xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Código Issues Pull requests Ações Pacotes Projetos Versões Wiki Atividade

Merge branch 'akpm' (patches from Andrew)

Ver código fonte 
Merge updates from Andrew Morton:
 "A large amount of MM, plenty more to come.

  Subsystems affected by this patch series:
   - tools
   - kthread
   - kbuild
   - scripts
   - ocfs2
   - vfs
   - mm: slub, kmemleak, pagecache, gup, swap, memcg, pagemap, mremap,
         sparsemem, kasan, pagealloc, vmscan, compaction, mempolicy,
         hugetlbfs, hugetlb"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (155 commits)
  include/linux/huge_mm.h: check PageTail in hpage_nr_pages even when !THP
  mm/hugetlb: fix build failure with HUGETLB_PAGE but not HUGEBTLBFS
  selftests/vm: fix map_hugetlb length used for testing read and write
  mm/hugetlb: remove unnecessary memory fetch in PageHeadHuge()
  mm/hugetlb.c: clean code by removing unnecessary initialization
  hugetlb_cgroup: add hugetlb_cgroup reservation docs
  hugetlb_cgroup: add hugetlb_cgroup reservation tests
  hugetlb: support file_region coalescing again
  hugetlb_cgroup: support noreserve mappings
  hugetlb_cgroup: add accounting for shared mappings
  hugetlb: disable region_add file_region coalescing
  hugetlb_cgroup: add reservation accounting for private mappings
  mm/hugetlb_cgroup: fix hugetlb_cgroup migration
  hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations
  hugetlb_cgroup: add hugetlb_cgroup reservation counter
  hugetlbfs: Use i_mmap_rwsem to address page fault/truncate race
  hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization
  mm/memblock.c: remove redundant assignment to variable max_addr
  mm: mempolicy: require at least one nodeid for MPOL_PREFERRED
  mm: mempolicy: use VM_BUG_ON_VMA in queue_pages_test_walk()
  ...
Esse commit está contido em:
Linus Torvalds
2020-04-02 13:55:34 -07:00
pai 7be97138e7 77d6b90948
commit 6cad420cc6
165 arquivos alterados com 4904 adições e 2260 exclusões
Baixar arquivo de patch Baixar arquivo de diferenças Expandir todos os arquivos Colapsar todos os arquivos

1
tools/testing/selftests/vm/.gitignore externo
Ver arquivo

@@ -14,3 +14,4 @@ virtual_address_range
gup_benchmark
va_128TBswitch
map_fixed_noreplace
write_to_hugetlbfs

2
tools/testing/selftests/vm/Makefile
Ver arquivo

@@ -14,6 +14,7 @@ TEST_GEN_FILES += map_fixed_noreplace
TEST_GEN_FILES += map_populate
TEST_GEN_FILES += mlock-random-test
TEST_GEN_FILES += mlock2-tests
TEST_GEN_FILES += mremap_dontunmap
TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
@@ -22,6 +23,7 @@ TEST_GEN_FILES += userfaultfd
ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64))
TEST_GEN_FILES += va_128TBswitch
TEST_GEN_FILES += virtual_address_range
TEST_GEN_FILES += write_to_hugetlbfs
endif
TEST_PROGS := run_vmtests

575
tools/testing/selftests/vm/charge_reserved_hugetlb.sh Arquivo normal
Ver arquivo

