Merge tag 'nfsd-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "The marquee feature for this release is that the limit on the maximum
  rsize and wsize has been raised to 4MB. The default remains at 1MB,
  but risk-seeking administrators now have the ability to try larger I/O
  sizes with NFS clients that support them. Eventually the default
  setting will be increased when we have confidence that this change
  will not have negative impact.

  With v6.16, NFSD now has its own debugfs file system where we can add
  experimental features and make them available outside of our
  development community without impacting production deployments. The
  first experimental setting added is one that makes all NFS READ
  operations use vfs_iter_read() instead of the NFSD splice actor. The
  plan is to eventually retire the splice actor, as that will enable a
  number of new capabilities such as the use of struct bio_vec from the
  top to the bottom of the NFSD stack.

  Jeff Layton contributed a number of observability improvements. The
  use of dprintk() in a number of high-traffic code paths has been
  replaced with static trace points.

  This release sees the continuation of efforts to harden the NFSv4.2
  COPY operation. Soon, the restriction on async COPY operations can be
  lifted.

  Many thanks to the contributors, reviewers, testers, and bug reporters
  who participated during the v6.16 development cycle"

* tag 'nfsd-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (60 commits)
  xdrgen: Fix code generated for counted arrays
  SUNRPC: Bump the maximum payload size for the server
  NFSD: Add a "default" block size
  NFSD: Remove NFSSVC_MAXBLKSIZE_V2 macro
  NFSD: Remove NFSD_BUFSIZE
  sunrpc: Remove the RPCSVC_MAXPAGES macro
  svcrdma: Adjust the number of entries in svc_rdma_send_ctxt::sc_pages
  svcrdma: Adjust the number of entries in svc_rdma_recv_ctxt::rc_pages
  sunrpc: Adjust size of socket's receive page array dynamically
  SUNRPC: Remove svc_rqst :: rq_vec
  SUNRPC: Remove svc_fill_write_vector()
  NFSD: Use rqstp->rq_bvec in nfsd_iter_write()
  SUNRPC: Export xdr_buf_to_bvec()
  NFSD: De-duplicate the svc_fill_write_vector() call sites
  NFSD: Use rqstp->rq_bvec in nfsd_iter_read()
  sunrpc: Replace the rq_bvec array with dynamically-allocated memory
  sunrpc: Replace the rq_pages array with dynamically-allocated memory
  sunrpc: Remove backchannel check in svc_init_buffer()
  sunrpc: Add a helper to derive maxpages from sv_max_mesg
  svcrdma: Reduce the number of rdma_rw contexts per-QP
  ...

1 files changed, 70 insertions, 20 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 160a839af405..cd689df2ca5d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -31,6 +31,7 @@
 #include <linux/exportfs.h>
 #include <linux/writeback.h>
 #include <linux/security.h>
+#include <linux/sunrpc/xdr.h>
 
 #include "xdr3.h"
 
@@ -47,6 +48,8 @@
 
 #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
 
+bool nfsd_disable_splice_read __read_mostly;
+
 /**
  * nfserrno - Map Linux errnos to NFS errnos
  * @errno: POSIX(-ish) error code to be mapped
@@ -244,7 +247,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	struct dentry		*dentry;
 	int			host_err;
 
-	dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
+	trace_nfsd_vfs_lookup(rqstp, fhp, name, len);
 
 	dparent = fhp->fh_dentry;
 	exp = exp_get(fhp->fh_export);
@@ -500,6 +503,8 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 	int		retries;
 
+	trace_nfsd_vfs_setattr(rqstp, fhp, iap, guardtime);
+
 	if (iap->ia_valid & ATTR_SIZE) {
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
 		ftype = S_IFREG;
@@ -1082,23 +1087,23 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	unsigned long v, total;
 	struct iov_iter iter;
 	loff_t ppos = offset;
-	struct page *page;
 	ssize_t host_err;
+	size_t len;
 
 	v = 0;
 	total = *count;
 	while (total) {
-		page = *(rqstp->rq_next_page++);
-		rqstp->rq_vec[v].iov_base = page_address(page) + base;
-		rqstp->rq_vec[v].iov_len = min_t(size_t, total, PAGE_SIZE - base);
-		total -= rqstp->rq_vec[v].iov_len;
+		len = min_t(size_t, total, PAGE_SIZE - base);
+		bvec_set_page(&rqstp->rq_bvec[v], *(rqstp->rq_next_page++),
+			      len, base);
+		total -= len;
 		++v;
 		base = 0;
 	}
-	WARN_ON_ONCE(v > ARRAY_SIZE(rqstp->rq_vec));
+	WARN_ON_ONCE(v > rqstp->rq_maxpages);
 
 	trace_nfsd_read_vector(rqstp, fhp, offset, *count);
-	iov_iter_kvec(&iter, ITER_DEST, rqstp->rq_vec, v, *count);
+	iov_iter_bvec(&iter, ITER_DEST, rqstp->rq_bvec, v, *count);
 	host_err = vfs_iter_read(file, &iter, &ppos, 0);
 	return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err);
 }
@@ -1140,11 +1145,27 @@ static int wait_for_concurrent_writes(struct file *file)
 	return err;
 }
 
