linux-kernel - [PATCH 2/3] nvme-pci: limit queue count to housekeeping cpus

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]

Date: Fri, 21 Jun 2024 15:53:11 +0200
From: Daniel Wagner <dwagner@...e.de>
To: Jens Axboe <axboe@...nel.dk>, Keith Busch <kbusch@...nel.org>, 
 Sagi Grimberg <sagi@...mberg.me>, Thomas Gleixner <tglx@...utronix.de>, 
 Christoph Hellwig <hch@....de>
Cc: Frederic Weisbecker <fweisbecker@...e.com>, 
 Mel Gorman <mgorman@...e.de>, Hannes Reinecke <hare@...e.de>, 
 Sridhar Balaraman <sbalaraman@...allelwireless.com>, 
 "brookxu.cn" <brookxu.cn@...il.com>, Ming Lei <ming.lei@...hat.com>, 
 linux-kernel@...r.kernel.org, linux-block@...r.kernel.org, 
 linux-nvme@...ts.infradead.org, Daniel Wagner <dwagner@...e.de>
Subject: [PATCH 2/3] nvme-pci: limit queue count to housekeeping cpus

The nvme-pci driver is ignoring the isolcpus and allocates IO queues for
all possible CPUs. But this could add noise to the isolated CPU whenever
there is IO issued on the isolated CPU. This is not always what the user
wants. Thus only ask for as many queues as there are housekeeping CPUs.

Note, the placement of the queues will be addressed in the next patch.

Signed-off-by: Daniel Wagner <dwagner@...e.de>
---
 block/blk-mq-cpumap.c   | 13 +++++++++++++
 drivers/nvme/host/pci.c |  4 ++--
 include/linux/blk-mq.h  |  1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 9638b25fd521..43c039900ef6 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -11,10 +11,23 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 #include <linux/group_cpus.h>
+#include <linux/sched/isolation.h>
 
 #include "blk.h"
 #include "blk-mq.h"
 
+unsigned int blk_mq_num_possible_queues(void)
+{
+	const struct cpumask *io_queue_mask;
+
+	io_queue_mask = housekeeping_cpumask(HK_TYPE_IO_QUEUE);
+	if (!cpumask_empty(io_queue_mask))
+		return cpumask_weight(io_queue_mask);
+
+	return num_possible_cpus();
+}
+EXPORT_SYMBOL_GPL(blk_mq_num_possible_queues);
+
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
 	const struct cpumask *masks;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 102a9fb0c65f..66999fa13b2c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -81,7 +81,7 @@ static int io_queue_count_set(const char *val, const struct kernel_param *kp)
 	int ret;
 
 	ret = kstrtouint(val, 10, &n);
-	if (ret != 0 || n > num_possible_cpus())
+	if (ret != 0 || n > blk_mq_num_possible_queues())
 		return -EINVAL;
 	return param_set_uint(val, kp);
 }
@@ -2263,7 +2263,7 @@ static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
 	 */
 	if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
 		return 1;
-	return num_possible_cpus() + dev->nr_write_queues + dev->nr_poll_queues;
+	return blk_mq_num_possible_queues() + dev->nr_write_queues + dev->nr_poll_queues;
 }
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 89ba6b16fe8b..2105cc78ca67 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -900,6 +900,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
 
+unsigned int blk_mq_num_possible_queues(void);
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 

-- 
2.45.2