There are a number of different reasons which can cause a partition to become invalid. A user seeing an invalid partition may not know exactly why. To help user to get a better understanding of the underlying reason, The cpuset.cpus.partition control file, when read, will now report the reason why a partition become invalid. When a partition does become invalid, reading the control file will show "root invalid (<reason>)" where <reason> is a string that describes why the partition is invalid.

Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 46 +++++++++++++++++++++++++++++++++++++++--- 1 file changed, 43 insertions(+), 3 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 7705950ad70b..5fec3c96465c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -78,6 +78,24 @@ struct fmeter { spinlock_t lock; /* guards read or write of above */ };

+/* + * Invalid partition error code + */ +enum prs_errcode { + PERR_NONE = 0, + PERR_INVCPUS, + PERR_NOCPUS, + PERR_PARENT, + PERR_HOTPLUG, +}; + +static const char * const perr_strings[] = { + [PERR_INVCPUS] = "Invalid change to cpuset.cpus", + [PERR_PARENT] = "Parent is no longer a partition root", + [PERR_NOCPUS] = "Parent unable to distribute cpu downstream", + [PERR_HOTPLUG] = "No cpu available due to hotplug", +}; + struct cpuset { struct cgroup_subsys_state css;

@@ -163,6 +181,9 @@ struct cpuset {

/* Handle for cpuset.cpus.partition */ struct cgroup_file partition_file; + + /* Invalid partiton error code, not lock protected */ + enum prs_errcode prs_err; };

/* @@ -272,8 +293,13 @@ static inline int is_partition_root(const struct cpuset *cs) static inline void notify_partition_change(struct cpuset *cs, int old_prs, int new_prs) { - if (old_prs != new_prs) - cgroup_file_notify(&cs->partition_file); + if (old_prs == new_prs) + return; + cgroup_file_notify(&cs->partition_file); + + /* Reset prs_err if not invalid */ + if (new_prs != PRS_ERROR) + WRITE_ONCE(cs->prs_err, PERR_NONE); }

static struct cpuset top_cpuset = { @@ -1243,6 +1269,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, cpu_active_mask)) part_error = true; cpumask_copy(tmp->addmask, parent->effective_cpus); + if ((READ_ONCE(cpuset->prs_err) == PERR_NONE) && part_error) + WRITE_ONCE(cpuset->prs_err, PERR_INVCPUS); } } else { /* @@ -1264,6 +1292,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, part_error = (is_partition_root(cpuset) && !parent->nr_subparts_cpus) || cpumask_equal(tmp->addmask, parent->effective_cpus); + if (is_partition_root(cpuset) && part_error) + WRITE_ONCE(cpuset->prs_err, PERR_NOCPUS); }

if (cmd == partcmd_update) { @@ -1427,6 +1457,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) * When parent is invalid, it has to be too. */ new_prs = PRS_ERROR; + WRITE_ONCE(cp->prs_err, PERR_PARENT); break; } } @@ -2551,6 +2582,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); + const char *err;

switch (cs->partition_root_state) { case PRS_ENABLED: @@ -2560,7 +2592,11 @@ static int sched_partition_show(struct seq_file *seq, void *v) seq_puts(seq, "member\n"); break; case PRS_ERROR: - seq_puts(seq, "root invalid\n"); + err = perr_strings[READ_ONCE(cs->prs_err)]; + if (err) + seq_printf(seq, "root invalid (%s)\n", err); + else + seq_puts(seq, "root invalid\n"); break; } return 0; @@ -3160,6 +3196,10 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; spin_unlock_irq(&callback_lock); + if (parent->partition_root_state == PRS_ERROR) + WRITE_ONCE(cs->prs_err, PERR_PARENT); + else + WRITE_ONCE(cs->prs_err, PERR_HOTPLUG); notify_partition_change(cs, old_prs, PRS_ERROR); } cpuset_force_rebuild();

Currently, a parent partition cannot distribute all its CPUs to child partitions with no CPUs left. However in some use cases, a management application may want to create a parent partition as a management unit with no task associated with it and has all its CPUs distributed to various child partitions dynamically according to their needs. Leaving a cpu in the parent partition in such a case is now a waste.

