github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-11-07 06:17:02 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

cgroup: Fixes for v7.4

Browse Source 
- cgroup.kill did not kill a process whose thread group leader had exited
   while other threads still ran, nor those threads once moved to another
   cgroup, letting a process survive its container being killed.
 
 - A cgroup.procs write under favordynmods could migrate a newly forked
   process before fork linked it to its cgroup, corrupting cgroup task lists.
 
 - cpuset partition fixes for nested hierarchies: invalidation, revival,
   shrinking and switches between root and isolated could leak isolated CPUs,
   skip or miscompute the housekeeping check, or leave wrong effective CPUs.
 
   - A root partition can no longer be created under an isolated parent or
     stay valid under one, as disabling it could leave no housekeeping CPUs.
 
   - Enabling a partition failed when a grandchild held tasks, although the
     parent had none of its own.
 
   - Separately, an allocation racing with a cpuset.mems update could drop
     its mempolicy nodemask and land on the wrong node, and a memoryless node
     in cpuset.mems triggered a spurious "movable nodes only" warning.
 
   - Two no-functional-change cleanups of the effective CPU computation.
 -----BEGIN PGP SIGNATURE-----
 
 iIQEABYKACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCauD/Ow4cdGpAa2VybmVs
 Lm9yZwAKCRCxYfJx3gVYGUHZAQDs9j6gMDplJmgdPYo9OE+lxV+CbeyQcAiKmYgU
 UKkYWQD/dQqxs+SocRMl6uPMInFCd9tplbZgAhbAKsmRWUfyBwI=
 =flEV
 -----END PGP SIGNATURE-----

Merge tag 'cgroup-for-7.4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - cgroup.kill did not kill a process whose thread group leader had
   exited while other threads still ran, nor those threads once moved to
   another cgroup, letting a process survive its container being killed

 - A cgroup.procs write under favordynmods could migrate a newly forked
   process before fork linked it to its cgroup, corrupting cgroup task
   lists

 - cpuset partition fixes for nested hierarchies: invalidation, revival,
   shrinking and switches between root and isolated could leak isolated
   CPUs, skip or miscompute the housekeeping check, or leave wrong
   effective CPUs:

     - A root partition can no longer be created under an isolated
       parent or stay valid under one, as disabling it could leave no
       housekeeping CPUs

     - Enabling a partition failed when a grandchild held tasks,
       although the parent had none of its own

     - Separately, an allocation racing with a cpuset.mems update could
       drop its mempolicy nodemask and land on the wrong node, and a
       memoryless node in cpuset.mems triggered a spurious "movable
       nodes only" warning

     - Two no-functional-change cleanups of the effective CPU
       computation

* tag 'cgroup-for-7.4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (27 commits)
  cgroup/cpuset: Integrate compute_partition_effective_cpumask() into compute_effective_cpumask()
  cgroup/cpuset: Relocate compute_*effective_cpumask() and compute_effective_nodemask()
  cgroup/cpuset: Release invalid isolated CPUs with a shrunk root partition parent
  cgroup/cpuset: Release invalid isolated CPUs in compute_partition_effective_cpumask()
  cgroup/cpuset: Make sure compute_partition_effective_cpumask() is only called for valid partition
  cgroup/cpuset: Prevent recursive call of remote_cpus_update() via update_cpumasks_hier()
  selftests/cgroup: Check for a single range nohz_full CPUs before running test matrix
  cgroup/cpuset: Minor fixes to prstate_housekeeping_conflict()
  cgroup/cpuset: Fix incorrect effective_cpus bug in update_cpumasks_hier()
  cgroup/cpuset: Properly compute effective xcpus in update_parent_effective_cpumask()
  cgroup/cpuset: Find furthest isolated ancestor for invalidated isolated partition
  cgroup: don't kill migrated processes through their exiting threads
  cgroup/cpuset: check effective mems for a movable-only configuration
  cgroup/cpuset: Fix task checking when enabling a partition
  cgroup: serialize migrations of newly forked processes
  selftests/cgroup: test cgroup.kill with an exited thread group leader
  cgroup: fix cgroup.kill for exited thread group leader
  selftests/cgroup: Skip test_cpuset_prs.sh test if some required CPUs are offline
  selftests/cgroup: Add tests for nohz_full housekeeping check
  selftests/cgroup: Add tests for isolcpus housekeeping check
  ...
This commit is contained in:
Linus Torvalds 2026-10-29 07:35:19 -10:00
commit 2152c755f7
6 changed files with 828 additions and 334 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Documentation/admin-guide/cgroup-v2.rst
View File

