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
  ...

6 files changed, 62 insertions, 27 deletions

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 74658cca0f38..48666b83fe68 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -119,14 +119,14 @@ void svc_destroy(struct svc_serv **svcp);
  * Linux limit; someone who cares more about NFS/UDP performance
  * can test a larger number.
  *
- * For TCP transports we have more freedom.  A size of 1MB is
- * chosen to match the client limit.  Other OSes are known to
- * have larger limits, but those numbers are probably beyond
- * the point of diminishing returns.
+ * For non-UDP transports we have more freedom.  A size of 4MB is
+ * chosen to accommodate clients that support larger I/O sizes.
  */
-#define RPCSVC_MAXPAYLOAD	(1*1024*1024u)
-#define RPCSVC_MAXPAYLOAD_TCP	RPCSVC_MAXPAYLOAD
-#define RPCSVC_MAXPAYLOAD_UDP	(32*1024u)
+enum {
+	RPCSVC_MAXPAYLOAD	= 4 * 1024 * 1024,
+	RPCSVC_MAXPAYLOAD_TCP	= RPCSVC_MAXPAYLOAD,
+	RPCSVC_MAXPAYLOAD_UDP	= 32 * 1024,
+};
 
 extern u32 svc_max_payload(const struct svc_rqst *rqstp);
 
@@ -150,14 +150,24 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp);
  * list.  xdr_buf.tail points to the end of the first page.
  * This assumes that the non-page part of an rpc reply will fit
  * in a page - NFSd ensures this.  lockd also has no trouble.
+ */
+
+/**
+ * svc_serv_maxpages - maximum count of pages needed for one RPC message
+ * @serv: RPC service context
+ *
+ * Returns a count of pages or vectors that can hold the maximum
+ * size RPC message for @serv.
  *
- * Each request/reply pair can have at most one "payload", plus two pages,
- * one for the request, and one for the reply.
- * We using ->sendfile to return read data, we might need one extra page
- * if the request is not page-aligned.  So add another '1'.
+ * Each request/reply pair can have at most one "payload", plus two
+ * pages, one for the request, and one for the reply.
+ * nfsd_splice_actor() might need an extra page when a READ payload
+ * is not page-aligned.
  */
-#define RPCSVC_MAXPAGES		((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \
-				+ 2 + 1)
+static inline unsigned long svc_serv_maxpages(const struct svc_serv *serv)
+{
+	return DIV_ROUND_UP(serv->sv_max_mesg, PAGE_SIZE) + 2 + 1;
+}
 
 /*
  * The context of a single thread, including the request currently being
@@ -188,14 +198,14 @@ struct svc_rqst {
 	struct xdr_stream	rq_res_stream;
 	struct page		*rq_scratch_page;
 	struct xdr_buf		rq_res;
-	struct page		*rq_pages[RPCSVC_MAXPAGES + 1];
+	unsigned long		rq_maxpages;	/* num of entries in rq_pages */
+	struct page *		*rq_pages;
 	struct page *		*rq_respages;	/* points into rq_pages */
 	struct page *		*rq_next_page; /* next reply page to use */
 	struct page *		*rq_page_end;  /* one past the last page */
 
 	struct folio_batch	rq_fbatch;
-	struct kvec		rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
-	struct bio_vec		rq_bvec[RPCSVC_MAXPAGES];
+	struct bio_vec		*rq_bvec;
 
 	__be32			rq_xid;		/* transmission id */
 	u32			rq_prog;	/* program number */
@@ -452,8 +462,6 @@ const char *	   svc_proc_name(const struct svc_rqst *rqstp);
 int		   svc_encode_result_payload(struct svc_rqst *rqstp,
 					     unsigned int offset,
 					     unsigned int length);
-unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
-					 struct xdr_buf *payload);
 char		  *svc_fill_symlink_pathname(struct svc_rqst *rqstp,
 					     struct kvec *first, void *p,
 					     size_t total);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 619fc0bd837a..22704c2e5b9b 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -202,7 +202,8 @@ struct svc_rdma_recv_ctxt {
 	struct svc_rdma_pcl	rc_reply_pcl;
 
 	unsigned int		rc_page_count;
-	struct page		*rc_pages[RPCSVC_MAXPAGES];
+	unsigned long		rc_maxpages;
+	struct page		*rc_pages[] __counted_by(rc_maxpages);
 };
 