To accommodate such use cases, a parent partition can now have all its CPUs distributed to its child partitions with 0 effective cpu left as long as it is not the top cpuset and it has no task at the time the child partition is being created. A terminal partition with no child partition underlying it, however, cannot have 0 effective cpu which will make the partition invalid.

Once an empty parent partition is formed, no new task can be moved into it.

Signed-off-by: Waiman Long longman@redhat.com --- kernel/cgroup/cpuset.c | 96 ++++++++++++++++++++++++++++++------------ 1 file changed, 69 insertions(+), 27 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d7b3eb024b84..73eff47a38de 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -305,6 +305,21 @@ static inline void notify_partition_change(struct cpuset *cs, WRITE_ONCE(cs->prs_err, PERR_NONE); }

+static inline int cpuset_has_tasks(const struct cpuset *cs) +{ + return cs->css.cgroup->nr_populated_csets; +} + +/* + * A empty partition (one with no effective cpu) is valid if it has no + * associated task and all its cpus have been distributed out to child + * partitions. + */ +static inline bool valid_empty_partition(const struct cpuset *cs) +{ + return !cpuset_has_tasks(cs) && cs->nr_subparts_cpus; +} + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -1211,22 +1226,32 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, if ((cmd == partcmd_enable) && css_has_online_children(&cpuset->css)) return -EBUSY;

- /* - * Enabling partition root is not allowed if not all the CPUs - * can be granted from parent's effective_cpus or at least one - * CPU will be left after that. - */ - if ((cmd == partcmd_enable) && - (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || - cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) - return -EINVAL; - /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { + bool parent_is_top_cpuset = !parent_cs(parent); + bool no_cpu_in_parent = cpumask_equal(cpuset->cpus_allowed, + parent->effective_cpus); + /* + * Enabling partition root is not allowed if not all the CPUs + * can be granted from parent's effective_cpus. If the parent + * is the top cpuset, at least one CPU must be left after that. + */ + if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || + (parent_is_top_cpuset && no_cpu_in_parent)) + return -EINVAL; + + /* + * A non-top parent can be left with no CPU as long as there + * is no task directly associated with the parent. For such + * a parent, no new task can be moved into it. + */ + if (no_cpu_in_parent && cpuset_has_tasks(parent)) + return -EINVAL; + cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { @@ -1257,9 +1282,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->subparts_cpus); /* * Make partition invalid if parent's effective_cpus could - * become empty. + * become empty and there are tasks in the parent. */ - if (adding && + if (adding && cpuset_has_tasks(parent) && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) part_error = true; @@ -1294,7 +1319,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, parent->effective_cpus); part_error = (is_partition_root(cpuset) && !parent->nr_subparts_cpus) || - cpumask_equal(tmp->addmask, parent->effective_cpus); + (cpumask_equal(tmp->addmask, parent->effective_cpus) && + cpuset_has_tasks(parent)); + if (is_partition_root(cpuset) && part_error) WRITE_ONCE(cpuset->prs_err, PERR_NOCPUS); } @@ -1397,9 +1424,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)

/* * If it becomes empty, inherit the effective mask of the - * parent, which is guaranteed to have some CPUs. + * parent, which is guaranteed to have some CPUs unless + * it is a partition root that has explicitly distributed + * out all its CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { + if (is_partition_root(cp) && + cpumask_equal(cp->cpus_allowed, cp->subparts_cpus)) + goto update_parent_subparts; + cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; @@ -1421,6 +1454,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) continue; }

+update_parent_subparts: /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call @@ -1497,12 +1531,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); - WARN_ON_ONCE(cpumask_empty(cp->effective_cpus)); }

- if (new_prs != old_prs) - cp->partition_root_state = new_prs; - + cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs, new_prs);

@@ -2254,6 +2285,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock;

+ /* + * On default hierarchy, task cannot be moved to a cpuset with empty + * effective cpus. + */ + if (is_in_v2_mode() && cpumask_empty(cs->effective_cpus)) + goto out_unlock; + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) @@ -3130,7 +3168,8 @@ hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { - if (cpumask_empty(new_cpus)) + /* A partition root is allowed to have empty effective cpus */ + if (cpumask_empty(new_cpus) && !is_partition_root(cs)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; @@ -3199,22 +3238,25 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)