@ -2778,7 +2778,9 @@ Cpuset Interface Files
be retained, but behaves more like a "member".
All possible state transitions among "member", "root" and
"isolated" are allowed.
"isolated" are allowed with the exception that a local child
"root" partition is not allowed to be created under an "isolated"
parent partition.
On read, the "cpuset.cpus.partition" file can show the following
values.

30
kernel/cgroup/cgroup.c
View File

@ -4303,7 +4303,7 @@ static void __cgroup_kill(struct cgroup *cgrp)
cgrp->kill_seq++;
spin_unlock_irq(&css_set_lock);
css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it);
css_task_iter_start(&cgrp->self, CSS_TASK_ITER_THREADED, &it);
while ((task = css_task_iter_next(&it))) {
/* Ignore kernel threads here. */
if (task->flags & PF_KTHREAD)
@ -6880,6 +6880,31 @@ static struct cgroup *cgroup_get_from_file(struct file *f)
return cgrp;
}
/*
* A new threadgroup gets its own cgroup_threadgroup_rwsem. Once its PID is
* visible, a cgroup.procs writer can find the child and lock that rwsem even
* though cgroup_post_fork() has not linked the child to its css_set yet.
*
* cgroup_can_fork() already holds the global read lock, which keeps
* cgroup_enable_per_threadgroup_rwsem stable. Lock the child's rwsem as a
* nested instance until cgroup_post_fork() finishes. Threads share their
* parent's signal_struct and are covered by the existing read lock.
*/
static void cgroup_fork_child_lock(struct task_struct *child)
{
if (cgroup_enable_per_threadgroup_rwsem &&
child->signal != current->signal)
down_read_nested(&child->signal->cgroup_threadgroup_rwsem,
SINGLE_DEPTH_NESTING);
}
static void cgroup_fork_child_unlock(struct task_struct *child)
{
if (cgroup_enable_per_threadgroup_rwsem &&
child->signal != current->signal)
up_read(&child->signal->cgroup_threadgroup_rwsem);
}
/**
* cgroup_css_set_fork - find or create a css_set for a child process
* @kargs: the arguments passed to create the child process
@ -7045,6 +7070,7 @@ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs)
goto out_revert;
} while_each_subsys_mask();
cgroup_fork_child_lock(child);
return 0;
out_revert:
@ -7079,6 +7105,7 @@ void cgroup_cancel_fork(struct task_struct *child,
if (ss->cancel_fork)
ss->cancel_fork(child, kargs->cset);
cgroup_fork_child_unlock(child);
cgroup_css_set_put_fork(kargs);
}
@ -7176,6 +7203,7 @@ void cgroup_post_fork(struct task_struct *child,
if (unlikely(kill))
do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID);
cgroup_fork_child_unlock(child);
cgroup_css_set_put_fork(kargs);
}

6
kernel/cgroup/cpuset-internal.h
View File

@ -35,6 +35,7 @@ enum prs_errcode {
PERR_HKEEPING,
PERR_ACCESS,
PERR_REMOTE,
PERR_ISOPARENT,
};
/* bits in struct cpuset flags field */
@ -160,6 +161,11 @@ struct cpuset {
*/
bool remote_partition;
/*
* Set to true when a remote partition is undergoing update.
*/
bool remote_partition_updating;
/*
* number of SCHED_DEADLINE tasks attached to this cpuset, so that we
* know when to rebuild associated root domain bandwidth information.