@@ -0,0 +1,575 @@
#!/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
local hugetlb_after=$(cat $hugetlb_usage)
local reserved_after=$(cat $reserved_usage)
echo After write:
echo hugetlb_usage="$hugetlb_after"
echo reserved_usage="$reserved_after"
hugetlb_difference=$(($hugetlb_after - $hugetlb_before))
reserved_difference=$(($reserved_after - $reserved_before))
}
function cleanup_hugetlb_memory() {
set +e
local cgroup="$1"
if [[ "$(pgrep -f write_to_hugetlbfs)" != "" ]]; then
echo killing write_to_hugetlbfs
killall -2 write_to_hugetlbfs
wait_for_hugetlb_memory_to_get_depleted $cgroup
fi
set -e
if [[ -e /mnt/huge ]]; then
rm -rf /mnt/huge/*
umount /mnt/huge
rmdir /mnt/huge
fi
}
function run_test() {
local size=$(($1 * ${MB} * 1024 * 1024))
local populate="$2"
local write="$3"
local cgroup_limit=$(($4 * ${MB} * 1024 * 1024))
local reservation_limit=$(($5 * ${MB} * 1024 * 1024))
local nr_hugepages="$6"
local method="$7"
local private="$8"
local expect_failure="$9"
local reserve="${10}"
# Function return values.
hugetlb_difference=0
reserved_difference=0
reservation_failed=0
oom_killed=0
echo nr hugepages = "$nr_hugepages"
echo "$nr_hugepages" >/proc/sys/vm/nr_hugepages
setup_cgroup "hugetlb_cgroup_test" "$cgroup_limit" "$reservation_limit"
mkdir -p /mnt/huge
mount -t hugetlbfs -o pagesize=${MB}M,size=256M none /mnt/huge
write_hugetlbfs_and_get_usage "hugetlb_cgroup_test" "$size" "$populate" \
"$write" "/mnt/huge/test" "$method" "$private" "$expect_failure" \
"$reserve"
cleanup_hugetlb_memory "hugetlb_cgroup_test"
local final_hugetlb=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.${MB}MB.$fault_usage_file)
local final_reservation=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.${MB}MB.$reservation_usage_file)
echo $hugetlb_difference
echo $reserved_difference
expect_equal "0" "$final_hugetlb" "final hugetlb is not zero"
expect_equal "0" "$final_reservation" "final reservation is not zero"
}
function run_multiple_cgroup_test() {
local size1="$1"
local populate1="$2"
local write1="$3"
local cgroup_limit1="$4"
local reservation_limit1="$5"
local size2="$6"
local populate2="$7"
local write2="$8"
local cgroup_limit2="$9"
local reservation_limit2="${10}"
local nr_hugepages="${11}"
local method="${12}"
local private="${13}"
local expect_failure="${14}"
local reserve="${15}"
# Function return values.
hugetlb_difference1=0
reserved_difference1=0
reservation_failed1=0
oom_killed1=0
hugetlb_difference2=0
reserved_difference2=0
reservation_failed2=0
oom_killed2=0
echo nr hugepages = "$nr_hugepages"
echo "$nr_hugepages" >/proc/sys/vm/nr_hugepages
setup_cgroup "hugetlb_cgroup_test1" "$cgroup_limit1" "$reservation_limit1"
setup_cgroup "hugetlb_cgroup_test2" "$cgroup_limit2" "$reservation_limit2"
mkdir -p /mnt/huge
mount -t hugetlbfs -o pagesize=${MB}M,size=256M none /mnt/huge
write_hugetlbfs_and_get_usage "hugetlb_cgroup_test1" "$size1" \
"$populate1" "$write1" "/mnt/huge/test1" "$method" "$private" \
"$expect_failure" "$reserve"
hugetlb_difference1=$hugetlb_difference
reserved_difference1=$reserved_difference
reservation_failed1=$reservation_failed
oom_killed1=$oom_killed
local cgroup1_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.${MB}MB.$fault_usage_file
local cgroup1_reservation_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.${MB}MB.$reservation_usage_file
local cgroup2_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.${MB}MB.$fault_usage_file
local cgroup2_reservation_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.${MB}MB.$reservation_usage_file
local usage_before_second_write=$(cat $cgroup1_hugetlb_usage)
local reservation_usage_before_second_write=$(cat $cgroup1_reservation_usage)
write_hugetlbfs_and_get_usage "hugetlb_cgroup_test2" "$size2" \
"$populate2" "$write2" "/mnt/huge/test2" "$method" "$private" \
"$expect_failure" "$reserve"
hugetlb_difference2=$hugetlb_difference
reserved_difference2=$reserved_difference
reservation_failed2=$reservation_failed
oom_killed2=$oom_killed
expect_equal "$usage_before_second_write" \
"$(cat $cgroup1_hugetlb_usage)" "Usage changed."
expect_equal "$reservation_usage_before_second_write" \
"$(cat $cgroup1_reservation_usage)" "Reservation usage changed."
cleanup_hugetlb_memory
local final_hugetlb=$(cat $cgroup1_hugetlb_usage)
local final_reservation=$(cat $cgroup1_reservation_usage)
expect_equal "0" "$final_hugetlb" \
"hugetlbt_cgroup_test1 final hugetlb is not zero"
expect_equal "0" "$final_reservation" \
"hugetlbt_cgroup_test1 final reservation is not zero"
local final_hugetlb=$(cat $cgroup2_hugetlb_usage)
local final_reservation=$(cat $cgroup2_reservation_usage)
expect_equal "0" "$final_hugetlb" \
"hugetlb_cgroup_test2 final hugetlb is not zero"
expect_equal "0" "$final_reservation" \
"hugetlb_cgroup_test2 final reservation is not zero"
}
cleanup
