linux-kernel - [PATCH] sched/topology: remove sysctl_sched_energy

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230829065040.920629-1-sshegde@linux.vnet.ibm.com>
Date:   Tue, 29 Aug 2023 12:20:40 +0530
From:   Shrikanth Hegde <sshegde@...ux.vnet.ibm.com>
To:     mingo@...hat.com, peterz@...radead.org, vincent.guittot@...aro.org
Cc:     sshegde@...ux.vnet.ibm.com, dietmar.eggemann@....com,
        vschneid@...hat.com, linux-kernel@...r.kernel.org,
        ionela.voinescu@....com, quentin.perret@....com,
        srikar@...ux.vnet.ibm.com, mgorman@...hsingularity.net,
        mingo@...nel.org
Subject: [PATCH] sched/topology: remove sysctl_sched_energy_aware depending on the architecture

Currently sysctl_sched_energy_aware doesn't alter the said behaviour on
some of the architectures. IIUC its meant to either force rebuild the
perf domains or cleanup the perf domains by echoing 1 or 0 respectively.

perf domains are not built when there is SMT, or when there is no
Asymmetric CPU topologies or when there is no frequency invariance.
Since such cases EAS is not set and perf domains are not built. By
changing the values of sysctl_sched_energy_aware, its not possible to
force build the perf domains. Hence remove this sysctl on such platforms
that dont support it at boot. Some of the settings can be changed later
such as smt_active by offlining the CPU's, In those cases
build_perf_domains returns true, in that case re-enable the sysctl.

Signed-off-by: Shrikanth Hegde <sshegde@...ux.vnet.ibm.com>
---
 kernel/sched/topology.c | 36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 05a5bc678c08..ff68366be280 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -208,7 +208,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)

 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 DEFINE_STATIC_KEY_FALSE(sched_energy_present);
-static unsigned int sysctl_sched_energy_aware = 1;
+static unsigned int sysctl_sched_energy_aware;
+static struct ctl_table_header *sysctl_eas_header;
 static DEFINE_MUTEX(sched_energy_mutex);
 static bool sched_energy_update;

@@ -226,6 +227,7 @@ static int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, state;
+	int prev_val = sysctl_sched_energy_aware;

 	if (write && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -233,8 +235,11 @@ static int sched_energy_aware_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write) {
 		state = static_branch_unlikely(&sched_energy_present);
-		if (state != sysctl_sched_energy_aware)
+		if (state != sysctl_sched_energy_aware && prev_val != sysctl_sched_energy_aware) {
+			if (sysctl_sched_energy_aware && !state)
+				pr_warn("Attempt to build energy domains when EAS is disabled\n");
 			rebuild_sched_domains_energy();
+		}
 	}

 	return ret;
@@ -255,7 +260,14 @@ static struct ctl_table sched_energy_aware_sysctls[] = {

 static int __init sched_energy_aware_sysctl_init(void)
 {
-	register_sysctl_init("kernel", sched_energy_aware_sysctls);
+	int cpu = cpumask_first(cpu_active_mask);
+
+	if (sched_smt_active() || !per_cpu(sd_asym_cpucapacity, cpu) ||
+	    !arch_scale_freq_invariant())
+		return 0;
+
+	sysctl_eas_header = register_sysctl("kernel", sched_energy_aware_sysctls);
+	sysctl_sched_energy_aware = 1;
 	return 0;
 }

@@ -336,10 +348,18 @@ static void sched_energy_set(bool has_eas)
 		if (sched_debug())
 			pr_info("%s: stopping EAS\n", __func__);
 		static_branch_disable_cpuslocked(&sched_energy_present);
+#ifdef CONFIG_PROC_SYSCTL
+		unregister_sysctl_table(sysctl_eas_header);
+#endif
+		sysctl_sched_energy_aware = 0;
 	} else if (has_eas && !static_branch_unlikely(&sched_energy_present)) {
 		if (sched_debug())
 			pr_info("%s: starting EAS\n", __func__);
 		static_branch_enable_cpuslocked(&sched_energy_present);
+#ifdef CONFIG_PROC_SYSCTL
+		sysctl_eas_header = register_sysctl("kernel", sched_energy_aware_sysctls);
+#endif
+		sysctl_sched_energy_aware = 1;
 	}
 }

@@ -380,15 +400,11 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 	struct cpufreq_policy *policy;
 	struct cpufreq_governor *gov;

-	if (!sysctl_sched_energy_aware)
-		goto free;
-
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
 	if (!per_cpu(sd_asym_cpucapacity, cpu)) {
-		if (sched_debug()) {
-			pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n",
-					cpumask_pr_args(cpu_map));
-		}
+		if (sched_debug())
+			pr_info("rd %*pbl: Disabling EAS,  CPUs do not have asymmetric capacities\n",
+				cpumask_pr_args(cpu_map));
 		goto free;
 	}

--
2.31.1