sunrpc: Replace the rq_pages array with dynamically-allocated memory

As a step towards making NFSD's maximum rsize and wsize variable at
run-time, replace the fixed-size rq_vec[] array in struct svc_rqst
with a chunk of dynamically-allocated memory.

On a system with 8-byte pointers and 4KB pages, pahole reports that
the rq_pages[] array is 2080 bytes. This patch replaces that with
a single 8-byte pointer field.

Reviewed-by: Jeff Layton <[email protected]>
Reviewed-by: NeilBrown <[email protected]>
Signed-off-by: Chuck Lever <[email protected]>

Author: chucklever

include/linux/sunrpc/svc.h

@@ -205,7 +205,8 @@ 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 */

net/sunrpc/svc.c

@@ -636,20 +636,22 @@ svc_destroy(struct svc_serv **servp)
 EXPORT_SYMBOL_GPL(svc_destroy);
 
 static bool
-svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
+svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node)
 {
-	unsigned long pages, ret;
+	unsigned long ret;
 
-	pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply.
-				       * We assume one is at most one page
-				       */
-	WARN_ON_ONCE(pages > RPCSVC_MAXPAGES);
-	if (pages > RPCSVC_MAXPAGES)
-		pages = RPCSVC_MAXPAGES;
+	rqstp->rq_maxpages = svc_serv_maxpages(serv);
 
-	ret = alloc_pages_bulk_node(GFP_KERNEL, node, pages,
+	/* rq_pages' last entry is NULL for historical reasons. */
+	rqstp->rq_pages = kcalloc_node(rqstp->rq_maxpages + 1,
+				       sizeof(struct page *),
+				       GFP_KERNEL, node);
+	if (!rqstp->rq_pages)
+		return false;
+
+	ret = alloc_pages_bulk_node(GFP_KERNEL, node, rqstp->rq_maxpages,
 				    rqstp->rq_pages);
-	return ret == pages;
+	return ret == rqstp->rq_maxpages;
 }
 
 /*
@@ -658,11 +660,12 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
 static void
 svc_release_buffer(struct svc_rqst *rqstp)
 {
-	unsigned int i;
+	unsigned long i;
 
-	for (i = 0; i < ARRAY_SIZE(rqstp->rq_pages); i++)
+	for (i = 0; i < rqstp->rq_maxpages; i++)
 		if (rqstp->rq_pages[i])
 			put_page(rqstp->rq_pages[i]);
+	kfree(rqstp->rq_pages);
 }
 
 static void
@@ -704,7 +707,7 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp->rq_resp)
 		goto out_enomem;
 
-	if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node))
+	if (!svc_init_buffer(rqstp, serv, node))
 		goto out_enomem;
 
 	rqstp->rq_err = -EAGAIN; /* No error yet */
@@ -896,7 +899,7 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads);
 bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page)
 {
 	struct page **begin = rqstp->rq_pages;
-	struct page **end = &rqstp->rq_pages[RPCSVC_MAXPAGES];
+	struct page **end = &rqstp->rq_pages[rqstp->rq_maxpages];
 
 	if (unlikely(rqstp->rq_next_page < begin || rqstp->rq_next_page > end)) {
 		trace_svc_replace_page_err(rqstp);

net/sunrpc/svc_xprt.c

@@ -652,18 +652,10 @@ static void svc_check_conn_limits(struct svc_serv *serv)
 
 static bool svc_alloc_arg(struct svc_rqst *rqstp)
 {
-	struct svc_serv *serv = rqstp->rq_server;
 	struct xdr_buf *arg = &rqstp->rq_arg;
 	unsigned long pages, filled, ret;
 
-	pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
-	if (pages > RPCSVC_MAXPAGES) {
-		pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n",
-			     pages, RPCSVC_MAXPAGES);
-		/* use as many pages as possible */
-		pages = RPCSVC_MAXPAGES;
-	}
-
+	pages = rqstp->rq_maxpages;
 	for (filled = 0; filled < pages; filled = ret) {
 		ret = alloc_pages_bulk(GFP_KERNEL, pages, rqstp->rq_pages);
 		if (ret > filled)

net/sunrpc/xprtrdma/svc_rdma_rw.c

@@ -765,7 +765,7 @@ static int svc_rdma_build_read_segment(struct svc_rqst *rqstp,
 		}
 		len -= seg_len;
 
-		if (len && ((head->rc_curpage + 1) > ARRAY_SIZE(rqstp->rq_pages)))
+		if (len && ((head->rc_curpage + 1) > rqstp->rq_maxpages))
 			goto out_overrun;
 	}