August 2023 - Linux-stable-mirror

stable-rc/linux-6.1.y baseline: 125 runs, 12 regressions (v6.1.48-5-g1d91878df63ce)

by kernelci.org bot

stable-rc/linux-6.1.y baseline: 125 runs, 12 regressions (v6.1.48-5-g1d91878df63ce) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ acer-chromebox-cxi4-puff | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 asus-C436FA-Flip-hatch | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 asus-CM1400CXA-dalboz | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 asus-cx9400-volteer | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 at91-sama5d4_xplained | arm | lab-baylibre | gcc-10 | multi_v7_defconfig | 1 beagle-xm | arm | lab-baylibre | gcc-10 | omap2plus_defconfig | 1 hp-x360-12b-c...4020-octopus | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 hp-x360-14a-cb0001xx-zork | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 lenovo-TPad-C13-Yoga-zork | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 r8a77960-ulcb | arm64 | lab-collabora | gcc-10 | defconfig | 1 r8a779m1-ulcb | arm64 | lab-collabora | gcc-10 | defconfig | 1 sun50i-h6-pine-h64 | arm64 | lab-collabora | gcc-10 | defconfig | 1 Details: https://kernelci.org/test/job/stable-rc/branch/linux-6.1.y/kernel/v6.1.48-5… Test: baseline Tree: stable-rc Branch: linux-6.1.y Describe: v6.1.48-5-g1d91878df63ce URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git SHA: 1d91878df63ceab6316c7c84876abc7eec08a2e4 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ acer-chromebox-cxi4-puff | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea385685a4696ea6286dec Results: 0 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.login: https://kernelci.org/test/case/id/64ea385685a4696ea6286ded new failure (last pass: v6.1.48) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ asus-C436FA-Flip-hatch | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea383ed4fbf3babb286dca Results: 6 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea383ed4fbf3babb286dcf failing since 149 days (last pass: v6.1.21, first fail: v6.1.22) 2023-08-26T17:36:46.161240 <8>[ 10.136584] <LAVA_SIGNAL_ENDRUN 0_dmesg 11364102_1.4.2.3.1> 2023-08-26T17:36:46.164210 + set +x 2023-08-26T17:36:46.268617 / # # 2023-08-26T17:36:46.369317 export SHELL=/bin/sh 2023-08-26T17:36:46.369531 # 2023-08-26T17:36:46.470061 / # export SHELL=/bin/sh. /lava-11364102/environment 2023-08-26T17:36:46.470240 2023-08-26T17:36:46.570779 / # . /lava-11364102/environment/lava-11364102/bin/lava-test-runner /lava-11364102/1 2023-08-26T17:36:46.571082 2023-08-26T17:36:46.577247 / # /lava-11364102/bin/lava-test-runner /lava-11364102/1 ... (12 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ asus-CM1400CXA-dalboz | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea3837fe654454bf286d9f Results: 6 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea3837fe654454bf286da4 failing since 149 days (last pass: v6.1.21, first fail: v6.1.22) 2023-08-26T17:36:37.678480 + <8>[ 11.143092] <LAVA_SIGNAL_ENDRUN 0_dmesg 11364085_1.4.2.3.1> 2023-08-26T17:36:37.678980 set +x 2023-08-26T17:36:37.784838 / # # 2023-08-26T17:36:37.887080 export SHELL=/bin/sh 2023-08-26T17:36:37.887799 # 2023-08-26T17:36:37.989180 / # export SHELL=/bin/sh. /lava-11364085/environment 2023-08-26T17:36:37.989931 2023-08-26T17:36:38.091393 / # . /lava-11364085/environment/lava-11364085/bin/lava-test-runner /lava-11364085/1 2023-08-26T17:36:38.092548 2023-08-26T17:36:38.097560 / # /lava-11364085/bin/lava-test-runner /lava-11364085/1 ... (12 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ asus-cx9400-volteer | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea3839fe654454bf286dac Results: 6 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea3839fe654454bf286db1 failing since 149 days (last pass: v6.1.21, first fail: v6.1.22) 2023-08-26T17:36:41.091934 <8>[ 7.668904] <LAVA_SIGNAL_ENDRUN 0_dmesg 11364073_1.4.2.3.1> 2023-08-26T17:36:41.095329 + set +x 2023-08-26T17:36:41.201184 2023-08-26T17:36:41.302972 / # #export SHELL=/bin/sh 2023-08-26T17:36:41.303770 2023-08-26T17:36:41.405200 / # export SHELL=/bin/sh. /lava-11364073/environment 2023-08-26T17:36:41.405927 2023-08-26T17:36:41.507508 / # . /lava-11364073/environment/lava-11364073/bin/lava-test-runner /lava-11364073/1 2023-08-26T17:36:41.508867 2023-08-26T17:36:41.514446 / # /lava-11364073/bin/lava-test-runner /lava-11364073/1 ... (12 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ at91-sama5d4_xplained | arm | lab-baylibre | gcc-10 | multi_v7_defconfig | 1 Details: https://kernelci.org/test/plan/id/64ea37ebd8ad26ff6e286d6d Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig Compiler: gcc-10 (arm-linux-gnueabihf-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.login: https://kernelci.org/test/case/id/64ea37ebd8ad26ff6e286d6e new failure (last pass: v6.1.46-195-g5165f4e9738c4) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ beagle-xm | arm | lab-baylibre | gcc-10 | omap2plus_defconfig | 1 Details: https://kernelci.org/test/plan/id/64ea37e94b884e302b286d77 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: omap2plus_defconfig Compiler: gcc-10 (arm-linux-gnueabihf-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.login: https://kernelci.org/test/case/id/64ea37e94b884e302b286d78 failing since 79 days (last pass: v6.1.31-40-g7d0a9678d276, first fail: v6.1.31-266-g8f4f686e321c) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ hp-x360-12b-c...4020-octopus | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea38224b884e302b286d82 Results: 6 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea38224b884e302b286d87 failing since 149 days (last pass: v6.1.21, first fail: v6.1.22) 2023-08-26T17:36:37.374229 + set +x 2023-08-26T17:36:37.380883 <8>[ 10.435070] <LAVA_SIGNAL_ENDRUN 0_dmesg 11364105_1.4.2.3.1> 2023-08-26T17:36:37.485137 / # # 2023-08-26T17:36:37.585730 export SHELL=/bin/sh 2023-08-26T17:36:37.585919 # 2023-08-26T17:36:37.686430 / # export SHELL=/bin/sh. /lava-11364105/environment 2023-08-26T17:36:37.686616 2023-08-26T17:36:37.787142 / # . /lava-11364105/environment/lava-11364105/bin/lava-test-runner /lava-11364105/1 2023-08-26T17:36:37.787465 2023-08-26T17:36:37.792444 / # /lava-11364105/bin/lava-test-runner /lava-11364105/1 ... (12 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ hp-x360-14a-cb0001xx-zork | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea38394b047d9d31286d6e Results: 6 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea38394b047d9d31286d73 failing since 149 days (last pass: v6.1.21, first fail: v6.1.22) 2023-08-26T17:36:39.520735 + set<8>[ 10.969254] <LAVA_SIGNAL_ENDRUN 0_dmesg 11364072_1.4.2.3.1> 2023-08-26T17:36:39.521314 +x 2023-08-26T17:36:39.629480 / # # 2023-08-26T17:36:39.731970 export SHELL=/bin/sh 2023-08-26T17:36:39.732376 # 2023-08-26T17:36:39.833708 / # export SHELL=/bin/sh. /lava-11364072/environment 2023-08-26T17:36:39.834553 2023-08-26T17:36:39.936337 / # . /lava-11364072/environment/lava-11364072/bin/lava-test-runner /lava-11364072/1 2023-08-26T17:36:39.937790 2023-08-26T17:36:39.942549 / # /lava-11364072/bin/lava-test-runner /lava-11364072/1 ... (12 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ lenovo-TPad-C13-Yoga-zork | x86_64 | lab-collabora | gcc-10 | x86_64_defcon...6-chromebook | 1 Details: https://kernelci.org/test/plan/id/64ea38273134160a22286e9c Results: 6 PASS, 1 FAIL, 0 SKIP Full config: x86_64_defconfig+x86-chromebook Compiler: gcc-10 (gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea38273134160a22286ea1 failing since 149 days (last pass: v6.1.21, first fail: v6.1.22) 2023-08-26T17:36:24.446817 <8>[ 12.125048] <LAVA_SIGNAL_ENDRUN 0_dmesg 11364104_1.4.2.3.1> 2023-08-26T17:36:24.550279 / # # 2023-08-26T17:36:24.650872 export SHELL=/bin/sh 2023-08-26T17:36:24.651086 # 2023-08-26T17:36:24.751588 / # export SHELL=/bin/sh. /lava-11364104/environment 2023-08-26T17:36:24.751823 2023-08-26T17:36:24.852386 / # . /lava-11364104/environment/lava-11364104/bin/lava-test-runner /lava-11364104/1 2023-08-26T17:36:24.852662 2023-08-26T17:36:24.857343 / # /lava-11364104/bin/lava-test-runner /lava-11364104/1 2023-08-26T17:36:24.863729 + export 'TESTRUN_ID=1_bootrr' ... (11 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ r8a77960-ulcb | arm64 | lab-collabora | gcc-10 | defconfig | 1 Details: https://kernelci.org/test/plan/id/64ea36a8c4d100f151286d6c Results: 4 PASS, 2 FAIL, 1 SKIP Full config: defconfig Compiler: gcc-10 (aarch64-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea36a8c4d100f151286d71 failing since 39 days (last pass: v6.1.38-393-gb6386e7314b4, first fail: v6.1.38-590-gce7ec1011187) 2023-08-26T17:31:39.401473 / # # 2023-08-26T17:31:39.503302 export SHELL=/bin/sh 2023-08-26T17:31:39.504045 # 2023-08-26T17:31:39.605333 / # export SHELL=/bin/sh. /lava-11363983/environment 2023-08-26T17:31:39.606249 2023-08-26T17:31:39.707721 / # . /lava-11363983/environment/lava-11363983/bin/lava-test-runner /lava-11363983/1 2023-08-26T17:31:39.708663 2023-08-26T17:31:39.709831 / # /lava-11363983/bin/lava-test-runner /lava-11363983/1 2023-08-26T17:31:39.773574 + export 'TESTRUN_ID=1_bootrr' 2023-08-26T17:31:39.774103 + cd /lav<8>[ 19.091163] <LAVA_SIGNAL_STARTRUN 1_bootrr 11363983_1.5.2.4.5> ... (28 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ r8a779m1-ulcb | arm64 | lab-collabora | gcc-10 | defconfig | 1 Details: https://kernelci.org/test/plan/id/64ea36bff9d092fe15286da3 Results: 5 PASS, 1 FAIL, 1 SKIP Full config: defconfig Compiler: gcc-10 (aarch64-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea36bff9d092fe15286da8 failing since 39 days (last pass: v6.1.38-393-gb6386e7314b4, first fail: v6.1.38-590-gce7ec1011187) 2023-08-26T17:30:35.595350 / # # 2023-08-26T17:30:36.674744 export SHELL=/bin/sh 2023-08-26T17:30:36.676493 # 2023-08-26T17:30:38.165687 / # export SHELL=/bin/sh. /lava-11363977/environment 2023-08-26T17:30:38.167539 2023-08-26T17:30:40.890447 / # . /lava-11363977/environment/lava-11363977/bin/lava-test-runner /lava-11363977/1 2023-08-26T17:30:40.891809 2023-08-26T17:30:40.901498 / # /lava-11363977/bin/lava-test-runner /lava-11363977/1 2023-08-26T17:30:40.961007 + export 'TESTRUN_ID=1_bootrr' 2023-08-26T17:30:40.961282 + cd /lava-113639<8>[ 28.466973] <LAVA_SIGNAL_STARTRUN 1_bootrr 11363977_1.5.2.4.5> ... (39 line(s) more) platform | arch | lab | compiler | defconfig | regressions -----------------------------+--------+---------------+----------+------------------------------+------------ sun50i-h6-pine-h64 | arm64 | lab-collabora | gcc-10 | defconfig | 1 Details: https://kernelci.org/test/plan/id/64ea36bef9d092fe15286d8d Results: 5 PASS, 1 FAIL, 1 SKIP Full config: defconfig Compiler: gcc-10 (aarch64-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110) Plain log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… HTML log: https://storage.kernelci.org//stable-rc/linux-6.1.y/v6.1.48-5-g1d91878df63c… Rootfs: http://storage.kernelci.org/images/rootfs/buildroot/buildroot-baseline/2023… * baseline.bootrr.deferred-probe-empty: https://kernelci.org/test/case/id/64ea36bef9d092fe15286d92 failing since 39 days (last pass: v6.1.38-393-gb6386e7314b4, first fail: v6.1.38-590-gce7ec1011187) 2023-08-26T17:31:53.898674 / # # 2023-08-26T17:31:53.999406 export SHELL=/bin/sh 2023-08-26T17:31:53.999685 # 2023-08-26T17:31:54.100446 / # export SHELL=/bin/sh. /lava-11363978/environment 2023-08-26T17:31:54.101127 2023-08-26T17:31:54.202546 / # . /lava-11363978/environment/lava-11363978/bin/lava-test-runner /lava-11363978/1 2023-08-26T17:31:54.203733 2023-08-26T17:31:54.212365 / # /lava-11363978/bin/lava-test-runner /lava-11363978/1 2023-08-26T17:31:54.284526 + export 'TESTRUN_ID=1_bootrr' 2023-08-26T17:31:54.285086 + cd /lava-1136397<8>[ 18.705015] <LAVA_SIGNAL_STARTRUN 1_bootrr 11363978_1.5.2.4.5> ... (11 line(s) more)

