From 311ead1be05d2348e89f873337c8375e856e1abb Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Wed, 3 Dec 2025 19:56:29 +0800 Subject: selftests: cgroup: Add cg_read_key_long_poll() to poll a cgroup key with retries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new helper function `cg_read_key_long_poll()` in cgroup_util.h. This function polls the specified key in a cgroup file until it matches the expected value or the retry limit is reached, with configurable wait intervals between retries. This helper is particularly useful for handling asynchronously updated cgroup statistics (e.g., memory.stat), where immediate reads may observe stale values, especially on busy systems. It allows tests and other utilities to handle such cases more flexibly. Signed-off-by: Guopeng Zhang Suggested-by: Michal Koutný Reviewed-by: Shakeel Butt Acked-by: Michal Koutný Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/lib/cgroup_util.c | 21 +++++++++++++++++++++ .../selftests/cgroup/lib/include/cgroup_util.h | 5 +++++ 2 files changed, 26 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c index 44c52f620fda..ce6c2642fd9b 100644 --- a/tools/testing/selftests/cgroup/lib/cgroup_util.c +++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c @@ -168,6 +168,27 @@ long cg_read_key_long(const char *cgroup, const char *control, const char *key) return atol(ptr + strlen(key)); } +long cg_read_key_long_poll(const char *cgroup, const char *control, + const char *key, long expected, int retries, + useconds_t wait_interval_us) +{ + long val = -1; + int i; + + for (i = 0; i < retries; i++) { + val = cg_read_key_long(cgroup, control, key); + if (val < 0) + return val; + + if (val == expected) + break; + + usleep(wait_interval_us); + } + + return val; +} + long cg_read_lc(const char *cgroup, const char *control) { char buf[PAGE_SIZE]; diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h index 7ab2824ed7b5..77f386dab5e8 100644 --- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h +++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h @@ -17,6 +17,8 @@ #define CG_NAMED_NAME "selftest" #define CG_PATH_FORMAT (!cg_test_v1_named ? "0::%s" : (":name=" CG_NAMED_NAME ":%s")) +#define DEFAULT_WAIT_INTERVAL_US (100 * 1000) /* 100 ms */ + /* * Checks if two given values differ by less than err% of their sum. */ @@ -64,6 +66,9 @@ extern int cg_read_strstr(const char *cgroup, const char *control, extern long cg_read_long(const char *cgroup, const char *control); extern long cg_read_long_fd(int fd); long cg_read_key_long(const char *cgroup, const char *control, const char *key); +long cg_read_key_long_poll(const char *cgroup, const char *control, + const char *key, long expected, int retries, + useconds_t wait_interval_us); extern long cg_read_lc(const char *cgroup, const char *control); extern int cg_write(const char *cgroup, const char *control, char *buf); extern int cg_open(const char *cgroup, const char *control, int flags); -- cgit v1.2.3 From 6360d444ae32871c6a048ac880ef3b871a439bad Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Wed, 3 Dec 2025 19:56:30 +0800 Subject: selftests: cgroup: make test_memcg_sock robust against delayed sock stats MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit test_memcg_sock() currently requires that memory.stat's "sock " counter is exactly zero immediately after the TCP server exits. On a busy system this assumption is too strict: - Socket memory may be freed with a small delay (e.g. RCU callbacks). - memcg statistics are updated asynchronously via the rstat flushing worker, so the "sock " value in memory.stat can stay non-zero for a short period of time even after all socket memory has been uncharged. As a result, test_memcg_sock() can intermittently fail even though socket memory accounting is working correctly. Make the test more robust by polling memory.stat for the "sock " counter and allowing it some time to drop to zero instead of checking it only once. The timeout is set to 3 seconds to cover the periodic rstat flush interval (FLUSH_TIME = 2*HZ by default) plus some scheduling slack. If the counter does not become zero within the timeout, the test still fails as before. On my test system, running test_memcontrol 50 times produced: - Before this patch: 6/50 runs passed. - After this patch: 50/50 runs passed. Signed-off-by: Guopeng Zhang Suggested-by: Lance Yang Reviewed-by: Shakeel Butt Acked-by: Michal Koutný Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_memcontrol.