680
kernel/cgroup/cpuset.c
View File

File diff suppressed because it is too large Load Diff

284
tools/testing/selftests/cgroup/test_cpuset_prs.sh
View File

@ -67,6 +67,30 @@ then
echo Y > /sys/kernel/debug/sched/verbose
fi
cleanup()
{
online_cpus
cd $CGROUP2
rmdir A1/A2/A3 A1/A2 A1 B1 test/A1 test/B1 test > /dev/null 2>&1
rmdir rtest/p1/c11 rtest/p1/c12 rtest/p2/c21 \
rtest/p2/c22 rtest/p1 rtest/p2 rtest > /dev/null 2>&1
[[ -n "$SCHED_DEBUG" ]] &&
echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
}
online_cpus()
{
[[ -n "$OFFLINE_CPUS" ]] && {
for C in $OFFLINE_CPUS
do
write_cpu_online ${C}=1
done
}
}
# Clean up the cgroupfs directory if the test is aborted.
trap cleanup 0 2 3 6
cd $CGROUP2
echo +cpuset > cgroup.subtree_control
@ -85,39 +109,84 @@ echo "" > test/cpuset.cpus
[[ $RESULT -eq 0 ]] && skip_test "Child cgroups are using cpuset!"
#
# If isolated CPUs have been reserved at boot time (as shown in
# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8
# that will be used by this script for testing purpose. If not, some of
# the tests may fail incorrectly. Wait a bit and retry again just in case
# these isolated CPUs are leftover from previous run and have just been
# cleaned up earlier in this script.
# If nohz_full CPUs have been reserved at boot time, they should not include
# CPUs 0-7 as that may fail some of the test cases. On the other hand if the
# set of nohz_full CPUs includes all the CPUs except 0-7 in a single range
# <first>-<last>, we can run a special set of housekeeping CPUs exhaustion
# tests to see if the cpuset code will reject them.
#
# These pre-isolated CPUs should stay in an isolated state throughout the
FIRST_NOHZ_FULL_CPU=
LAST_NOHZ_FULL_CPU=
RUN_NOHZ_FULL_TESTS=
NOHZ_FULL_CPUS=
[[ -f /sys/devices/system/cpu/nohz_full ]] &&
NOHZ_FULL_CPUS=$(cat /sys/devices/system/cpu/nohz_full)
LAST_PRESENT_CPU=$(cat /sys/devices/system/cpu/present | sed -e "s/.*[,-]//")
[[ -n "$NOHZ_FULL_CPUS" ]] && {
FIRST_NOHZ_FULL_CPU=$(echo $NOHZ_FULL_CPUS | sed -e "s/[,-].*//")
LAST_NOHZ_FULL_CPU=$(echo $NOHZ_FULL_CPUS | sed -e "s/,.*//;s/.*[-]//")
echo "Boot nohz_full CPUs: $NOHZ_FULL_CPUS"
}
[[ -n "$FIRST_NOHZ_FULL_CPU" && "$FIRST_NOHZ_FULL_CPU" -le 7 ]] &&
skip_test "Boot NOHZ_FULL CPUs overlap CPUs to be tested!"
[[ -n "$FIRST_NOHZ_FULL_CPU" && "$FIRST_NOHZ_FULL_CPU" = 8 &&
"$LAST_NOHZ_FULL_CPU" = $LAST_PRESENT_CPU ]] && RUN_NOHZ_FULL_TESTS=1
#
# If isolated CPUs have been reserved at boot time (as shown in
# /sys/devices/system/cpu/isolated), these isolated CPUs should be outside of
# CPUs 0-8 that will be used by this script for testing purpose. If not, some
# of the tests may fail incorrectly.
#
# The current set of isolated CPUs (as shown in cpuset.cpus.isolated) should
# be the same as the boot value. If not, wait a bit and retry again just in
# case these isolated CPUs are leftover from previous run and have just been
# cleaned up earlier in this script. If they still don't match, we report an
# warning and skip the test.
#
# These boot isolated CPUs should stay in an isolated state throughout the
# testing process for now.
#
BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
