All of lore.kernel.org
 help / color / mirror / Atom feed
From: James Morse <james.morse@arm.com>
To: x86@kernel.org, linux-kernel@vger.kernel.org
Cc: Fenghua Yu <fenghua.yu@intel.com>,
	Reinette Chatre <reinette.chatre@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	H Peter Anvin <hpa@zytor.com>, Babu Moger <Babu.Moger@amd.com>,
	James Morse <james.morse@arm.com>,
	shameerali.kolothum.thodi@huawei.com,
	D Scott Phillips OS <scott@os.amperecomputing.com>,
	carl@os.amperecomputing.com, lcherian@marvell.com,
	bobo.shaobowang@huawei.com, tan.shaopeng@fujitsu.com,
	xingxin.hx@openanolis.org, baolin.wang@linux.alibaba.com,
	Jamie Iles <quic_jiles@quicinc.com>,
	Xin Hao <xhao@linux.alibaba.com>,
	peternewman@google.com
Subject: [PATCH v3 08/19] x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow
Date: Mon, 20 Mar 2023 17:26:09 +0000	[thread overview]
Message-ID: <20230320172620.18254-9-james.morse@arm.com> (raw)
In-Reply-To: <20230320172620.18254-1-james.morse@arm.com>

The limbo and overflow code picks a CPU to use from the domain's list
of online CPUs. Work is then scheduled on these CPUs to maintain
the limbo list and any counters that may overflow.

cpumask_any() may pick a CPU that is marked nohz_full, which will
either penalise the work that CPU was dedicated to, or delay the
processing of limbo list or counters that may overflow. Perhaps
indefinitely. Delaying the overflow handling will skew the bandwidth
values calculated by mba_sc, which expects to be called once a second.

Add cpumask_any_housekeeping() as a replacement for cpumask_any()
that prefers housekeeping CPUs. This helper will still return
a nohz_full CPU if that is the only option. The CPU to use is
re-evaluated each time the limbo/overflow work runs. This ensures
the work will move off a nohz_full CPU once a houskeeping CPU is
available.

Signed-off-by: James Morse <james.morse@arm.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h | 23 +++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 17 ++++++++++++-----
 include/linux/tick.h                   |  3 ++-
 3 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 87545e4beb70..0b5fd5a0cda2 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -7,6 +7,7 @@
 #include <linux/kernfs.h>
 #include <linux/fs_context.h>
 #include <linux/jump_label.h>
+#include <linux/tick.h>
 #include <asm/resctrl.h>
 
 #define L3_QOS_CDP_ENABLE		0x01ULL
@@ -55,6 +56,28 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
 
+/**
+ * cpumask_any_housekeeping() - Chose any cpu in @mask, preferring those that
+ *			        aren't marked nohz_full
+ * @mask:	The mask to pick a CPU from.
+ *
+ * Returns a CPU in @mask. If there are houskeeping CPUs that don't use
+ * nohz_full, these are preferred.
+ */
+static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
+{
+	int cpu, hk_cpu;
+
+	cpu = cpumask_any(mask);
+	if (tick_nohz_full_cpu(cpu)) {
+		hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
+		if (hk_cpu < nr_cpu_ids)
+			cpu = hk_cpu;
+	}
+
+	return cpu;
+}
+
 struct rdt_fs_context {
 	struct kernfs_fs_context	kfc;
 	bool				enable_cdpl2;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index a2ae4be4b2ba..3bec5c59ca0e 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -745,9 +745,9 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
 void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	int cpu = smp_processor_id();
 	struct rdt_resource *r;
 	struct rdt_domain *d;
+	int cpu;
 
 	mutex_lock(&rdtgroup_mutex);
 
@@ -756,8 +756,10 @@ void cqm_handle_limbo(struct work_struct *work)
 
 	__check_limbo(d, false);
 
-	if (has_busy_rmid(r, d))
+	if (has_busy_rmid(r, d)) {
+		cpu = cpumask_any_housekeeping(&d->cpu_mask);
 		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
+	}
 
 	mutex_unlock(&rdtgroup_mutex);
 }
@@ -767,7 +769,7 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any_housekeeping(&dom->cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
 	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
@@ -777,10 +779,10 @@ void mbm_handle_overflow(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
-	int cpu = smp_processor_id();
 	struct list_head *head;
 	struct rdt_resource *r;
 	struct rdt_domain *d;
+	int cpu;
 
 	mutex_lock(&rdtgroup_mutex);
 
@@ -801,6 +803,11 @@ void mbm_handle_overflow(struct work_struct *work)
 			update_mba_bw(prgrp, d);
 	}
 
+	/*
+	 * Re-check for housekeeping CPUs. This allows the overflow handler to
+	 * move off a nohz_full CPU quickly.
+	 */
+	cpu = cpumask_any_housekeeping(&d->cpu_mask);
 	schedule_delayed_work_on(cpu, &d->mbm_over, delay);
 
 out_unlock:
@@ -814,7 +821,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
 
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any_housekeeping(&dom->cpu_mask);
 	dom->mbm_work_cpu = cpu;
 	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
diff --git a/include/linux/tick.h b/include/linux/tick.h
index bfd571f18cfd..ae2e9019fc18 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -174,9 +174,10 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 static inline void tick_nohz_idle_stop_tick_protected(void) { }
 #endif /* !CONFIG_NO_HZ_COMMON */
 
