linux-kernel - [PATCH v3] cpufreq: powernv: Set the cpus to nominal frequency during reboot/kexec

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: <1410430423-1246-1-git-send-email-shilpa.bhat@linux.vnet.ibm.com>
Date:	Thu, 11 Sep 2014 15:43:43 +0530
From:	Shilpasri G Bhat <shilpa.bhat@...ux.vnet.ibm.com>
To:	viresh.kumar@...aro.org, benh@...nel.crashing.org
Cc:	linuxppc-dev@...ts.ozlabs.org, rjw@...ysocki.net,
	linux-pm@...r.kernel.org, linux-kernel@...r.kernel.org,
	preeti@...ux.vnet.ibm.com, David.Laight@...LAB.COM,
	Shilpasri G Bhat <shilpa.bhat@...ux.vnet.ibm.com>
Subject: [PATCH v3] cpufreq: powernv: Set the cpus to nominal frequency during reboot/kexec

This patch ensures the cpus to kexec/reboot at nominal frequency.
Nominal frequency is the highest cpu frequency on PowerPC at
which the cores can run without getting throttled.

If the host kernel had set the cpus to a low pstate and then it
kexecs/reboots to a cpufreq disabled kernel it would cause the target
kernel to perform poorly. It will also increase the boot up time of
the target kernel. So set the cpus to high pstate, in this case to
nominal frequency before rebooting to avoid such scenarios.

The reboot notifier will set the cpus to nominal frequncy.

Signed-off-by: Shilpasri G Bhat <shilpa.bhat@...ux.vnet.ibm.com>
Suggested-by: Viresh Kumar <viresh.kumar@...aro.org>
Reviewed-by: Preeti U Murthy <preeti@...ux.vnet.ibm.com>
---
Changes v2->v3:
We return EBUSY when cpufreq governor tries to change the frequency
after rebooting is set to true. This results in console being flushed
with error messages indicating failed attempts to change the
frequency. So instead of returning EBUSY we return 0 to stop the
governor from changing the frequency without alerting a failure to 
do the same on reboot, as this  is not an errorneaos condition.

Changes v1->v2:
Invoke .target() driver callback to set the cpus to nominal frequency
in reboot notifier, instead of calling cpufreq_suspend() as suggested
by Viresh Kumar.
Modified the commit message.

 drivers/cpufreq/powernv-cpufreq.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 379c083..f772a55 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -26,6 +26,7 @@
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
@@ -35,6 +36,7 @@
 #define POWERNV_MAX_PSTATES	256
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+static bool rebooting;
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -284,6 +286,15 @@ static void set_pstate(void *freq_data)
 }
 
 /*
+ * get_nominal_index: Returns the index corresponding to the nominal
+ * pstate in the cpufreq table
+ */
+static inline unsigned int get_nominal_index(void)
+{
+	return powernv_pstate_info.max - powernv_pstate_info.nominal;
+}
+
+/*
  * powernv_cpufreq_target_index: Sets the frequency corresponding to
  * the cpufreq table entry indexed by new_index on the cpus in the
  * mask policy->cpus
@@ -293,6 +304,9 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 {
 	struct powernv_smp_call_data freq_data;
 
+	if (unlikely(rebooting) && new_index != get_nominal_index())
+		return 0;
+
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
 	/*
@@ -317,6 +331,25 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return cpufreq_table_validate_and_show(policy, powernv_freqs);
 }
 
+static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb,
+				unsigned long action, void *unused)
+{
+	int cpu;
+	struct cpufreq_policy cpu_policy;
+
+	rebooting = true;
+	for_each_online_cpu(cpu) {
+		cpufreq_get_policy(&cpu_policy, cpu);
+		powernv_cpufreq_target_index(&cpu_policy, get_nominal_index());
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block powernv_cpufreq_reboot_nb = {
+	.notifier_call = powernv_cpufreq_reboot_notifier,
+};
+
 static struct cpufreq_driver powernv_cpufreq_driver = {
 	.name		= "powernv-cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
@@ -342,12 +375,14 @@ static int __init powernv_cpufreq_init(void)
 		return rc;
 	}
 
+	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	return cpufreq_register_driver(&powernv_cpufreq_driver);
 }
 module_init(powernv_cpufreq_init);
 
 static void __exit powernv_cpufreq_exit(void)
 {
+	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
 }
 module_exit(powernv_cpufreq_exit);
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/