[[ -n "$BOOT_ISOLCPUS" ]] && {
sleep 0.5
BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
}
if [[ -n "$BOOT_ISOLCPUS" ]]
then
[[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] &&
skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested"
echo "Pre-isolated CPUs: $BOOT_ISOLCPUS"
fi
BOOT_ISOLCPUS=$(cat /sys/devices/system/cpu/isolated)
CURRENT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
FIRST_ISOLCPUS=
TEST_ISOLCPUS=
cleanup()
{
online_cpus
cd $CGROUP2
rmdir A1/A2/A3 A1/A2 A1 B1 test/A1 test/B1 test > /dev/null 2>&1
rmdir rtest/p1/c11 rtest/p1/c12 rtest/p2/c21 \
rtest/p2/c22 rtest/p1 rtest/p2 rtest > /dev/null 2>&1
[[ -n "$SCHED_DEBUG" ]] &&
echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
[[ -n "$BOOT_ISOLCPUS" ]] && {
FIRST_ISOLCPUS=$(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//")
echo "Boot isolated CPUs: $BOOT_ISOLCPUS"
[[ $FIRST_ISOLCPUS -le 8 ]] &&
skip_test "Boot isolated CPUs overlap CPUs to be tested"
}
[[ "$BOOT_ISOLCPUS" != "$CURRENT_ISOLCPUS" ]] && {
sleep 0.5
CURRENT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
[[ "$BOOT_ISOLCPUS" != "$CURRENT_ISOLCPUS" ]] &&
skip_test "Current isolated CPUs ($CURRENT_ISOLCPUS) don't match boot isolated CPUs!"
}
#
# This test assumes that all the relevant CPUs being tested are online.
# If some of them are offline, some of the tests may fail. So we are going to
# skip running this test script if some of the required CPUs may be offline.
# The required CPUs include CPUs 0-7 and the first boot time isolated CPU if
# present. However the check below is not exhaustive and can be a false
# positive, but users should not run this test if some CPUs are offline.
#
ONLINE_CPUS=$(cat /sys/devices/system/cpu/online | sed -e "s/,.*//")
ONLINE_FIRST=$(echo $ONLINE_CPUS | sed -e "s/-.*//")
ONLINE_LAST=$(echo $ONLINE_CPUS | sed -e "s/.*-//")
if [[ -n "$FIRST_ISOLCPUS" ]]
then
LAST_REQUIRED_CPU=$FIRST_ISOLCPUS
else
LAST_REQUIRED_CPU=7
fi
[[ $ONLINE_FIRST != 0 || $ONLINE_LAST -lt $LAST_REQUIRED_CPU ]] &&
skip_test "Some of the required CPUs are offline or not present!"
# Pause in ms
pause()
{
@ -202,7 +271,7 @@ test_add_proc()
#
# ECPUs - effective CPUs of cpusets
# Pstate - partition root state
# ISOLCPUS - isolated CPUs (<icpus>[,<icpus2>])
# ISOLCPUS - isolated CPUs (<icpus>[,<icpus2>] or .)
#
# Note that if there are 2 fields in ISOLCPUS, the first one is for
# sched-debug matching which includes offline CPUs and single-CPU partitions
@ -278,6 +347,7 @@ TEST_MATRIX=(
" C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
" C4:X0-3 X1-3 X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
" C4:X0-3 X1-3 X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
" CX1-6 C1-4:P1 . C4-5 . C1-3 . . 0 A1:4-6|A2:1-3|B1:4-5 A2:P1"
