On Wed, Aug 14, 2024 at 12:14 AM <jeffxu@xxxxxxxxxxxx> wrote: > > From: Jeff Xu <jeffxu@xxxxxxxxxxxx> > > mremap doesn't allow relocate, expand, shrink across VMA boundaries, > refactor the code to check src address range before doing anything on > the destination, i.e. destination won't be unmapped, if src address > failed the boundaries check. > > This also allows us to remove can_modify_mm from mremap.c, since > the src address must be single VMA, can_modify_vma is used. > > It is likely this will improve the performance on mremap, previously > the code does sealing check using can_modify_mm for the src address range, > and the new code removed the loop (used by can_modify_mm). > > In order to verify this patch doesn't regress on mremap, I added tests in > mseal_test, the test patch can be applied before mremap refactor patch or > checkin independently. > > Also this patch doesn't change mseal's existing schematic: if sealing fail, > user can expect the src/dst address isn't updated. So this patch can be > applied regardless if we decided to go with current out-of-loop approach > or in-loop approach currently in discussion. > > Regarding the perf test report by stress-ng [1] title: > 8be7258aad: stress-ng.pagemove.page_remaps_per_sec -4.4% regression > > The test is using below for testing: > stress-ng --timeout 60 --times --verify --metrics --no-rand-seed --pagemove 64 > > I can't repro this using ChromeOS, the pagemove test shows large value > of stddev and stderr, and can't reasonably refect the performance impact. > > For example: I write a c program [2] to run the above pagemove test 10 times > and calculate the stddev, stderr, for 3 commits: > > 1> before mseal feature is added: > Ops/sec: > Mean : 3564.40 > Std Dev : 2737.35 (76.80% of Mean) > Std Err : 865.63 (24.29% of Mean) > > 2> after mseal feature is added: > Ops/sec: > Mean : 2703.84 > Std Dev : 2085.13 (77.12% of Mean) > Std Err : 659.38 (24.39% of Mean) > > 3> after current patch (mremap refactor) > Ops/sec: > Mean : 3603.67 > Std Dev : 2422.22 (67.22% of Mean) > Std Err : 765.97 (21.26% of Mean) > > The result shows 21%-24% stderr, this means whatever perf improvment/impact > there might be won't be measured correctly by this test. > > This test machine has 32G memory, Intel(R) Celeron(R) 7305, 5 CPU. > And I reboot the machine before each test, and take the first 10 runs with > run_stress_ng 10 > > (I will run longer duration to see if test still shows large stdDev,StdErr) > I took more samples (100 run ), the stddev/stderr is smaller, however still not at a range that can reasonably measure the perf improvement here. The tests were taken using the same machine as (10 times run above) and exact the same steps: i.e. change to certain kernel commit, reboot test device, take the first test result. 1> Before mseal feature is added: Statistics: Ops/sec: Mean : 1733.26 Std Dev : 842.13 (48.59% of Mean) Std Err : 84.21 (4.86% of Mean) 2> After mseal feature is added Statistics: Ops/sec: Mean : 1701.53 Std Dev : 1017.29 (59.79% of Mean) Std Err : 101.73 (5.98% of Mean) 3> After mremap refactor (this patch) Statistics: Ops/sec: Mean : 1097.04 Std Dev : 860.67 (78.45% of Mean) Std Err : 86.07 (7.85% of Mean) Summary: even when the stderr is down to 4%-%8 percentage range, the stddev is still too big. Hence, there are other unknown, random variables that impact this test. -Jeff > [1] https://lore.kernel.org/lkml/202408041602.caa0372-oliver.sang@xxxxxxxxx/ > [2] https://github.com/peaktocreek/mmperf/blob/main/run_stress_ng.c > > > Jeff Xu (2): > mseal:selftest mremap across VMA boundaries. > mseal: refactor mremap to remove can_modify_mm > > mm/internal.h | 24 ++ > mm/mremap.c | 77 +++---- > mm/mseal.c | 17 -- > tools/testing/selftests/mm/mseal_test.c | 293 +++++++++++++++++++++++- > 4 files changed, 353 insertions(+), 58 deletions(-) > > -- > 2.46.0.76.ge559c4bf1a-goog >