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] mm: enable page walking API to lock vmas during the walk" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 49b0638502da097c15d46cd4e871dbaa022caf7c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082625-monotone-traps-6498@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 49b0638502da ("mm: enable page walking API to lock vmas during the walk") 6c21e066f925 ("mm/mempolicy: Take VMA lock before replacing policy") 24139c07f413 ("mm/ksm: unmerge and clear VM_MERGEABLE when setting PR_SET_MEMORY_MERGE=0") d7597f59d1d3 ("mm: add new api to enable ksm per process") ddc65971bb67 ("prctl: add PR_GET_AUXV to copy auxv to userspace") b507808ebce2 ("mm: implement memory-deny-write-execute as a prctl") d7c0e68dab98 ("mm/ksm: convert break_ksm() to use walk_page_range_vma()") e07cda5f232f ("mm/pagewalk: add walk_page_range_vma()") 58f595c66591 ("mm/ksm: simplify break_ksm() to not rely on VM_FAULT_WRITE") c31783eeae7b ("mm/pagewalk: don't trigger test_walk() in walk_page_vma()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 49b0638502da097c15d46cd4e871dbaa022caf7c Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan <surenb(a)google.com> Date: Fri, 4 Aug 2023 08:27:19 -0700 Subject: [PATCH] mm: enable page walking API to lock vmas during the walk walk_page_range() and friends often operate under write-locked mmap_lock. With introduction of vma locks, the vmas have to be locked as well during such walks to prevent concurrent page faults in these areas. Add an additional member to mm_walk_ops to indicate locking requirements for the walk. The change ensures that page walks which prevent concurrent page faults by write-locking mmap_lock, operate correctly after introduction of per-vma locks. With per-vma locks page faults can be handled under vma lock without taking mmap_lock at all, so write locking mmap_lock would not stop them. The change ensures vmas are properly locked during such walks. A sample issue this solves is do_mbind() performing queue_pages_range() to queue pages for migration. Without this change a concurrent page can be faulted into the area and be left out of migration. Link: https://lkml.kernel.org/r/20230804152724.3090321-2-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Suggested-by: Linus Torvalds <torvalds(a)linuxfoundation.org> Suggested-by: Jann Horn <jannh(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Davidlohr Bueso <dave(a)stgolabs.net> Cc: Hugh Dickins <hughd(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Laurent Dufour <ldufour(a)linux.ibm.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Michel Lespinasse <michel(a)lespinasse.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index 0dc85556dec5..ec98e526167e 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -145,6 +145,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops subpage_walk_ops = { .pmd_entry = subpage_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ea3d61de065b..161d0b34c2cb 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -102,6 +102,7 @@ static const struct mm_walk_ops pageattr_ops = { .pmd_entry = pageattr_pmd_entry, .pte_entry = pageattr_pte_entry, .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, }; static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 9c8af31be970..906a7bfc2a78 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2514,6 +2514,7 @@ static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops thp_split_walk_ops = { .pmd_entry = thp_split_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static inline void thp_split_mm(struct mm_struct *mm) @@ -2565,6 +2566,7 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start, static const struct mm_walk_ops zap_zero_walk_ops = { .pmd_entry = __zap_zero_pages, + .walk_lock = PGWALK_WRLOCK, }; /* @@ -2655,6 +2657,7 @@ static const struct mm_walk_ops enable_skey_walk_ops = { .hugetlb_entry = __s390_enable_skey_hugetlb, .pte_entry = __s390_enable_skey_pte, .pmd_entry = __s390_enable_skey_pmd, + .walk_lock = PGWALK_WRLOCK, }; int s390_enable_skey(void) @@ -2692,6 +2695,7 @@ static int __s390_reset_cmma(pte_t *pte, unsigned long addr, static const struct mm_walk_ops reset_cmma_walk_ops = { .pte_entry = __s390_reset_cmma, + .walk_lock = PGWALK_WRLOCK, }; void s390_reset_cmma(struct mm_struct *mm) @@ -2728,6 +2732,7 @@ static int s390_gather_pages(pte_t *ptep, unsigned long addr, static const struct mm_walk_ops gather_pages_ops = { .pte_entry = s390_gather_pages, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fc744964816e..fafff1bd34cd 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -757,12 +757,14 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, static const struct mm_walk_ops smaps_walk_ops = { .pmd_entry = smaps_pte_range, .hugetlb_entry = smaps_hugetlb_range, + .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops smaps_shmem_walk_ops = { .pmd_entry = smaps_pte_range, .hugetlb_entry = smaps_hugetlb_range, .pte_hole = smaps_pte_hole, + .walk_lock = PGWALK_RDLOCK, }; /* @@ -1244,6 +1246,7 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end, static const struct mm_walk_ops clear_refs_walk_ops = { .pmd_entry = clear_refs_pte_range, .test_walk = clear_refs_test_walk, + .walk_lock = PGWALK_WRLOCK, }; static ssize_t clear_refs_write(struct file *file, const char __user *buf, @@ -1621,6 +1624,7 @@ static const struct mm_walk_ops pagemap_ops = { .pmd_entry = pagemap_pmd_range, .pte_hole = pagemap_pte_hole, .hugetlb_entry = pagemap_hugetlb_range, + .walk_lock = PGWALK_RDLOCK, }; /* @@ -1934,6 +1938,7 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, static const struct mm_walk_ops show_numa_ops = { .hugetlb_entry = gather_hugetlb_stats, .pmd_entry = gather_pte_stats, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 27a6df448ee5..27cd1e59ccf7 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -6,6 +6,16 @@ struct mm_walk; +/* Locking requirement during a page walk. */ +enum page_walk_lock { + /* mmap_lock should be locked for read to stabilize the vma tree */ + PGWALK_RDLOCK = 0, + /* vma will be write-locked during the walk */ + PGWALK_WRLOCK = 1, + /* vma is expected to be already write-locked during the walk */ + PGWALK_WRLOCK_VERIFY = 2, +}; + /** * struct mm_walk_ops - callbacks for walk_page_range * @pgd_entry: if set, called for each non-empty PGD (top-level) entry @@ -66,6 +76,7 @@ struct mm_walk_ops { int (*pre_vma)(unsigned long start, unsigned long end, struct mm_walk *walk); void (*post_vma)(struct mm_walk *walk); + enum page_walk_lock walk_lock; }; /* diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 2fcc9731528a..e0e59d420fca 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -386,6 +386,7 @@ static int damon_mkold_hugetlb_entry(pte_t *pte, unsigned long hmask, static const struct mm_walk_ops damon_mkold_ops = { .pmd_entry = damon_mkold_pmd_entry, .hugetlb_entry = damon_mkold_hugetlb_entry, + .walk_lock = PGWALK_RDLOCK, }; static void damon_va_mkold(struct mm_struct *mm, unsigned long addr) @@ -525,6 +526,7 @@ static int damon_young_hugetlb_entry(pte_t *pte, unsigned long hmask, static const struct mm_walk_ops damon_young_ops = { .pmd_entry = damon_young_pmd_entry, .hugetlb_entry = damon_young_hugetlb_entry, + .walk_lock = PGWALK_RDLOCK, }; static bool damon_va_young(struct mm_struct *mm, unsigned long addr, diff --git a/mm/hmm.c b/mm/hmm.c index 855e25e59d8f..277ddcab4947 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -562,6 +562,7 @@ static const struct mm_walk_ops hmm_walk_ops = { .pte_hole = hmm_vma_walk_hole, .hugetlb_entry = hmm_vma_walk_hugetlb_entry, .test_walk = hmm_vma_walk_test, + .walk_lock = PGWALK_RDLOCK, }; /** diff --git a/mm/ksm.c b/mm/ksm.c index d20d7662419b..d7b5b95e936e 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -455,6 +455,12 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex static const struct mm_walk_ops break_ksm_ops = { .pmd_entry = break_ksm_pmd_entry, + .walk_lock = PGWALK_RDLOCK, +}; + +static const struct mm_walk_ops break_ksm_lock_vma_ops = { + .pmd_entry = break_ksm_pmd_entry, + .walk_lock = PGWALK_WRLOCK, }; /* @@ -470,16 +476,17 @@ static const struct mm_walk_ops break_ksm_ops = { * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ -static int break_ksm(struct vm_area_struct *vma, unsigned long addr) +static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma) { vm_fault_t ret = 0; + const struct mm_walk_ops *ops = lock_vma ? + &break_ksm_lock_vma_ops : &break_ksm_ops; do { int ksm_page; cond_resched(); - ksm_page = walk_page_range_vma(vma, addr, addr + 1, - &break_ksm_ops, NULL); + ksm_page = walk_page_range_vma(vma, addr, addr + 1, ops, NULL); if (WARN_ON_ONCE(ksm_page < 0)) return ksm_page; if (!ksm_page) @@ -565,7 +572,7 @@ static void