From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751683AbdE0DeQ (ORCPT ); Fri, 26 May 2017 23:34:16 -0400 Received: from mail-pf0-f179.google.com ([209.85.192.179]:32796 "EHLO mail-pf0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751304AbdE0DeE (ORCPT ); Fri, 26 May 2017 23:34:04 -0400 From: John Stultz To: lkml Cc: John Stultz , Thomas Gleixner , Ingo Molnar , Miroslav Lichvar , Richard Cochran , Prarit Bhargava , Stephen Boyd , Kevin Brodsky , Will Deacon , Daniel Mentz Subject: [RFC][PATCH 2/4] time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting Date: Fri, 26 May 2017 20:33:53 -0700 Message-Id: <1495856035-6622-3-git-send-email-john.stultz@linaro.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1495856035-6622-1-git-send-email-john.stultz@linaro.org> References: <1495856035-6622-1-git-send-email-john.stultz@linaro.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Due to how the MONOTONIC_RAW accumulation logic was handled, there is the potential for a 1ns discontinuity when we do accumulations. This small discontinuity has for the most part gone un-noticed, but since ARM64 enabled CLOCK_MONOTONIC_RAW in their vDSO clock_gettime implementation, we've seen failures with the inconsistency-check test in kselftest. This patch addresses the issue by using the same sub-ns accumulation handling that CLOCK_MONOTONIC uses, which avoids the issue for in-kernel users. Since the ARM64 vDSO implementation has its own clock_gettime calculation logic, this patch reduces the frequency of errors, but failures are still seen. The ARM64 vDSO will need to be updated to include the sub-nanosecond xtime_nsec values in its calculation for this issue to be completely fixed. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Cc: Stephen Boyd Cc: Kevin Brodsky Cc: Will Deacon Cc: Daniel Mentz Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 4 ++-- kernel/time/timekeeping.c | 21 ++++++++++++--------- 2 files changed, 14 insertions(+), 11 deletions(-) diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 110f453..528cc86 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -58,7 +58,7 @@ struct tk_read_base { * interval. * @xtime_remainder: Shifted nano seconds left over when rounding * @cycle_interval - * @raw_interval: Raw nano seconds accumulated per NTP interval. + * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. * @ntp_error: Difference between accumulated time and NTP time in ntp * shifted nano seconds. * @ntp_error_shift: Shift conversion between clock shifted nano seconds and @@ -100,7 +100,7 @@ struct timekeeper { u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; - u32 raw_interval; + u64 raw_interval; /* The ntp_tick_length() value currently being used. * This cached copy ensures we consistently apply the tick * length for an entire tick, as ntp_tick_length may change diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index abc1968..35d3ba3 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -282,7 +282,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; - tk->raw_interval = (interval * clock->mult) >> clock->shift; + tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { @@ -1994,7 +1994,7 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; - u64 raw_nsecs; + u64 nsecps; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) @@ -2009,14 +2009,17 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ - raw_nsecs = (u64)tk->raw_interval << shift; - raw_nsecs += tk->raw_time.tv_nsec; - if (raw_nsecs >= NSEC_PER_SEC) { - u64 raw_secs = raw_nsecs; - raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); - tk->raw_time.tv_sec += raw_secs; + tk->tkr_raw.xtime_nsec += (u64)tk->raw_time.tv_nsec + << tk->tkr_raw.shift; + tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; + nsecps = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; + while (tk->tkr_raw.xtime_nsec >= nsecps) { + tk->tkr_raw.xtime_nsec -= nsecps; + tk->raw_time.tv_sec++; } - tk->raw_time.tv_nsec = raw_nsecs; + tk->raw_time.tv_nsec = tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift; + tk->tkr_raw.xtime_nsec -= (u64)tk->raw_time.tv_nsec + << tk->tkr_raw.shift; /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; -- 2.7.4