/* * In the unlikely event that a partition root has empty - * effective_cpus, we will have to force any child partitions, - * if present, to become invalid by setting nr_subparts_cpus to 0 - * without causing itself to become invalid. + * effective_cpus with tasks, we will have to force any child + * partitions, if present, to become invalid by setting + * nr_subparts_cpus to 0 without causing itself to become invalid. */ - if (is_partition_root(cs) && cs->nr_subparts_cpus && - cpumask_empty(&new_cpus)) { + if (is_partition_root(cs) && cpumask_empty(&new_cpus) && + !valid_empty_partition(cs)) { cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); compute_effective_cpumask(&new_cpus, cs, parent); }

/* - * If empty effective_cpus or zero nr_subparts_cpus or its parent - * becomes erroneous, we have to transition it to the erroneous state. + * Force the partition to become invalid if either one of + * the following conditions hold: + * 1) empty effective cpus but not valid empty partition. + * 2) parent is invalid or doesn't grant any cpus to child partitions. */ - if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || + if (is_partition_root(cs) && + ((cpumask_empty(&new_cpus) && !valid_empty_partition(cs)) || (parent->partition_root_state == PRS_ERROR) || !parent->nr_subparts_cpus)) { int old_prs;

Add a test script test_cpuset_prs.sh with a helper program wait_inotify for exercising the cpuset v2 partition root state code.

Signed-off-by: Waiman Long longman@redhat.com --- tools/testing/selftests/cgroup/Makefile | 5 +- .../selftests/cgroup/test_cpuset_prs.sh | 663 ++++++++++++++++++ tools/testing/selftests/cgroup/wait_inotify.c | 86 +++ 3 files changed, 752 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/cgroup/test_cpuset_prs.sh create mode 100644 tools/testing/selftests/cgroup/wait_inotify.c

diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 59e222460581..3f1fd3f93f41 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -Wall -pthread