break_cow(struct ksm_rmap_item *rmap_item) mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (vma) - break_ksm(vma, addr); + break_ksm(vma, addr, false); mmap_read_unlock(mm); } @@ -871,7 +878,7 @@ static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list) * in cmp_and_merge_page on one of the rmap_items we would be removing. */ static int unmerge_ksm_pages(struct vm_area_struct *vma, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, bool lock_vma) { unsigned long addr; int err = 0; @@ -882,7 +889,7 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, if (signal_pending(current)) err = -ERESTARTSYS; else - err = break_ksm(vma, addr); + err = break_ksm(vma, addr, lock_vma); } return err; } @@ -1029,7 +1036,7 @@ static int unmerge_and_remove_all_rmap_items(void) if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) continue; err = unmerge_ksm_pages(vma, - vma->vm_start, vma->vm_end); + vma->vm_start, vma->vm_end, false); if (err) goto error; } @@ -2530,7 +2537,7 @@ static int __ksm_del_vma(struct vm_area_struct *vma) return 0; if (vma->anon_vma) { - err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end); + err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true); if (err) return err; } @@ -2668,7 +2675,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; /* just ignore the advice */ if (vma->anon_vma) { - err = unmerge_ksm_pages(vma, start, end); + err = unmerge_ksm_pages(vma, start, end, true); if (err) return err; } diff --git a/mm/madvise.c b/mm/madvise.c index 886f06066622..bfe0e06427bd 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -233,6 +233,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, static const struct mm_walk_ops swapin_walk_ops = { .pmd_entry = swapin_walk_pmd_entry, + .walk_lock = PGWALK_RDLOCK, }; static void shmem_swapin_range(struct vm_area_struct *vma, @@ -534,6 +535,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, static const struct mm_walk_ops cold_walk_ops = { .pmd_entry = madvise_cold_or_pageout_pte_range, + .walk_lock = PGWALK_RDLOCK, }; static void madvise_cold_page_range(struct mmu_gather *tlb, @@ -757,6 +759,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops madvise_free_walk_ops = { .pmd_entry = madvise_free_pte_range, + .walk_lock = PGWALK_RDLOCK, }; static int madvise_free_single_vma(struct vm_area_struct *vma, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e8ca4bdcb03c..315fd5f45e3c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6024,6 +6024,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, static const struct mm_walk_ops precharge_walk_ops = { .pmd_entry = mem_cgroup_count_precharge_pte_range, + .walk_lock = PGWALK_RDLOCK, }; static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) @@ -6303,6 +6304,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, static const struct mm_walk_ops charge_walk_ops = { .pmd_entry = mem_cgroup_move_charge_pte_range, + .walk_lock = PGWALK_RDLOCK, }; static void mem_cgroup_move_charge(void) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9a285038d765..139b31fdb678 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -831,6 +831,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, static const struct mm_walk_ops hwp_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/mm/mempolicy.c b/mm/mempolicy.c index c53f8beeb507..ec2eaceffd74 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -718,6 +718,14 @@ static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, + .walk_lock = PGWALK_RDLOCK, +}; + +static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { + .hugetlb_entry = queue_folios_hugetlb, + .pmd_entry = queue_folios_pte_range, + .test_walk = queue_pages_test_walk, + .walk_lock = PGWALK_WRLOCK, }; /* @@ -738,7 +746,7 @@ static const struct mm_walk_ops queue_pages_walk_ops = { static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, - struct list_head *pagelist) + struct list_head *pagelist, bool lock_vma) { int err; struct queue_pages qp = { @@ -749,8 +757,10 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .end = end, .first = NULL, }; + const struct mm_walk_ops *ops = lock_vma ? + &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; - err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); + err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ @@ -1078,7 +1088,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, vma = find_vma(mm, 0); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, - flags | MPOL_MF_DISCONTIG_OK, &pagelist); + flags | MPOL_MF_DISCONTIG_OK, &pagelist, false); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, @@ -1321,12 +1331,8 @@ static long do_mbind(unsigned long start, unsigned long len, * Lock the VMAs before scanning for pages to migrate, to ensure we don't * miss a concurrently inserted page. */ - vma_iter_init(&vmi, mm, start); - for_each_vma_range(vmi, vma, end) - vma_start_write(vma); - ret = queue_pages_range(mm, start, end, nmask, - flags | MPOL_MF_INVERT, &pagelist); + flags | MPOL_MF_INVERT, &pagelist, true); if (ret < 0) { err = ret; diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 8365158460ed..d5f492356e3e 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -279,6 +279,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, static const struct mm_walk_ops migrate_vma_walk_ops = { .pmd_entry = migrate_vma_collect_pmd, .pte_hole = migrate_vma_collect_hole, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/mm/mincore.c b/mm/mincore.c index b7f7a516b26c..dad3622cc963 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -176,6 +176,7 @@ static const struct mm_walk_ops mincore_walk_ops = { .pmd_entry = mincore_pte_range, .pte_hole = mincore_unmapped_range, .hugetlb_entry = mincore_hugetlb, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/mm/mlock.c b/mm/mlock.c index 0a0c996c5c21..479e09d0994c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -371,6 +371,7 @@ static void mlock_vma_pages_range(struct vm_area_struct *vma, { static const struct mm_walk_ops mlock_walk_ops = { .pmd_entry = mlock_pte_range, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; /* diff --git a/mm/mprotect.c b/mm/mprotect.c index 6f658d483704..3aef1340533a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -568,6 +568,7 @@ static const struct mm_walk_ops prot_none_walk_ops = { .pte_entry = prot_none_pte_entry, .hugetlb_entry = prot_none_hugetlb_entry, .test_walk = prot_none_test, + .walk_lock = PGWALK_WRLOCK, }; int diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 2022333805d3..9b2d23fbf4d3 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -400,6 +400,33 @@ static int __walk_page_range(unsigned long start, unsigned long end, return err; } +static inline void process_mm_walk_lock(struct mm_struct *mm, + enum page_walk_lock walk_lock) +{ + if (walk_lock == PGWALK_RDLOCK) + mmap_assert_locked(mm); + else + mmap_assert_write_locked(mm); +} + +static inline void process_vma_walk_lock(struct vm_area_struct *vma, + enum page_walk_lock walk_lock) +{ +#ifdef CONFIG_PER_VMA_LOCK + switch (walk_lock) { + case PGWALK_WRLOCK: + vma_start_write(vma); + break; + case PGWALK_WRLOCK_VERIFY: + vma_assert_write_locked(vma); + break; + case PGWALK_RDLOCK: + /* PGWALK_RDLOCK is handled by process_mm_walk_lock */ + break; + } +#endif +} + /** * walk_page_range - walk page table with caller specific callbacks * @mm: mm_struct representing the target process of page table walk @@ -459,7 +486,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, if (!walk.mm) return -EINVAL; - mmap_assert_locked(walk.mm); + process_mm_walk_lock(walk.mm, ops->walk_lock); vma = find_vma(walk.mm, start); do { @@ -474,6 +501,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, if (ops->pte_hole) err = ops->pte_hole(start, next, -1, &walk); } else { /* inside vma */ + process_vma_walk_lock(vma, ops->walk_lock); walk.vma = vma; next = min(end, vma->vm_end); vma = find_vma(mm, vma->vm_end); @@ -549,7 +577,8 @@ int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, if (start < vma->vm_start || end > vma->vm_end) return -EINVAL; - mmap_assert_locked(walk.mm); + process_mm_walk_lock(walk.mm, ops->walk_lock); + process_vma_walk_lock(vma, ops->walk_lock); return __walk_page_range(start, end, &walk); } @@ -566,7 +595,8 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, if (!walk.mm) return -EINVAL; - mmap_assert_locked(walk.mm); + process_mm_walk_lock(walk.mm, ops->walk_lock); + process_vma_walk_lock(vma, ops->walk_lock); return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 1080209a568b..3555927df9b5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4284,6 +4284,7 @@ static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_ static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, + .walk_lock = PGWALK_RDLOCK, }; int err;