# Nested remote/local partition tests
" C0-3 C1-3 C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \
@ -288,16 +358,19 @@ TEST_MATRIX=(
A1:P0|A2:P1|A3:P0|B1:P1"
" C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \
A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
" C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \
A1:P0|A2:P2|A3:P1 2-4|2-3"
" C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \
A1:P0|A2:P2|A3:P1 2"
" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
. . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \
A1:P0|A2:P-2|A3:P-1 ."
" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
. . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \
A1:P0|A2:P2|A3:P-1 2-4"
" C1-6:P1 C3-6:P1 C5-6:P1 . . P2 . . 0 A1:1-2|A2:3-6|A3:5-6 \
A1:P1|A2:P2|A3:P-1 3-6"
" C1-6:P2 C3-6:P2 C3-4:P2 . . C5-6 . . 0 A1:1-4|A2:5-6|A3:5-6 \
A1:P2|A2:P2|A3:P-2 1-6"
" C1-4:X2-4 C2-4:X3-4:P1 C3-4:X4:P2 \
. . X5 . . 0 A1:1-4|A2:2-4|A3:3-4 \
A1:P0|A2:P-1|A3:P-2 ."
" C1-5:X3-5:P2 C3-5:X4-5:P2 C4-5:X5:P2 \
. X1-4 . . . 0 A1:1-3|A2:4|A3:4 \
A1:P2|A2:P2|A3:P-2 1-4"
" C1-4:X2-4 C1-4:X3-4:P1 C3-4:X4:P2 \
. . . X1 . 0 A1:1-2|A2:3-4|A3:3-4 \
A1:P0|A2:P1|A3:P-2 ."
" CX1-3:P1 CX1-3 CX1-3 . . . P1 . 0 A1:1-3|A2:1-3|A3:1-3 \
A1:P1|A2:P0|A3:P-1"
@ -331,8 +404,8 @@ TEST_MATRIX=(
" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
. . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
# Local partition CPU change tests
" C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
" C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
" C0-5:P1 C4-5:P2 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P1|A2:P2 3-5"
" C0-5:P1 C4-5:P2 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P1|A2:P2 4-5"
# cpus_allowed/exclusive_cpus update tests
" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
@ -360,6 +433,10 @@ TEST_MATRIX=(
# cpuset.cpus is allowed, but those extra CPUs are ignored.
" C2-3:P1 C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1"
# A child cannot recover until its exclusive CPUs are available again.
" CX1-4:P1 CX3-4:P1 . . X1-2 . . . 0 A1:1-2|A2:1-2|XA2: A1:P1|A2:P-1"
" CX1-4:P1 CX3-4:P1 . . X1-2:X1-4 . . . 0 A1:1-2|A2:3-4|XA2:3-4 A1:P1|A2:P1"
# Taking away all CPUs from parent or itself if there are tasks
# will make the partition invalid.
" C2-3:P1 C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
@ -385,6 +462,9 @@ TEST_MATRIX=(
# Enabling partition with child cpusets is allowed
" C0-1 C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1"
# Tasks below a new partition belong to it, not to its parent.
" C1-2:P1 C1-2 C1-2:T . . P1 . . 0 A1:|A2:1-2|A3:1-2 A1:P1|A2:P1"
# A partition root with non-partition root parent is invalid| but it
# can be made valid if its parent becomes a partition root too.
" C0-1 C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2"
@ -430,6 +510,28 @@ TEST_MATRIX=(
# cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs
" C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3"