-all: +all: ${HELPER_PROGS}

TEST_FILES := with_stress.sh -TEST_PROGS := test_stress.sh +TEST_PROGS := test_stress.sh test_cpuset_prs.sh +TEST_GEN_FILES := wait_inotify TEST_GEN_PROGS = test_memcontrol TEST_GEN_PROGS += test_kmem TEST_GEN_PROGS += test_core diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh new file mode 100755 index 000000000000..5a8fba05cbfb --- /dev/null +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -0,0 +1,663 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test for cpuset v2 partition root state (PRS) +# +# The sched verbose flag is set, if available, so that the console log +# can be examined for the correct setting of scheduling domain. +# + +skip_test() { + echo "$1" + echo "Test SKIPPED" + exit 0 +} + +[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" + +# Set sched verbose flag, if available +[[ -d /sys/kernel/debug/sched ]] && echo Y > /sys/kernel/debug/sched/verbose + +# Get wait_inotify location +WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify + +# Find cgroup v2 mount point +CGROUP2=$(mount -t cgroup2 | head -1 | awk -e '{print $3}') +[[ -n "$CGROUP2" ]] || skip_test "Cgroup v2 mount point not found!" + +CPUS=$(lscpu | grep "^CPU(s)" | sed -e "s/.*:[[:space:]]*//") +[[ $CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!" + +# Set verbose flag and delay factor +PROG=$1 +VERBOSE= +DELAY_FACTOR=1 +while [[ "$1" = -* ]] +do + case "$1" in + -v) VERBOSE=1 + break + ;; + -d) DELAY_FACTOR=$2 + shift + break + ;; + *) echo "Usage: $PROG [-v] [-d <delay-factor>" + exit + ;; + esac + shift +done + +cd $CGROUP2 +echo +cpuset > cgroup.subtree_control +[[ -d test ]] || mkdir test +cd test + +# Pause in ms +pause() +{ + DELAY=$1 + LOOP=0 + while [[ $LOOP -lt $DELAY_FACTOR ]] + do + sleep $DELAY + ((LOOP++)) + done + return 0 +} + +console_msg() +{ + MSG=$1 + echo "$MSG" + echo "" > /dev/console + echo "$MSG" > /dev/console + pause 0.01 +} + +test_partition() +{ + EXPECTED_VAL=$1 + echo $EXPECTED_VAL > cpuset.cpus.partition + [[ $? -eq 0 ]] || exit 1 + ACTUAL_VAL=$(cat cpuset.cpus.partition) + [[ $ACTUAL_VAL != $EXPECTED_VAL ]] && { + echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $EXPECTED_VAL" + echo "Test FAILED" + exit 1 + } +} + +test_effective_cpus() +{ + EXPECTED_VAL=$1 + ACTUAL_VAL=$(cat cpuset.cpus.effective) + [[ "$ACTUAL_VAL" != "$EXPECTED_VAL" ]] && { + echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$EXPECTED_VAL'" + echo "Test FAILED" + exit 1 + } +} + +# Adding current process to cgroup.procs as a test +test_add_proc() +{ + OUTSTR="$1" + ERRMSG=$((echo $$ > cgroup.procs) |& cat) + echo $ERRMSG | grep -q "$OUTSTR" + [[ $? -ne 0 ]] && { + echo "cgroup.procs: expect '$OUTSTR', got '$ERRMSG'" + echo "Test FAILED" + exit 1 + } + echo $$ > $CGROUP2/cgroup.procs # Move out the task +} + +# +# Testing the new "isolated" partition root type +# +test_isolated() +{ + echo 2-3 > cpuset.cpus + TYPE=$(cat cpuset.cpus.partition) + [[ $TYPE = member ]] || echo member > cpuset.cpus.partition + + console_msg "Change from member to root" + test_partition root + + console_msg "Change from root to isolated" + test_partition isolated + + console_msg "Change from isolated to member" + test_partition member + + console_msg "Change from member to isolated" + test_partition isolated + + console_msg "Change from isolated to root" + test_partition root + + console_msg "Change from root to member" + test_partition member + + # + # Testing partition root with no cpu + # + console_msg "Distribute all cpus to child partition" + echo +cpuset > cgroup.subtree_control + test_partition root + + mkdir A1 + cd A1 + echo 2-3 > cpuset.cpus + test_partition root + test_effective_cpus 2-3 + cd .. + test_effective_cpus "" + + console_msg "Moving task to partition test" + test_add_proc "No space left" + cd A1 + test_add_proc "" + cd .. + + console_msg "Shrink and expand child partition" + cd A1 + echo 2 > cpuset.cpus + cd .. + test_effective_cpus 3 + cd A1 + echo 2-3 > cpuset.cpus + cd .. + test_effective_cpus "" + + # Cleaning up + console_msg "Cleaning up" + echo $$ > $CGROUP2/cgroup.procs + [[ -d A1 ]] && rmdir A1 +} + +# +# Cpuset controller state transition test matrix. +# +# Cgroup test hierarchy +# +# test -- A1 -- A2 -- A3 +# - B1 +# +# P<v> = set cpus.partition (0:member, 1:root, 2:isolated, -1:root invalid) +# C<l> = add cpu-list +# S<p> = use prefix in subtree_control +# T = put a task into cgroup +# O<c>-<v> = Write <v> to CPU online file of <c> +# +SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" +TEST_MATRIX=( + # test old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + " S+ C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1" + " S+ C0-1 . . C2-3 P1 . . . 0 " + " S+ C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 " + " S+ C0-1 . . C2-3 P1:S+ C1:P1 . . 0 " + " S+ C0-1:S+ . . C2-3 . . . P1 0 " + " S+ C0-1:P1 . . C2-3 S+ C1 . . 0 " + " S+ C0-1:P1 . . C2-3 S+ C1:P1 . . 0 " + " S+ C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 " + " S+ C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5" + " S+ C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5" + " S+ C0-1 . . C2-3:P1 . . . C2 0 " + " S+ C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5" + " S+ C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1,A2:2-3" + " S+ C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1,A2:2-3" + " S+ C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3,A2:3 A1:P1,A2:P0" + " S+ C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4,A2:2" + " S+ C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:,B1:0-2 A1:P1,A2:P1" + " S+ $SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + + # CPU offlining cases: + " S+ C0-1 . . C2-3 S+ C4-5 . O2-0 0 A1:0-1,B1:3" + " S+ C0-3:P1:S+ C2-3:P1 . . O2-0 . . . 0 A1:0-1,A2:3" + " S+ C0-3:P1:S+ C2-3:P1 . . O2-0 O2-1 . . 0 A1:0-1,A2:2-3" + " S+ C0-3:P1:S+ C2-3:P1 . . O1-0 . . . 0 A1:0,A2:2-3" + " S+ C0-3:P1:S+ C2-3:P1 . . O1-0 O1-1 . . 0 A1:0-1,A2:2-3" + " S+ C2-3:P1:S+ C3:P1 . . O3-0 O3-1 . . 0 A1:2,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P2 . . O3-0 O3-1 . . 0 A1:2,A2:3 A1:P1,A2:P2" + " S+ C2-3:P1:S+ C3:P1 . . O2-0 O2-1 . . 0 A1:2,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P2 . . O2-0 O2-1 . . 0 A1:2,A2:3 A1:P1,A2:P2" + " S+ C2-3:P1:S+ C3:P1 . . O2-0 . . . 0 A1:,A2:3 A1:P1,A2:P1" + " S+ C2-3:P1:S+ C3:P1 . . O3-0 . . . 0 A1:2,A2:2 A1:P1,A2:P-1" + " S+ C2-3:P1:S+ C3:P1 . . T:O2-0 . . . 0 A1:3,A2:3 A1:P1,A2:P-1" + " S+ $SETUP_A123_PARTITIONS . O1-0 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . O2-0 . . . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . O3-0 . . . 0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . . T:O2-0 . . 0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . . . T:O3-0 . 0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 O1-1 . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . . T:O2-0 O2-1 . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . . . T:O3-0 O3-1 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 O2-0 O1-1 . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1" + " S+ $SETUP_A123_PARTITIONS . T:O1-0 O2-0 O2-1 . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" + + # test old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + # + # Incorrect change to cpuset.cpus invalidates partition root + # + # Adding CPUs to partition root that are not in parent's + # cpuset.cpus.effective makes it invalid. + " S+ C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1" + + # Taking away all CPUs from parent or itself if there are tasks + # will make the partition invalid. + " S+ C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1" + " S+ $SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" + " S+ $SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" + + # Changing a partition root member invalidates child partitions + " S+ C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3,A2:3 A1:P0,A2:P-1" + " S+ $SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1" + + # test old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate + # ---- ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ + # Failure cases: + + # To become a partition root, cpuset.cpus must be a subset of + # parent's cpuset.cpus.effective. + " S+ C0-1 . . C2-3 S+ C4-5:P1 . . 1 " + + # A cpuset cannot become a partition root if it has child cpusets + # with non-empty cpuset.cpus. + " S+ C0-1:S+ C1 . C2-3 P1 . . . 1 " + + # Any change to cpuset.cpus of a partition root must be exclusive. + " S+ C0-1:P1 . . C2-3 C0-2 . . . 1 " + " S+ C0-1 . . C2-3:P1 . . . C1 1 " + " S+ C2-3:P1:S+ C2:P1 . C1 C1-3 . . . 1 " + + # Deletion of CPUs distributed to child partition root is not allowed. + " S+ C0-1:P1:S+ C1 . C2-3 C4-5 . . . 1 " + " S+ C0-3:P1:S+ C2-3:P1 . . C0-2 . . . 1 " + + # A task cannot be added to a non-terminal partition with no cpu + " S+ C2-3:P1:S+ C3:P1 . . O2-0:T . . . 1 A1:,A2:3 A1:P1,A2:P1" +) + +# +# Write to the cpu online file +# $1 - <c>-<v> where <c> = cpu number, <v> value to be written +# +write_cpu_online() +{ + CPU=${1%-*} + VAL=${1#*-} + CPUFILE=//sys/devices/system/cpu/cpu${CPU}/online + if [[ $VAL -eq 0 ]] + then + OFFLINE_CPUS="$OFFLINE_CPUS $CPU" + else + [[ -n "$OFFLINE_CPUS" ]] && { + OFFLINE_CPUS=$(echo $CPU $CPU $OFFLINE_CPUS | fmt -1 |\ + sort | uniq -u) + } + fi + echo $VAL > $CPUFILE + pause 0.01 +} + +# +# Set controller state +# $1 - cgroup directory +# $2 - state +# $3 - showerr +# +# The presence of ":" in state means transition from one to the next. +# +set_ctrl_state() +{ + TMPMSG=/tmp/.msg_$$ + CGRP=$1 + STATE=$2 + SHOWERR=${3}${VERBOSE} + CTRL=${CTRL:=$CONTROLLER} + HASERR=0 + REDIRECT="2> $TMPMSG" + [[ -z "$STATE" || "$STATE" = '.' ]] && return 0 + + rm -f $TMPMSG + for CMD in $(echo $STATE | sed -e "s/:/ /g") + do + TFILE=$CGRP/cgroup.procs + SFILE=$CGRP/cgroup.subtree_control + PFILE=$CGRP/cpuset.cpus.partition + CFILE=$CGRP/cpuset.cpus + S=$(expr substr $CMD 1 1) + if [[ $S = S ]] + then + PREFIX=${CMD#?} + COMM="echo ${PREFIX}${CTRL} > $SFILE" + eval $COMM $REDIRECT + elif [[ $S = C ]] + then + CPUS=${CMD#?} + COMM="echo $CPUS > $CFILE" + eval $COMM $REDIRECT + elif [[ $S = P ]] + then + VAL=${CMD#?} + case $VAL in + 0) VAL=member + ;; + 1) VAL=root + ;; + 2) VAL=isolated + ;; + *) + echo "Invalid partiton state - $VAL" + exit 1 + ;; + esac + COMM="echo $VAL > $PFILE" + eval $COMM $REDIRECT + elif [[ $S = O ]] + then + VAL=${CMD#?