From: Eric Dumazet Date: Fri, 24 Mar 2006 11:18:10 +0000 (-0800) Subject: [PATCH] HOTPLUG_CPU: avoid hitting too many cachelines in recalc_bh_state() X-Git-Tag: firefly_0821_release~37327 X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=8a14342683b1e3adcf5f78660a42fcbd95b44a35;p=firefly-linux-kernel-4.4.55.git [PATCH] HOTPLUG_CPU: avoid hitting too many cachelines in recalc_bh_state() Instead of using for_each_cpu(i), we can use for_each_online_cpu(i). When a CPU goes offline (ie removed from online map), it might have a non null bh_accounting.nr, so this patch adds a transfer of this counter to an online CPU counter. We already have a hotcpu_notifier, (function buffer_cpu_notify()), where we can do this bh_accounting. Signed-off-by: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/fs/buffer.c b/fs/buffer.c index 36c7253bea72..11ca6eb46a33 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3078,7 +3078,7 @@ static void recalc_bh_state(void) if (__get_cpu_var(bh_accounting).ratelimit++ < 4096) return; __get_cpu_var(bh_accounting).ratelimit = 0; - for_each_cpu(i) + for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } @@ -3127,6 +3127,9 @@ static void buffer_exit_cpu(int cpu) brelse(b->bhs[i]); b->bhs[i] = NULL; } + get_cpu_var(bh_accounting).nr += per_cpu(bh_accounting, cpu).nr; + per_cpu(bh_accounting, cpu).nr = 0; + put_cpu_var(bh_accounting); } static int buffer_cpu_notify(struct notifier_block *self,