1 year, 9 months

3
2
0 0

FAILED: patch "[PATCH] madvise:madvise_cold_or_pageout_pte_range(): don't use" failed to apply to 6.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.4.y git checkout FETCH_HEAD git cherry-pick -x 2f406263e3e954aa24c1248edcfa9be0c1bb30fa # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082620-overact-feisty-c309@gregkh' --subject-prefix 'PATCH 6.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2f406263e3e954aa24c1248edcfa9be0c1bb30fa Mon Sep 17 00:00:00 2001 From: Yin Fengwei <fengwei.yin(a)intel.com> Date: Tue, 8 Aug 2023 10:09:15 +0800 Subject: [PATCH] madvise:madvise_cold_or_pageout_pte_range(): don't use mapcount() against large folio for sharing check Patch series "don't use mapcount() to check large folio sharing", v2. In madvise_cold_or_pageout_pte_range() and madvise_free_pte_range(), folio_mapcount() is used to check whether the folio is shared. But it's not correct as folio_mapcount() returns total mapcount of large folio. Use folio_estimated_sharers() here as the estimated number is enough. This patchset will fix the cases: User space application call madvise() with MADV_FREE, MADV_COLD and MADV_PAGEOUT for specific address range. There are THP mapped to the range. Without the patchset, the THP is skipped. With the patch, the THP will be split and handled accordingly. David reported the cow self test skip some cases because of MADV_PAGEOUT skip THP: https://lore.kernel.org/linux-mm/9e92e42d-488f-47db-ac9d-75b24cd0d037@intel… and I confirmed this patchset make it work again. This patch (of 3): Commit 07e8c82b5eff ("madvise: convert madvise_cold_or_pageout_pte_range() to use folios") replaced the page_mapcount() with folio_mapcount() to check whether the folio is shared by other mapping. It's not correct for large folio. folio_mapcount() returns the total mapcount of large folio which is not suitable to detect whether the folio is shared. Use folio_estimated_sharers() which returns a estimated number of shares. That means it's not 100% correct. It should be OK for madvise case here. User-visible effects is that the THP is skipped when user call madvise. But the correct behavior is THP should be split and processed then. NOTE: this change is a temporary fix to reduce the user-visible effects before the long term fix from David is ready. Link: https://lkml.kernel.org/r/20230808020917.2230692-1-fengwei.yin@intel.com Link: https://lkml.kernel.org/r/20230808020917.2230692-2-fengwei.yin@intel.com Fixes: 07e8c82b5eff ("madvise: convert madvise_cold_or_pageout_pte_range() to use folios") Signed-off-by: Yin Fengwei <fengwei.yin(a)intel.com> Reviewed-by: Yu Zhao <yuzhao(a)google.com> Reviewed-by: Ryan Roberts <ryan.roberts(a)arm.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Vishal Moola (Oracle) <vishal.moola(a)gmail.com> Cc: Yang Shi <shy828301(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index bfe0e06427bd..46802b4cf65a 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -384,7 +384,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, folio = pfn_folio(pmd_pfn(orig_pmd)); /* Do not interfere with other mappings of this folio */ - if (folio_mapcount(folio) != 1) + if (folio_estimated_sharers(folio) != 1) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) @@ -458,7 +458,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, if (folio_test_large(folio)) { int err; - if (folio_mapcount(folio) != 1) + if (folio_estimated_sharers(folio) != 1) break; if (pageout_anon_only_filter && !folio_test_anon(folio)) break;

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] maple_tree: disable mas_wr_append() when other readers are" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x cfeb6ae8bcb96ccf674724f223661bbcef7b0d0b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082644-dimmed-purse-07c2@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: cfeb6ae8bcb9 ("maple_tree: disable mas_wr_append() when other readers are possible") 2e1da329b424 ("maple_tree: add comments and some minor cleanups to mas_wr_append()") c6fc9e4a5c50 ("maple_tree: add mas_wr_new_end() to calculate new_end accurately") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From cfeb6ae8bcb96ccf674724f223661bbcef7b0d0b Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" <Liam.Howlett(a)oracle.com> Date: Fri, 18 Aug 2023 20:43:55 -0400 Subject: [PATCH] maple_tree: disable mas_wr_append() when other readers are possible The current implementation of append may cause duplicate data and/or incorrect ranges to be returned to a reader during an update. Although this has not been reported or seen, disable the append write operation while the tree is in rcu mode out of an abundance of caution. During the analysis of the mas_next_slot() the following was artificially created by separating the writer and reader code: Writer: reader: mas_wr_append set end pivot updates end metata Detects write to last slot last slot write is to start of slot store current contents in slot overwrite old end pivot mas_next_slot(): read end metadata read old end pivot return with incorrect range store new value Alternatively: Writer: reader: mas_wr_append set end pivot updates end metata Detects write to last slot last lost write to end of slot store value mas_next_slot(): read end metadata read old end pivot read new end pivot return with incorrect range set old end pivot There may be other accesses that are not safe since we are now updating both metadata and pointers, so disabling append if there could be rcu readers is the safest action. Link: https://lkml.kernel.org/r/20230819004356.1454718-2-Liam.Howlett@oracle.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 4dd73cf936a6..f723024e1426 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4265,6 +4265,10 @@ static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) * mas_wr_append: Attempt to append * @wr_mas: the maple write state * + * This is currently unsafe in rcu mode since the end of the node may be cached + * by readers while the node contents may be updated which could result in + * inaccurate information. + * * Return: True if appended, false otherwise */ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) @@ -4274,6 +4278,9 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) struct ma_state *mas = wr_mas->mas; unsigned char node_pivots = mt_pivots[wr_mas->type]; + if (mt_in_rcu(mas->tree)) + return false; + if (mas->offset != wr_mas->node_end) return false;

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] maple_tree: disable mas_wr_append() when other readers are" failed to apply to 6.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.4.y git checkout FETCH_HEAD git cherry-pick -x cfeb6ae8bcb96ccf674724f223661bbcef7b0d0b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082642-energetic-playpen-0bea@gregkh' --subject-prefix 'PATCH 6.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From cfeb6ae8bcb96ccf674724f223661bbcef7b0d0b Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" <Liam.Howlett(a)oracle.com> Date: Fri, 18 Aug 2023 20:43:55 -0400 Subject: [PATCH] maple_tree: disable mas_wr_append() when other readers are possible The current implementation of append may cause duplicate data and/or incorrect ranges to be returned to a reader during an update. Although this has not been reported or seen, disable the append write operation while the tree is in rcu mode out of an abundance of caution. During the analysis of the mas_next_slot() the following was artificially created by separating the writer and reader code: Writer: reader: mas_wr_append set end pivot updates end metata Detects write to last slot last slot write is to start of slot store current contents in slot overwrite old end pivot mas_next_slot(): read end metadata read old end pivot return with incorrect range store new value Alternatively: Writer: reader: mas_wr_append set end pivot updates end metata Detects write to last slot last lost write to end of slot store value mas_next_slot(): read end metadata read old end pivot read new end pivot return with incorrect range set old end pivot There may be other accesses that are not safe since we are now updating both metadata and pointers, so disabling append if there could be rcu readers is the safest action. Link: https://lkml.kernel.org/r/20230819004356.1454718-2-Liam.Howlett@oracle.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 4dd73cf936a6..f723024e1426 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4265,6 +4265,10 @@ static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) * mas_wr_append: Attempt to append * @wr_mas: the maple write state * + * This is currently unsafe in rcu mode since the end of the node may be cached + * by readers while the node contents may be updated which could result in + * inaccurate information. + * * Return: True if appended, false otherwise */ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) @@ -4274,6 +4278,9 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas) struct ma_state *mas = wr_mas->mas; unsigned char node_pivots = mt_pivots[wr_mas->type]; + if (mt_in_rcu(mas->tree)) + return false; + if (mas->offset != wr_mas->node_end) return false;

