--- /dev/null
+From 53916d5fd3c0b658de3463439dd2b7ce765072cb Mon Sep 17 00:00:00 2001
+From: Juri Lelli <juri.lelli@redhat.com>
+Date: Fri, 15 Nov 2024 11:48:29 +0000
+Subject: sched/deadline: Check bandwidth overflow earlier for hotplug
+
+From: Juri Lelli <juri.lelli@redhat.com>
+
+commit 53916d5fd3c0b658de3463439dd2b7ce765072cb upstream.
+
+Currently we check for bandwidth overflow potentially due to hotplug
+operations at the end of sched_cpu_deactivate(), after the cpu going
+offline has already been removed from scheduling, active_mask, etc.
+This can create issues for DEADLINE tasks, as there is a substantial
+race window between the start of sched_cpu_deactivate() and the moment
+we possibly decide to roll-back the operation if dl_bw_deactivate()
+returns failure in cpuset_cpu_inactive(). An example is a throttled
+task that sees its replenishment timer firing while the cpu it was
+previously running on is considered offline, but before
+dl_bw_deactivate() had a chance to say no and roll-back happened.
+
+Fix this by directly calling dl_bw_deactivate() first thing in
+sched_cpu_deactivate() and do the required calculation in the former
+function considering the cpu passed as an argument as offline already.
+
+By doing so we also simplify sched_cpu_deactivate(), as there is no need
+anymore for any kind of roll-back if we fail early.
+
+Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Reviewed-by: Phil Auld <pauld@redhat.com>
+Tested-by: Waiman Long <longman@redhat.com>
+Link: https://lore.kernel.org/r/Zzc1DfPhbvqDDIJR@jlelli-thinkpadt14gen4.remote.csb
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/sched/core.c | 22 +++++++---------------
+ kernel/sched/deadline.c | 12 ++++++++++--
+ 2 files changed, 17 insertions(+), 17 deletions(-)
+
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -8182,19 +8182,14 @@ static void cpuset_cpu_active(void)
+ cpuset_update_active_cpus();
+ }
+
+-static int cpuset_cpu_inactive(unsigned int cpu)
++static void cpuset_cpu_inactive(unsigned int cpu)
+ {
+ if (!cpuhp_tasks_frozen) {
+- int ret = dl_bw_deactivate(cpu);
+-
+- if (ret)
+- return ret;
+ cpuset_update_active_cpus();
+ } else {
+ num_cpus_frozen++;
+ partition_sched_domains(1, NULL, NULL);
+ }
+- return 0;
+ }
+
+ static inline void sched_smt_present_inc(int cpu)
+@@ -8256,6 +8251,11 @@ int sched_cpu_deactivate(unsigned int cp
+ struct rq *rq = cpu_rq(cpu);
+ int ret;
+
++ ret = dl_bw_deactivate(cpu);
++
++ if (ret)
++ return ret;
++
+ /*
+ * Remove CPU from nohz.idle_cpus_mask to prevent participating in
+ * load balancing when not active
+@@ -8301,15 +8301,7 @@ int sched_cpu_deactivate(unsigned int cp
+ return 0;
+
+ sched_update_numa(cpu, false);
+- ret = cpuset_cpu_inactive(cpu);
+- if (ret) {
+- sched_smt_present_inc(cpu);
+- sched_set_rq_online(rq, cpu);
+- balance_push_set(cpu, false);
+- set_cpu_active(cpu, true);
+- sched_update_numa(cpu, true);
+- return ret;
+- }
++ cpuset_cpu_inactive(cpu);
+ sched_domains_numa_masks_clear(cpu);
+ return 0;
+ }
+--- a/kernel/sched/deadline.c
++++ b/kernel/sched/deadline.c
+@@ -3500,6 +3500,13 @@ static int dl_bw_manage(enum dl_bw_reque
+ break;
+ case dl_bw_req_deactivate:
+ /*
++ * cpu is not off yet, but we need to do the math by
++ * considering it off already (i.e., what would happen if we
++ * turn cpu off?).
++ */
++ cap -= arch_scale_cpu_capacity(cpu);
++
++ /*
+ * cpu is going offline and NORMAL tasks will be moved away
+ * from it. We can thus discount dl_server bandwidth
+ * contribution as it won't need to be servicing tasks after
+@@ -3516,9 +3523,10 @@ static int dl_bw_manage(enum dl_bw_reque
+ if (dl_b->total_bw - fair_server_bw > 0) {
+ /*
+ * Leaving at least one CPU for DEADLINE tasks seems a
+- * wise thing to do.
++ * wise thing to do. As said above, cpu is not offline
++ * yet, so account for that.