for populate in "" "-o"; do
for method in 0 1 2; do
for private in "" "-r"; do
for reserve in "" "-n"; do
# Skip mmap(MAP_HUGETLB | MAP_SHARED). Doesn't seem to be supported.
if [[ "$method" == 1 ]] && [[ "$private" == "" ]]; then
continue
fi
# Skip populated shmem tests. Doesn't seem to be supported.
if [[ "$method" == 2"" ]] && [[ "$populate" == "-o" ]]; then
continue
fi
if [[ "$method" == 2"" ]] && [[ "$reserve" == "-n" ]]; then
continue
fi
cleanup
echo
echo
echo
echo Test normal case.
echo private=$private, populate=$populate, method=$method, reserve=$reserve
run_test 5 "$populate" "" 10 10 10 "$method" "$private" "0" "$reserve"
echo Memory charged to hugtlb=$hugetlb_difference
echo Memory charged to reservation=$reserved_difference
if [[ "$populate" == "-o" ]]; then
expect_equal "$((5 * $MB * 1024 * 1024))" "$hugetlb_difference" \
"Reserved memory charged to hugetlb cgroup."
else
expect_equal "0" "$hugetlb_difference" \
"Reserved memory charged to hugetlb cgroup."
fi
if [[ "$reserve" != "-n" ]] || [[ "$populate" == "-o" ]]; then
expect_equal "$((5 * $MB * 1024 * 1024))" "$reserved_difference" \
"Reserved memory not charged to reservation usage."
else
expect_equal "0" "$reserved_difference" \
"Reserved memory not charged to reservation usage."
fi
echo 'PASS'
cleanup
echo
echo
echo
echo Test normal case with write.
echo private=$private, populate=$populate, method=$method, reserve=$reserve
run_test 5 "$populate" '-w' 5 5 10 "$method" "$private" "0" "$reserve"
echo Memory charged to hugtlb=$hugetlb_difference
echo Memory charged to reservation=$reserved_difference
expect_equal "$((5 * $MB * 1024 * 1024))" "$hugetlb_difference" \
"Reserved memory charged to hugetlb cgroup."
expect_equal "$((5 * $MB * 1024 * 1024))" "$reserved_difference" \
"Reserved memory not charged to reservation usage."
echo 'PASS'
cleanup
continue
echo
echo
echo
echo Test more than reservation case.
echo private=$private, populate=$populate, method=$method, reserve=$reserve
if [ "$reserve" != "-n" ]; then
run_test "5" "$populate" '' "10" "2" "10" "$method" "$private" "1" \
"$reserve"
expect_equal "1" "$reservation_failed" "Reservation succeeded."
fi
echo 'PASS'
cleanup
echo
echo
echo
echo Test more than cgroup limit case.
echo private=$private, populate=$populate, method=$method, reserve=$reserve
# Not sure if shm memory can be cleaned up when the process gets sigbus'd.
if [[ "$method" != 2 ]]; then
run_test 5 "$populate" "-w" 2 10 10 "$method" "$private" "1" "$reserve"
expect_equal "1" "$oom_killed" "Not oom killed."
fi
echo 'PASS'
cleanup
echo
echo
echo
echo Test normal case, multiple cgroups.
echo private=$private, populate=$populate, method=$method, reserve=$reserve
run_multiple_cgroup_test "3" "$populate" "" "10" "10" "5" \
"$populate" "" "10" "10" "10" \
"$method" "$private" "0" "$reserve"
echo Memory charged to hugtlb1=$hugetlb_difference1
echo Memory charged to reservation1=$reserved_difference1
echo Memory charged to hugtlb2=$hugetlb_difference2
echo Memory charged to reservation2=$reserved_difference2
if [[ "$reserve" != "-n" ]] || [[ "$populate" == "-o" ]]; then
expect_equal "3" "$reserved_difference1" \
"Incorrect reservations charged to cgroup 1."
expect_equal "5" "$reserved_difference2" \
"Incorrect reservation charged to cgroup 2."
else
expect_equal "0" "$reserved_difference1" \
"Incorrect reservations charged to cgroup 1."
expect_equal "0" "$reserved_difference2" \
"Incorrect reservation charged to cgroup 2."
fi
if [[ "$populate" == "-o" ]]; then
expect_equal "3" "$hugetlb_difference1" \
"Incorrect hugetlb charged to cgroup 1."
expect_equal "5" "$hugetlb_difference2" \
"Incorrect hugetlb charged to cgroup 2."
else
expect_equal "0" "$hugetlb_difference1" \
"Incorrect hugetlb charged to cgroup 1."
expect_equal "0" "$hugetlb_difference2" \
"Incorrect hugetlb charged to cgroup 2."
fi
echo 'PASS'
cleanup
echo
echo
echo
echo Test normal case with write, multiple cgroups.
echo private=$private, populate=$populate, method=$method, reserve=$reserve
run_multiple_cgroup_test "3" "$populate" "-w" "10" "10" "5" \
"$populate" "-w" "10" "10" "10" \
"$method" "$private" "0" "$reserve"
echo Memory charged to hugtlb1=$hugetlb_difference1
echo Memory charged to reservation1=$reserved_difference1
echo Memory charged to hugtlb2=$hugetlb_difference2
echo Memory charged to reservation2=$reserved_difference2
expect_equal "3" "$hugetlb_difference1" \
"Incorrect hugetlb charged to cgroup 1."
expect_equal "3" "$reserved_difference1" \
"Incorrect reservation charged to cgroup 1."
expect_equal "5" "$hugetlb_difference2" \
"Incorrect hugetlb charged to cgroup 2."
expect_equal "5" "$reserved_difference2" \
"Incorrected reservation charged to cgroup 2."
echo 'PASS'
cleanup
done # reserve
done # private
done # populate
done # method
umount $cgroup_path
rmdir $cgroup_path

