linux-kernel - [PATCH RFC 2/2] mm/page_alloc: free_pcppages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230817-free_pcppages_bulk-v1-2-c14574a9f80c@kernel.org>
Date:   Thu, 17 Aug 2023 23:05:24 -0700
From:   Chris Li <chrisl@...nel.org>
To:     Andrew Morton <akpm@...ux-foundation.org>,
        Kemeng Shi <shikemeng@...weicloud.com>
Cc:     akpm@...ux-foundation.org, baolin.wang@...ux.alibaba.com,
        mgorman@...hsingularity.net, Michal Hocko <mhocko@...e.com>,
        david@...hat.com, willy@...radead.org, linux-mm@...ck.org,
        Namhyung Kim <namhyung@...gle.com>,
        Greg Thelen <gthelen@...gle.com>, linux-kernel@...r.kernel.org,
        Chris Li <chrisl@...nel.org>
Subject: [PATCH RFC 2/2] mm/page_alloc: free_pcppages_bulk clean up

This patch does not have functional change. Just pure clean up.

It removes the pindex_max and pindex_min and replaces it with a simpler
loop.

It uses for_each_entry_safe_reverse() to replace the loop over
list_last_entry(). It produces slightly better machine code.

Signed-off-by: Chris Li <chrisl@...nel.org>
---
 mm/page_alloc.c | 38 +++++++++++++-------------------------
 1 file changed, 13 insertions(+), 25 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 347cb93081a02..d64d0f5ec70b4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1209,11 +1209,9 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 					int pindex)
 {
 	unsigned long flags;
-	int min_pindex = 0;
-	int max_pindex = NR_PCP_LISTS - 1;
 	unsigned int order;
 	bool isolated_pageblocks;
-	struct page *page;
+	int i;
 
 	/* Ensure requested pindex is drained first. */
 	pindex = pindex - 1;
@@ -1221,31 +1219,18 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	spin_lock_irqsave(&zone->lock, flags);
 	isolated_pageblocks = has_isolate_pageblock(zone);
 
-	while (count > 0) {
+	for (i = 0; i < NR_PCP_LISTS; i++, pindex++) {
 		struct list_head *list;
 		int nr_pages;
+		struct page *page, *next;
 
-		/* Remove pages from lists in a round-robin fashion. */
-		do {
-			if (++pindex > max_pindex)
-				pindex = min_pindex;
-			list = &pcp->lists[pindex];
-			if (!list_empty(list))
-				break;
-
-			if (pindex == max_pindex)
-				max_pindex--;
-			if (pindex == min_pindex)
-				min_pindex++;
-		} while (1);
-
+		if (pindex == NR_PCP_LISTS)
+			pindex = 0;
+		list = pcp->lists + pindex;
 		order = pindex_to_order(pindex);
 		nr_pages = 1 << order;
-		do {
-			int mt;
-
-			page = list_last_entry(list, struct page, pcp_list);
-			mt = get_pcppage_migratetype(page);
+		list_for_each_entry_safe_reverse(page, next, list, lru) {
+			int mt = get_pcppage_migratetype(page);
 
 			/* must delete to avoid corrupting pcp list */
 			list_del(&page->pcp_list);
@@ -1260,9 +1245,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 
 			__free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE);
 			trace_mm_page_pcpu_drain(page, order, mt);
-		} while (count > 0 && pcp->count > 0 && !list_empty(list));
-	}
 
+			if (count <= 0 || pcp->count <= 0)
+				goto out;
+		}
+	}
+out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 

-- 
2.42.0.rc1.204.g551eb34607-goog