linux-kernel - [PATCH] sched/isolation: isolate from handling managed interrupt

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-next>] [day] [month] [year] [list]

Message-Id: <20200116094806.25372-1-ming.lei@redhat.com>
Date:   Thu, 16 Jan 2020 17:48:06 +0800
From:   Ming Lei <ming.lei@...hat.com>
To:     linux-kernel@...r.kernel.org
Cc:     Ming Lei <ming.lei@...hat.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Peter Xu <peterx@...hat.com>,
        Juri Lelli <juri.lelli@...hat.com>
Subject: [PATCH] sched/isolation: isolate from handling managed interrupt

Userspace can't change managed interrupt's affinity via /proc interface,
however application often requires the specified isolated CPUs not
disturbed by interrupts.

Add sub-parameter 'managed_irq' for 'isolcpus', so that we can isolate
from handling managed interrupt.

Not select isolated CPU as effective CPU if the interupt affinity includes
at least one housekeeping CPU. This way guarantees that isolated CPUs won't
be interrupted by managed irq if IO isn't submitted from any isolated CPU.

Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Peter Xu <peterx@...hat.com>
Cc: Juri Lelli <juri.lelli@...hat.com>
Signed-off-by: Ming Lei <ming.lei@...hat.com>
---
 .../admin-guide/kernel-parameters.txt         |  9 ++++++++
 include/linux/sched/isolation.h               |  1 +
 kernel/irq/manage.c                           | 22 ++++++++++++++++++-
 kernel/sched/isolation.c                      |  6 +++++
 4 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ade4e6ec23e0..e0f18ac866d4 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1933,6 +1933,15 @@
 			  <cpu number> begins at 0 and the maximum value is
 			  "number of CPUs in system - 1".
 
+			managed_irq
+			  Isolate from handling managed interrupt. Userspace can't
+			  change managed interrupt's affinity via /proc interface,
+			  however application often requires the specified isolated
+			  CPUs not disturbed by interrupts. This way guarantees that
+			  isolated CPU won't be interrupted if IO isn't submitted
+			  from isolated CPU when managed interrupt is used by IO
+			  drivers.
+
 			The format of <cpu-list> is described above.
 
 
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 6c8512d3be88..0fbcbacd1b29 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -13,6 +13,7 @@ enum hk_flags {
 	HK_FLAG_TICK		= (1 << 4),
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
+	HK_FLAG_MANAGED_IRQ	= (1 << 7),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1753486b440c..9cc972d28d3c 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -20,6 +20,7 @@
 #include <linux/sched/task.h>
 #include <uapi/linux/sched/types.h>
 #include <linux/task_work.h>
+#include <linux/sched/isolation.h>
 
 #include "internals.h"
 
@@ -212,12 +213,29 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 {
 	struct irq_desc *desc = irq_data_to_desc(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
+	const struct cpumask *housekeeping_mask =
+		housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
 	int ret;
+	cpumask_var_t tmp_mask = (struct cpumask *)mask;
 
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
-	ret = chip->irq_set_affinity(data, mask, force);
+	zalloc_cpumask_var(&tmp_mask, GFP_ATOMIC);
+
+	/*
+	 * Userspace can't change managed irq's affinity, make sure that
+	 * isolated CPU won't be selected as the effective CPU if this
+	 * irq's affinity includes at least one housekeeping CPU.
+	 *
+	 * This way guarantees that isolated CPU won't be interrupted if
+	 * IO isn't submitted from isolated CPU.
+	 */
+	if (irqd_affinity_is_managed(data) && tmp_mask &&
+			cpumask_intersects(mask, housekeeping_mask))
+		cpumask_and(tmp_mask, mask, housekeeping_mask);
+
+	ret = chip->irq_set_affinity(data, tmp_mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
@@ -229,6 +247,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 		ret = 0;
 	}
 
+	free_cpumask_var(tmp_mask);
+
 	return ret;
 }
 
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 9fcb2a695a41..008d6ac2342b 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str)
 			continue;
 		}
 
+		if (!strncmp(str, "managed_irq,", 12)) {
+			str += 12;
+			flags |= HK_FLAG_MANAGED_IRQ;
+			continue;
+		}
+
 		pr_warn("isolcpus: Error, unknown flag\n");
 		return 0;
 	}
-- 
2.20.1