+ */
+- if (dl_bw_cpus(cpu))
++ if (dl_bw_cpus(cpu) - 1)
+ overflow = __dl_overflow(dl_b, cap, fair_server_bw, 0);
+ else
+ overflow = 1;
--- /dev/null
+From d4742f6ed7ea6df56e381f82ba4532245fa1e561 Mon Sep 17 00:00:00 2001
+From: Juri Lelli <juri.lelli@redhat.com>
+Date: Thu, 14 Nov 2024 14:28:10 +0000
+Subject: sched/deadline: Correctly account for allocated bandwidth during hotplug
+
+From: Juri Lelli <juri.lelli@redhat.com>
+
+commit d4742f6ed7ea6df56e381f82ba4532245fa1e561 upstream.
+
+For hotplug operations, DEADLINE needs to check that there is still enough
+bandwidth left after removing the CPU that is going offline. We however
+fail to do so currently.
+
+Restore the correct behavior by restructuring dl_bw_manage() a bit, so
+that overflow conditions (not enough bandwidth left) are properly
+checked. Also account for dl_server bandwidth, i.e. discount such
+bandwidth in the calculation since NORMAL tasks will be anyway moved
+away from the CPU as a result of the hotplug operation.
+
+Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Reviewed-by: Phil Auld <pauld@redhat.com>
+Tested-by: Waiman Long <longman@redhat.com>
+Link: https://lore.kernel.org/r/20241114142810.794657-3-juri.lelli@redhat.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/sched/core.c | 2 +-
+ kernel/sched/deadline.c | 48 +++++++++++++++++++++++++++++++++++++++---------
+ kernel/sched/sched.h | 2 +-
+ 3 files changed, 41 insertions(+), 11 deletions(-)
+
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -8185,7 +8185,7 @@ static void cpuset_cpu_active(void)
+ static int cpuset_cpu_inactive(unsigned int cpu)
+ {
+ if (!cpuhp_tasks_frozen) {
+- int ret = dl_bw_check_overflow(cpu);
++ int ret = dl_bw_deactivate(cpu);
+
+ if (ret)
+ return ret;
+--- a/kernel/sched/deadline.c
++++ b/kernel/sched/deadline.c
+@@ -3464,29 +3464,31 @@ int dl_cpuset_cpumask_can_shrink(const s
+ }
+
+ enum dl_bw_request {
+- dl_bw_req_check_overflow = 0,
++ dl_bw_req_deactivate = 0,
+ dl_bw_req_alloc,
+ dl_bw_req_free
+ };
+
+ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
+ {
+- unsigned long flags;
++ unsigned long flags, cap;
+ struct dl_bw *dl_b;
+ bool overflow = 0;
++ u64 fair_server_bw = 0;
+
+ rcu_read_lock_sched();
+ dl_b = dl_bw_of(cpu);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+
+- if (req == dl_bw_req_free) {
++ cap = dl_bw_capacity(cpu);
++ switch (req) {
++ case dl_bw_req_free:
+ __dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
+- } else {
+- unsigned long cap = dl_bw_capacity(cpu);
+-
++ break;
++ case dl_bw_req_alloc:
+ overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
+
+- if (req == dl_bw_req_alloc && !overflow) {
++ if (!overflow) {
+ /*
+ * We reserve space in the destination
+ * root_domain, as we can't fail after this point.
+@@ -3495,6 +3497,34 @@ static int dl_bw_manage(enum dl_bw_reque
+ */
+ __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
+ }
++ break;
++ case dl_bw_req_deactivate:
++ /*
++ * cpu is going offline and NORMAL tasks will be moved away
++ * from it. We can thus discount dl_server bandwidth
++ * contribution as it won't need to be servicing tasks after
++ * the cpu is off.
++ */
++ if (cpu_rq(cpu)->fair_server.dl_server)
++ fair_server_bw = cpu_rq(cpu)->fair_server.dl_bw;
++
++ /*
++ * Not much to check if no DEADLINE bandwidth is present.
++ * dl_servers we can discount, as tasks will be moved out the
++ * offlined CPUs anyway.
++ */
++ if (dl_b->total_bw - fair_server_bw > 0) {
++ /*
++ * Leaving at least one CPU for DEADLINE tasks seems a
++ * wise thing to do.
