x86, sched: Prevent divisions by zero in frequency invariant accounting

Message ID 20200422144055.18171-1-ggherdovich@suse.cz
State New
Headers show
Series
  • x86, sched: Prevent divisions by zero in frequency invariant accounting
Related show

Commit Message

Giovanni Gherdovich April 22, 2020, 2:40 p.m.
The product mcnt * arch_max_freq_ratio could be zero if it 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.

Signed-off-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Fixes: 1567c3e3467c ("x86, sched: Add support for frequency invariance")
---
 arch/x86/kernel/smpboot.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Patch

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8c89e4d9ad28..fb71395cbcad 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -2055,14 +2055,14 @@  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 (!mcnt)
+		return;
 
 	freq_scale = div64_u64(acnt, mcnt);