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
  ...

5 files changed, 53 insertions, 8 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index b0c6b0d34d02..e0d909d35763 100644
--- a/include/linux/fs.h
+++ b/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);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 2de3b2ddd19a..1915bdba2fad 100644
--- a/include/linux/fsnotify_backend.h
+++ b/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 */
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index c7f38e897174..f8603724fbee 100644
--- a/include/linux/sunrpc/cache.h
+++ b/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;
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 981f0d726ad4..40f65888dd38 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/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);
 
diff --git a/include/uapi/linux/nfsd/cld.h b/include/uapi/linux/nfsd/cld.h
index b1e9de4f07d5..a519313af953 100644
--- a/include/uapi/linux/nfsd/cld.h
+++ b/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 */