x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow

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 housekeeping
CPU is available.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Link: https://lore.kernel.org/r/20240213184438.16675-13-james.morse@arm.com
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index b7b9d9230bef0c83ae72b323ea37cefd49c26496..81f5de916db8cae2c42ccbb404a3ab3245863160 100644 (file)
--- 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>
 
@@ -55,6 +56,29 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS            GENMASK(6, 0)
 
+/**
+ * cpumask_any_housekeeping() - Choose 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 housekeeping CPUs that don't use
+ * nohz_full, these are preferred.
+ */
+static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
+{
+       unsigned int cpu, hk_cpu;
+
+       cpu = cpumask_any(mask);
+       if (!tick_nohz_full_cpu(cpu))
+               return 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 101f1b112d170323c078965a4b9845ce3a060d56..38f85e53ca931c608cb7218a4f2518b01af46e18 100644 (file)
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -761,7 +761,6 @@ 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_domain *d;
 
        mutex_lock(&rdtgroup_mutex);
@@ -770,8 +769,11 @@ void cqm_handle_limbo(struct work_struct *work)
 
        __check_limbo(d, false);
 
-       if (has_busy_rmid(d))
-               schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
+       if (has_busy_rmid(d)) {
+               d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask);
+               schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
+                                        delay);
+       }
 
        mutex_unlock(&rdtgroup_mutex);
 }
@@ -781,7 +783,7 @@ 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);
@@ -791,7 +793,6 @@ 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;
@@ -815,7 +816,12 @@ void mbm_handle_overflow(struct work_struct *work)
                        update_mba_bw(prgrp, d);
        }
 
-       schedule_delayed_work_on(cpu, &d->mbm_over, delay);
+       /*
+        * Re-check for housekeeping CPUs. This allows the overflow handler to
+        * move off a nohz_full CPU quickly.
+        */
+       d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask);
+       schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
 
 out_unlock:
        mutex_unlock(&rdtgroup_mutex);
@@ -828,7 +834,7 @@ 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);
 }