linux-kernel - [PATCH V3 2/3] arm64: topology: Reorder init_amu

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

Message-Id: <87d517c24630494afd9ba5769c2e2b10ee1d3f5d.1608010334.git.viresh.kumar@linaro.org>
Date:   Tue, 15 Dec 2020 11:04:15 +0530
From:   Viresh Kumar <viresh.kumar@...aro.org>
To:     Ionela Voinescu <ionela.voinescu@....com>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>
Cc:     Viresh Kumar <viresh.kumar@...aro.org>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: [PATCH V3 2/3] arm64: topology: Reorder init_amu_fie() a bit

This patch does a couple of optimizations in init_amu_fie(), like early
exits from paths where we don't need to continue any further, avoid the
enable/disable dance, moving the calls to
topology_scale_freq_invariant() just when we need them, instead of at
the top of the routine, and avoiding calling it for the third time.

Signed-off-by: Viresh Kumar <viresh.kumar@...aro.org>
---
V3:
- Skipped the enable/disable dance.
- No need to call topology_scale_freq_invariant() multiple times.

 arch/arm64/kernel/topology.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index ebadc73449f9..57267d694495 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -221,8 +221,8 @@ static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
 
 static int __init init_amu_fie(void)
 {
-	bool invariance_status = topology_scale_freq_invariant();
 	cpumask_var_t valid_cpus;
+	bool invariant;
 	int ret = 0;
 	int cpu;
 
@@ -249,18 +249,19 @@ static int __init init_amu_fie(void)
 	if (cpumask_equal(valid_cpus, cpu_present_mask))
 		cpumask_copy(amu_fie_cpus, cpu_present_mask);
 
-	if (!cpumask_empty(amu_fie_cpus)) {
-		pr_info("CPUs[%*pbl]: counters will be used for FIE.",
-			cpumask_pr_args(amu_fie_cpus));
-		static_branch_enable(&amu_fie_key);
-	}
+	if (cpumask_empty(amu_fie_cpus))
+		goto free_valid_mask;
 
-	/*
-	 * If the system is not fully invariant after AMU init, disable
-	 * partial use of counters for frequency invariance.
-	 */
-	if (!topology_scale_freq_invariant())
-		static_branch_disable(&amu_fie_key);
+	invariant = topology_scale_freq_invariant();
+
+	/* We aren't fully invariant yet */
+	if (!invariant && !cpumask_equal(amu_fie_cpus, cpu_present_mask))
+		goto free_valid_mask;
+
+	static_branch_enable(&amu_fie_key);
+
+	pr_info("CPUs[%*pbl]: counters will be used for FIE.",
+		cpumask_pr_args(amu_fie_cpus));
 
 	/*
 	 * Task scheduler behavior depends on frequency invariance support,
@@ -268,7 +269,7 @@ static int __init init_amu_fie(void)
 	 * a result of counter initialisation and use, retrigger the build of
 	 * scheduling domains to ensure the information is propagated properly.
 	 */
-	if (invariance_status != topology_scale_freq_invariant())
+	if (!invariant)
 		rebuild_sched_domains_energy();
 
 free_valid_mask:
-- 
2.25.0.rc1.19.g042ed3e048af