+extern cpumask_var_t tick_nohz_full_mask;
+
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
-extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
-- 
2.39.2


  parent reply	other threads:[~2023-03-20 17:50 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-20 17:26 [PATCH v3 00/19] x86/resctrl: monitored closid+rmid together, separate arch/fs locking James Morse
2023-03-20 17:26 ` [PATCH v3 01/19] x86/resctrl: Track the closid with the rmid James Morse
2023-03-20 17:26 ` [PATCH v3 02/19] x86/resctrl: Access per-rmid structures by index James Morse
2023-03-21 10:57   ` Ilpo Järvinen
2023-03-31 23:19   ` Reinette Chatre
2023-04-24 13:06   ` Peter Newman
2023-05-25 17:32     ` James Morse
2023-03-20 17:26 ` [PATCH v3 03/19] x86/resctrl: Create helper for RMID allocation and mondata dir creation James Morse
2023-03-21 11:05   ` Ilpo Järvinen
2023-03-31 23:20   ` Reinette Chatre
2023-03-20 17:26 ` [PATCH v3 04/19] x86/resctrl: Move rmid allocation out of mkdir_rdt_prepare() James Morse
2023-03-20 17:26 ` [PATCH v3 05/19] x86/resctrl: Allow RMID allocation to be scoped by CLOSID James Morse
2023-03-21 11:29   ` Ilpo Järvinen
2023-03-20 17:26 ` [PATCH v3 06/19] x86/resctrl: Allow the allocator to check if a CLOSID can allocate clean RMID James Morse
2023-03-31 23:21   ` Reinette Chatre
2023-04-27 14:09     ` James Morse
2023-03-20 17:26 ` [PATCH v3 07/19] x86/resctrl: Move CLOSID/RMID matching and setting to use helpers James Morse
2023-03-20 17:26 ` James Morse [this message]
2023-03-21 13:21   ` [PATCH v3 08/19] x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow Ilpo Järvinen
2023-04-27 14:09     ` James Morse
2023-03-21 15:14   ` Ilpo Järvinen
2023-04-27 14:09     ` James Morse
2023-04-27 14:25       ` Ilpo Järvinen
2023-05-25 17:32         ` James Morse
2023-03-31 23:24   ` Reinette Chatre
2023-04-27 14:10     ` James Morse
2023-04-27 23:36       ` Reinette Chatre
2023-05-25 17:32         ` James Morse
2023-03-20 17:26 ` [PATCH v3 09/19] x86/resctrl: Queue mon_event_read() instead of sending an IPI James Morse
2023-03-22 14:07   ` Peter Newman
2023-03-23  9:09     ` Peter Newman
2023-04-27 14:12       ` James Morse
2023-04-27 14:11     ` James Morse
2023-03-31 23:25   ` Reinette Chatre
2023-04-27 14:12     ` James Morse
2023-03-20 17:26 ` [PATCH v3 10/19] x86/resctrl: Allow resctrl_arch_rmid_read() to sleep James Morse
2023-03-31 23:26   ` Reinette Chatre
2023-04-27 14:12     ` James Morse
2023-03-20 17:26 ` [PATCH v3 11/19] x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read() James Morse
2023-03-31 23:27   ` Reinette Chatre
2023-04-27 14:19     ` James Morse
2023-04-27 23:40       ` Reinette Chatre
2023-05-25 17:31         ` James Morse
2023-03-20 17:26 ` [PATCH v3 12/19] x86/resctrl: Make resctrl_mounted checks explicit James Morse
2023-03-31 23:28   ` Reinette Chatre
2023-04-27 14:19     ` James Morse
2023-04-27 23:37       ` Reinette Chatre
2023-05-25 17:31         ` James Morse
2023-03-20 17:26 ` [PATCH v3 13/19] x86/resctrl: Move alloc/mon static keys into helpers James Morse
2023-03-20 17:26 ` [PATCH v3 14/19] x86/resctrl: Make rdt_enable_key the arch's decision to switch James Morse
2023-03-20 17:26 ` [PATCH v3 15/19] x86/resctrl: Add helpers for system wide mon/alloc capable James Morse
2023-03-31 23:29   ` Reinette Chatre
2023-04-27 14:19     ` James Morse
2023-03-20 17:26 ` [PATCH v3 16/19] x86/resctrl: Add cpu online callback for resctrl work James Morse
2023-03-31 23:29   ` Reinette Chatre
2023-03-20 17:26 ` [PATCH v3 17/19] x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but cpu James Morse
2023-03-21 15:12   ` Ilpo Järvinen
2023-03-21 15:25     ` Ilpo Järvinen
2023-04-27 14:20       ` James Morse
2023-03-20 17:26 ` [PATCH v3 18/19] x86/resctrl: Add cpu offline callback for resctrl work James Morse
2023-03-21 15:32   ` Ilpo Järvinen
2023-04-27 14:20     ` James Morse
2023-04-27 14:51       ` Ilpo Järvinen
2023-04-05 23:48   ` Reinette Chatre
2023-04-27 14:20     ` James Morse
2023-03-20 17:26 ` [PATCH v3 19/19] x86/resctrl: Separate arch and fs resctrl locks James Morse
2023-05-23 17:14 ` [PATCH v3 00/19] x86/resctrl: monitored closid+rmid together, separate arch/fs locking Tony Luck
2023-05-25 17:31   ` James Morse
2023-05-25 21:00     ` Tony Luck
2023-05-28 20:52       ` Drew Fustini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230320172620.18254-9-james.morse@arm.com \
    --to=james.morse@arm.com \
    --cc=Babu.Moger@amd.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bobo.shaobowang@huawei.com \
    --cc=bp@alien8.de \
    --cc=carl@os.amperecomputing.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=lcherian@marvell.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peternewman@google.com \
    --cc=quic_jiles@quicinc.com \
    --cc=reinette.chatre@intel.com \
    --cc=scott@os.amperecomputing.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=tan.shaopeng@fujitsu.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --cc=xhao@linux.alibaba.com \
    --cc=xingxin.hx@openanolis.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.