+/**
+ * nfsd_vfs_write - write data to an already-open file
+ * @rqstp: RPC execution context
+ * @fhp: File handle of file to write into
+ * @nf: An open file matching @fhp
+ * @offset: Byte offset of start
+ * @payload: xdr_buf containing the write payload
+ * @cnt: IN: number of bytes to write, OUT: number of bytes actually written
+ * @stable: An NFS stable_how value
+ * @verf: NFS WRITE verifier
+ *
+ * Upon return, caller must invoke fh_put on @fhp.
+ *
+ * Return values:
+ *   An nfsstat value in network byte order.
+ */
 __be32
-nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
-				loff_t offset, struct kvec *vec, int vlen,
-				unsigned long *cnt, int stable,
-				__be32 *verf)
+nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
+	       struct nfsd_file *nf, loff_t offset,
+	       const struct xdr_buf *payload, unsigned long *cnt,
+	       int stable, __be32 *verf)
 {
 	struct nfsd_net		*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct file		*file = nf->nf_file;
@@ -1159,6 +1180,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	unsigned int		pflags = current->flags;
 	rwf_t			flags = 0;
 	bool			restore_flags = false;
+	unsigned int		nvecs;
 
 	trace_nfsd_write_opened(rqstp, fhp, offset, *cnt);
 
@@ -1186,7 +1208,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	if (stable && !fhp->fh_use_wgather)
 		flags |= RWF_SYNC;
 
-	iov_iter_kvec(&iter, ITER_SOURCE, vec, vlen, *cnt);
+	nvecs = xdr_buf_to_bvec(rqstp->rq_bvec, rqstp->rq_maxpages, payload);
+	iov_iter_bvec(&iter, ITER_SOURCE, rqstp->rq_bvec, nvecs, *cnt);
 	since = READ_ONCE(file->f_wb_err);
 	if (verf)
 		nfsd_copy_write_verifier(verf, nn);
@@ -1237,6 +1260,8 @@ out_nfserr:
  */
 bool nfsd_read_splice_ok(struct svc_rqst *rqstp)
 {
+	if (nfsd_disable_splice_read)
+		return false;
 	switch (svc_auth_flavor(rqstp)) {
 	case RPC_AUTH_GSS_KRB5I:
 	case RPC_AUTH_GSS_KRB5P:
@@ -1284,14 +1309,24 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	return err;
 }
 
-/*
- * Write data to a file.
- * The stable flag requests synchronous writes.
- * N.B. After this call fhp needs an fh_put
+/**
+ * nfsd_write - open a file and write data to it
+ * @rqstp: RPC execution context
+ * @fhp: File handle of file to write into; nfsd_write() may modify it
+ * @offset: Byte offset of start
+ * @payload: xdr_buf containing the write payload
+ * @cnt: IN: number of bytes to write, OUT: number of bytes actually written
+ * @stable: An NFS stable_how value
+ * @verf: NFS WRITE verifier
+ *
+ * Upon return, caller must invoke fh_put on @fhp.
+ *
+ * Return values:
+ *   An nfsstat value in network byte order.
  */
 __be32
 nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
-	   struct kvec *vec, int vlen, unsigned long *cnt, int stable,
+	   const struct xdr_buf *payload, unsigned long *cnt, int stable,
 	   __be32 *verf)
 {
 	struct nfsd_file *nf;
@@ -1303,8 +1338,8 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
 	if (err)
 		goto out;
 
-	err = nfsd_vfs_write(rqstp, fhp, nf, offset, vec,
-			vlen, cnt, stable, verf);
+	err = nfsd_vfs_write(rqstp, fhp, nf, offset, payload, cnt,
+			     stable, verf);
 	nfsd_file_put(nf);
 out:
 	trace_nfsd_write_done(rqstp, fhp, offset, *cnt);
@@ -1340,6 +1375,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	loff_t			start, end;
 	struct nfsd_net		*nn;
 
+	trace_nfsd_commit_start(rqstp, fhp, offset, count);
+
 	/*
 	 * Convert the client-provided (offset, count) range to a
 	 * (start, end) range. If the client-provided range falls
@@ -1378,6 +1415,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	} else
 		nfsd_copy_write_verifier(verf, nn);
 
+	trace_nfsd_commit_done(rqstp, fhp, offset, count);
 	return err;
 }
 
@@ -1541,6 +1579,8 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	__be32		err;
 	int		host_err;
 
+	trace_nfsd_vfs_create(rqstp, fhp, type, fname, flen);
+
 	if (isdotent(fname, flen))
 		return nfserr_exist;
 
@@ -1641,6 +1681,8 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	__be32		err, cerr;
 	int		host_err;
 
+	trace_nfsd_vfs_symlink(rqstp, fhp, fname, flen, path);
+
 	err = nfserr_noent;
 	if (!flen || path[0] == '\0')
 		goto out;
@@ -1709,6 +1751,8 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	__be32		err;
 	int		host_err;
 
+	trace_nfsd_vfs_link(rqstp, ffhp, tfhp, name, len);
+
 	err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_CREATE);
 	if (err)
 		goto out;
@@ -1826,6 +1870,8 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	int		host_err;
 	bool		close_cached = false;
 
+	trace_nfsd_vfs_rename(rqstp, ffhp, tfhp, fname, flen, tname, tlen);
+
 	err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE);
 	if (err)
 		goto out;
@@ -1984,6 +2030,8 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	__be32		err;
 	int		host_err;
 
+	trace_nfsd_vfs_unlink(rqstp, fhp, fname, flen);
+
 	err = nfserr_acces;
 	if (!flen || isdotent(fname, flen))
 		goto out;
@@ -2272,6 +2320,8 @@ nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, in
 {
 	__be32 err;
 
+	trace_nfsd_vfs_statfs(rqstp, fhp);
+
 	err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
 	if (!err) {
 		struct path path = {