linux-kernel - [PATCH 2/5] blkcg: don't use percpu for merged stats

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: <1331232840-16044-3-git-send-email-tj@kernel.org>
Date:	Thu,  8 Mar 2012 10:53:57 -0800
From:	Tejun Heo <tj@...nel.org>
To:	axboe@...nel.dk, vgoyal@...hat.com
Cc:	akpm@...ux-foundation.org, linux-kernel@...r.kernel.org,
	dpshah@...gle.com, ctalbott@...gle.com, rni@...gle.com,
	Tejun Heo <tj@...nel.org>
Subject: [PATCH 2/5] blkcg: don't use percpu for merged stats

With recent plug merge updates, merged stats are no longer called for
plug merges and now only updated while holding queue_lock.  As
stats_lock is scheduled to be removed, there's no reason to use percpu
for merged stats.  Don't use percpu for merged stats.

Signed-off-by: Tejun Heo <tj@...nel.org>
Cc: Vivek Goyal <vgoyal@...hat.com>
---
 block/blk-cgroup.c |   26 ++++++--------------------
 block/blk-cgroup.h |    6 +++---
 2 files changed, 9 insertions(+), 23 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 622fb41..6eedf3a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -451,27 +451,13 @@ void blkiocg_update_io_merged_stats(struct blkio_group *blkg,
 				    bool direction, bool sync)
 {
 	struct blkg_policy_data *pd = blkg->pd[pol->plid];
-	struct blkio_group_stats_cpu *stats_cpu;
+	struct blkio_group_stats *stats;
 	unsigned long flags;
 
-	/* If per cpu stats are not allocated yet, don't do any accounting. */
-	if (pd->stats_cpu == NULL)
-		return;
-
-	/*
-	 * Disabling interrupts to provide mutual exclusion between two
-	 * writes on same cpu. It probably is not needed for 64bit. Not
-	 * optimizing that case yet.
-	 */
-	local_irq_save(flags);
-
-	stats_cpu = this_cpu_ptr(pd->stats_cpu);
-
-	u64_stats_update_begin(&stats_cpu->syncp);
-	blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
-				direction, sync);
-	u64_stats_update_end(&stats_cpu->syncp);
-	local_irq_restore(flags);
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &pd->stats;
+	blkio_add_stat(stats->stat_arr[BLKIO_STAT_MERGED], 1, direction, sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
@@ -1342,7 +1328,7 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
 						BLKIO_STAT_WAIT_TIME, 1, 0);
 		case BLKIO_PROP_io_merged:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_CPU_MERGED, 1, 1);
+						BLKIO_STAT_MERGED, 1, 0);
 		case BLKIO_PROP_io_queued:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
 						BLKIO_STAT_QUEUED, 1, 0);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 1de32fe..6c8e3e3 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -29,10 +29,12 @@ enum blkio_policy_id {
 #ifdef CONFIG_BLK_CGROUP
 
 enum stat_type {
+	/* Number of IOs merged */
+	BLKIO_STAT_MERGED,
 	/* Total time spent (in ns) between request dispatch to the driver and
 	 * request completion for IOs doen by this cgroup. This may not be
 	 * accurate when NCQ is turned on. */
-	BLKIO_STAT_SERVICE_TIME = 0,
+	BLKIO_STAT_SERVICE_TIME,
 	/* Total time spent waiting in scheduler queue in ns */
 	BLKIO_STAT_WAIT_TIME,
 	/* Number of IOs queued up */
@@ -57,8 +59,6 @@ enum stat_type_cpu {
 	BLKIO_STAT_CPU_SERVICE_BYTES,
 	/* Total IOs serviced, post merge */
 	BLKIO_STAT_CPU_SERVICED,
-	/* Number of IOs merged */
-	BLKIO_STAT_CPU_MERGED,
 	BLKIO_STAT_CPU_NR
 };
 
-- 
1.7.7.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/