From cd1cb3350561d2bf544ddfef76fbf0b1c9c7178f Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 23 Oct 2019 16:37:44 +0100 Subject: sched/topology: Don't try to build empty sched domains Turns out hotplugging CPUs that are in exclusive cpusets can lead to the cpuset code feeding empty cpumasks to the sched domain rebuild machinery. This leads to the following splat: Internal error: Oops: 96000004 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 235 Comm: kworker/5:2 Not tainted 5.4.0-rc1-00005-g8d495477d62e #23 Hardware name: ARM Juno development board (r0) (DT) Workqueue: events cpuset_hotplug_workfn pstate: 60000005 (nZCv daif -PAN -UAO) pc : build_sched_domains (./include/linux/arch_topology.h:23 kernel/sched/topology.c:1898 kernel/sched/topology.c:1969) lr : build_sched_domains (kernel/sched/topology.c:1966) Call trace: build_sched_domains (./include/linux/arch_topology.h:23 kernel/sched/topology.c:1898 kernel/sched/topology.c:1969) partition_sched_domains_locked (kernel/sched/topology.c:2250) rebuild_sched_domains_locked (./include/linux/bitmap.h:370 ./include/linux/cpumask.h:538 kernel/cgroup/cpuset.c:955 kernel/cgroup/cpuset.c:978 kernel/cgroup/cpuset.c:1019) rebuild_sched_domains (kernel/cgroup/cpuset.c:1032) cpuset_hotplug_workfn (kernel/cgroup/cpuset.c:3205 (discriminator 2)) process_one_work (./arch/arm64/include/asm/jump_label.h:21 ./include/linux/jump_label.h:200 ./include/trace/events/workqueue.h:114 kernel/workqueue.c:2274) worker_thread (./include/linux/compiler.h:199 ./include/linux/list.h:268 kernel/workqueue.c:2416) kthread (kernel/kthread.c:255) ret_from_fork (arch/arm64/kernel/entry.S:1167) Code: f860dae2 912802d6 aa1603e1 12800000 (f8616853) The faulty line in question is: cap = arch_scale_cpu_capacity(cpumask_first(cpu_map)); and we're not checking the return value against nr_cpu_ids (we shouldn't have to!), which leads to the above. Prevent generate_sched_domains() from returning empty cpumasks, and add some assertion in build_sched_domains() to scream bloody murder if it happens again. The above splat was obtained on my Juno r0 with the following reproducer: $ cgcreate -g cpuset:asym $ cgset -r cpuset.cpus=0-3 asym $ cgset -r cpuset.mems=0 asym $ cgset -r cpuset.cpu_exclusive=1 asym $ cgcreate -g cpuset:smp $ cgset -r cpuset.cpus=4-5 smp $ cgset -r cpuset.mems=0 smp $ cgset -r cpuset.cpu_exclusive=1 smp $ cgset -r cpuset.sched_load_balance=0 . $ echo 0 > /sys/devices/system/cpu/cpu4/online $ echo 0 > /sys/devices/system/cpu/cpu5/online Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar.Eggemann@arm.com Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: hannes@cmpxchg.org Cc: lizefan@huawei.com Cc: morten.rasmussen@arm.com Cc: qperret@google.com Cc: tj@kernel.org Cc: vincent.guittot@linaro.org Fixes: 05484e098448 ("sched/topology: Add SD_ASYM_CPUCAPACITY flag detection") Link: https://lkml.kernel.org/r/20191023153745.19515-2-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/cgroup/cpuset.c | 3 ++- kernel/sched/topology.c | 5 ++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c52bc91f882b..c87ee6412b36 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -798,7 +798,8 @@ static int generate_sched_domains(cpumask_var_t **domains, cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; - if (is_sched_load_balance(cp)) + if (is_sched_load_balance(cp) && + !