} + write_cpu_online $VAL + elif [[ $S = T ]] + then + COMM="echo 0 > $TFILE" + eval $COMM $REDIRECT + fi + RET=$? + [[ $RET -ne 0 ]] && { + [[ -n "$SHOWERR" ]] && { + echo "$COMM" + cat $TMPMSG + } + HASERR=1 + } + pause 0.01 + rm -f $TMPMSG + done + return $HASERR +} + +set_ctrl_state_noerr() +{ + CGRP=$1 + STATE=$2 + [[ -d $CGRP ]] || mkdir $CGRP + set_ctrl_state $CGRP $STATE 1 + [[ $? -ne 0 ]] && { + echo "ERROR: Failed to set $2 to cgroup $1!" + exit 1 + } +} + +online_cpus() +{ + [[ -n "OFFLINE_CPUS" ]] && { + for C in $OFFLINE_CPUS + do + write_cpu_online ${C}-1 + done + } +} + +# +# Return 1 if the list of effective cpus isn't the same as the initial list. +# +reset_cgroup_states() +{ + echo 0 > $CGROUP2/cgroup.procs + online_cpus + rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1 + set_ctrl_state . S- + pause 0.01 +} + +dump_states() +{ + for DIR in A1 A1/A2 A1/A2/A3 B1 + do + ECPUS=$DIR/cpuset.cpus.effective + PRS=$DIR/cpuset.cpus.partition + [[ -e $ECPUS ]] && echo "$ECPUS: $(cat $ECPUS)" + [[ -e $PRS ]] && echo "$PRS: $(cat $PRS)" + done +} + +# +# Check effective cpus +# $1 - check string, format: <cgroup>:<cpu-list>[,<cgroup>:<cpu-list>]* +# +check_effective_cpus() +{ + CHK_STR=$1 + for CHK in $(echo $CHK_STR | sed -e "s/,/ /g") + do + set -- $(echo $CHK | sed -e "s/:/ /g") + CGRP=$1 + CPUS=$2 + [[ $CGRP = A2 ]] && CGRP=A1/A2 + [[ $CGRP = A3 ]] && CGRP=A1/A2/A3 + FILE=$CGRP/cpuset.cpus.effective + [[ -e $FILE ]] || return 1 + [[ $CPUS = $(cat $FILE) ]] || return 1 + done +} + +# +# Check cgroup states +# $1 - check string, format: <cgroup>:<state>[,<cgroup>:<state>]* +# +check_cgroup_states() +{ + CHK_STR=$1 + for CHK in $(echo $CHK_STR | sed -e "s/,/ /g") + do + set -- $(echo $CHK | sed -e "s/:/ /g") + CGRP=$1 + STATE=$2 + FILE= + EVAL=$(expr substr $STATE 2 2) + [[ $CGRP = A2 ]] && CGRP=A1/A2 + [[ $CGRP = A3 ]] && CGRP=A1/A2/A3 + + case $STATE in + P*) FILE=$CGRP/cpuset.cpus.partition + ;; + *) echo "Unknown state: $STATE!" + exit 1 + ;; + esac + VAL=$(cat $FILE) + + case "$VAL" in + member) VAL=0 + ;; + root) VAL=1 + ;; + isolated) + VAL=2 + ;; + "root invalid"*) + VAL=-1 + ;; + esac + [[ $EVAL != $VAL ]] && return 1 + done + return 0 +} + +# +# Run cpuset state transition test +# $1 - test matrix name +# +# This test is somewhat fragile as delays (sleep x) are added in various +# places to make sure state changes are fully propagated before the next +# action. These delays may need to be adjusted if running in a slower machine. +# +run_state_test() +{ + TEST=$1 + CONTROLLER=cpuset + CPULIST=0-6 + I=0 + eval CNT="${#$TEST[@]}" + + reset_cgroup_states + echo $CPULIST > cpuset.cpus + echo root > cpuset.cpus.partition + console_msg "Running state transition test ..." + + while [[ $I -lt $CNT ]] + do + echo "Running test $I ..." > /dev/console + eval set -- "${$TEST[$I]}" + ROOT=$1 + OLD_A1=$2 + OLD_A2=$3 + OLD_A3=$4 + OLD_B1=$5 + NEW_A1=$6 + NEW_A2=$7 + NEW_A3=$8 + NEW_B1=$9 + RESULT=${10} + ECPUS=${11} + STATES=${12} + + set_ctrl_state_noerr . $ROOT + set_ctrl_state_noerr A1 $OLD_A1 + set_ctrl_state_noerr A1/A2 $OLD_A2 + set_ctrl_state_noerr A1/A2/A3 $OLD_A3 + set_ctrl_state_noerr B1 $OLD_B1 + RETVAL=0 + set_ctrl_state A1 $NEW_A1; ((RETVAL += $?)) + set_ctrl_state A1/A2 $NEW_A2; ((RETVAL += $?)) + set_ctrl_state A1/A2/A3 $NEW_A3; ((RETVAL += $?)) + set_ctrl_state B1 $NEW_B1; ((RETVAL += $?)) + + [[ $RETVAL -ne $RESULT ]] && { + echo "Test $TEST[$I] failed result check!" + eval echo "${$TEST[$I]}" + dump_states + online_cpus + exit 1 + } + + [[ -n "$ECPUS" && "$ECPUS" != . ]] && { + check_effective_cpus $ECPUS + [[ $? -ne 0 ]] && { + echo "Test $TEST[$I] failed effective CPU check!" + eval echo "${$TEST[$I]}" + echo + dump_states + online_cpus + exit 1 + } + } + + [[ -n "$STATES" ]] && { + check_cgroup_states $STATES + [[ $? -ne 0 ]] && { + echo "FAILED: Test $TEST[$I] failed states