 /*
@@ -244,7 +245,8 @@ struct svc_rdma_send_ctxt {
 	void			*sc_xprt_buf;
 	int			sc_page_count;
 	int			sc_cur_sge_no;
-	struct page		*sc_pages[RPCSVC_MAXPAGES];
+	unsigned long		sc_maxpages;
+	struct page		**sc_pages;
 	struct ib_sge		sc_sges[];
 };
 
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 72be60952579..369a89aea186 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -53,6 +53,7 @@ struct svc_xprt {
 	struct svc_xprt_class	*xpt_class;
 	const struct svc_xprt_ops *xpt_ops;
 	struct kref		xpt_ref;
+	ktime_t			xpt_qtime;
 	struct list_head	xpt_list;
 	struct lwq_node		xpt_ready;
 	unsigned long		xpt_flags;
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index bf45d9e8492a..963bbe251e52 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -40,7 +40,9 @@ struct svc_sock {
 
 	struct completion	sk_handshake_done;
 
-	struct page *		sk_pages[RPCSVC_MAXPAGES];	/* received data */
+	/* received data */
+	unsigned long		sk_maxpages;
+	struct page *		sk_pages[] __counted_by(sk_maxpages);
 };
 
 static inline u32 svc_sock_reclen(struct svc_sock *svsk)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 5d331383047b..67db3f2953d5 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -2040,19 +2040,20 @@ TRACE_EVENT(svc_xprt_dequeue,
 
 	TP_STRUCT__entry(
 		SVC_XPRT_ENDPOINT_FIELDS(rqst->rq_xprt)
-
 		__field(unsigned long, wakeup)
+		__field(unsigned long, qtime)
 	),
 
 	TP_fast_assign(
-		SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+		ktime_t ktime = ktime_get();
 
-		__entry->wakeup = ktime_to_us(ktime_sub(ktime_get(),
-							rqst->rq_qtime));
+		SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt);
+		__entry->wakeup = ktime_to_us(ktime_sub(ktime, rqst->rq_qtime));
+		__entry->qtime = ktime_to_us(ktime_sub(ktime, rqst->rq_xprt->xpt_qtime));
 	),
 
-	TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu",
-		SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup)
+	TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu qtime-us=%lu",
+		SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup, __entry->qtime)
 );
 
 DECLARE_EVENT_CLASS(svc_xprt_event,
diff --git a/include/trace/misc/fs.h b/include/trace/misc/fs.h
index 738b97f22f36..0406ebe2a80a 100644
--- a/include/trace/misc/fs.h
+++ b/include/trace/misc/fs.h
@@ -120,3 +120,24 @@
 		{ LOOKUP_BENEATH,	"BENEATH" }, \
 		{ LOOKUP_IN_ROOT,	"IN_ROOT" }, \
 		{ LOOKUP_CACHED,	"CACHED" })
+
+#define show_ia_valid_flags(flags)			\
+	__print_flags(flags, "|",			\
+		{ ATTR_MODE,		"MODE" },	\
+		{ ATTR_UID,		"UID" },	\
+		{ ATTR_GID,		"GID" },	\
+		{ ATTR_SIZE,		"SIZE" },	\
+		{ ATTR_ATIME,		"ATIME" },	\
+		{ ATTR_MTIME,		"MTIME" },	\
+		{ ATTR_CTIME,		"CTIME" },	\
+		{ ATTR_ATIME_SET,	"ATIME_SET" },	\
+		{ ATTR_MTIME_SET,	"MTIME_SET" },	\
+		{ ATTR_FORCE,		"FORCE" },	\
+		{ ATTR_KILL_SUID,	"KILL_SUID" },	\
+		{ ATTR_KILL_SGID,	"KILL_SGID" },	\
+		{ ATTR_FILE,		"FILE" },	\
+		{ ATTR_KILL_PRIV,	"KILL_PRIV" },	\
+		{ ATTR_OPEN,		"OPEN" },	\
+		{ ATTR_TIMES_SET,	"TIMES_SET" },	\
+		{ ATTR_TOUCH,		"TOUCH"},	\
+		{ ATTR_DELEG,		"DELEG"})