# Creation of root partition under an isolated partition is not allowed
" C1-3:P2 C2 . . . P1 . . 0 A1:1-3|A2:2 A1:P2|A2:P-1 1-3"
" C1-3:P2 C2 . . . P2 . . 0 A1:1,3|A2:2 A1:P2|A2:P2 1-3"
" C1-3:P2 C2:P2 . . . P1 . . 0 A1:1-3|A2:2 A1:P2|A2:P-1 1-3"
" C1-3:P2 C2:P1 . . . C2-3 . . 0 A1:1-3|A2:2-3 A1:P2|A2:P-1 1-3"
# A middle isolated parent shrunk below coverage: the released CPUs of
# an invalidated child stay isolated as a higher ancestor still covers them.
" CX0-4:P2 CX2-4:P2 CX3-4:P2 . . X2 . . 0 A1:0-1,3-4|A2:2|A3:2 \
A1:P2|A2:P2|A3:P-2 0-4"
# When an isolated partition child with root partition parent is invalidated,
# its effective xcpus will be removed from isolated_cpus.
" C1-4:P1 C3-4:P2 . . T:C3-4 . . . 0 A1:3-4|A2:3-4 A1:P1|A2:P-2 ."
# When a root partition parent with an isolated partition child is shrunk
# so that its effective xcpus is no longer a superset of its child effective
# xcpus, the invalid isolated CPUs should be removed from cpuset.cpus.isolated.
" C1-4:P1 C3-4:P2 . . T:C4-6 . . . 0 A1:5-6|A2:4 A1:P1|A2:P2 4"
" C1-4:P1 C1-2:P2 . . T:C4-6 . . . 0 A1:4-6|A2:4-6 A1:P1|A2:P-2 ."
#
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
# Failure cases:
@ -444,6 +546,57 @@ TEST_MATRIX=(
" C0-3 . . C4-5 X3-5 . . . 1 A1:0-3|B1:4-5"
)
# Test matrix with boot time isolated CPUs present for housekeeping check testing
ISOLCPUS_TEST_MATRIX=(
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
# A local isolated partition containing boot isolated CPU cannot be
# switched to root partition.
" C1-2,I:P2 . . . P1 . . . 0 A1:1-2,I A1:P-1 ."
# A remote isolated partition containing boot isolated CPU cannot be
# switched to root partition.
" X1-2,I CX1-2,I:P2 . . . P1 . . 0 A2:1-2,I A2:P-1 ."
# A local isolated partition with a boot isolated CPU distributed to a
# child isolated partition also cannot be switched to a root partition.
" C1-3,I:P2 C1,I:P2 . . P1 . . . 0 A1:1-3,I|A2:1,I A1:P-1|A2:P-2 ."
# A remote isolated partition with a boot isolated CPU distributed to a
# child isolated partition also cannot be switched to a root partition.
" X1-3,I C1-3,I:P2 C1,I:P2 . . P1 . . 0 A2:1-3,I|A3:1,I A2:P-1|A3:P-2 ."
# The cpumask of a local root partition cannot be changed to include a
# boot isolated CPU.
" C1-2:P1 . . . C2,I . . . 0 A1:2,I A1:P-1 ."
# The cpumask of a remote root partition cannot be changed to include a
# boot isolated CPU.
" CX1-2,I CX1-2:P1 . . . CX2,I . . 0 A1:1-2,I|A2:2,I A2:P-1 ."
# Passing an boot isolated CPU down to a child root partition will invalidate it
" C2-3,I:X2-3 CX2-3,I . . . P1 . . 0 A1:I|A2:2-3 A2:P1 ."
" C2-3,I:X2-3 CX2-3,I:P1 . . X2-3,I . . . 0 A1:2-3,I|A2:2-3,I A2:P-1 ."
# An invalidated root partition must stay invalid when cpus grows but
# effective xcpus still contains a boot isolated CPU.
" CX1,I:P1 . . . C1,2,I . . . 0 A1:1-2,I|XA1:1,I A1:P-1 ."
# Growing cpus.exclusive must not revive it either
" CX1-2,I:X1,I:P1 . . . X1,2,I . . . 0 A1:1-2,I|XA1:1-2,I A1:P-1 ."