check!" + eval echo "${$TEST[$I]}" + echo + dump_states + online_cpus + exit 1 + } + } + + reset_cgroup_states + # + # Check to see if effective cpu list changes + # + pause 0.05 + NEWLIST=$(cat cpuset.cpus.effective) + [[ $NEWLIST != $CPULIST ]] && { + echo "Effective cpus changed to $NEWLIST after test $I!" + exit 1 + } + [[ -n "$VERBOSE" ]] && echo "Test $I done." + ((I++)) + done + echo "All $I tests of $TEST PASSED." + + echo member > cpuset.cpus.partition +} + +# +# Wait for inotify event for the given file and read it +# $1: cgroup file to wait for +# $2: file to store the read result +# +wait_inotify() +{ + CGROUP_FILE=$1 + OUTPUT_FILE=$2 + + $WAIT_INOTIFY $CGROUP_FILE + cat $CGROUP_FILE > $OUTPUT_FILE +} + +# +# Test if inotify events are properly generated when going into and out of +# invalid partition state. +# +test_inotify() +{ + ERR=0 + PRS=/tmp/.prs_$$ + [[ -f $WAIT_INOTIFY ]] || { + echo "wait_inotify not found, inotify test SKIPPED." + return + } + + pause 0.01 + echo 1 > cpuset.cpus + echo 0 > cgroup.procs + echo root > cpuset.cpus.partition + pause 0.01 + rm -f $PRS + wait_inotify $PWD/cpuset.cpus.partition $PRS & + pause 0.01 + set_ctrl_state . "O1-0" + pause 0.01 + check_cgroup_states ".:P-1" + if [[ $? -ne 0 ]] + then + echo "FAILED: Inotify test - partition not invalid" + ERR=1 + elif [[ ! -f $PRS ]] + then + echo "FAILED: Inotify test - event not generated" + ERR=1 + kill %1 + elif [[ $(cat $PRS) != "root invalid"* ]] + then + echo "FAILED: Inotify test - incorrect state" + cat $PRS + ERR=1 + fi + online_cpus + echo member > cpuset.cpus.partition + echo 0 > ../cgroup.procs + if [[ $ERR -ne 0 ]] + then + exit 1 + else + echo "Inotify test PASSED" + fi +} + +run_state_test TEST_MATRIX +test_isolated +test_inotify +echo "All tests PASSED." +cd .. +rmdir test diff --git a/tools/testing/selftests/cgroup/wait_inotify.c b/tools/testing/selftests/cgroup/wait_inotify.c new file mode 100644 index 000000000000..d0758881f6bb --- /dev/null +++ b/tools/testing/selftests/cgroup/wait_inotify.c @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Wait until an inotify event on the given cgroup file. + */ +#include <linux/limits.h> +#include <sys/inotify.h> +#include <sys/mman.h> +#include <sys/ptrace.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +const char usage[] = "Usage: %s [-v] <cgroup_file>\n"; +static char *file; +static int verbose; + +static inline void fail_message(char *msg) +{ + fprintf(stderr, msg, file); + exit(1); +} + +int main(int argc, char *argv[]) +{ + char *cmd = argv[0]; + int c, fd; + struct pollfd fds = { .events = POLLIN, }; + + while ((c = getopt(argc, argv, "v")) != -1) { + switch (c) { + case 'v': + verbose++; + break; + } + argv++, argc--; + } + + if (argc != 2) { + fprintf(stderr, usage, cmd); + return -1; + } + file = argv[1]; + fd = open(file, O_RDONLY); + if (fd < 0) + fail_message("Cgroup file %s not found!\n"); + close(fd); + + fd = inotify_init(); + if (fd < 0) + fail_message("inotify_init() fails on %s!\n"); + if (inotify_add_watch(fd, file, IN_MODIFY) < 0) + fail_message("inotify_add_watch() fails on %s!\n"); + fds.fd = fd; + + /* + * poll waiting loop + */ + for (;;) { + int ret = poll(&fds, 1, 10000); + if (ret < 0) { + if (errno == EINTR) + continue; + perror("poll"); + exit(1); + } + if ((ret > 0) && (fds.revents & POLLIN)) + break; + } + if (verbose) { + struct inotify_event events[10]; + long len; + + usleep(1000); + len = read(fd, events, sizeof(events)); + printf("Number of events read = %ld\n", + len/sizeof(struct inotify_event)); + } + close(fd); + return 0; +}