[lkml]   [2018]   [Apr]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Patch in this message
Subject[PATCH 4.16 08/26] x86/tsc: Prevent 32bit truncation in calc_hpet_ref()
4.16-stable review patch.  If anyone has any objections, please let me know.


From: Xiaoming Gao <>

commit d3878e164dcd3925a237a20e879432400e369172 upstream.

The TSC calibration code uses HPET as reference. The conversion normalizes
the delta of two HPET timestamps:

hpetref = ((tshpet1 - tshpet2) * HPET_PERIOD) / 1e6

and then divides the normalized delta of the corresponding TSC timestamps
by the result to calulate the TSC frequency.

tscfreq = ((tstsc1 - tstsc2 ) * 1e6) / hpetref

This uses do_div() which takes an u32 as the divisor, which worked so far
because the HPET frequency was low enough that 'hpetref' never exceeded

On Skylake machines the HPET frequency increased so 'hpetref' can exceed
32bit. do_div() truncates the divisor, which causes the calibration to

Use div64_u64() to avoid the problem.

[ tglx: Fixes whitespace mangled patch and rewrote changelog ]

Signed-off-by: Xiaoming Gao <>
Signed-off-by: Thomas Gleixner <>
Signed-off-by: Greg Kroah-Hartman <>

arch/x86/kernel/tsc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 d
hpet2 -= hpet1;
tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
do_div(tmp, 1000000);
- do_div(deltatsc, tmp);
+ deltatsc = div64_u64(deltatsc, tmp);

return (unsigned long) deltatsc;

 \ /
  Last update: 2018-04-25 12:35    [W:0.101 / U:6.584 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site