15
tools/testing/selftests/vm/gup_benchmark.c
Ver arquivo

@@ -18,6 +18,10 @@
#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
#define PIN_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
/* Just the flags we need, copied from mm.h: */
#define FOLL_WRITE 0x01 /* check pte is writable */
@@ -40,8 +44,14 @@ int main(int argc, char **argv)
char *file = "/dev/zero";
char *p;
while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) {
while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
switch (opt) {
case 'a':
cmd = PIN_FAST_BENCHMARK;
break;
case 'b':
cmd = PIN_BENCHMARK;
break;
case 'm':
size = atoi(optarg) * MB;
break;
@@ -63,6 +73,9 @@ int main(int argc, char **argv)
case 'U':
cmd = GUP_BENCHMARK;
break;
case 'u':
cmd = GUP_FAST_BENCHMARK;
break;
case 'w':
write = 1;
break;

244
tools/testing/selftests/vm/hugetlb_reparenting_test.sh Arquivo normal
Ver arquivo

@@ -0,0 +1,244 @@
#!/bin/bash
# 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
usage_file=usage_in_bytes
if [[ "$1" == "-cgroup-v2" ]]; then
cgroup2=1
usage_file=current
fi
CGROUP_ROOT='/dev/cgroup/memory'
MNT='/mnt/huge/'
if [[ ! -e $CGROUP_ROOT ]]; then
mkdir -p $CGROUP_ROOT
if [[ $cgroup2 ]]; then
mount -t cgroup2 none $CGROUP_ROOT
sleep 1
echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
else
mount -t cgroup memory,hugetlb $CGROUP_ROOT
fi
fi
function get_machine_hugepage_size() {
hpz=$(grep -i hugepagesize /proc/meminfo)
kb=${hpz:14:-3}
mb=$(($kb / 1024))
echo $mb
}
MB=$(get_machine_hugepage_size)
function cleanup() {
echo cleanup
set +e
rm -rf "$MNT"/* 2>/dev/null
umount "$MNT" 2>/dev/null
rmdir "$MNT" 2>/dev/null
rmdir "$CGROUP_ROOT"/a/b 2>/dev/null
rmdir "$CGROUP_ROOT"/a 2>/dev/null
rmdir "$CGROUP_ROOT"/test1 2>/dev/null
echo 0 >/proc/sys/vm/nr_hugepages
set -e
}
function assert_state() {
local expected_a="$1"
local expected_a_hugetlb="$2"
local expected_b=""
local expected_b_hugetlb=""
if [ ! -z ${3:-} ] && [ ! -z ${4:-} ]; then
expected_b="$3"
expected_b_hugetlb="$4"
fi
local tolerance=$((5 * 1024 * 1024))
local actual_a
actual_a="$(cat "$CGROUP_ROOT"/a/memory.$usage_file)"
if [[ $actual_a -lt $(($expected_a - $tolerance)) ]] ||
[[ $actual_a -gt $(($expected_a + $tolerance)) ]]; then
echo actual a = $((${actual_a%% *} / 1024 / 1024)) MB
echo expected a = $((${expected_a%% *} / 1024 / 1024)) MB
echo fail
cleanup
exit 1
fi
local actual_a_hugetlb
actual_a_hugetlb="$(cat "$CGROUP_ROOT"/a/hugetlb.${MB}MB.$usage_file)"
if [[ $actual_a_hugetlb -lt $(($expected_a_hugetlb - $tolerance)) ]] ||
[[ $actual_a_hugetlb -gt $(($expected_a_hugetlb + $tolerance)) ]]; then
echo actual a hugetlb = $((${actual_a_hugetlb%% *} / 1024 / 1024)) MB
echo expected a hugetlb = $((${expected_a_hugetlb%% *} / 1024 / 1024)) MB
echo fail
cleanup
exit 1
fi
if [[ -z "$expected_b" || -z "$expected_b_hugetlb" ]]; then
return
fi
local actual_b
actual_b="$(cat "$CGROUP_ROOT"/a/b/memory.$usage_file)"
if [[ $actual_b -lt $(($expected_b - $tolerance)) ]] ||
[[ $actual_b -gt $(($expected_b + $tolerance)) ]]; then
echo actual b = $((${actual_b%% *} / 1024 / 1024)) MB
echo expected b = $((${expected_b%% *} / 1024 / 1024)) MB
echo fail
cleanup
exit 1
fi
local actual_b_hugetlb
actual_b_hugetlb="$(cat "$CGROUP_ROOT"/a/b/hugetlb.${MB}MB.$usage_file)"
if [[ $actual_b_hugetlb -lt $(($expected_b_hugetlb - $tolerance)) ]] ||
[[ $actual_b_hugetlb -gt $(($expected_b_hugetlb + $tolerance)) ]]; then
echo actual b hugetlb = $((${actual_b_hugetlb%% *} / 1024 / 1024)) MB
echo expected b hugetlb = $((${expected_b_hugetlb%% *} / 1024 / 1024)) MB
echo fail
cleanup
exit 1
fi
}
function setup() {
echo 100 >/proc/sys/vm/nr_hugepages
mkdir "$CGROUP_ROOT"/a
sleep 1
if [[ $cgroup2 ]]; then
echo "+hugetlb +memory" >$CGROUP_ROOT/a/cgroup.subtree_control
else
echo 0 >$CGROUP_ROOT/a/cpuset.mems
echo 0 >$CGROUP_ROOT/a/cpuset.cpus
fi
mkdir "$CGROUP_ROOT"/a/b
if [[ ! $cgroup2 ]]; then
echo 0 >$CGROUP_ROOT/a/b/cpuset.mems
echo 0 >$CGROUP_ROOT/a/b/cpuset.cpus
fi
mkdir -p "$MNT"
mount -t hugetlbfs none "$MNT"
}
write_hugetlbfs() {
local cgroup="$1"
local path="$2"
local size="$3"
if [[ $cgroup2 ]]; then
echo $$ >$CGROUP_ROOT/$cgroup/cgroup.procs
else
echo 0 >$CGROUP_ROOT/$cgroup/cpuset.mems
echo 0 >$CGROUP_ROOT/$cgroup/cpuset.cpus
echo $$ >"$CGROUP_ROOT/$cgroup/tasks"
fi
./write_to_hugetlbfs -p "$path" -s "$size" -m 0 -o
if [[ $cgroup2 ]]; then
echo $$ >$CGROUP_ROOT/cgroup.procs
else
echo $$ >"$CGROUP_ROOT/tasks"
fi
echo
}
set -e
size=$((${MB} * 1024 * 1024 * 25)) # 50MB = 25 * 2MB hugepages.
cleanup
echo
echo
echo Test charge, rmdir, uncharge
setup
echo mkdir
mkdir $CGROUP_ROOT/test1
echo write
write_hugetlbfs test1 "$MNT"/test $size
echo rmdir
rmdir $CGROUP_ROOT/test1
mkdir $CGROUP_ROOT/test1
echo uncharge
rm -rf /mnt/huge/*
cleanup
echo done
echo
echo
if [[ ! $cgroup2 ]]; then
echo "Test parent and child hugetlb usage"
setup
echo write
write_hugetlbfs a "$MNT"/test $size
echo Assert memory charged correctly for parent use.
assert_state 0 $size 0 0
write_hugetlbfs a/b "$MNT"/test2 $size
echo Assert memory charged correctly for child use.
assert_state 0 $(($size * 2)) 0 $size
rmdir "$CGROUP_ROOT"/a/b
sleep 5
echo Assert memory reparent correctly.
assert_state 0 $(($size * 2))
rm -rf "$MNT"/*
umount "$MNT"
echo Assert memory uncharged correctly.
assert_state 0 0
cleanup
fi
echo
echo
echo "Test child only hugetlb usage"
echo setup
setup
echo write
write_hugetlbfs a/b "$MNT"/test2 $size
echo Assert memory charged correctly for child only use.
assert_state 0 $(($size)) 0 $size
rmdir "$CGROUP_ROOT"/a/b
echo Assert memory reparent correctly.
assert_state 0 $size
rm -rf "$MNT"/*
umount "$MNT"
echo Assert memory uncharged correctly.
assert_state 0 0
cleanup
echo ALL PASS
umount $CGROUP_ROOT
rm -rf $CGROUP_ROOT

14
tools/testing/selftests/vm/map_hugetlb.c
Ver arquivo

@@ -45,20 +45,20 @@ static void check_bytes(char *addr)
printf("First hex is %x\n", *((unsigned int *)addr));
}
static void write_bytes(char *addr)
static void write_bytes(char *addr, size_t length)
{
unsigned long i;
for (i = 0; i < LENGTH; i++)
for (i = 0; i < length; i++)
*(addr + i) = (char)i;
}
static int read_bytes(char *addr)
static int read_bytes(char *addr, size_t length)
{
unsigned long i;
check_bytes(addr);
for (i = 0; i < LENGTH; i++)
for (i = 0; i < length; i++)
if (*(addr + i) != (char)i) {
printf("Mismatch at %lu\n", i);
return 1;
@@ -96,11 +96,11 @@ int main(int argc, char **argv)
printf("Returned address is %p\n", addr);
check_bytes(addr);
write_bytes(addr);
ret = read_bytes(addr);
write_bytes(addr, length);
ret = read_bytes(addr, length);
/* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
if (munmap(addr, LENGTH)) {
if (munmap(addr, length)) {
perror("munmap");
exit(1);
}

