path: root/tools/testing/selftests/vm/charge_reserved_hugetlb.sh

#!/bin/sh
# SPDX-License-Identifier: GPL-2.0

set -e

if [[ $(id -u) -ne 0 ]]; then
  echo "This test must be run as root. Skipping..."
  exit 0
fi

fault_limit_file=limit_in_bytes
reservation_limit_file=rsvd.limit_in_bytes
fault_usage_file=usage_in_bytes
reservation_usage_file=rsvd.usage_in_bytes

if [[ "$1" == "-cgroup-v2" ]]; then
  cgroup2=1
  fault_limit_file=max
  reservation_limit_file=rsvd.max
  fault_usage_file=current
  reservation_usage_file=rsvd.current
fi

cgroup_path=/dev/cgroup/memory
if [[ ! -e $cgroup_path ]]; then
  mkdir -p $cgroup_path
  if [[ $cgroup2 ]]; then
    mount -t cgroup2 none $cgroup_path
  else
    mount -t cgroup memory,hugetlb $cgroup_path
  fi
fi

if [[ $cgroup2 ]]; then
  echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control
fi

function cleanup() {
  if [[ $cgroup2 ]]; then
    echo $$ >$cgroup_path/cgroup.procs
  else
    echo $$ >$cgroup_path/tasks
  fi

  if [[ -e /mnt/huge ]]; then
    rm -rf /mnt/huge/*
    umount /mnt/huge || echo error
    rmdir /mnt/huge
  fi
  if [[ -e $cgroup_path/hugetlb_cgroup_test ]]; then
    rmdir $cgroup_path/hugetlb_cgroup_test
  fi
  if [[ -e $cgroup_path/hugetlb_cgroup_test1 ]]; then
    rmdir $cgroup_path/hugetlb_cgroup_test1
  fi
  if [[ -e $cgroup_path/hugetlb_cgroup_test2 ]]; then
    rmdir $cgroup_path/hugetlb_cgroup_test2
  fi
  echo 0 >/proc/sys/vm/nr_hugepages
  echo CLEANUP DONE
}

function expect_equal() {
  local expected="$1"
  local actual="$2"
  local error="$3"

  if [[ "$expected" != "$actual" ]]; then
    echo "expected ($expected) != actual ($actual): $3"
    cleanup
    exit 1
  fi
}

function get_machine_hugepage_size() {
  hpz=$(grep -i hugepagesize /proc/meminfo)
  kb=${hpz:14:-3}
  mb=$(($kb / 1024))
  echo $mb
}

MB=$(get_machine_hugepage_size)

function setup_cgroup() {
  local name="$1"
  local cgroup_limit="$2"
  local reservation_limit="$3"

  mkdir $cgroup_path/$name

  echo writing cgroup limit: "$cgroup_limit"
  echo "$cgroup_limit" >$cgroup_path/$name/hugetlb.${MB}MB.$fault_limit_file

  echo writing reseravation limit: "$reservation_limit"
  echo "$reservation_limit" > \
    $cgroup_path/$name/hugetlb.${MB}MB.$reservation_limit_file

  if [ -e "$cgroup_path/$name/cpuset.cpus" ]; then
    echo 0 >$cgroup_path/$name/cpuset.cpus
  fi
  if [ -e "$cgroup_path/$name/cpuset.mems" ]; then
    echo 0 >$cgroup_path/$name/cpuset.mems
  fi
}

function wait_for_hugetlb_memory_to_get_depleted() {
  local cgroup="$1"
  local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
  # Wait for hugetlbfs memory to get depleted.
  while [ $(cat $path) != 0 ]; do
    echo Waiting for hugetlb memory to get depleted.
    cat $path
    sleep 0.5
  done
}

function wait_for_hugetlb_memory_to_get_reserved() {
  local cgroup="$1"
  local size="$2"

  local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
  # Wait for hugetlbfs memory to get written.
  while [ $(cat $path) != $size ]; do
    echo Waiting for hugetlb memory reservation to reach size $size.
    cat $path
    sleep 0.5
  done
}

function wait_for_hugetlb_memory_to_get_written() {
  local cgroup="$1"
  local size="$2"

  local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
  # Wait for hugetlbfs memory to get written.
  while [ $(cat $path) != $size ]; do
    echo Waiting for hugetlb memory to reach size $size.
    cat $path
    sleep 0.5
  done
}

function write_hugetlbfs_and_get_usage() {
  local cgroup="$1"
  local size="$2"
  local populate="$3"
  local write="$4"
  local path="$5"
  local method="$6"
  local private="$7"
  local expect_failure="$8"
  local reserve="$9"

  # Function return values.
  reservation_failed=0
  oom_killed=0
  hugetlb_difference=0
  reserved_difference=0

  local hugetlb_usage=$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file
  local reserved_usage=$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file

  local hugetlb_before=$(cat $hugetlb_usage)
  local reserved_before=$(cat $reserved_usage)

  echo
  echo Starting:
  echo hugetlb_usage="$hugetlb_before"
  echo reserved_usage="$reserved_before"
  echo expect_failure is "$expect_failure"

  output=$(mktemp)
  set +e
  if [[ "$method" == "1" ]] || [[ "$method" == 2 ]] ||
    [[ "$private" == "-r" ]] && [[ "$expect_failure" != 1 ]]; then

    bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
      "$cgroup" "$path" "$method" "$private" "-l" "$reserve" 2>&1 | tee $output &

    local write_result=$?
    local write_pid=$!

    until grep -q -i "DONE" $output; do
      echo waiting for DONE signal.
      if ! ps $write_pid > /dev/null
      then
        echo "FAIL: The write died"
        cleanup
        exit 1
      fi
      sleep 0.5
    done

    echo ================= write_hugetlb_memory.sh output is:
    cat $output
    echo ================= end output.

    if [[ "$populate" == "-o" ]] || [[ "$write" == "-w" ]]; then
      wait_for_hugetlb_memory_to_get_written "$cgroup" "$size"
    elif [[ "$reserve" != "-n" ]]; then
      wait_for_hugetlb_memory_to_get_reserved "$cgroup" "$size"
    else
      # This case doesn't produce visible effects, but we still have
      # to wait for the async process to start and execute...
      sleep 0.5
    fi

    echo write_result is $write_result
  else
    bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
      "$cgroup" "$path" "$method" "$private" "$reserve"
    local write_result=$?

    if [[ "$reserve" != "-n" ]]; then
      wait_for_hugetlb_memory_to_get_reserved "$cgroup" "$size"
    fi
  fi
  set -e

  if [[ "$write_result" == 1 ]]; then
    reservation_failed=1
  fi

  # On linus/master, the above process gets SIGBUS'd on oomkill, with
  # return code 135. On earlier kernels, it gets actual oomkill, with return
  # code 137, so just check for both conditions in case we're testing
  # against an earlier kernel.
  if [[ "$write_result" == 135 ]] || [[ "$write_result" == 137 ]]; then
    oom_killed=1
  fi