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 4e1647568c5b..2fb096a2a9f9 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -21,6 +21,8 @@ #include "kselftest.h" #include "cgroup_util.h" +#define MEMCG_SOCKSTAT_WAIT_RETRIES 30 + static bool has_localevents; static bool has_recursiveprot; @@ -1384,6 +1386,7 @@ static int test_memcg_sock(const char *root) int bind_retries = 5, ret = KSFT_FAIL, pid, err; unsigned short port; char *memcg; + long sock_post = -1; memcg = cg_name(root, "memcg_test"); if (!memcg) @@ -1432,7 +1435,22 @@ static int test_memcg_sock(const char *root) if (cg_read_long(memcg, "memory.current") < 0) goto cleanup; - if (cg_read_key_long(memcg, "memory.stat", "sock ")) + /* + * memory.stat is updated asynchronously via the memcg rstat + * flushing worker, which runs periodically (every 2 seconds, + * see FLUSH_TIME). On a busy system, the "sock " counter may + * stay non-zero for a short period of time after the TCP + * connection is closed and all socket memory has been + * uncharged. + * + * Poll memory.stat for up to 3 seconds (~FLUSH_TIME plus some + * scheduling slack) and require that the "sock " counter + * eventually drops to zero. + */ + sock_post = cg_read_key_long_poll(memcg, "memory.stat", "sock ", 0, + MEMCG_SOCKSTAT_WAIT_RETRIES, + DEFAULT_WAIT_INTERVAL_US); + if (sock_post) goto cleanup; ret = KSFT_PASS; -- cgit v1.2.3 From 50133c09d189a26f4cc6e78e382864fd599a1dc4 Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Wed, 3 Dec 2025 19:56:31 +0800 Subject: selftests: cgroup: Replace sleep with cg_read_key_long_poll() for waiting on nr_dying_descendants MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the manual sleep-and-retry logic in test_kmem_dead_cgroups() with the new helper `cg_read_key_long_poll()`. This change improves the robustness of the test by polling the "nr_dying_descendants" counter in `cgroup.stat` until it reaches 0 or the timeout is exceeded. Additionally, increase the retry timeout to 8 seconds (from 5 seconds) based on testing results: - With 5-second timeout: 4/20 runs passed. - With 8-second timeout: 20/20 runs passed. The 8 second timeout is based on stress testing of test_kmem_dead_cgroups() under load: 5 seconds was occasionally not enough for reclaim of dying descendants to complete, whereas 8 seconds consistently covered the observed latencies. This value is intended as a generous upper bound for the asynchronous reclaim and is not tied to any specific kernel constant, so it can be adjusted in the future if reclaim behavior changes. Signed-off-by: Guopeng Zhang Reviewed-by: Shakeel Butt Acked-by: Michal Koutný Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_kmem.c | 33 ++++++++++++++---------------- 1 file changed, 15 insertions(+), 18 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index ca38525484e3..eeabd34bf083 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -26,6 +26,7 @@ */ #define MAX_VMSTAT_ERROR (4096 * 64 * get_nprocs()) +#define KMEM_DEAD_WAIT_RETRIES 80 static int alloc_dcache(const char *cgroup, void *arg) { @@ -306,9 +307,7 @@ static int test_kmem_dead_cgroups(const char *root) { int ret = KSFT_FAIL; char *parent; - long dead; - int i; - int max_time = 20; + long dead = -1; parent = cg_name(root, "kmem_dead_cgroups_test"); if (!parent) @@ -323,21 +322,19 @@ static int test_kmem_dead_cgroups(const char *root) if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30)) goto cleanup; - for (i = 0; i < max_time; i++) { - dead = cg_read_key_long(parent, "cgroup.stat", - "nr_dying_descendants "); - if (dead == 0) { - ret = KSFT_PASS; - break; - } - /* - * Reclaiming cgroups might take some time, - * let's wait a bit and repeat. - */ - sleep(1); - if (i > 5) - printf("Waiting time longer than 5s; wait: %ds (dead: %ld)\n", i, dead); - } + /* + * Allow up to ~8s for reclaim of dying descendants to complete. + * This is a generous upper bound derived from stress testing, not + * from a specific kernel constant, and can be adjusted if reclaim + * behavior changes in the future. + */ + dead = cg_read_key_long_poll(parent, "cgroup.stat", + "nr_dying_descendants ", 0, KMEM_DEAD_WAIT_RETRIES, + DEFAULT_WAIT_INTERVAL_US); + if (dead) + goto cleanup; + + ret = KSFT_PASS; cleanup: cg_destroy(parent); -- cgit v1.2.3 From 2a3602030d800b6600ef55c31e21bc54611f7770 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 12 Jan 2026 11:00:20 -0500 Subject: cgroup/cpuset: Don't invalidate sibling partitions on cpuset.cpus conflict Currently, when setting a cpuset's cpuset.cpus to a value that conflicts with the cpuset.cpus/cpuset.cpus.exclusive of a sibling partition, the sibling's partition state becomes invalid. This is overly harsh and is probably not necessary. The cpuset.cpus.exclusive control file, if set, will override the cpuset.cpus of the same cpuset when creating a cpuset partition. So cpuset.cpus has less priority than cpuset.cpus.exclusive in setting up a partition. However, it cannot override a conflicting cpuset.cpus file in a sibling cpuset and the partition creation process will fail. This is inconsistent. That will also make using cpuset.cpus.exclusive less valuable as a tool to set up cpuset partitions as the users have to check if such a cpuset.cpus conflict exists or not. Fix these problems by making sure that once a cpuset.cpus.exclusive is set without failure, it will always be allowed to form a valid partition as long as at least one CPU can be granted from its parent irrespective of the state of the siblings' cpuset.cpus values. Of course, setting cpuset.cpus.exclusive will fail if it conflicts with the cpuset.cpus.exclusive or the cpuset.cpus.exclusive.effective value of a sibling. Partition can still be created by setting only cpuset.cpus without setting cpuset.cpus.exclusive. However, any conflicting CPUs in sibling's cpuset.cpus.exclusive.effective and cpuset.cpus.exclusive values will be removed from its cpuset.cpus.exclusive.effective as long as there is still one or more CPUs left and can be granted from its parent. This CPU stripping is currently done in rm_siblings_excl_cpus(). The new code will now try its best to enable the creation of new partitions with only cpuset.cpus set without invalidating existing ones. However it is not guaranteed that all the CPUs requested in cpuset.cpus will be used in the new partition even when all these CPUs can be granted from the parent. This is similar to the fact that cpuset.cpus.effective may not be able to include all the CPUs requested in cpuset.cpus. In this case, the parent may not able to grant all the exclusive CPUs requested in cpuset.cpus to cpuset.cpus.exclusive.effective if some of them have already been granted to other partitions earlier. With the creation of multiple sibling partitions by setting only cpuset.cpus, this does have the side effect that their exact cpuset.cpus.exclusive.effective settings will depend on the order of partition creation if there are conflicts. Due to the exclusive nature of the CPUs in a partition, it is not easy to make it fair other than the old behavior of invalidating all the conflicting partitions. For example, # echo "0-2" > A1/cpuset.cpus # echo "root" > A1/cpuset.cpus.partition # cat A1/cpuset.cpus.partition root # cat A1/cpuset.cpus.exclusive.effective 0-2 # echo "2-4" > B1/cpuset.cpus # echo "root" > B1/cpuset.cpus.partition # cat B1/cpuset.cpus.partition root # cat B1/cpuset.cpus.exclusive.effective 3-4 # cat B1/cpuset.cpus.effective 3-4 For users who want to be sure that they can get most of the CPUs they want, cpuset.cpus.exclusive should be used instead if they can set it successfully without failure. Setting cpuset.cpus.exclusive will guarantee that sibling conflicts from then onward is no longer possible. To make this change, we have to separate out the is_cpu_exclusive() check in cpus_excl_conflict() into a cgroup v1 only cpuset1_cpus_excl_conflict() helper. The cpus_allowed_validate_change() helper is now no longer needed and can be removed. Some existing tests in test_cpuset_prs.sh are updated and new ones are added to reflect the new behavior. The cgroup-v2.rst doc file is also updated the clarify what exclusive CPUs will be used when a partition is created. Reported-by: Sun Shaojie Closes: https://lore.kernel.org/lkml/20251117015708.977585-1-sunshaojie@kylinos.cn/ Signed-off-by: Waiman Long Reviewed-by: Chen