233
tools/testing/selftests/vm/mlock2-tests.c
Ver arquivo

@@ -67,59 +67,6 @@ out:
return ret;
}
static uint64_t get_pageflags(unsigned long addr)
{
FILE *file;
uint64_t pfn;
unsigned long offset;
file = fopen("/proc/self/pagemap", "r");
if (!file) {
perror("fopen pagemap");
_exit(1);
}
offset = addr / getpagesize() * sizeof(pfn);
if (fseek(file, offset, SEEK_SET)) {
perror("fseek pagemap");
_exit(1);
}
if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
perror("fread pagemap");
_exit(1);
}
fclose(file);
return pfn;
}
static uint64_t get_kpageflags(unsigned long pfn)
{
uint64_t flags;
FILE *file;
file = fopen("/proc/kpageflags", "r");
if (!file) {
perror("fopen kpageflags");
_exit(1);
}
if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
perror("fseek kpageflags");
_exit(1);
}
if (fread(&flags, sizeof(flags), 1, file) != 1) {
perror("fread kpageflags");
_exit(1);
}
fclose(file);
return flags;
}
#define VMFLAGS "VmFlags:"
static bool is_vmflag_set(unsigned long addr, const char *vmflag)
@@ -159,19 +106,13 @@ out:
#define RSS "Rss:"
#define LOCKED "lo"
static bool is_vma_lock_on_fault(unsigned long addr)
static unsigned long get_value_for_name(unsigned long addr, const char *name)
{
bool ret = false;
bool locked;
FILE *smaps = NULL;
unsigned long vma_size, vma_rss;
char *line = NULL;
char *value;
size_t size = 0;
locked = is_vmflag_set(addr, LOCKED);
if (!locked)
goto out;
char *value_ptr;
FILE *smaps = NULL;
unsigned long value = -1UL;
smaps = seek_to_smaps_entry(addr);
if (!smaps) {
@@ -180,112 +121,70 @@ static bool is_vma_lock_on_fault(unsigned long addr)
}
while (getline(&line, &size, smaps) > 0) {
if (!strstr(line, SIZE)) {
if (!strstr(line, name)) {
free(line);
line = NULL;
size = 0;
continue;
}
value = line + strlen(SIZE);
if (sscanf(value, "%lu kB", &vma_size) < 1) {
value_ptr = line + strlen(name);
if (sscanf(value_ptr, "%lu kB", &value) < 1) {
printf("Unable to parse smaps entry for Size\n");
goto out;
}
break;
}
while (getline(&line, &size, smaps) > 0) {
if (!strstr(line, RSS)) {
free(line);
line = NULL;
size = 0;
continue;
}
value = line + strlen(RSS);
if (sscanf(value, "%lu kB", &vma_rss) < 1) {
printf("Unable to parse smaps entry for Rss\n");
goto out;
}
break;
}
ret = locked && (vma_rss < vma_size);
out:
free(line);
if (smaps)
fclose(smaps);
return ret;
free(line);
return value;
}
static bool is_vma_lock_on_fault(unsigned long addr)
{
bool locked;
unsigned long vma_size, vma_rss;
locked = is_vmflag_set(addr, LOCKED);
if (!locked)
return false;
vma_size = get_value_for_name(addr, SIZE);
vma_rss = get_value_for_name(addr, RSS);
/* only one page is faulted in */
return (vma_rss < vma_size);
}
#define PRESENT_BIT 0x8000000000000000ULL
#define PFN_MASK 0x007FFFFFFFFFFFFFULL
#define UNEVICTABLE_BIT (1UL << 18)
static int lock_check(char *map)
static int lock_check(unsigned long addr)
{
unsigned long page_size = getpagesize();
uint64_t page1_flags, page2_flags;
bool locked;
unsigned long vma_size, vma_rss;
page1_flags = get_pageflags((unsigned long)map);
page2_flags = get_pageflags((unsigned long)map + page_size);
locked = is_vmflag_set(addr, LOCKED);
if (!locked)
return false;
/* Both pages should be present */
if (((page1_flags & PRESENT_BIT) == 0) ||
((page2_flags & PRESENT_BIT) == 0)) {
printf("Failed to make both pages present\n");
return 1;
}
vma_size = get_value_for_name(addr, SIZE);
vma_rss = get_value_for_name(addr, RSS);
page1_flags = get_kpageflags(page1_flags & PFN_MASK);
page2_flags = get_kpageflags(page2_flags & PFN_MASK);
/* Both pages should be unevictable */
if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
((page2_flags & UNEVICTABLE_BIT) == 0)) {
printf("Failed to make both pages unevictable\n");
return 1;
}
if (!is_vmflag_set((unsigned long)map, LOCKED)) {
printf("VMA flag %s is missing on page 1\n", LOCKED);
return 1;
}
if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
printf("VMA flag %s is missing on page 2\n", LOCKED);
return 1;
}
return 0;
return (vma_rss == vma_size);
}
static int unlock_lock_check(char *map)
{
unsigned long page_size = getpagesize();
uint64_t page1_flags, page2_flags;
page1_flags = get_pageflags((unsigned long)map);
page2_flags = get_pageflags((unsigned long)map + page_size);
page1_flags = get_kpageflags(page1_flags & PFN_MASK);
page2_flags = get_kpageflags(page2_flags & PFN_MASK);
if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
printf("A page is still marked unevictable after unlock\n");
return 1;
}
if (is_vmflag_set((unsigned long)map, LOCKED)) {
printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
return 1;
}
if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
return 1;
}
return 0;
}
@@ -311,7 +210,7 @@ static int test_mlock_lock()
goto unmap;
}
if (lock_check(map))
if (!lock_check((unsigned long)map))
goto unmap;
/* Now unlock and recheck attributes */
@@ -330,64 +229,18 @@ out:
static int onfault_check(char *map)
{
unsigned long page_size = getpagesize();
uint64_t page1_flags, page2_flags;
page1_flags = get_pageflags((unsigned long)map);
page2_flags = get_pageflags((unsigned long)map + page_size);
/* Neither page should be present */
if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
printf("Pages were made present by MLOCK_ONFAULT\n");
return 1;
}
*map = 'a';
page1_flags = get_pageflags((unsigned long)map);
page2_flags = get_pageflags((unsigned long)map + page_size);
/* Only page 1 should be present */
if ((page1_flags & PRESENT_BIT) == 0) {
printf("Page 1 is not present after fault\n");
return 1;
} else if (page2_flags & PRESENT_BIT) {
printf("Page 2 was made present\n");
return 1;
}
page1_flags = get_kpageflags(page1_flags & PFN_MASK);
/* Page 1 should be unevictable */
if ((page1_flags & UNEVICTABLE_BIT) == 0) {
printf("Failed to make faulted page unevictable\n");
return 1;
}
if (!is_vma_lock_on_fault((unsigned long)map)) {
printf("VMA is not marked for lock on fault\n");
return 1;
}
if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
printf("VMA is not marked for lock on fault\n");
return 1;
}
return 0;
}
static int unlock_onfault_check(char *map)
{
unsigned long page_size = getpagesize();
uint64_t page1_flags;
page1_flags = get_pageflags((unsigned long)map);
page1_flags = get_kpageflags(page1_flags & PFN_MASK);
if (page1_flags & UNEVICTABLE_BIT) {
printf("Page 1 is still marked unevictable after unlock\n");
return 1;
}
if (is_vma_lock_on_fault((unsigned long)map) ||
is_vma_lock_on_fault((unsigned long)map + page_size)) {
@@ -445,7 +298,6 @@ static int test_lock_onfault_of_present()
char *map;
int ret = 1;
unsigned long page_size = getpagesize();
uint64_t page1_flags, page2_flags;
map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
@@ -465,17 +317,6 @@ static int test_lock_onfault_of_present()
goto unmap;
}
page1_flags = get_pageflags((unsigned long)map);
page2_flags = get_pageflags((unsigned long)map + page_size);
page1_flags = get_kpageflags(page1_flags & PFN_MASK);
page2_flags = get_kpageflags(page2_flags & PFN_MASK);
/* Page 1 should be unevictable */
if ((page1_flags & UNEVICTABLE_BIT) == 0) {
printf("Failed to make present page unevictable\n");
goto unmap;
}
if (!is_vma_lock_on_fault((unsigned long)map) ||
!is_vma_lock_on_fault((unsigned long)map + page_size)) {
printf("VMA with present pages is not marked lock on fault\n");
@@ -507,7 +348,7 @@ static int test_munlockall()
goto out;
}
if (lock_check(map))
if (!lock_check((unsigned long)map))
goto unmap;
if (munlockall()) {
@@ -549,7 +390,7 @@ static int test_munlockall()
goto out;
}
if (lock_check(map))
if (!lock_check((unsigned long)map))
goto unmap;
if (munlockall()) {

