Merge branch 'for-4.2' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "A relatively quiet cycle, with a mix of cleanup and smaller bugfixes"

* 'for-4.2' of git://linux-nfs.org/~bfields/linux: (24 commits)
  sunrpc: use sg_init_one() in krb5_rc4_setup_enc/seq_key()
  nfsd: wrap too long lines in nfsd4_encode_read
  nfsd: fput rd_file from XDR encode context
  nfsd: take struct file setup fully into nfs4_preprocess_stateid_op
  nfsd: refactor nfs4_preprocess_stateid_op
  nfsd: clean up raparams handling
  nfsd: use swap() in sort_pacl_range()
  rpcrdma: Merge svcrdma and xprtrdma modules into one
  svcrdma: Add a separate "max data segs macro for svcrdma
  svcrdma: Replace GFP_KERNEL in a loop with GFP_NOFAIL
  svcrdma: Keep rpcrdma_msg fields in network byte-order
  svcrdma: Fix byte-swapping in svc_rdma_sendto.c
  nfsd: Update callback sequnce id only CB_SEQUENCE success
  nfsd: Reset cb_status in nfsd4_cb_prepare() at retrying
  svcrdma: Remove svc_rdma_xdr_decode_deferred_req()
  SUNRPC: Move EXPORT_SYMBOL for svc_process
  uapi/nfs: Add NFSv4.1 ACL definitions
  nfsd: Remove dead declarations
  nfsd: work around a gcc-5.1 warning
  nfsd: Checking for acl support does not require fetching any acls
  ...

Documentation/filesystems/nfs/knfsd-stats.txt

@@ -68,16 +68,10 @@ sockets-enqueued
 	rate of change for this counter is zero; significantly non-zero
 	values may indicate a performance limitation.
 
-	This can happen either because there are too few nfsd threads in the
-	thread pool for the NFS workload (the workload is thread-limited),
-	or because the NFS workload needs more CPU time than is available in
-	the thread pool (the workload is CPU-limited).  In the former case,
-	configuring more nfsd threads will probably improve the performance
-	of the NFS workload.  In the latter case, the sunrpc server layer is
-	already choosing not to wake idle nfsd threads because there are too
-	many nfsd threads which want to run but cannot, so configuring more
-	nfsd threads will make no difference whatsoever.  The overloads-avoided
-	statistic (see below) can be used to distinguish these cases.
+	This can happen because there are too few nfsd threads in the thread
+	pool for the NFS workload (the workload is thread-limited), in which
+	case configuring more nfsd threads will probably improve the
+	performance of the NFS workload.
 
 threads-woken
 	Counts how many times an idle nfsd thread is woken to try to
@@ -88,36 +82,6 @@ threads-woken
 	thing.  The ideal rate of change for this counter will be close
 	to but less than the rate of change of the packets-arrived counter.
 
-overloads-avoided
-	Counts how many times the sunrpc server layer chose not to wake an
-	nfsd thread, despite the presence of idle nfsd threads, because
-	too many nfsd threads had been recently woken but could not get
-	enough CPU time to actually run.
-
-	This statistic counts a circumstance where the sunrpc layer
-	heuristically avoids overloading the CPU scheduler with too many
-	runnable nfsd threads.  The ideal rate of change for this counter
-	is zero.  Significant non-zero values indicate that the workload
-	is CPU limited.  Usually this is associated with heavy CPU usage
-	on all the CPUs in the nfsd thread pool.
-
-	If a sustained large overloads-avoided rate is detected on a pool,
-	the top(1) utility should be used to check for the following
-	pattern of CPU usage on all the CPUs associated with the given
-	nfsd thread pool.
-
-	 - %us ~= 0 (as you're *NOT* running applications on your NFS server)
-
-	 - %wa ~= 0
-
-	 - %id ~= 0
-
-	 - %sy + %hi + %si ~= 100
-
-	If this pattern is seen, configuring more nfsd threads will *not*
-	improve the performance of the workload.  If this patten is not
-	seen, then something more subtle is wrong.
-
 threads-timedout
 	Counts how many times an nfsd thread triggered an idle timeout,
 	i.e. was not woken to handle any incoming network packets for

fs/nfsd/nfs3xdr.c

@@ -805,7 +805,7 @@ encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name,
 
 static __be32
 compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
-		const char *name, int namlen)
+		 const char *name, int namlen, u64 ino)
 {
 	struct svc_export	*exp;
 	struct dentry		*dparent, *dchild;
@@ -830,19 +830,21 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
 		goto out;
 	if (d_really_is_negative(dchild))
 		goto out;
+	if (dchild->d_inode->i_ino != ino)
+		goto out;
 	rv = fh_compose(fhp, exp, dchild, &cd->fh);
 out:
 	dput(dchild);
 	return rv;
 }
 