)
# Test matrix to be run when boot time nohz_full CPUs cover all CPUs except CPUs 0-7
NOHZ_FULL_TEST_MATRIX=(
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
# Using all the nohz_full HK CPUs 0-7 in isolated partition is not allowed
" C0-7 . . . P2 . . . 0 A1:0-7 A1:P-2 ."
" C2-7:P2 . . . C0-4 . . . 0 A1:0-4 A1:P2 0-4"
" C1-7:P2 C5-7:P2 . . . . . C0:P2 0 A1:1-4|A2:5-7|B1:0
A1:P2|A2:P2|B1:P-2 1-7"
)
#
# Cpuset controller remote partition test matrix.
#
@ -496,8 +649,8 @@ REMOTE_TEST_MATRIX=(
p1:P1|c11:P1|c12:P-1"
# Narrowing cpuset.cpus to previously sibling-excluded CPUs should
# not return CPUs that were never actually owned.
" C1-4:P1 . C1-2:P1 C1-3:P2 . . \
. . . C3 . . p1:4|c11:1-2|c12:3 \
" C1-5:P1 . C1-2:P1 C1-3:P2 . . \
. . . C3 . . p1:4-5|c11:1-2|c12:3 \
p1:P1|c11:P1|c12:P2 3"
# Expanding cpuset.cpus to include a previously sibling-excluded CPU
# after the sibling has become a member should correctly request it.
@ -541,6 +694,27 @@ write_cpu_online()
pause 0.05
}
#
# Set the CPUS variable
# $1 - the passed in cpu parameter
#
# The special "I" CPU if present is being replaced by the first boot CPU
# and assigned to the "CPUS" variable when the TEST_ISOLCPUS flag is set.
# If not, the program will exit with an error.
#
set_cpus()
{
local cpus=$1
if [[ $(expr "$cpus" : ".*I") -gt 0 ]]
then
[[ -z "$TEST_ISOLCPUS" ]] &&
skip_test "Special 'I' CPU added to non-isolcpus testing matrix!"
CPUS=$(echo $cpus | sed -e "s/I/$FIRST_ISOLCPUS/")
else
CPUS=$cpus
fi
}
#
# Set controller state
# $1 - cgroup directory
@ -575,16 +749,16 @@ set_ctrl_state()
}
case $CMD in
X*)
CPUS=${CMD#?}
set_cpus ${CMD#?}
COMM="echo $CPUS > $XFILE"
eval $COMM $REDIRECT
;;
CX*)
CPUS=${CMD#??}
set_cpus ${CMD#??}
COMM="echo $CPUS > $CFILE; echo $CPUS > $XFILE"
eval $COMM $REDIRECT
;;
C*) CPUS=${CMD#?}
C*) set_cpus ${CMD#?}
COMM="echo $CPUS > $CFILE"
eval $COMM $REDIRECT
;;
@ -641,16 +815,6 @@ set_ctrl_state_noerr()
}
}
online_cpus()
{
[[ -n "$OFFLINE_CPUS" ]] && {
for C in $OFFLINE_CPUS
do
write_cpu_online ${C}=1
done
}
}
#
# Remove all the test cgroup directories
#
@ -978,8 +1142,11 @@ run_state_test()
I=0
eval CNT="\${#$TEST[@]}"
# Skip isolcpus specific test matrix if FIRST_ISOLCPUS not defined
[[ -n "$TEST_ISOLCPUS" && -z "$FIRST_ISOLCPUS" ]] && return
reset_cgroup_states
console_msg "Running state transition test ..."
console_msg "Running state transition test for $TEST ..."
while [[ $I -lt $CNT ]]
do
@ -998,7 +1165,7 @@ run_state_test()
NEW_A3=$7
NEW_B1=$8
RESULT=$9
ECPUS=${10}
ECPUS=$(echo ${10} | sed -e "s/I/${FIRST_ISOLCPUS}/g")
STATES=${11}
ICPUS=${12}
@ -1281,9 +1448,10 @@ test_inotify()
echo "" > cpuset.cpus
}
trap cleanup 0 2 3 6
run_state_test TEST_MATRIX
run_remote_state_test REMOTE_TEST_MATRIX
TEST_ISOLCPUS=1 run_state_test ISOLCPUS_TEST_MATRIX
[[ -n "$RUN_NOHZ_FULL_TESTS" ]] && run_state_test NOHZ_FULL_TEST_MATRIX
test_isolated
test_boot_isolated
test_inotify

