| 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
| ||
|
Message-ID: <TYAPR01MB63307451E66EBDB7F885F13D8B51A@TYAPR01MB6330.jpnprd01.prod.outlook.com>
Date: Fri, 9 Jun 2023 11:10:14 +0000
From: "Shaopeng Tan (Fujitsu)" <tan.shaopeng@...itsu.com>
To: 'James Morse' <james.morse@....com>,
"x86@...nel.org" <x86@...nel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
CC: Fenghua Yu <fenghua.yu@...el.com>,
Reinette Chatre <reinette.chatre@...el.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
H Peter Anvin <hpa@...or.com>,
Babu Moger <Babu.Moger@....com>,
"shameerali.kolothum.thodi@...wei.com"
<shameerali.kolothum.thodi@...wei.com>,
D Scott Phillips OS <scott@...amperecomputing.com>,
"carl@...amperecomputing.com" <carl@...amperecomputing.com>,
"lcherian@...vell.com" <lcherian@...vell.com>,
"bobo.shaobowang@...wei.com" <bobo.shaobowang@...wei.com>,
"xingxin.hx@...nanolis.org" <xingxin.hx@...nanolis.org>,
"baolin.wang@...ux.alibaba.com" <baolin.wang@...ux.alibaba.com>,
Jamie Iles <quic_jiles@...cinc.com>,
Xin Hao <xhao@...ux.alibaba.com>,
"peternewman@...gle.com" <peternewman@...gle.com>,
"dfustini@...libre.com" <dfustini@...libre.com>
Subject: RE: [PATCH v4 21/24] x86/resctrl: Allow overflow/limbo handlers to be
scheduled on any-but cpu
Hi James,
> 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.
>
> A subsequent patch moves these calls to be before CPUs have been removed,
> so this exclude_cpus behaviour is temporary.
>
> Tested-by: Shaopeng Tan <tan.shaopeng@...itsu.com>
> Signed-off-by: James Morse <james.morse@....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
>
> Changes since v3:
> * Marked an explanatory comment as temporary as the subsequent patch is
> no longer adjacent.
> ---
> arch/x86/kernel/cpu/resctrl/core.c | 8 +++--
> arch/x86/kernel/cpu/resctrl/internal.h | 37
> +++++++++++++++++++++-- arch/x86/kernel/cpu/resctrl/monitor.c
> | 42 +++++++++++++++++++++-----
> arch/x86/kernel/cpu/resctrl/rdtgroup.c | 6 ++--
> include/linux/resctrl.h | 3 ++
> 5 files changed, 82 insertions(+), 14 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/resctrl/core.c
> b/arch/x86/kernel/cpu/resctrl/core.c
> index e00f3542e60e..187ed127a446 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);
> + /*
> + * temporary: 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 021a8956518c..9cba8fc405b9 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -79,6 +79,37 @@ 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 housekeeping
> +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 ced933694f60..ae02185f3354 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -485,7 +485,7 @@ 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++;
> }
> @@ -810,15 +810,28 @@ 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) @@ -864,7 +877,14
> @@ 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;
> @@ -875,9 +895,15 @@ 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);
Should RESCTRL_PICK_ANY_CPU be used instead of -1?
Best regards,
Shaopeng TAN
Powered by blists - more mailing lists