-static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
+static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen, u64 ino)
 {
 	struct svc_fh	*fh = &cd->scratch;
 	__be32 err;
 
 	fh_init(fh, NFS3_FHSIZE);
-	err = compose_entry_fh(cd, fh, name, namlen);
+	err = compose_entry_fh(cd, fh, name, namlen, ino);
 	if (err) {
 		*p++ = 0;
 		*p++ = 0;
@@ -927,7 +929,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		p = encode_entry_baggage(cd, p, name, namlen, ino);
 
 		if (plus)
-			p = encode_entryplus_baggage(cd, p, name, namlen);
+			p = encode_entryplus_baggage(cd, p, name, namlen, ino);
 		num_entry_words = p - cd->buffer;
 	} else if (*(page+1) != NULL) {
 		/* temporarily encode entry into next page, then move back to
@@ -941,7 +943,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
 
 		if (plus)
-			p1 = encode_entryplus_baggage(cd, p1, name, namlen);
+			p1 = encode_entryplus_baggage(cd, p1, name, namlen, ino);
 
 		/* determine entry word length and lengths to go in pages */
 		num_entry_words = p1 - tmp;

fs/nfsd/nfs4acl.c

@@ -52,10 +52,6 @@
 #define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE)
 #define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL)
 
-/* We don't support these bits; insist they be neither allowed nor denied */
-#define NFS4_MASK_UNSUPP (NFS4_ACE_DELETE | NFS4_ACE_WRITE_OWNER \
-		| NFS4_ACE_READ_NAMED_ATTRS | NFS4_ACE_WRITE_NAMED_ATTRS)
-
 /* flags used to simulate posix default ACLs */
 #define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \
 		| NFS4_ACE_DIRECTORY_INHERIT_ACE)
@@ -64,9 +60,6 @@
 		| NFS4_ACE_INHERIT_ONLY_ACE \
 		| NFS4_ACE_IDENTIFIER_GROUP)
 
-#define MASK_EQUAL(mask1, mask2) \
-	( ((mask1) & NFS4_ACE_MASK_ALL) == ((mask2) & NFS4_ACE_MASK_ALL) )
-
 static u32
 mask_from_posix(unsigned short perm, unsigned int flags)
 {
@@ -126,11 +119,6 @@ low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags)
 		*mode |= ACL_EXECUTE;
 }
 
-struct ace_container {
-	struct nfs4_ace  *ace;
-	struct list_head  ace_l;
-};
-
 static short ace2type(struct nfs4_ace *);
 static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *,
 				unsigned int);
@@ -384,7 +372,6 @@ pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2)
 static void
 sort_pacl_range(struct posix_acl *pacl, int start, int end) {
 	int sorted = 0, i;
-	struct posix_acl_entry tmp;
 
 	/* We just do a bubble sort; easy to do in place, and we're not
 	 * expecting acl's to be long enough to justify anything more. */
@@ -394,9 +381,8 @@ sort_pacl_range(struct posix_acl *pacl, int start, int end) {
 			if (pace_gt(&pacl->a_entries[i],
 				    &pacl->a_entries[i+1])) {
 				sorted = 0;
-				tmp = pacl->a_entries[i];
-				pacl->a_entries[i] = pacl->a_entries[i+1];
-				pacl->a_entries[i+1] = tmp;
+				swap(pacl->a_entries[i],
+				     pacl->a_entries[i + 1]);
 			}
 		}
 	}

fs/nfsd/nfs4callback.c

@@ -455,6 +455,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr,
 	if (unlikely(status || cb->cb_status))
 		return status;
 
