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 17/19] x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but cpu
Date: Mon, 20 Mar 2023 17:26:18 +0000 [thread overview]
Message-ID: <20230320172620.18254-18-james.morse@arm.com> (raw)
In-Reply-To: <20230320172620.18254-1-james.morse@arm.com>
When a CPU is taken offline resctrl may need to move the overflow or
limbo handlers to run on a different CPU.
Once the offline callbacks have been split, cqm_setup_limbo_handler()
will be called while the CPU that is going offline is still present
in the cpu_mask.
Pass the CPU to exclude to cqm_setup_limbo_handler() and
mbm_setup_overflow_handler(). These functions can use a variant of
cpumask_any_but() when selecting the CPU. -1 is used to indicate no CPUs
need excluding.
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Signed-off-by: James Morse <james.morse@arm.com>
---
Changes since v2:
* Rephrased a comment to avoid a two letter bad-word. (we)
* Avoid assigning mbm_work_cpu if the domain is going to be free()d
* Added cpumask_any_housekeeping_but(), I dislike the name
---
arch/x86/kernel/cpu/resctrl/core.c | 8 +++--
arch/x86/kernel/cpu/resctrl/internal.h | 37 ++++++++++++++++++++--
arch/x86/kernel/cpu/resctrl/monitor.c | 43 +++++++++++++++++++++-----
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 6 ++--
include/linux/resctrl.h | 3 ++
5 files changed, 83 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 8e25ea49372e..aafe4b74587c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -582,12 +582,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
cancel_delayed_work(&d->mbm_over);
- mbm_setup_overflow_handler(d, 0);
+ /*
+ * exclude_cpu=-1 as this CPU has already been removed
+ * by cpumask_clear_cpu()d
+ */
+ mbm_setup_overflow_handler(d, 0, RESCTRL_PICK_ANY_CPU);
}
if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
has_busy_rmid(r, d)) {
cancel_delayed_work(&d->cqm_limbo);
- cqm_setup_limbo_handler(d, 0);
+ cqm_setup_limbo_handler(d, 0, RESCTRL_PICK_ANY_CPU);
}
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3eb5b307b809..47838ba6876e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -78,6 +78,37 @@ static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
return cpu;
}
+/**
+ * cpumask_any_housekeeping_but() - Chose any cpu in @mask, preferring those
+ * that aren't marked nohz_full, excluding
+ * the provided CPU
+ * @mask: The mask to pick a CPU from.
+ * @exclude_cpu:The CPU to avoid picking.
+ *
+ * Returns a CPU from @mask, but not @but. If there are houskeeping CPUs that
+ * don't use nohz_full, these are preferred.
+ * Returns >= nr_cpu_ids if no CPUs are available.
+ */
+static inline unsigned int
+cpumask_any_housekeeping_but(const struct cpumask *mask, int exclude_cpu)
+{
+ int cpu, hk_cpu;
+
+ cpu = cpumask_any_but(mask, exclude_cpu);
+ if (tick_nohz_full_cpu(cpu)) {
+ hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
+ if (hk_cpu == exclude_cpu) {
+ hk_cpu = cpumask_nth_andnot(1, 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;
@@ -564,11 +595,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
struct rdt_domain *d, struct rdtgroup *rdtgrp,
int evtid, int first);
void mbm_setup_overflow_handler(struct rdt_domain *dom,
- unsigned long delay_ms);
+ unsigned long delay_ms,
+ int exclude_cpu);
void mbm_handle_overflow(struct work_struct *work);
void __init intel_rdt_mbm_apply_quirk(void);
bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
void __check_limbo(struct rdt_domain *d, bool force_free);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f0f2e61b15d5..11fa5d79c81d 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -477,7 +477,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
* setup up the limbo worker.
*/
if (!has_busy_rmid(r, d))
- cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
+ cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, -1);
set_bit(idx, d->rmid_busy_llc);
entry->busy++;
}
@@ -812,15 +812,28 @@ void cqm_handle_limbo(struct work_struct *work)
mutex_unlock(&rdtgroup_mutex);
}
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
+ * domain.
+ * @delay_ms: How far in the future the handler should run.
+ * @exclude_cpu: Which CPU the handler should not run on, -1 to pick any CPU.
+ */
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask);
- dom->cqm_work_cpu = cpu;
+ if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
+ cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ else
+ cpu = cpumask_any_housekeeping_but(&dom->cpu_mask,
+ exclude_cpu);
- schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+ if (cpu < nr_cpu_ids) {
+ dom->cqm_work_cpu = cpu;
+ schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+ }
}
void mbm_handle_overflow(struct work_struct *work)
@@ -862,7 +875,14 @@ void mbm_handle_overflow(struct work_struct *work)
mutex_unlock(&rdtgroup_mutex);
}
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
+ * domain.
+ * @delay_ms: How far in the future the handler should run.
+ * @exclude_cpu: Which CPU the handler should not run on, -1 to pick any CPU.
+ */
+void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
@@ -870,9 +890,16 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
if (!resctrl_mounted || !resctrl_arch_mon_capable())
return;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ if (exclude_cpu == -1)
+ cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ else
+ cpu = cpumask_any_housekeeping_but(&dom->cpu_mask,
+ exclude_cpu);
+
dom->mbm_work_cpu = cpu;
- schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+
+ if (cpu < nr_cpu_ids)
+ schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
}
static int dom_data_init(struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 410b2b451c30..bf206bdb21ee 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2520,7 +2520,8 @@ static int rdt_get_tree(struct fs_context *fc)
if (is_mbm_enabled()) {
r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
list_for_each_entry(dom, &r->domains, list)
- mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
+ mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
}
goto out;
@@ -3686,7 +3687,8 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
if (is_mbm_enabled()) {
INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
- mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+ mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
}
if (is_llc_occupancy_enabled())
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 5a66d034aa61..3ea7d618f33f 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -9,6 +9,9 @@
/* CLOSID value used by the default control group */
#define RESCTRL_RESERVED_CLOSID 0
+/* Indicates no CPU needs to be excluded */
+#define RESCTRL_PICK_ANY_CPU -1
+
#ifdef CONFIG_PROC_CPU_RESCTRL
int proc_resctrl_show(struct seq_file *m,
--
2.39.2
next prev parent reply other threads:[~2023-03-20 17:47 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 ` [PATCH v3 08/19] x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow James Morse
2023-03-21 13:21 ` 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 ` James Morse [this message]
2023-03-21 15:12 ` [PATCH v3 17/19] x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but cpu 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=20230320172620.18254-18-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).