313
tools/testing/selftests/vm/mremap_dontunmap.c Arquivo normal
Ver arquivo

@@ -0,0 +1,313 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Tests for mremap w/ MREMAP_DONTUNMAP.
*
* Copyright 2020, Brian Geffon <bgeffon@google.com>
*/
#define _GNU_SOURCE
#include <sys/mman.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include "../kselftest.h"
#ifndef MREMAP_DONTUNMAP
#define MREMAP_DONTUNMAP 4
#endif
unsigned long page_size;
char *page_buffer;
static void dump_maps(void)
{
char cmd[32];
snprintf(cmd, sizeof(cmd), "cat /proc/%d/maps", getpid());
system(cmd);
}
#define BUG_ON(condition, description) \
do { \
if (condition) { \
fprintf(stderr, "[FAIL]\t%s():%d\t%s:%s\n", __func__, \
__LINE__, (description), strerror(errno)); \
dump_maps(); \
exit(1); \
} \
} while (0)
// Try a simple operation for to "test" for kernel support this prevents
// reporting tests as failed when it's run on an older kernel.
static int kernel_support_for_mremap_dontunmap()
{
int ret = 0;
unsigned long num_pages = 1;
void *source_mapping = mmap(NULL, num_pages * page_size, PROT_NONE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(source_mapping == MAP_FAILED, "mmap");
// This simple remap should only fail if MREMAP_DONTUNMAP isn't
// supported.
void *dest_mapping =
mremap(source_mapping, num_pages * page_size, num_pages * page_size,
MREMAP_DONTUNMAP | MREMAP_MAYMOVE, 0);
if (dest_mapping == MAP_FAILED) {
ret = errno;
} else {
BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
"unable to unmap destination mapping");
}
BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
"unable to unmap source mapping");
return ret;
}
// This helper will just validate that an entire mapping contains the expected
// byte.
static int check_region_contains_byte(void *addr, unsigned long size, char byte)
{
BUG_ON(size & (page_size - 1),
"check_region_contains_byte expects page multiples");
BUG_ON((unsigned long)addr & (page_size - 1),
"check_region_contains_byte expects page alignment");
memset(page_buffer, byte, page_size);
unsigned long num_pages = size / page_size;
unsigned long i;
// Compare each page checking that it contains our expected byte.
for (i = 0; i < num_pages; ++i) {
int ret =
memcmp(addr + (i * page_size), page_buffer, page_size);
if (ret) {
return ret;
}
}
return 0;
}
// this test validates that MREMAP_DONTUNMAP moves the pagetables while leaving
// the source mapping mapped.
static void mremap_dontunmap_simple()
{
unsigned long num_pages = 5;
void *source_mapping =
mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(source_mapping == MAP_FAILED, "mmap");
memset(source_mapping, 'a', num_pages * page_size);
// Try to just move the whole mapping anywhere (not fixed).
void *dest_mapping =
mremap(source_mapping, num_pages * page_size, num_pages * page_size,
MREMAP_DONTUNMAP | MREMAP_MAYMOVE, NULL);
BUG_ON(dest_mapping == MAP_FAILED, "mremap");
// Validate that the pages have been moved, we know they were moved if
// the dest_mapping contains a's.
BUG_ON(check_region_contains_byte
(dest_mapping, num_pages * page_size, 'a') != 0,
"pages did not migrate");
BUG_ON(check_region_contains_byte
(source_mapping, num_pages * page_size, 0) != 0,
"source should have no ptes");
BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
"unable to unmap destination mapping");
BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
"unable to unmap source mapping");
}
// This test validates MREMAP_DONTUNMAP will move page tables to a specific
// destination using MREMAP_FIXED, also while validating that the source
// remains intact.
static void mremap_dontunmap_simple_fixed()
{
unsigned long num_pages = 5;
// Since we want to guarantee that we can remap to a point, we will
// create a mapping up front.
void *dest_mapping =
mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(dest_mapping == MAP_FAILED, "mmap");
memset(dest_mapping, 'X', num_pages * page_size);
void *source_mapping =
mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(source_mapping == MAP_FAILED, "mmap");
memset(source_mapping, 'a', num_pages * page_size);
void *remapped_mapping =
mremap(source_mapping, num_pages * page_size, num_pages * page_size,
MREMAP_FIXED | MREMAP_DONTUNMAP | MREMAP_MAYMOVE,
dest_mapping);
BUG_ON(remapped_mapping == MAP_FAILED, "mremap");
BUG_ON(remapped_mapping != dest_mapping,
"mremap should have placed the remapped mapping at dest_mapping");
// The dest mapping will have been unmap by mremap so we expect the Xs
// to be gone and replaced with a's.
BUG_ON(check_region_contains_byte
(dest_mapping, num_pages * page_size, 'a') != 0,
"pages did not migrate");
// And the source mapping will have had its ptes dropped.
BUG_ON(check_region_contains_byte
(source_mapping, num_pages * page_size, 0) != 0,
"source should have no ptes");
BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
"unable to unmap destination mapping");
BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
"unable to unmap source mapping");
}
// This test validates that we can MREMAP_DONTUNMAP for a portion of an