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] batman-adv: Hold rtnl lock during MTU update via netlink" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y git checkout FETCH_HEAD git cherry-pick -x 987aae75fc1041072941ffb622b45ce2359a99b9 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082645-unicycle-diaphragm-272c@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^.. Possible dependencies: 987aae75fc10 ("batman-adv: Hold rtnl lock during MTU update via netlink") 3e15b06eb7e4 ("batman-adv: Add fragmentation mesh genl configuration") a1c8de803296 ("batman-adv: Add distributed_arp_table mesh genl configuration") 43ff6105a527 ("batman-adv: Add bridge_loop_avoidance mesh genl configuration") d7e52506b680 ("batman-adv: Add bonding mesh genl configuration") e43d16b87dc2 ("batman-adv: Add ap_isolation mesh/vlan genl configuration") 9ab4cee5ced9 ("batman-adv: Add aggregated_ogms mesh genl configuration") 49e7e37cd981 ("batman-adv: Prepare framework for vlan genl config") 5c55a40fa801 ("batman-adv: Prepare framework for hardif genl config") 600405135360 ("batman-adv: Prepare framework for mesh genl config") c4a7a8d9bb8f ("batman-adv: Move common genl doit code pre/post hooks") fb69be697916 ("batman-adv: Add inconsistent hardif netlink dump detection") 53dd9a68ba68 ("batman-adv: add multicast flags netlink support") 41aeefcc38a2 ("batman-adv: add DAT cache netlink support") fec149f5d323 ("batman-adv: Convert packet.h to uapi header") 7e9a8c2ce7c5 ("batman-adv: Use parentheses in function kernel-doc") 7db7d9f369a4 ("batman-adv: Add SPDX license identifier above copyright header") 40b16b9be577 ("batman-adv: use inline kernel-doc for uapi constants") 706cc9f51d9a ("batman-adv: Add argument names for function ptr definitions") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 987aae75fc1041072941ffb622b45ce2359a99b9 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann <sven(a)narfation.org> Date: Mon, 21 Aug 2023 21:48:48 +0200 Subject: [PATCH] batman-adv: Hold rtnl lock during MTU update via netlink The automatic recalculation of the maximum allowed MTU is usually triggered by code sections which are already rtnl lock protected by callers outside of batman-adv. But when the fragmentation setting is changed via batman-adv's own batadv genl family, then the rtnl lock is not yet taken. But dev_set_mtu requires that the caller holds the rtnl lock because it uses netdevice notifiers. And this code will then fail the check for this lock: RTNL: assertion failed at net/core/dev.c (1953) Cc: stable(a)vger.kernel.org Reported-by: syzbot+f8812454d9b3ac00d282(a)syzkaller.appspotmail.com Fixes: c6a953cce8d0 ("batman-adv: Trigger events for auto adjusted MTU") Signed-off-by: Sven Eckelmann <sven(a)narfation.org> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://lore.kernel.org/r/20230821-batadv-missing-mtu-rtnl-lock-v1-1-1c5a7b… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index ad5714f737be..6efbc9275aec 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -495,7 +495,10 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + + rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); + rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) {

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] batman-adv: Hold rtnl lock during MTU update via netlink" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 987aae75fc1041072941ffb622b45ce2359a99b9 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082644-placard-bullfight-dbc3@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 987aae75fc10 ("batman-adv: Hold rtnl lock during MTU update via netlink") 3e15b06eb7e4 ("batman-adv: Add fragmentation mesh genl configuration") a1c8de803296 ("batman-adv: Add distributed_arp_table mesh genl configuration") 43ff6105a527 ("batman-adv: Add bridge_loop_avoidance mesh genl configuration") d7e52506b680 ("batman-adv: Add bonding mesh genl configuration") e43d16b87dc2 ("batman-adv: Add ap_isolation mesh/vlan genl configuration") 9ab4cee5ced9 ("batman-adv: Add aggregated_ogms mesh genl configuration") 49e7e37cd981 ("batman-adv: Prepare framework for vlan genl config") 5c55a40fa801 ("batman-adv: Prepare framework for hardif genl config") 600405135360 ("batman-adv: Prepare framework for mesh genl config") c4a7a8d9bb8f ("batman-adv: Move common genl doit code pre/post hooks") fb69be697916 ("batman-adv: Add inconsistent hardif netlink dump detection") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 987aae75fc1041072941ffb622b45ce2359a99b9 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann <sven(a)narfation.org> Date: Mon, 21 Aug 2023 21:48:48 +0200 Subject: [PATCH] batman-adv: Hold rtnl lock during MTU update via netlink The automatic recalculation of the maximum allowed MTU is usually triggered by code sections which are already rtnl lock protected by callers outside of batman-adv. But when the fragmentation setting is changed via batman-adv's own batadv genl family, then the rtnl lock is not yet taken. But dev_set_mtu requires that the caller holds the rtnl lock because it uses netdevice notifiers. And this code will then fail the check for this lock: RTNL: assertion failed at net/core/dev.c (1953) Cc: stable(a)vger.kernel.org Reported-by: syzbot+f8812454d9b3ac00d282(a)syzkaller.appspotmail.com Fixes: c6a953cce8d0 ("batman-adv: Trigger events for auto adjusted MTU") Signed-off-by: Sven Eckelmann <sven(a)narfation.org> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://lore.kernel.org/r/20230821-batadv-missing-mtu-rtnl-lock-v1-1-1c5a7b… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index ad5714f737be..6efbc9275aec 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -495,7 +495,10 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + + rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); + rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) {

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] batman-adv: Don't increase MTU when set by user" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.14.y git checkout FETCH_HEAD git cherry-pick -x d8e42a2b0addf238be8b3b37dcd9795a5c1be459 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082656-sadly-harness-6601@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^.. Possible dependencies: d8e42a2b0add ("batman-adv: Don't increase MTU when set by user") c6a953cce8d0 ("batman-adv: Trigger events for auto adjusted MTU") 8b84cc4fb556 ("batman-adv: Use inline kernel-doc for enum/struct") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From d8e42a2b0addf238be8b3b37dcd9795a5c1be459 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann <sven(a)narfation.org> Date: Wed, 19 Jul 2023 10:01:15 +0200 Subject: [PATCH] batman-adv: Don't increase MTU when set by user If the user set an MTU value, it usually means that there are special requirements for the MTU. But if an interface gots activated, the MTU was always recalculated and then the user set value was overwritten. The only reason why this user set value has to be overwritten, is when the MTU has to be decreased because batman-adv is not able to transfer packets with the user specified size. Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Cc: stable(a)vger.kernel.org Signed-off-by: Sven Eckelmann <sven(a)narfation.org> Signed-off-by: Simon Wunderlich <sw(a)simonwunderlich.de> diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index ae5762af0146..24c9c0c3f316 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -630,7 +630,19 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) */ void batadv_update_min_mtu(struct net_device *soft_iface) { - dev_set_mtu(soft_iface, batadv_hardif_min_mtu(soft_iface)); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int limit_mtu; + int mtu; + + mtu = batadv_hardif_min_mtu(soft_iface); + + if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; + else + limit_mtu = ETH_DATA_LEN; + + mtu = min(mtu, limit_mtu); + dev_set_mtu(soft_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index d3fdf82282af..85d00dc9ce32 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -153,11 +153,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { + struct batadv_priv *bat_priv = netdev_priv(dev); + /* check ranges */ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu; return 0; } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ca9449ec9836..cf1a0eafe3ab 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1546,6 +1546,12 @@ struct batadv_priv { /** @soft_iface: net device which holds this struct as private data */ struct net_device *soft_iface; + /** + * @mtu_set_by_user: MTU was set once by user + * protected by rtnl_lock + */ + int mtu_set_by_user; + /** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters)