++ */
++ if (dl_bw_cpus(cpu))
++ overflow = __dl_overflow(dl_b, cap, fair_server_bw, 0);
++ else
++ overflow = 1;
++ }
++
++ break;
+ }
+
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+@@ -3503,9 +3533,9 @@ static int dl_bw_manage(enum dl_bw_reque
+ return overflow ? -EBUSY : 0;
+ }
+
+-int dl_bw_check_overflow(int cpu)
++int dl_bw_deactivate(int cpu)
+ {
+- return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0);
++ return dl_bw_manage(dl_bw_req_deactivate, cpu, 0);
+ }
+
+ int dl_bw_alloc(int cpu, u64 dl_bw)
+--- a/kernel/sched/sched.h
++++ b/kernel/sched/sched.h
+@@ -362,7 +362,7 @@ extern void __getparam_dl(struct task_st
+ extern bool __checkparam_dl(const struct sched_attr *attr);
+ extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
+ extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
+-extern int dl_bw_check_overflow(int cpu);
++extern int dl_bw_deactivate(int cpu);
+ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec);
+ /*
+ * SCHED_DEADLINE supports servers (nested scheduling) with the following
--- /dev/null
+From 41d4200b7103152468552ee50998cda914102049 Mon Sep 17 00:00:00 2001
+From: Juri Lelli <juri.lelli@redhat.com>
+Date: Thu, 14 Nov 2024 14:28:09 +0000
+Subject: sched/deadline: Restore dl_server bandwidth on non-destructive root domain changes
+
+From: Juri Lelli <juri.lelli@redhat.com>
+
+commit 41d4200b7103152468552ee50998cda914102049 upstream.
+
+When root domain non-destructive changes (e.g., only modifying one of
+the existing root domains while the rest is not touched) happen we still
+need to clear DEADLINE bandwidth accounting so that it's then properly
+restored, taking into account DEADLINE tasks associated to each cpuset
+(associated to each root domain). After the introduction of dl_servers,
+we fail to restore such servers contribution after non-destructive
+changes (as they are only considered on destructive changes when
+runqueues are attached to the new domains).
+
+Fix this by making sure we iterate over the dl_servers attached to
+domains that have not been destroyed and add their bandwidth
+contribution back correctly.
+
+Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Reviewed-by: Phil Auld <pauld@redhat.com>
+Tested-by: Waiman Long <longman@redhat.com>
+Link: https://lore.kernel.org/r/20241114142810.794657-2-juri.lelli@redhat.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/sched/deadline.c | 17 ++++++++++++++---
+ kernel/sched/topology.c | 8 +++++---
+ 2 files changed, 19 insertions(+), 6 deletions(-)
+
+--- a/kernel/sched/deadline.c
++++ b/kernel/sched/deadline.c
+@@ -2964,11 +2964,22 @@ void dl_add_task_root_domain(struct task
+
+ void dl_clear_root_domain(struct root_domain *rd)
+ {
+- unsigned long flags;
++ int i;
+
+- raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
++ guard(raw_spinlock_irqsave)(&rd->dl_bw.lock);
+ rd->dl_bw.total_bw = 0;
+- raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
++
++ /*
++ * dl_server bandwidth is only restored when CPUs are attached to root
++ * domains (after domains are created or CPUs moved back to the
++ * default root doamin).
++ */
++ for_each_cpu(i, rd->span) {
++ struct sched_dl_entity *dl_se = &cpu_rq(i)->fair_server;
++
++ if (dl_server(dl_se) && cpu_active(i))
++ rd->dl_bw.total_bw += dl_se->dl_bw;
++ }
+ }
+
+ #endif /* CONFIG_SMP */
+--- a/kernel/sched/topology.c
++++ b/kernel/sched/topology.c
+@@ -2721,9 +2721,11 @@ void partition_sched_domains_locked(int
+
+ /*
+ * This domain won't be destroyed and as such
+- * its dl_bw->total_bw needs to be cleared. It
+- * will be recomputed in function
+- * update_tasks_root_domain().
++ * its dl_bw->total_bw needs to be cleared.
++ * Tasks contribution will be then recomputed
++ * in function dl_update_tasks_root_domain(),
++ * dl_servers contribution in function
++ * dl_restore_server_root_domain().
+ */
+ rd = cpu_rq(cpumask_any(doms_cur[i]))->rd;
+ dl_clear_root_domain(rd);
drm-zynqmp_dp-fix-integer-overflow-in-zynqmp_dp_rate_get.patch
drm-xe-tracing-fix-a-potential-tp_printk-uaf.patch
drm-renesas-rz-du-increase-supported-resolutions.patch
+sched-deadline-restore-dl_server-bandwidth-on-non-destructive-root-domain-changes.patch
+sched-deadline-correctly-account-for-allocated-bandwidth-during-hotplug.patch
+sched-deadline-check-bandwidth-overflow-earlier-for-hotplug.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