// existing mapping.
static void mremap_dontunmap_partial_mapping()
{
/*
* source mapping:
* --------------
* | aaaaaaaaaa |
* --------------
* to become:
* --------------
* | aaaaa00000 |
* --------------
* With the destination mapping containing 5 pages of As.
* ---------
* | aaaaa |
* ---------
*/
unsigned long num_pages = 10;
void *source_mapping =
mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(source_mapping == MAP_FAILED, "mmap");
memset(source_mapping, 'a', num_pages * page_size);
// We will grab the last 5 pages of the source and move them.
void *dest_mapping =
mremap(source_mapping + (5 * page_size), 5 * page_size,
5 * page_size,
MREMAP_DONTUNMAP | MREMAP_MAYMOVE, NULL);
BUG_ON(dest_mapping == MAP_FAILED, "mremap");
// We expect the first 5 pages of the source to contain a's and the
// final 5 pages to contain zeros.
BUG_ON(check_region_contains_byte(source_mapping, 5 * page_size, 'a') !=
0, "first 5 pages of source should have original pages");
BUG_ON(check_region_contains_byte
(source_mapping + (5 * page_size), 5 * page_size, 0) != 0,
"final 5 pages of source should have no ptes");
// Finally we expect the destination to have 5 pages worth of a's.
BUG_ON(check_region_contains_byte(dest_mapping, 5 * page_size, 'a') !=
0, "dest mapping should contain ptes from the source");
BUG_ON(munmap(dest_mapping, 5 * page_size) == -1,
"unable to unmap destination mapping");
BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
"unable to unmap source mapping");
}
// This test validates that we can remap over only a portion of a mapping.
static void mremap_dontunmap_partial_mapping_overwrite(void)
{
/*
* source mapping:
* ---------
* |aaaaa|
* ---------
* dest mapping initially:
* -----------
* |XXXXXXXXXX|
* ------------
* Source to become:
* ---------
* |00000|
* ---------
* With the destination mapping containing 5 pages of As.
* ------------
* |aaaaaXXXXX|
* ------------
*/
void *source_mapping =
mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(source_mapping == MAP_FAILED, "mmap");
memset(source_mapping, 'a', 5 * page_size);
void *dest_mapping =
mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(dest_mapping == MAP_FAILED, "mmap");
memset(dest_mapping, 'X', 10 * page_size);
// We will grab the last 5 pages of the source and move them.
void *remapped_mapping =
mremap(source_mapping, 5 * page_size,
5 * page_size,
MREMAP_DONTUNMAP | MREMAP_MAYMOVE | MREMAP_FIXED, dest_mapping);
BUG_ON(dest_mapping == MAP_FAILED, "mremap");
BUG_ON(dest_mapping != remapped_mapping, "expected to remap to dest_mapping");
BUG_ON(check_region_contains_byte(source_mapping, 5 * page_size, 0) !=
0, "first 5 pages of source should have no ptes");
// Finally we expect the destination to have 5 pages worth of a's.
BUG_ON(check_region_contains_byte(dest_mapping, 5 * page_size, 'a') != 0,
"dest mapping should contain ptes from the source");
// Finally the last 5 pages shouldn't have been touched.
BUG_ON(check_region_contains_byte(dest_mapping + (5 * page_size),
5 * page_size, 'X') != 0,
"dest mapping should have retained the last 5 pages");
BUG_ON(munmap(dest_mapping, 10 * page_size) == -1,
"unable to unmap destination mapping");
BUG_ON(munmap(source_mapping, 5 * page_size) == -1,
"unable to unmap source mapping");
}
int main(void)
{
page_size = sysconf(_SC_PAGE_SIZE);
// test for kernel support for MREMAP_DONTUNMAP skipping the test if
// not.
if (kernel_support_for_mremap_dontunmap() != 0) {
printf("No kernel support for MREMAP_DONTUNMAP\n");
return KSFT_SKIP;
}
// Keep a page sized buffer around for when we need it.
page_buffer =
mmap(NULL, page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
BUG_ON(page_buffer == MAP_FAILED, "unable to mmap a page.");
mremap_dontunmap_simple();
mremap_dontunmap_simple_fixed();
mremap_dontunmap_partial_mapping();
mremap_dontunmap_partial_mapping_overwrite();
BUG_ON(munmap(page_buffer, page_size) == -1,
"unable to unmap page buffer");
printf("OK\n");
return 0;
}

37
tools/testing/selftests/vm/run_vmtests
Ver arquivo

@@ -123,6 +123,28 @@ else
echo "[PASS]"
fi
echo "--------------------------------------------"
echo "running 'gup_benchmark -U' (normal/slow gup)"
echo "--------------------------------------------"
./gup_benchmark -U
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
echo "------------------------------------------"
echo "running gup_benchmark -b (pin_user_pages)"
echo "------------------------------------------"
./gup_benchmark -b
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
else
echo "[PASS]"
fi
echo "-------------------"
echo "running userfaultfd"
echo "-------------------"
@@ -270,4 +292,19 @@ else
exitcode=1
fi
echo "------------------------------------"
echo "running MREMAP_DONTUNMAP smoke test"
echo "------------------------------------"
./mremap_dontunmap
ret_val=$?
if [ $ret_val -eq 0 ]; then
echo "[PASS]"
elif [ $ret_val -eq $ksft_skip ]; then
echo "[SKIP]"
exitcode=$ksft_skip
else
echo "[FAIL]"
exitcode=1
fi
exit $exitcode