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] tracing/synthetic: Use union instead of casts" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x ddeea494a16f32522bce16ee65f191d05d4b8282 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082627-celibacy-uncoiled-9fae@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: ddeea494a16f ("tracing/synthetic: Use union instead of casts") 116b41162f8b ("Merge tag 'probes-v6.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ddeea494a16f32522bce16ee65f191d05d4b8282 Mon Sep 17 00:00:00 2001 From: Sven Schnelle <svens(a)linux.ibm.com> Date: Wed, 16 Aug 2023 17:49:26 +0200 Subject: [PATCH] tracing/synthetic: Use union instead of casts The current code uses a lot of casts to access the fields member in struct synth_trace_events with different sizes. This makes the code hard to read, and had already introduced an endianness bug. Use a union and struct instead. Link: https://lkml.kernel.org/r/20230816154928.4171614-2-svens@linux.ibm.com Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Fixes: 00cf3d672a9dd ("tracing: Allow synthetic events to pass around stacktraces") Signed-off-by: Sven Schnelle <svens(a)linux.ibm.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3930e676436c..1e8bbdb8da90 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -59,6 +59,17 @@ int trace_raw_output_prep(struct trace_iterator *iter, extern __printf(2, 3) void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...); +/* Used to find the offset and length of dynamic fields in trace events */ +struct trace_dynamic_info { +#ifdef CONFIG_CPU_BIG_ENDIAN + u16 offset; + u16 len; +#else + u16 len; + u16 offset; +#endif +}; + /* * The trace entry - the most basic unit of tracing. This is what * is printed in the end as a single line in the trace output, such as: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e1edc2197fc8..95956f75bea5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1295,6 +1295,14 @@ static inline void trace_branch_disable(void) /* set ring buffers to default size if not already done so */ int tracing_update_buffers(void); +union trace_synth_field { + u8 as_u8; + u16 as_u16; + u32 as_u32; + u64 as_u64; + struct trace_dynamic_info as_dynamic; +}; + struct ftrace_event_field { struct list_head link; const char *name; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index dd398afc8e25..7fff8235075f 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -127,7 +127,7 @@ static bool synth_event_match(const char *system, const char *event, struct synth_trace_event { struct trace_entry ent; - u64 fields[]; + union trace_synth_field fields[]; }; static int synth_event_define_fields(struct trace_event_call *call) @@ -321,19 +321,19 @@ static const char *synth_field_fmt(char *type) static void print_synth_event_num_val(struct trace_seq *s, char *print_fmt, char *name, - int size, u64 val, char *space) + int size, union trace_synth_field *val, char *space) { switch (size) { case 1: - trace_seq_printf(s, print_fmt, name, (u8)val, space); + trace_seq_printf(s, print_fmt, name, val->as_u8, space); break; case 2: - trace_seq_printf(s, print_fmt, name, (u16)val, space); + trace_seq_printf(s, print_fmt, name, val->as_u16, space); break; case 4: - trace_seq_printf(s, print_fmt, name, (u32)val, space); + trace_seq_printf(s, print_fmt, name, val->as_u32, space); break; default: @@ -374,36 +374,26 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, /* parameter values */ if (se->fields[i]->is_string) { if (se->fields[i]->is_dynamic) { - u32 offset, data_offset; - char *str_field; - - offset = (u32)entry->fields[n_u64]; - data_offset = offset & 0xffff; - - str_field = (char *)entry + data_offset; + union trace_synth_field *data = &entry->fields[n_u64]; trace_seq_printf(s, print_fmt, se->fields[i]->name, STR_VAR_LEN_MAX, - str_field, + (char *)entry + data->as_dynamic.offset, i == se->n_fields - 1 ? "" : " "); n_u64++; } else { trace_seq_printf(s, print_fmt, se->fields[i]->name, STR_VAR_LEN_MAX, - (char *)&entry->fields[n_u64], + (char *)&entry->fields[n_u64].as_u64, i == se->n_fields - 1 ? "" : " "); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } } else if (se->fields[i]->is_stack) { - u32 offset, data_offset, len; unsigned long *p, *end; + union trace_synth_field *data = &entry->fields[n_u64]; - offset = (u32)entry->fields[n_u64]; - data_offset = offset & 0xffff; - len = offset >> 16; - - p = (void *)entry + data_offset; - end = (void *)p + len - (sizeof(long) - 1); + p = (void *)entry + data->as_dynamic.offset; + end = (void *)p + data->as_dynamic.len - (sizeof(long) - 1); trace_seq_printf(s, "%s=STACK:\n", se->fields[i]->name); @@ -419,13 +409,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, print_synth_event_num_val(s, print_fmt, se->fields[i]->name, se->fields[i]->size, - entry->fields[n_u64], + &entry->fields[n_u64], space); if (strcmp(se->fields[i]->type, "gfp_t") == 0) { trace_seq_puts(s, " ("); trace_print_flags_seq(s, "|", - entry->fields[n_u64], + entry->fields[n_u64].as_u64, __flags); trace_seq_putc(s, ')'); } @@ -454,21 +444,16 @@ static unsigned int trace_string(struct synth_trace_event *entry, int ret; if (is_dynamic) { - u32 data_offset; + union trace_synth_field *data = &entry->fields[*n_u64]; - data_offset = struct_size(entry, fields, event->n_u64); - data_offset += data_size; - - len = fetch_store_strlen((unsigned long)str_val); - - data_offset |= len << 16; - *(u32 *)&entry->fields[*n_u64] = data_offset; + data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size; + data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val); ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); (*n_u64)++; } else { - str_field = (char *)&entry->fields[*n_u64]; + str_field = (char *)&entry->fields[*n_u64].as_u64; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if ((unsigned long)str_val < TASK_SIZE) @@ -492,6 +477,7 @@ static unsigned int trace_stack(struct synth_trace_event *entry, unsigned int data_size, unsigned int *n_u64) { + union trace_synth_field *data = &entry->fields[*n_u64]; unsigned int len; u32 data_offset; void *data_loc; @@ -515,8 +501,9 @@ static unsigned int trace_stack(struct synth_trace_event *entry, memcpy(data_loc, stack, len); /* Fill in the field that holds the offset/len combo */ - data_offset |= len << 16; - *(u32 *)&entry->fields[*n_u64] = data_offset; + + data->as_dynamic.offset = data_offset; + data->as_dynamic.len = len; (*n_u64)++; @@ -592,19 +579,19 @@ static notrace void trace_event_raw_event_synth(void *__data, switch (field->size) { case 1: - *(u8 *)&entry->fields[n_u64] = (u8)val; + entry->fields[n_u64].as_u8 = (u8)val; break; case 2: - *(u16 *)&entry->fields[n_u64] = (u16)val; + entry->fields[n_u64].as_u16 = (u16)val; break; case 4: - *(u32 *)&entry->fields[n_u64] = (u32)val; + entry->fields[n_u64].as_u32 = (u32)val; break; default: - entry->fields[n_u64] = val; + entry->fields[n_u64].as_u64 = val; break; } n_u64++; @@ -1791,19 +1778,19 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) switch (field->size) { case 1: - *(u8 *)&state.entry->fields[n_u64] = (u8)val; + state.entry->fields[n_u64].as_u8 = (u8)val; break; case 2: - *(u16 *)&state.entry->fields[n_u64] = (u16)val; + state.entry->fields[n_u64].as_u16 = (u16)val; break; case 4: - *(u32 *)&state.entry->fields[n_u64] = (u32)val; + state.entry->fields[n_u64].as_u32 = (u32)val; break; default: - state.entry->fields[n_u64] = val; + state.entry->fields[n_u64].as_u64 = val; break; } n_u64++; @@ -1884,19 +1871,19 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals, switch (field->size) { case 1: - *(u8 *)&state.entry->fields[n_u64] = (u8)val; + state.entry->fields[n_u64].as_u8 = (u8)val; break; case 2: - *(u16 *)&state.entry->fields[n_u64] = (u16)val; + state.entry->fields[n_u64].as_u16 = (u16)val; break; case 4: - *(u32 *)&state.entry->fields[n_u64] = (u32)val; + state.entry->fields[n_u64].as_u32 = (u32)val; break; default: - state.entry->fields[n_u64] = val; + state.entry->fields[n_u64].as_u64 = val; break; } n_u64++; @@ -2031,19 +2018,19 @@ static int __synth_event_add_val(const char *field_name, u64 val, } else { switch (field->size) { case 1: - *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val; + trace_state->entry->fields[field->offset].as_u8 = (u8)val; break; case 2: - *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val; + trace_state->entry->fields[field->offset].as_u16 = (u16)val; break; case 4: - *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val; + trace_state->entry->fields[field->offset].as_u32 = (u32)val; break; default: - trace_state->entry->fields[field->offset] = val; + trace_state->entry->fields[field->offset].as_u64 = val; break; } }

