[<prev] [next>] [day] [month] [year] [list]
Message-ID: <20240115102523.2336742-1-kernel@pankajraghav.com>
Date: Mon, 15 Jan 2024 11:25:22 +0100
From: "Pankaj Raghav (Samsung)" <kernel@...kajraghav.com>
To: willy@...radead.org,
akpm@...ux-foundation.org
Cc: linux-mm@...ck.org,
gost.dev@...sung.com,
linux-kernel@...r.kernel.org,
linux-fsdevel@...r.kernel.org,
Pankaj Raghav <p.raghav@...sung.com>
Subject: [PATCH] readahead: use ilog2 instead of a while loop in page_cache_ra_order()
From: Pankaj Raghav <p.raghav@...sung.com>
A while loop is used to adjust the new_order to be lower than the
ra->size. ilog2 could be used to do the same instead of using a loop.
ilog2 typically resolves to a bit scan reverse instruction. This is
particularly useful when ra->size is smaller than the 2^new_order as it
resolves in one instruction instead of looping to find the new_order.
No functional changes.
Signed-off-by: Pankaj Raghav <p.raghav@...sung.com>
---
mm/readahead.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/mm/readahead.c b/mm/readahead.c
index c81234fa655a..18b23126eb52 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -500,10 +500,8 @@ void page_cache_ra_order(struct readahead_control *ractl,
if (new_order < MAX_PAGECACHE_ORDER) {
new_order += 2;
- if (new_order > MAX_PAGECACHE_ORDER)
- new_order = MAX_PAGECACHE_ORDER;
- while ((1 << new_order) > ra->size)
- new_order--;
+ new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order);
+ new_order = min_t(unsigned int, new_order, ilog2(ra->size));
}
filemap_invalidate_lock_shared(mapping);
base-commit: 8d04a7e2ee3fd6aabb8096b00c64db0d735bc874
--
2.43.0
Powered by blists - more mailing lists