All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=801651

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=6e72c0310dc40c627c93d96f7323d792bdfdaf5d76693b8ad2d1807044a46246


Bot(s) for this bug's original alert(s):

android-nexus6

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8957577894094843392

=== Auto-CCing suspected CL author kolos@chromium.org ===

Hi kolos@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Maxim Kolosovskiy
  Commit : 6a83c2c4d82e4c1c196580539ac271ae2b592656
  Date   : Thu Jan 11 11:52:59 2018
  Subject: [Password Manager] Notify WebAutofillClient even if the page prevents all text-input events

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : smoothness.key_mobile_sites_smooth
  Metric       : first_gesture_scroll_update_latency/http___www.cnn.com_2012_10_03_politics_michelle-obama-debate_index.html
  Change       : 211.43% | 10.3656666667 -> 32.2816666667

Revision             Result                   N
chromium@528533      10.3657 +- 0.793605      6      good
chromium@528569      9.4995 +- 0.714895       6      good
chromium@528587      9.6635 +- 1.91225        6      good
chromium@528596      9.32883 +- 1.58944       6      good
chromium@528599      9.71217 +- 2.93791       6      good
chromium@528600      33.272 +- 4.96082        6      bad       <--
chromium@528601      31.5157 +- 3.83593       6      bad
chromium@528605      32.2817 +- 6.35064       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...www.cnn.com.2012.10.03.politics.michelle.obama.debate.index.html smoothness.key_mobile_sites_smooth

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8957577894094843392


For feedback, file a bug with component Speed>Bisection

tkent@: looks like this CL (https://chromium-review.googlesource.com/c/chromium/src/+/856996) is not efficient. Any ideas how we can fix this? Perhaps we should check IsProcessingUserGesture in HTMLInputElement and don't pass it further to the renderer. 

Let's revert the CL ASAP because we'll branch this week, then discuss in Issue 798716.

I've reverted the CL.

the culprit is reverted https://chromium-review.googlesource.com/c/chromium/src/+/867830 Sorry for no response.