1 year, 9 months

1
0
0 0

FAILED: patch "[PATCH] tracing/synthetic: Use union instead of casts" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x ddeea494a16f32522bce16ee65f191d05d4b8282 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023082621-lather-parlor-5f56@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: ddeea494a16f ("tracing/synthetic: Use union instead of casts") 116b41162f8b ("Merge tag 'probes-v6.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ddeea494a16f32522bce16ee65f191d05d4b8282 Mon Sep 17 00:00:00 2001 From: Sven Schnelle <svens(a)linux.ibm.com> Date: Wed, 16 Aug 2023 17:49:26 +0200 Subject: [PATCH] tracing/synthetic: Use union instead of casts The current code uses a lot of casts to access the fields member in struct synth_trace_events with different sizes. This makes the code hard to read, and had already introduced an endianness bug. Use a union and struct instead. Link: https://lkml.kernel.org/r/20230816154928.4171614-2-svens@linux.ibm.com Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Fixes: 00cf3d672a9dd ("tracing: Allow synthetic events to pass around stacktraces") Signed-off-by: Sven Schnelle <svens(a)linux.ibm.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3930e676436c..1e8bbdb8da90 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -59,6 +59,17 @@ int trace_raw_output_prep(struct trace_iterator *iter, extern __printf(2, 3) void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...); +/* Used to find the offset and length of dynamic fields in trace events */ +struct trace_dynamic_info { +#ifdef CONFIG_CPU_BIG_ENDIAN + u16 offset; + u16 len; +#else + u16 len; + u16 offset; +#endif +}; + /* * The trace entry - the most basic unit of tracing. This is what * is printed in the end as a single line in the trace output, such as: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e1edc2197fc8..95956f75bea5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1295,6 +1295,14 @@ static inline void trace_branch_disable(void) /* set ring buffers to default size if not already done so */ int tracing_update_buffers(void); +union trace_synth_field { + u8 as_u8; + u16 as_u16; + u32 as_u32; + u64 as_u64; + struct trace_dynamic_info as_dynamic; +}; + struct ftrace_event_field { struct list_head link; const char *name; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index dd398afc8e25..7fff8235075f 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -127,7 +127,7 @@ static bool synth_event_match(const char *system, const char *event, struct synth_trace_event { struct trace_entry ent; - u64 fields[]; + union trace_synth_field fields[]; }; static int synth_event_define_fields(struct trace_event_call *call) @@ -321,19 +321,19 @@ static const char *synth_field_fmt(char *type) static void print_synth_event_num_val(struct trace_seq *s, char *print_fmt, char *name, - int size, u64 val, char *space) + int size, union trace_synth_field *val, char *space) { switch (size) { case 1: - trace_seq_printf(s, print_fmt, name, (u8)val, space); + trace_seq_printf(s, print_fmt, name, val->as_u8, space); break; case 2: - trace_seq_printf(s, print_fmt, name, (u16)val, space); + trace_seq_printf(s, print_fmt, name, val->as_u16, space); break; case 4: - trace_seq_printf(s, print_fmt, name, (u32)val, space); + trace_seq_printf(s, print_fmt, name, val->as_u32, space); break; default: @@ -374,36 +374,26 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, /* parameter values */ if (se->fields[i]->is_string) { if (se->fields[i]->is_dynamic) { - u32 offset, data_offset; - char *str_field; - - offset = (u32)entry->fields[n_u64]; - data_offset = offset & 0xffff; - - str_field = (char *)entry + data_offset; + union trace_synth_field *data = &entry->fields[n_u64]; trace_seq_printf(s, print_fmt, se->fields[i]->name, STR_VAR_LEN_MAX, - str_field, + (char *)entry + data->as_dynamic.offset, i == se->n_fields - 1 ? "" : " "); n_u64++; } else { trace_seq_printf(s, print_fmt, se->fields[i]->name, STR_VAR_LEN_MAX, - (char *)&entry->fields[n_u64], + (char *)&entry->fields[n_u64].as_u64, i == se->n_fields - 1 ? "" : " "); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } } else if (se->fields[i]->is_stack) { - u32 offset, data_offset, len; unsigned long *p, *end; + union trace_synth_field *data = &entry->fields[n_u64]; - offset = (u32)entry->fields[n_u64]; - data_offset = offset & 0xffff; - len = offset >> 16; - - p = (void *)entry + data_offset; - end = (void *)p + len - (sizeof(long) - 1); + p = (void *)entry + data->as_dynamic.offset; + end = (void *)p + data->as_dynamic.len - (sizeof(long) - 1); trace_seq_printf(s, "%s=STACK:\n", se->fields[i]->name); @@ -419,13 +409,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, print_synth_event_num_val(s, print_fmt, se->fields[i]->name, se->fields[i]->size, - entry->fields[n_u64], + &entry->fields[n_u64], space); if (strcmp(se->fields[i]->type, "gfp_t") == 0) { trace_seq_puts(s, " ("); trace_print_flags_seq(s, "|", - entry->fields[n_u64], + entry->fields[n_u64].as_u64, __flags); trace_seq_putc(s, ')'); } @@ -454,21 +444,16 @@ static unsigned int trace_string(struct synth_trace_event *entry, int ret; if (is_dynamic) { - u32 data_offset; + union trace_synth_field *data = &entry->fields[*n_u64]; - data_offset = struct_size(entry, fields, event->n_u64); - data_offset += data_size; - - len = fetch_store_strlen((unsigned long)str_val); - - data_offset |= len << 16; - *(u32 *)&entry->fields[*n_u64] = data_offset; + data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size; + data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val); ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); (*n_u64)++; } else { - str_field = (char *)&entry->fields[*n_u64]; + str_field = (char *)&entry->fields[*n_u64].as_u64; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if ((unsigned long)str_val < TASK_SIZE) @@ -492,6 +477,7 @@ static unsigned int trace_stack(struct synth_trace_event *entry, unsigned int data_size, unsigned int *n_u64) { + union trace_synth_field *data = &entry->fields[*n_u64]; unsigned int len; u32 data_offset; void *data_loc; @@ -515,8 +501,9 @@ static unsigned int trace_stack(struct synth_trace_event *entry, memcpy(data_loc, stack, len); /* Fill in the field that holds the offset/len combo */ - data_offset |= len << 16; - *(u32 *)&entry->fields[*n_u64] = data_offset; + + data->as_dynamic.offset = data_offset; + data->as_dynamic.len = len; (*n_u64)++; @@ -592,19 +579,19 @@ static notrace void trace_event_raw_event_synth(void *__data, switch (field->size) { case 1: - *(u8 *)&entry->fields[n_u64] = (u8)val; + entry->fields[n_u64].as_u8 = (u8)val; break; case 2: - *(u16 *)&entry->fields[n_u64] = (u16)val; + entry->fields[n_u64].as_u16 = (u16)val; break; case 4: - *(u32 *)&entry->fields[n_u64] = (u32)val; + entry->fields[n_u64].as_u32 = (u32)val; break; default: - entry->fields[n_u64] = val; + entry->fields[n_u64].as_u64 = val; break; } n_u64++; @@ -1791,19 +1778,19 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) switch (field->size) { case 1: - *(u8 *)&state.entry->fields[n_u64] = (u8)val; + state.entry->fields[n_u64].as_u8 = (u8)val; break; case 2: - *(u16 *)&state.entry->fields[n_u64] = (u16)val; + state.entry->fields[n_u64].as_u16 = (u16)val; break; case 4: - *(u32 *)&state.entry->fields[n_u64] = (u32)val; + state.entry->fields[n_u64].as_u32 = (u32)val; break; default: - state.entry->fields[n_u64] = val; + state.entry->fields[n_u64].as_u64 = val; break; } n_u64++; @@ -1884,19 +1871,19 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals, switch (field->size) { case 1: - *(u8 *)&state.entry->fields[n_u64] = (u8)val; + state.entry->fields[n_u64].as_u8 = (u8)val; break; case 2: - *(u16 *)&state.entry->fields[n_u64] = (u16)val; + state.entry->fields[n_u64].as_u16 = (u16)val; break; case 4: - *(u32 *)&state.entry->fields[n_u64] = (u32)val; + state.entry->fields[n_u64].as_u32 = (u32)val; break; default: - state.entry->fields[n_u64] = val; + state.entry->fields[n_u64].as_u64 = val; break; } n_u64++; @@ -2031,19 +2018,19 @@ static int __synth_event_add_val(const char *field_name, u64 val, } else { switch (field->size) { case 1: - *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val; + trace_state->entry->fields[field->offset].as_u8 = (u8)val; break; case 2: - *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val; + trace_state->entry->fields[field->offset].as_u16 = (u16)val; break; case 4: - *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val; + trace_state->entry->fields[field->offset].as_u32 = (u32)val; break; default: - trace_state->entry->fields[field->offset] = val; + trace_state->entry->fields[field->offset].as_u64 = val; break; } }

1 year, 9 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2023