Ridong Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_cpuset_prs.sh | 26 +++++++++++++++++------ 1 file changed, 19 insertions(+), 7 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index a17256d9f88a..ff4540b0490e 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -269,7 +269,7 @@ TEST_MATRIX=( " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3|A2:1-3|A3:2-3|B1:2-3 A1:P0|A3:P0|B1:P-2" + " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" @@ -318,7 +318,7 @@ TEST_MATRIX=( # Invalid to valid local partition direct transition tests " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" - " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:4-6 A1:P-2|B1:P0" + " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" # Local partition invalidation tests @@ -388,10 +388,10 @@ TEST_MATRIX=( " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" - # A non-exclusive cpuset.cpus change will invalidate partition and its siblings - " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P0" - " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P-1" - " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P0|B1:P-1" + # A non-exclusive cpuset.cpus change will not invalidate its siblings partition. + " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:3 A1:P1|B1:P0" + " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-1|XA1:0-1|B1:2-3 A1:P1|B1:P1" + " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-1|B1:2-3 A1:P0|B1:P1" # cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it " C0-3 . . C4-5 X5 . . . 0 A1:0-3|B1:4-5" @@ -417,6 +417,14 @@ TEST_MATRIX=( " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" + # When multiple partitions with conflicting cpuset.cpus are created, the + # latter created ones will only get what are left of the available exclusive + # CPUs. + " C1-3:P1 . . . . . . C3-5:P1 0 A1:1-3|B1:4-5:XB1:4-5 A1:P1|B1:P1" + + # cpuset.cpus can be set to a subset of sibling's cpuset.cpus.exclusive + " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2" + # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: @@ -427,7 +435,7 @@ TEST_MATRIX=( # Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5" - # cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive + # cpuset.cpus.exclusive cannot be set to a superset of sibling's cpuset.cpus " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3|B1:4-5" ) @@ -477,6 +485,10 @@ REMOTE_TEST_MATRIX=( . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \ 1-2,4-6|1-2,5-6" + # c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition + " C1-5:P1:S+ . C1-4:P1 C2-3 . . \ + . . . P1 . . p1:5|c11:1-4|c12:5 \ + p1:P1|c11:P1|c12:P-1" ) # -- cgit v1.2.3 From 272bd8183376a9e20fe08bacbaa44003d7c8acaa Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 12 Jan 2026 11:00:21 -0500 Subject: cgroup/cpuset: Move the v1 empty cpus/mems check to cpuset1_validate_change() As stated in commit 1c09b195d37f ("cpuset: fix a regression in validating config change"), it is not allowed to clear masks of a cpuset if there're tasks in it. This is specific to v1 since empty "cpuset.cpus" or "cpuset.mems" will cause the v2 cpuset to inherit the effective CPUs or memory nodes from its parent. So it is OK to have empty cpus or mems even if there are tasks in the cpuset. Move this empty cpus/mems check in validate_change() to cpuset1_validate_change() to allow more flexibility in setting cpus or mems in v2. cpuset_is_populated() needs to be moved into cpuset-internal.h as it is needed by the empty cpus/mems checking code. Also add a test case to test_cpuset_prs.sh to verify that. Reported-by: Chen Ridong Closes: https://lore.kernel.org/lkml/7a3ec392-2e86-4693-aa9f-1e668a668b9c@huaweicloud.com/ Signed-off-by: Waiman Long Reviewed-by: Chen Ridong Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_cpuset_prs.sh | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index ff4540b0490e..5dff3ad53867 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -425,6 +425,9 @@ TEST_MATRIX=( # cpuset.cpus can be set to a subset of sibling's cpuset.cpus.exclusive " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2" + # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs + " C1-3:S+ C2 . . . T:C . . 0 A1:1-3|A2:1-3" + # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: -- cgit v1.2.3