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index b5667a273bf6..9318acf1d1fe 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1948,7 +1948,7 @@ next_level: static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) { - enum s_alloc alloc_state; + enum s_alloc alloc_state = sa_none; struct sched_domain *sd; struct s_data d; struct rq *rq = NULL; @@ -1956,6 +1956,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att struct sched_domain_topology_level *tl_asym; bool has_asym = false; + if (WARN_ON(cpumask_empty(cpu_map))) + goto error; + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); if (alloc_state != sa_rootdomain) goto error; -- cgit v1.2.3 From e284df705cf1eeedb5ec3a66ed82d17a64659150 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 23 Oct 2019 16:37:45 +0100 Subject: sched/topology: Allow sched_asym_cpucapacity to be disabled While the static key is correctly initialized as being disabled, it will remain forever enabled once turned on. This means that if we start with an asymmetric system and hotplug out enough CPUs to end up with an SMP system, the static key will remain set - which is obviously wrong. We should detect this and turn off things like misfit migration and capacity aware wakeups. As Quentin pointed out, having separate root domains makes this slightly trickier. We could have exclusive cpusets that create an SMP island - IOW, the domains within this root domain will not see any asymmetry. This means we can't just disable the key on domain destruction, we need to count how many asymmetric root domains we have. Consider the following example using Juno r0 which is 2+4 big.LITTLE, where two identical cpusets are created: they both span both big and LITTLE CPUs: asym0 asym1 [ ][ ] L L B L L B $ cgcreate -g cpuset:asym0 $ cgset -r cpuset.cpus=0,1,3 asym0 $ cgset -r cpuset.mems=0 asym0 $ cgset -r cpuset.cpu_exclusive=1 asym0 $ cgcreate -g cpuset:asym1 $ cgset -r cpuset.cpus=2,4,5 asym1 $ cgset -r cpuset.mems=0 asym1 $ cgset -r cpuset.cpu_exclusive=1 asym1 $ cgset -r cpuset.sched_load_balance=0 . (the CPU numbering may look odd because on the Juno LITTLEs are CPUs 0,3-5 and bigs are CPUs 1-2) If we make one of those SMP (IOW remove asymmetry) by e.g. hotplugging its big core, we would end up with an SMP cpuset and an asymmetric cpuset - the static key must remain set, because we still have one asymmetric root domain. With the above example, this could be done with: $ echo 0 > /sys/devices/system/cpu/cpu2/online Which would result in: asym0 asym1 [ ][ ] L L B L L When both SMP and asymmetric cpusets are present, all CPUs will observe sched_asym_cpucapacity being set (it is system-wide), but not all CPUs observe asymmetry in their sched domain hierarchy: per_cpu(sd_asym_cpucapacity, ) == per_cpu(sd_asym_cpucapacity, ) == NULL Change the simple key enablement to an increment, and decrement the key counter when destroying domains that cover asymmetric CPUs. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Cc: Dietmar.Eggemann@arm.com Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: hannes@cmpxchg.org Cc: lizefan@huawei.com Cc: morten.rasmussen@arm.com Cc: qperret@google.com Cc: tj@kernel.org Cc: vincent.guittot@linaro.org Fixes: df054e8445a4 ("sched/topology: Add static_key for asymmetric CPU capacity optimizations") Link: https://lkml.kernel.org/r/20191023153745.19515-3-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/topology.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 9318acf1d1fe..49b835f1305f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2029,7 +2029,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att rcu_read_unlock(); if (has_asym) - static_branch_enable_cpuslocked(&sched_asym_cpucapacity); + static_branch_inc_cpuslocked(&sched_asym_cpucapacity); if (rq && sched_debug_enabled) { pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", @@ -2124,8 +2124,12 @@ int sched_init_domains(const struct cpumask *cpu_map) */ static void detach_destroy_domains(const struct cpumask *cpu_map) { + unsigned int cpu = cpumask_any(cpu_map); int i; + if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu))) + static_branch_dec_cpuslocked(&sched_asym_cpucapacity); + rcu_read_lock(); for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); -- cgit v1.2.3