23
tools/testing/selftests/vm/write_hugetlb_memory.sh Arquivo normal
Ver arquivo

@@ -0,0 +1,23 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
set -e
size=$1
populate=$2
write=$3
cgroup=$4
path=$5
method=$6
private=$7
want_sleep=$8
reserve=$9
echo "Putting task in cgroup '$cgroup'"
echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs
echo "Method is $method"
set +e
./write_to_hugetlbfs -p "$path" -s "$size" "$write" "$populate" -m "$method" \
"$private" "$want_sleep" "$reserve"

242
tools/testing/selftests/vm/write_to_hugetlbfs.c Arquivo normal
Ver arquivo

@@ -0,0 +1,242 @@
// SPDX-License-Identifier: GPL-2.0
/*
* This program reserves and uses hugetlb memory, supporting a bunch of
* scenarios needed by the charged_reserved_hugetlb.sh test.
*/
#include <err.h>
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/shm.h>
#include <sys/stat.h>
#include <sys/mman.h>
/* Global definitions. */
enum method {
HUGETLBFS,
MMAP_MAP_HUGETLB,
SHM,
MAX_METHOD
};
/* Global variables. */
static const char *self;
static char *shmaddr;
static int shmid;
/*
* Show usage and exit.
*/
static void exit_usage(void)
{
printf("Usage: %s -p <path to hugetlbfs file> -s <size to map> "
"[-m <0=hugetlbfs | 1=mmap(MAP_HUGETLB)>] [-l] [-r] "
"[-o] [-w] [-n]\n",
self);
exit(EXIT_FAILURE);
}
void sig_handler(int signo)
{
printf("Received %d.\n", signo);
if (signo == SIGINT) {
printf("Deleting the memory\n");
if (shmdt((const void *)shmaddr) != 0) {
perror("Detach failure");
shmctl(shmid, IPC_RMID, NULL);
exit(4);
}
shmctl(shmid, IPC_RMID, NULL);
printf("Done deleting the memory\n");
}
exit(2);
}
int main(int argc, char **argv)
{
int fd = 0;
int key = 0;
int *ptr = NULL;
int c = 0;
int size = 0;
char path[256] = "";
enum method method = MAX_METHOD;
int want_sleep = 0, private = 0;
int populate = 0;
int write = 0;
int reserve = 1;
unsigned long i;
if (signal(SIGINT, sig_handler) == SIG_ERR)
err(1, "\ncan't catch SIGINT\n");
/* Parse command-line arguments. */
setvbuf(stdout, NULL, _IONBF, 0);
self = argv[0];
while ((c = getopt(argc, argv, "s:p:m:owlrn")) != -1) {
switch (c) {
case 's':
size = atoi(optarg);
break;
case 'p':
strncpy(path, optarg, sizeof(path));
break;
case 'm':
if (atoi(optarg) >= MAX_METHOD) {
errno = EINVAL;
perror("Invalid -m.");
exit_usage();
}
method = atoi(optarg);
break;
case 'o':
populate = 1;
break;
case 'w':
write = 1;
break;
case 'l':
want_sleep = 1;
break;
case 'r':
private
= 1;
break;
case 'n':
reserve = 0;
break;
default:
errno = EINVAL;
perror("Invalid arg");
exit_usage();
}
}
if (strncmp(path, "", sizeof(path)) != 0) {
printf("Writing to this path: %s\n", path);
} else {
errno = EINVAL;
perror("path not found");
exit_usage();
}
if (size != 0) {
printf("Writing this size: %d\n", size);
} else {
errno = EINVAL;
perror("size not found");
exit_usage();
}
if (!populate)
printf("Not populating.\n");
else
printf("Populating.\n");
if (!write)
printf("Not writing to memory.\n");
if (method == MAX_METHOD) {
errno = EINVAL;
perror("-m Invalid");
exit_usage();
} else
printf("Using method=%d\n", method);
if (!private)
printf("Shared mapping.\n");
else
printf("Private mapping.\n");
if (!reserve)
printf("NO_RESERVE mapping.\n");
else
printf("RESERVE mapping.\n");
switch (method) {
case HUGETLBFS:
printf("Allocating using HUGETLBFS.\n");
fd = open(path, O_CREAT | O_RDWR, 0777);
if (fd == -1)
err(1, "Failed to open file.");
ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
(private ? MAP_PRIVATE : MAP_SHARED) |
(populate ? MAP_POPULATE : 0) |
(reserve ? 0 : MAP_NORESERVE),
fd, 0);
if (ptr == MAP_FAILED) {
close(fd);
err(1, "Error mapping the file");
}
break;
case MMAP_MAP_HUGETLB:
printf("Allocating using MAP_HUGETLB.\n");
ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
(private ? (MAP_PRIVATE | MAP_ANONYMOUS) :
MAP_SHARED) |
MAP_HUGETLB | (populate ? MAP_POPULATE : 0) |
(reserve ? 0 : MAP_NORESERVE),
-1, 0);
if (ptr == MAP_FAILED)
err(1, "mmap");
printf("Returned address is %p\n", ptr);
break;
case SHM:
printf("Allocating using SHM.\n");
shmid = shmget(key, size,
SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W);
if (shmid < 0) {
shmid = shmget(++key, size,
SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W);
if (shmid < 0)
err(1, "shmget");
}
printf("shmid: 0x%x, shmget key:%d\n", shmid, key);
ptr = shmat(shmid, NULL, 0);
if (ptr == (int *)-1) {
perror("Shared memory attach failure");
shmctl(shmid, IPC_RMID, NULL);
exit(2);
}
printf("shmaddr: %p\n", ptr);
break;
default:
errno = EINVAL;
err(1, "Invalid method.");
}
if (write) {
printf("Writing to memory.\n");
memset(ptr, 1, size);
}
if (want_sleep) {
/* Signal to caller that we're done. */
printf("DONE\n");
/* Hold memory until external kill signal is delivered. */
while (1)
sleep(100);
}
if (method == HUGETLBFS)
close(fd);
return 0;
}