linux-kernel - Re: [PATCH v4 3/6] x86,sched: Add support for frequency invariance on XEON_PHI

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]
Date:   Wed, 18 Dec 2019 21:22:36 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Giovanni Gherdovich <ggherdovich@...e.cz>
Cc:     Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...e.de>,
        Len Brown <lenb@...nel.org>,
        "Rafael J . Wysocki" <rjw@...ysocki.net>, x86@...nel.org,
        linux-pm@...r.kernel.org, linux-kernel@...r.kernel.org,
        Mel Gorman <mgorman@...hsingularity.net>,
        Matt Fleming <matt@...eblueprint.co.uk>,
        Viresh Kumar <viresh.kumar@...aro.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Paul Turner <pjt@...gle.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Quentin Perret <qperret@...rret.net>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Doug Smythies <dsmythies@...us.net>
Subject: Re: [PATCH v4 3/6] x86,sched: Add support for frequency invariance
 on XEON_PHI_KNL/KNM

On Wed, Nov 13, 2019 at 01:46:51PM +0100, Giovanni Gherdovich wrote:
> The scheduler needs the ratio freq_curr/freq_max for frequency-invariant
> accounting. On Xeon Phi CPUs set freq_max to the second-highest frequency
> reported by the CPU.
> 
> Xeon Phi CPUs such as Knights Landing and Knights Mill typically have either
> one or two turbo frequencies; in the former case that's 100 MHz above the base
> frequency, in the latter case the two levels are 100 MHz and 200 MHz above
> base frequency.
> 
> We set freq_max to the second-highest frequency reported by the CPU. This
> could be the base frequency (if only one turbo level is available) or the first
> turbo level (if two levels are available). The rationale is to compromise
> between power efficiency or performance -- going straight to max turbo would
> favor efficiency and blindly using base freq would favor performance.
> 
> For reference, this is how MSR_TURBO_RATIO_LIMIT must be parsed on a Xeon Phi
> to get the available frequencies (taken from a comment in turbostat's sources):
> 
>     [0] -- Reserved
>     [7:1] -- Base value of number of active cores of bucket 1.
>     [15:8] -- Base value of freq ratio of bucket 1.
>     [20:16] -- +ve delta of number of active cores of bucket 2.
>     i.e. active cores of bucket 2 =
>     active cores of bucket 1 + delta
>     [23:21] -- Negative delta of freq ratio of bucket 2.
>     i.e. freq ratio of bucket 2 =
>     freq ratio of bucket 1 - delta
>     [28:24]-- +ve delta of number of active cores of bucket 3.
>     [31:29]-- -ve delta of freq ratio of bucket 3.
>     [36:32]-- +ve delta of number of active cores of bucket 4.
>     [39:37]-- -ve delta of freq ratio of bucket 4.
>     [44:40]-- +ve delta of number of active cores of bucket 5.
>     [47:45]-- -ve delta of freq ratio of bucket 5.
>     [52:48]-- +ve delta of number of active cores of bucket 6.
>     [55:53]-- -ve delta of freq ratio of bucket 6.
>     [60:56]-- +ve delta of number of active cores of bucket 7.
>     [63:61]-- -ve delta of freq ratio of bucket 7.

Does it make sense to write a complete decoder and pass a @size
parameter just like the skx/glm case?

(I've no idea on the 4 I passed in, probably wants to be something else)

---
Index: linux-2.6/arch/x86/kernel/smpboot.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/smpboot.c
+++ linux-2.6/arch/x86/kernel/smpboot.c
@@ -1863,36 +1863,12 @@ static const struct x86_cpu_id has_glm_t
 	{}
 };

-static int get_knl_turbo_ratio(u64 *turbo_ratio)
+static bool knl_set_cpu_max_freq(u64 *ratio, u64 *turbo_ratio, int size)
 {
+	int delta_cores, delta_fratio;
+	int cores, fratio;
+	int err, i;
 	u64 msr;
-	u32 ratio, delta_ratio;
-	int err, i, found = 0;
-
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
-	if (err)
-		return err;
-
-	ratio = (msr >> 8) & 0xFF;
-
-	for (i = 16; i < 64; i += 8) {
-		delta_ratio = (msr >> (i + 5)) & 0x7;
-		if (delta_ratio) {
-			*turbo_ratio = ratio - delta_ratio;
-			found = 1;
-			break;
-		}
-	}
-
-	if (!found)
-		return 1;
-
-	return 0;
-}
-
-static bool knl_set_cpu_max_freq(u64 *ratio, u64 *turbo_ratio)
-{
-	int err;

 	if (!x86_match_cpu(has_knl_turbo_ratio_limits))
 		return false;
@@ -1901,15 +1877,32 @@ static bool knl_set_cpu_max_freq(u64 *ra
 	if (err)
 		return false;

-	/* second highest turbo ratio */
-	err = get_knl_turbo_ratio(turbo_ratio);
+	*ratio = (*ratio >> 8) & 0xFF; /* max P state ratio */
+
+	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
 	if (err)
 		return false;

-	/* max P state ratio */
-	*ratio = (*ratio >> 8) & 0xFF;
+	cores = (msr >> 1) & 0x7F;
+	fratio = (msr >> 8) & 0xFF;

-	return true;
+	i = 16;
+	do {
+		if (cores >= size) {
+			*turbo_ratio = fratio;
+			return true;
+		}
+
+		delta_cores = (msr >> i) & 0x1F;
+		delta_fratio = (msr >> (i + 5)) & 0x07;
+
+		cores += delta_cores;
+		fratio -= delta_fratio;
+
+		i += 8;
+	} while (i < 64);
+
+	return false;
 }

 static bool skx_set_cpu_max_freq(u64 *ratio, u64 *turbo_ratio, int size)
@@ -1975,7 +1968,7 @@ static void intel_set_cpu_max_freq(void)
 	    skx_set_cpu_max_freq(&ratio, &turbo_ratio, 1))
 		goto set_value;

-	if (knl_set_cpu_max_freq(&ratio, &turbo_ratio))
+	if (knl_set_cpu_max_freq(&ratio, &turbo_ratio, 4))
 		goto set_value;

 	if (x86_match_cpu(has_skx_turbo_ratio_limits) &&