x86, sched: check for counters overflow in frequency invariant accounting (e2b0d619) · Commits · 戴 / test

The product mcnt * arch_max_freq_ratio can overflows u64. For context, a large value for arch_max_freq_ratio would be 5000, corresponding to a turbo_freq/base_freq ratio of 5 (normally it's more like 1500-2000). A large increment frequency for the MPERF counter would be 5GHz (the base clock of all CPUs on the market today is less than that). With these figures, a CPU would need to go without a scheduler tick for around 8 days for the u64 overflow to happen. It is unlikely, but the check is warranted. Under similar conditions, the difference acnt of two consecutive APERF readings can overflow as well. In these circumstances is appropriate to disable frequency invariant accounting: the feature relies on measures of the clock frequency done at every scheduler tick, which need to be "fresh" to be at all meaningful. A note on i386: prior to version 5.1, the GCC compiler didn't have the builtin function __builtin_mul_overflow. In these GCC versions the macro check_mul_overflow needs __udivdi3() to do (u64)a/b, which the kernel doesn't provide. For this reason this change fails to build on i386 if GCC<5.1, and we protect the entire frequency invariant code behind CONFIG_X86_64 (special thanks to "kbuild test robot" <lkp@intel.com>). Fixes: ("x86, sched: Add support for frequency invariance") Signed-off-by:

Giovanni Gherdovich <ggherdovich@suse.cz> Signed-off-by:

Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by:

Rafael J. Wysocki <rafael.j.wysocki@intel.com> Link: https://lkml.kernel.org/r/20200531182453.15254-2-ggherdovich@suse.cz

arch/x86/include/asm/topology.h

+1 −1

Original line number	Diff line number	Diff line
		@@ -193,7 +193,7 @@ static inline void sched_clear_itmt_support(void)
		}
		#endif /* CONFIG_SCHED_MC_PRIO */

		#ifdef CONFIG_SMP
		#if defined(CONFIG_SMP) && defined(CONFIG_X86_64)
		#include <asm/cpufeature.h>

		DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key);

arch/x86/kernel/smpboot.c

+28 −5

Original line number	Diff line number	Diff line
		@@ -56,6 +56,7 @@
		#include <linux/cpuidle.h>
		#include <linux/numa.h>
		#include <linux/pgtable.h>
		#include <linux/overflow.h>

		#include <asm/acpi.h>
		#include <asm/desc.h>
		@@ -1777,6 +1778,7 @@ void native_play_dead(void)

		#endif

		#ifdef CONFIG_X86_64
		/*
		* APERF/MPERF frequency ratio computation.
		*
		@@ -2048,11 +2050,19 @@ static void init_freq_invariance(bool secondary)
		}
		}

		static void disable_freq_invariance_workfn(struct work_struct *work)
		{
		static_branch_disable(&arch_scale_freq_key);
		}

		static DECLARE_WORK(disable_freq_invariance_work,
		disable_freq_invariance_workfn);

		DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;

		void arch_scale_freq_tick(void)
		{
		u64 freq_scale;
		u64 freq_scale = SCHED_CAPACITY_SCALE;
		u64 aperf, mperf;
		u64 acnt, mcnt;

		@@ -2064,19 +2074,32 @@ void arch_scale_freq_tick(void)

		acnt = aperf - this_cpu_read(arch_prev_aperf);
		mcnt = mperf - this_cpu_read(arch_prev_mperf);
		if (!mcnt)
		return;

		this_cpu_write(arch_prev_aperf, aperf);
		this_cpu_write(arch_prev_mperf, mperf);

		acnt <<= 2*SCHED_CAPACITY_SHIFT;
		mcnt *= arch_max_freq_ratio;
		if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
		goto error;

		if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) \|\| !mcnt)
		goto error;

		freq_scale = div64_u64(acnt, mcnt);
		if (!freq_scale)
		goto error;

		if (freq_scale > SCHED_CAPACITY_SCALE)
		freq_scale = SCHED_CAPACITY_SCALE;

		this_cpu_write(arch_freq_scale, freq_scale);
		return;

		error:
		pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
		schedule_work(&disable_freq_invariance_work);
		}
		#else
		static inline void init_freq_invariance(bool secondary)
		{
		}
		#endif /* CONFIG_X86_64 */

Admin message