158
tools/testing/selftests/cgroup/test_kill.c
View File

@ -2,10 +2,13 @@
#include <errno.h>
#include <linux/limits.h>
#include <sched.h>
#include <signal.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
@ -315,6 +318,159 @@ static int test_cgkill_clone_into_killed(const char *root)
return ret;
}
static int sleep_forever(void *arg)
{
for (;;)
pause();
return 0;
}
/*
* Start a thread and exit the main thread only, leaving behind a zombie
* thread group leader with a live thread.
*/
static int exit_leader_fn(const char *cgroup, void *arg)
{
const size_t stack_size = 64 * 1024;
char *stack = malloc(stack_size);
if (!stack)
return EXIT_FAILURE;
if (clone(sleep_forever, stack + stack_size,
CLONE_VM | CLONE_FS | CLONE_FILES | CLONE_SIGHAND |
CLONE_THREAD | CLONE_SYSVSEM, NULL) < 0)
return EXIT_FAILURE;
syscall(SYS_exit, 0);
return EXIT_FAILURE;
}
static int wait_for_zombie_leader(pid_t pid)
{
int i;
for (i = 0; i < 100; i++) {
if (!proc_read_strstr(pid, false, "stat", ") Z "))
return 0;
usleep(10000);
}
return -1;
}
/*
* Test that cgroup.kill kills a process whose thread group leader has
* already exited while its other threads are still running.
*/
static int test_cgkill_exited_leader(const char *root)
{
int ret = KSFT_FAIL;
char *cgroup = NULL;
pid_t pid = -ESRCH;
cgroup = cg_name(root, "cg_test_exited_leader");
if (!cgroup)
goto cleanup;
if (cg_create(cgroup))
goto cleanup;
pid = cg_run_nowait(cgroup, exit_leader_fn, NULL);
if (pid < 0)
goto cleanup;
if (wait_for_zombie_leader(pid))
goto cleanup;
if (cg_read_strcmp(cgroup, "cgroup.events", "populated 1\n"))
goto cleanup;
if (cg_write(cgroup, "cgroup.kill", "1"))
goto cleanup;
if (cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (pid > 0) {
kill(pid, SIGKILL);
wait_for_pid(pid);
}
if (cgroup)
cg_destroy(cgroup);
free(cgroup);
return ret;
}
/*
* Test that cgroup.kill kills the threads of a process that were migrated
* to the cgroup after their thread group leader had exited, and so are
* not listed in its cgroup.procs.
*/
static int test_cgkill_exited_leader_migrated(const char *root)
{
char *parent = NULL, *src = NULL, *dst = NULL;
int ret = KSFT_FAIL;
pid_t pid = -ESRCH;
parent = cg_name(root, "cg_test_exited_leader_migrated");
if (!parent)
goto cleanup;
src = cg_name(parent, "src");
if (!src)
goto cleanup;
dst = cg_name(parent, "dst");
if (!dst)
goto cleanup;
if (cg_create(parent) || cg_create(src) || cg_create(dst))
goto cleanup;
pid = cg_run_nowait(src, exit_leader_fn, NULL);
if (pid < 0)
goto cleanup;
if (wait_for_zombie_leader(pid))
goto cleanup;
/* The exiting leader stays behind, only the live thread is moved. */
if (cg_enter(dst, pid))
goto cleanup;
if (cg_read_strcmp(dst, "cgroup.events", "populated 1\n") ||
cg_read_strcmp(dst, "cgroup.procs", ""))
goto cleanup;
if (cg_write(dst, "cgroup.kill", "1"))
goto cleanup;
if (cg_read_strcmp_wait(dst, "cgroup.events", "populated 0\n"))
goto cleanup;
ret = KSFT_PASS;
cleanup:
if (pid > 0) {
kill(pid, SIGKILL);
wait_for_pid(pid);
}
if (dst)
cg_destroy(dst);
if (src)
cg_destroy(src);
if (parent)
cg_destroy(parent);
free(dst);
free(src);
free(parent);
return ret;
}
#define T(x) { x, #x }
struct cgkill_test {
int (*fn)(const char *root);
@ -324,6 +480,8 @@ struct cgkill_test {
T(test_cgkill_tree),
T(test_cgkill_forkbomb),
T(test_cgkill_clone_into_killed),
T(test_cgkill_exited_leader),
T(test_cgkill_exited_leader_migrated),
};
#undef T