+	cb->cb_update_seq_nr = true;
 	return decode_cb_sequence4resok(xdr, cb);
 }
 
@@ -875,6 +876,8 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	u32 minorversion = clp->cl_minorversion;
 
 	cb->cb_minorversion = minorversion;
+	cb->cb_update_seq_nr = false;
+	cb->cb_status = 0;
 	if (minorversion) {
 		if (!nfsd41_cb_get_slot(clp, task))
 			return;
@@ -891,9 +894,16 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		clp->cl_minorversion);
 
 	if (clp->cl_minorversion) {
-		/* No need for lock, access serialized in nfsd4_cb_prepare */
-		if (!task->tk_status)
+		/*
+		 * No need for lock, access serialized in nfsd4_cb_prepare
+		 *
+		 * RFC5661 20.9.3
+		 * If CB_SEQUENCE returns an error, then the state of the slot
+		 * (sequence ID, cached reply) MUST NOT change.
+		 */
+		if (cb->cb_update_seq_nr)
 			++clp->cl_cb_session->se_cb_seq_nr;
+
 		clear_bit(0, &clp->cl_cb_slot_busy);
 		rpc_wake_up_next(&clp->cl_cb_waitq);
 		dprintk("%s: freed slot, new seqid=%d\n", __func__,
@@ -1090,6 +1100,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 	cb->cb_ops = ops;
 	INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
 	cb->cb_status = 0;
+	cb->cb_update_seq_nr = false;
 	cb->cb_need_restart = false;
 }
 

fs/nfsd/nfs4proc.c

@@ -760,8 +760,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 
-	/* no need to check permission - this will be done in nfsd_read() */
-
 	read->rd_filp = NULL;
 	if (read->rd_offset >= OFFSET_MAX)
 		return nfserr_inval;
@@ -778,9 +776,9 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* check stateid */
-	if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
-						 cstate, &read->rd_stateid,
-						 RD_STATE, &read->rd_filp))) {
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid,
+			RD_STATE, &read->rd_filp, &read->rd_tmp_file);
+	if (status) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
 	}
@@ -924,8 +922,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	int err;
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
-		status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
-			&setattr->sa_stateid, WR_STATE, NULL);
+		status = nfs4_preprocess_stateid_op(rqstp, cstate,
+			&setattr->sa_stateid, WR_STATE, NULL, NULL);
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -986,13 +984,11 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	unsigned long cnt;
 	int nvecs;
 
-	/* no need to check permission - this will be done in nfsd_write() */
-
 	if (write->wr_offset >= OFFSET_MAX)
 		return nfserr_inval;
 
-	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
-					cstate, stateid, WR_STATE, &filp);
+	status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE,
+			&filp, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
@@ -1005,11 +1001,10 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nvecs = fill_in_write_vector(rqstp->rq_vec, write);
 	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
-	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
-			     write->wr_offset, rqstp->rq_vec, nvecs,
-			     &cnt, &write->wr_how_written);
-	if (filp)
-		fput(filp);
+	status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp,
+				write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
+				&write->wr_how_written);
+	fput(filp);
 
 	write->wr_bytes_written = cnt;
 
@@ -1023,15 +1018,13 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	__be32 status = nfserr_notsupp;
 	struct file *file;
 
-	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
+	status = nfs4_preprocess_stateid_op(rqstp, cstate,
 					    &fallocate->falloc_stateid,
-					    WR_STATE, &file);
+					    WR_STATE, &file, NULL);
 	if (status != nfs_ok) {
 		dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
 		return status;
 	}
-	if (!file)
-		return nfserr_bad_stateid;
 
 	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file,
 				     fallocate->falloc_offset,
@@ -1064,15 +1057,13 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	__be32 status;
 	struct file *file;
 
-	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
+	status = nfs4_preprocess_stateid_op(rqstp, cstate,
 					    &seek->seek_stateid,
-					    RD_STATE, &file);
+					    RD_STATE, &file, NULL);
 	if (status) {
 		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
 		return status;
 	}
-	if (!file)
-		return nfserr_bad_stateid;
 
 	switch (seek->seek_whence) {
 	case NFS4_CONTENT_DATA:
@@ -1732,10 +1723,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			be32_to_cpu(status));
 
 		nfsd4_cstate_clear_replay(cstate);
-		/* XXX Ugh, we need to get rid of this kind of special case: */
-		if (op->opnum == OP_READ && op->u.read.rd_filp)
-			fput(op->u.read.rd_filp);
-
 		nfsd4_increment_op_stats(op->opnum);
 	}