From e52a8250480acd3b26534793c61816e30d85fbb6 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 1 Oct 2018 10:07:06 +0200
Subject: [PATCH] fuse: realloc page array

Writeback caching currently allocates requests with the maximum number of
possible pages, while the actual number of pages per request depends on a
couple of factors that cannot be determined when the request is allocated
(whether page is already under writeback, whether page is contiguous with
previous pages already added to a request).

This patch allows such requests to start with no page allocation (all pages
inline) and grow the page array on demand.

If the max_pages tunable remains the default value, then this will mean
just one allocation that is the same size as before.  If the tunable is
larger, then this adds at most 3 additional memory allocations (which is
generously compensated by the improved performance from the larger
request).

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c    | 49 ++++++++++++++++++++++++++++++++++++++++++++----
 fs/fuse/file.c   |  8 +++++++-
 fs/fuse/fuse_i.h |  4 ++++
 3 files changed, 56 insertions(+), 5 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 69d4df78a417..ae813e609932 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -54,6 +54,18 @@ static void fuse_request_init(struct fuse_req *req, struct page **pages,
 	__set_bit(FR_PENDING, &req->flags);
 }
 
+static struct page **fuse_req_pages_alloc(unsigned int npages, gfp_t flags,
+					  struct fuse_page_desc **desc)
+{
+	struct page **pages;
+
+	pages = kzalloc(npages * (sizeof(struct page *) +
+				  sizeof(struct fuse_page_desc)), flags);
+	*desc = (void *) pages + npages * sizeof(struct page *);
+
+	return pages;
+}
+
 static struct fuse_req *__fuse_request_alloc(unsigned npages, gfp_t flags)
 {
 	struct fuse_req *req = kmem_cache_zalloc(fuse_req_cachep, flags);
@@ -63,13 +75,12 @@ static struct fuse_req *__fuse_request_alloc(unsigned npages, gfp_t flags)
 
 		WARN_ON(npages > FUSE_MAX_MAX_PAGES);
 		if (npages > FUSE_REQ_INLINE_PAGES) {
-			pages = kzalloc(npages * (sizeof(*pages) +
-						  sizeof(*page_descs)), flags);
+			pages = fuse_req_pages_alloc(npages, flags,
+						     &page_descs);
 			if (!pages) {
 				kmem_cache_free(fuse_req_cachep, req);
 				return NULL;
 			}
-			page_descs = (void *) pages + npages * sizeof(*pages);
 		} else if (npages) {
 			pages = req->inline_pages;
 			page_descs = req->inline_page_descs;
@@ -91,11 +102,41 @@ struct fuse_req *fuse_request_alloc_nofs(unsigned npages)
 	return __fuse_request_alloc(npages, GFP_NOFS);
 }
 
-void fuse_request_free(struct fuse_req *req)
+static void fuse_req_pages_free(struct fuse_req *req)
 {
 	if (req->pages != req->inline_pages)
 		kfree(req->pages);
+}
 
+bool fuse_req_realloc_pages(struct fuse_conn *fc, struct fuse_req *req,
+			    gfp_t flags)
+{
+	struct page **pages;
+	struct fuse_page_desc *page_descs;
+	unsigned int npages = min_t(unsigned int,
+				    max_t(unsigned int, req->max_pages * 2,
+					  FUSE_DEFAULT_MAX_PAGES_PER_REQ),
+				    fc->max_pages);
+	WARN_ON(npages <= req->max_pages);
+
+	pages = fuse_req_pages_alloc(npages, flags, &page_descs);
+	if (!pages)
+		return false;
+
+	memcpy(pages, req->pages, sizeof(struct page *) * req->max_pages);
+	memcpy(page_descs, req->page_descs,
+	       sizeof(struct fuse_page_desc) * req->max_pages);
+	fuse_req_pages_free(req);
+	req->pages = pages;
+	req->page_descs = page_descs;
+	req->max_pages = npages;
+
+	return true;
+}
+
+void fuse_request_free(struct fuse_req *req)
+{
+	fuse_req_pages_free(req);
 	kmem_cache_free(fuse_req_cachep, req);
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 035843b501fe..f5507198ea00 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1827,7 +1827,13 @@ static int fuse_writepages_fill(struct page *page,
 	     data->orig_pages[req->num_pages - 1]->index + 1 != page->index)) {
 		fuse_writepages_send(data);
 		data->req = NULL;
+	} else if (req && req->num_pages == req->max_pages) {
+		if (!fuse_req_realloc_pages(fc, req, GFP_NOFS)) {
+			fuse_writepages_send(data);
+			req = data->req = NULL;
+		}
 	}
+
 	err = -ENOMEM;
 	tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
 	if (!tmp_page)
@@ -1850,7 +1856,7 @@ static int fuse_writepages_fill(struct page *page,
 		struct fuse_inode *fi = get_fuse_inode(inode);
 
 		err = -ENOMEM;
-		req = fuse_request_alloc_nofs(fc->max_pages);
+		req = fuse_request_alloc_nofs(FUSE_REQ_INLINE_PAGES);
 		if (!req) {
 			__free_page(tmp_page);
 			goto out_unlock;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 3d578745c852..b7d96e7b5e0f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -879,6 +879,10 @@ struct fuse_req *fuse_request_alloc(unsigned npages);
 
 struct fuse_req *fuse_request_alloc_nofs(unsigned npages);
 
+bool fuse_req_realloc_pages(struct fuse_conn *fc, struct fuse_req *req,
+			    gfp_t flags);
+
+
 /**
  * Free a request
  */