linux-kernel - [PATCH 03/17] pseries/lpar: Process steal metrics

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: <20251204175405.1511340-4-srikar@linux.ibm.com>
Date: Thu,  4 Dec 2025 23:23:51 +0530
From: Srikar Dronamraju <srikar@...ux.ibm.com>
To: linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org,
        Peter Zijlstra <peterz@...radead.org>
Cc: Ben Segall <bsegall@...gle.com>,
        Christophe Leroy <christophe.leroy@...roup.eu>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Ingo Molnar <mingo@...nel.org>, Juri Lelli <juri.lelli@...hat.com>,
        K Prateek Nayak <kprateek.nayak@....com>,
        Madhavan Srinivasan <maddy@...ux.ibm.com>,
        Mel Gorman <mgorman@...e.de>, Michael Ellerman <mpe@...erman.id.au>,
        Nicholas Piggin <npiggin@...il.com>,
        Shrikanth Hegde <sshegde@...ux.ibm.com>,
        Srikar Dronamraju <srikar@...ux.ibm.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Swapnil Sapkal <swapnil.sapkal@....com>,
        Thomas Huth <thuth@...hat.com>,
        Valentin Schneider <vschneid@...hat.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        virtualization@...ts.linux.dev, Yicong Yang <yangyicong@...ilicon.com>,
        Ilya Leoshkevich <iii@...ux.ibm.com>
Subject: [PATCH 03/17] pseries/lpar: Process steal metrics

Based on steal metrics, find the ratio of current runtime to steal.
This ratio would further be used to soft offline/online the core.

Steal above a limit would indicate that there is more contention on
cores and hence few cores would be soft-offlined. Steal below a limit
would indicate that there are probably available cores and hence few
cores would be soft-onlined.

Currently only the first online CPU will calculate the steal and even
this CPU will process steal metrics at a 1 second granularity. Also
currently this steal processing is enabled on non-KVM shared logical
partitions. Since the steal time would be portion of the processor's
runtime, use a multiple to bump up the steal time so that its easier to
compare with limits.

Signed-off-by: Srikar Dronamraju <srikar@...ux.ibm.com>
---
 arch/powerpc/platforms/pseries/lpar.c    | 50 ++++++++++++++++++++++++
 arch/powerpc/platforms/pseries/pseries.h |  4 ++
 2 files changed, 54 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index dde12b27ba60..3431730a10ea 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -659,6 +659,53 @@ static int __init vcpudispatch_stats_procfs_init(void)
 machine_device_initcall(pseries, vcpudispatch_stats_procfs_init);
 
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+#define STEAL_MULTIPLE (STEAL_RATIO * STEAL_RATIO)
+#define PURR_UPDATE_TB tb_ticks_per_sec
+
+static void trigger_softoffline(unsigned long steal_ratio)
+{
+}
+
+static bool should_cpu_process_steal(int cpu)
+{
+	if (cpu == cpumask_first(cpu_online_mask))
+		return true;
+
+	return false;
+}
+
+static void process_steal(int cpu)
+{
+	static unsigned long next_tb, prev_steal;
+	unsigned long steal_ratio, delta_tb;
+	unsigned long tb = mftb();
+	unsigned long steal = 0;
+	unsigned int i;
+
+	if (!should_cpu_process_steal(cpu))
+		return;
+
+	if (tb < next_tb)
+		return;
+
+	for_each_online_cpu(i) {
+		struct lppaca *lppaca = &lppaca_of(i);
+
+		steal += be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+		steal += be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb));
+	}
+
+	if (next_tb && prev_steal) {
+		delta_tb = max(tb - (next_tb - PURR_UPDATE_TB), 1);
+		steal_ratio = (steal - prev_steal) * STEAL_MULTIPLE;
+		steal_ratio /= (delta_tb * num_online_cpus());
+		trigger_softoffline(steal_ratio);
+	}
+
+	next_tb = tb + PURR_UPDATE_TB;
+	prev_steal = steal;
+}
+
 u64 pseries_paravirt_steal_clock(int cpu)
 {
 	struct lppaca *lppaca = &lppaca_of(cpu);
@@ -667,6 +714,9 @@ u64 pseries_paravirt_steal_clock(int cpu)
 	steal = be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
 	steal += be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb));
 
+	if (is_shared_processor() && !is_kvm_guest())
+		process_steal(cpu);
+
 	/*
 	 * VPA steal time counters are reported at TB frequency. Hence do a
 	 * conversion to ns before using.
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 3968a6970fa8..68cf25152870 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -26,6 +26,10 @@ void pSeries_machine_check_log_err(void);
 #ifdef CONFIG_SMP
 extern void smp_init_pseries(void);
 
+#ifdef CONFIG_PPC_SPLPAR
+#define STEAL_RATIO 100
+#endif
+
 /* Get state of physical CPU from query_cpu_stopped */
 int smp_query_cpu_stopped(unsigned int pcpu);
 #define QCSS_STOPPED 0
-- 
2.43.7