_vers;		/* upcall version */
+	__u8		cm_cmd;			/* upcall command */
+	__s16		cm_status;		/* return code */
+	__u32		cm_xid;			/* transaction id */
+	union {
+		struct cld_name	cm_name;
+		__u8		cm_version;	/* for getting max version */
+		struct cld_clntinfo cm_clntinfo; /* name & princ hash */
 	} __attribute__((packed)) cm_u;
 } __attribute__((packed));
 
+struct cld_msg_hdr {
+	__u8		cm_vers;		/* upcall version */
+	__u8		cm_cmd;			/* upcall command */
+	__s16		cm_status;		/* return code */
+	__u32		cm_xid;			/* transaction id */
+} __attribute__((packed));
+
 #endif /* !_NFSD_CLD_H */

net/sunrpc/cache.c

@@ -373,7 +373,7 @@ void sunrpc_init_cache_detail(struct cache_detail *cd)
 	spin_lock(&cache_list_lock);
 	cd->nextcheck = 0;
 	cd->entries = 0;
-	atomic_set(&cd->readers, 0);
+	atomic_set(&cd->writers, 0);
 	cd->last_close = 0;
 	cd->last_warn = -1;
 	list_add(&cd->others, &cache_list);
@@ -1029,11 +1029,13 @@ static int cache_open(struct inode *inode, struct file *filp,
 		}
 		rp->offset = 0;
 		rp->q.reader = 1;
-		atomic_inc(&cd->readers);
+
 		spin_lock(&queue_lock);
 		list_add(&rp->q.list, &cd->queue);
 		spin_unlock(&queue_lock);
 	}
+	if (filp->f_mode & FMODE_WRITE)
+		atomic_inc(&cd->writers);
 	filp->private_data = rp;
 	return 0;
 }
@@ -1062,8 +1064,10 @@ static int cache_release(struct inode *inode, struct file *filp,
 		filp->private_data = NULL;
 		kfree(rp);
 
+	}
+	if (filp->f_mode & FMODE_WRITE) {
+		atomic_dec(&cd->writers);
 		cd->last_close = seconds_since_boot();
-		atomic_dec(&cd->readers);
 	}
 	module_put(cd->owner);
 	return 0;
@@ -1171,7 +1175,7 @@ static void warn_no_listener(struct cache_detail *detail)
 
 static bool cache_listeners_exist(struct cache_detail *detail)
 {
-	if (atomic_read(&detail->readers))
+	if (atomic_read(&detail->writers))
 		return true;
 	if (detail->last_close == 0)
 		/* This cache was never opened */
@@ -1520,6 +1524,9 @@ static ssize_t write_flush(struct file *file, const char __user *buf,
 	cd->nextcheck = now;
 	cache_flush();
 
+	if (cd->flush)
+		cd->flush();
+
 	*ppos += count;
 	return count;
 }

net/sunrpc/svc.c

@@ -1233,8 +1233,8 @@ svc_generic_init_request(struct svc_rqst *rqstp,
 
 	if (rqstp->rq_vers >= progp->pg_nvers )
 		goto err_bad_vers;
-	  versp = progp->pg_vers[rqstp->rq_vers];
-	  if (!versp)
+	versp = progp->pg_vers[rqstp->rq_vers];
+	if (!versp)
 		goto err_bad_vers;
 
 	/*

net/sunrpc/xprtrdma/svc_rdma.c

@@ -73,8 +73,6 @@ atomic_t rdma_stat_rq_prod;
 atomic_t rdma_stat_sq_poll;
 atomic_t rdma_stat_sq_prod;
 
-struct workqueue_struct *svc_rdma_wq;
-
 /*
  * This function implements reading and resetting an atomic_t stat
  * variable through read/write to a proc file. Any write to the file
@@ -230,7 +228,6 @@ static struct ctl_table svcrdma_root_table[] = {
 void svc_rdma_cleanup(void)
 {
 	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
-	destroy_workqueue(svc_rdma_wq);
 	if (svcrdma_table_header) {
 		unregister_sysctl_table(svcrdma_table_header);
 		svcrdma_table_header = NULL;
@@ -246,10 +243,6 @@ int svc_rdma_init(void)
 	dprintk("\tmax_bc_requests  : %u\n", svcrdma_max_bc_requests);
 	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
 
-	svc_rdma_wq = alloc_workqueue("svc_rdma", 0, 0);
-	if (!svc_rdma_wq)
-		return -ENOMEM;
-
 	if (!svcrdma_table_header)
 		svcrdma_table_header =
 			register_sysctl_table(svcrdma_root_table);

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

@@ -172,9 +172,10 @@ static void svc_rdma_recv_ctxt_destroy(struct svcxprt_rdma *rdma,
 void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
+	struct llist_node *node;
 
-	while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_recv_ctxts))) {
-		list_del(&ctxt->rc_list);
+	while ((node = llist_del_first(&rdma->sc_recv_ctxts))) {
+		ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node);
 		svc_rdma_recv_ctxt_destroy(rdma, ctxt);
 	}
 }
@@ -183,21 +184,18 @@ static struct svc_rdma_recv_ctxt *
 svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
+	struct llist_node *node;
 
-	spin_lock(&rdma->sc_recv_lock);
-	ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_recv_ctxts);
-	if (!ctxt)
+	node = llist_del_first(&rdma->sc_recv_ctxts);
+	if (!node)
 		goto out_empty;
-	list_del(&ctxt->rc_list);
-	spin_unlock(&rdma->sc_recv_lock);
+	ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node);
 
 out:
 	ctxt->rc_page_count = 0;
 	return ctxt;
 
 out_empty:
-	spin_unlock(&rdma->sc_recv_lock);
-
 	ctxt = svc_rdma_recv_ctxt_alloc(rdma);
 	if (!ctxt)
 		return NULL;
@@ -218,11 +216,9 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 	for (i = 0; i < ctxt->rc_page_count; i++)
 		put_page(ctxt->rc_pages[i]);
 
-	if (!ctxt->rc_temp) {
-		spin_lock(&rdma->sc_recv_lock);
-		list_add(&ctxt->rc_list, &rdma->sc_recv_ctxts);
-		spin_unlock(&rdma->sc_recv_lock);
-	} else
+	if (!ctxt->rc_temp)
+		llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts);
+	else
 		svc_rdma_recv_ctxt_destroy(rdma, ctxt);
 }
 

net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -140,14 +140,13 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_send_ctxts);
-	INIT_LIST_HEAD(&cma_xprt->sc_recv_ctxts);
+	init_llist_head(&cma_xprt->sc_recv_ctxts);
 	INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts);
 	init_waitqueue_head(&cma_xprt->sc_send_wait);
 
 	spin_lock_init(&cma_xprt->sc_lock);
 	spin_lock_init(&cma_xprt->sc_rq_dto_lock);
 	spin_lock_init(&cma_xprt->sc_send_lock);
-	spin_lock_init(&cma_xprt->sc_recv_lock);
 	spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);
 
 	/*
@@ -630,8 +629,9 @@ static void svc_rdma_free(struct svc_xprt *xprt)
 {
 	struct svcxprt_rdma *rdma =
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
+
 	INIT_WORK(&rdma->sc_work, __svc_rdma_free);
-	queue_work(svc_rdma_wq, &rdma->sc_work);
+	schedule_work(&rdma->sc_work);
 }
 
 static int svc_rdma_has_wspace(struct svc_xprt *xprt)