diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 353c8f83439a..a3d363502b7b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5207,10 +5207,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); - if (it->task_pos) { + while (it->task_pos && !it->cur_task) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); - get_task_struct(it->cur_task); + /* a task on dying_tasks with zero refcount is only valid for + * RCU readers, not even interesting for + * CSS_TASK_ITER_WITH_DEAD, find another one */ + it->cur_task = tryget_task_struct(it->cur_task); css_task_iter_advance(it); } -- knotmirror 0.0.1 From c774ec8f0a5d02a06d34c27f5a7de7e333b91265 Mon Sep 17 00:00:00 2001 From: Eva Kurchatova Date: Wed, 16 Sep 2026 23:44:31 +0300 Subject: [PATCH 2/7] selftests: cgroup: give the O_TMPFILE open in get_temp_fd() a mode O_TMPFILE, like O_CREAT, needs the third argument. Without it glibc refuses the call at compile time as soon as fortification is on: In function 'open', inlined from 'get_temp_fd' at test_memcontrol.c:33:9: /usr/include/bits/fcntl2.h:52:11: error: call to '__open_missing_mode' declared with attribute error: open with O_CREAT or O_TMPFILE in second argument needs 3 arguments The fortify checks take effect only once the compiler optimises, and cgroup/Makefile builds with "-Wall -pthread" alone, so this goes unnoticed in a plain build. Building the tests with the flags distributions commonly use, -O2 -D_FORTIFY_SOURCE=3, loses test_memcontrol entirely. Fixes: 84092dbcf901 ("selftests: cgroup: add memory controller self-tests") Signed-off-by: Eva Kurchatova Signed-off-by: Tejun Heo --- tools/testing/selftests/cgroup/test_memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 3a84d068fbf3..0ed82347044e 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -30,7 +30,7 @@ static int page_size; int get_temp_fd(void) { - return open(".", O_TMPFILE | O_RDWR | O_EXCL); + return open(".", O_TMPFILE | O_RDWR | O_EXCL, 0600); } int alloc_pagecache(int fd, size_t size) -- knotmirror 0.0.1 From 1765a153d985c231357145e26798f9408db10e42 Mon Sep 17 00:00:00 2001 From: Guopeng Zhang Date: Thu, 24 Sep 2026 17:15:36 +0800 Subject: [PATCH 3/7] cgroup/pids: Restore pids.events notifications in local mode A fork rejected by the pids controller increments the counter reported by pids.events. When local event accounting is selected, however, pids_event() returns after notifying only events_local_file, leaving pids.events pollers asleep. On legacy hierarchies, pids.events.local does not exist. With pids_localevents, pids.events reports the same local counter. In both cases, pids.events changes without generating a notification. This can be reproduced with a pids_localevents mount: mkdir /tmp/test mount -t cgroup2 -o pids_localevents none /tmp/test mkdir /tmp/test/t echo 1 > /tmp/test/t/pids.max cat /tmp/test/t/pids.events # max 0 timeout 3 inotifywait -e modify /tmp/test/t/pids.events & sh -c 'echo $$ > /tmp/test/t/cgroup.procs; (true &)' 2>/dev/null wait cat /tmp/test/t/pids.events # max 1 Without this patch, inotifywait times out without reporting an event. Notify pids.events before returning from the local event path. Fixes: 3f26a885a068 ("cgroup/pids: Add pids.events.local") Cc: stable@vger.kernel.org # v6.11+ Signed-off-by: Guopeng Zhang Signed-off-by: Tejun Heo --- kernel/cgroup/pids.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index ecbb839d2acb..78cdc0558d0c 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -253,6 +253,11 @@ static void pids_event(struct pids_cgroup *pids_forking, } if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) || cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) { + /* + * pids.events reports the local counter on legacy hierarchies + * and when pids_localevents is enabled. + */ + cgroup_file_notify(&p->events_file); cgroup_file_notify(&p->events_local_file); return; } -- knotmirror 0.0.1 From 31c88350b7dd1522792f726f79607f31bb55c50f Mon Sep 17 00:00:00 2001 From: Hui Peng Date: Thu, 24 Sep 2026 04:27:27 +0000 Subject: [PATCH 4/7] cgroup/cpuset: Return PERR_NOCPUS in remote_partition_enable() on subpartitions_cpus conflict When a remote partition is created underneath an existing local partition via a non-partition (PRS_MEMBER) intermediate cgroup, update_prstate() sees parent->partition_root_state == PRS_MEMBER and calls remote_partition_enable(). Commit 86888c7bd117 ("cgroup/cpuset: Add warnings to catch inconsistency in exclusive CPUs") replaced the cpumask_intersects(tmp->new_cpus, subpartitions_cpus) error check in remote_partition_enable() with WARN_ON_ONCE(). As a result, remote_partition_enable() emits a warning and proceeds to enable the remote partition on CPUs that are already owned by the ancestor local partition in subpartitions_cpus. This can be reproduced on Linux 7.3.0-rc3 with: mkdir -p /tmp/cg1 mount -t cgroup2 none /tmp/cg1 echo "+cpuset" > /tmp/cg1/cgroup.subtree_control mkdir /tmp/cg1/A echo 1 > /tmp/cg1/A/cpuset.cpus echo 1 > /tmp/cg1/A/cpuset.cpus.exclusive echo root > /tmp/cg1/A/cpuset.cpus.partition echo "+cpuset" > /tmp/cg1/A/cgroup.subtree_control mkdir /tmp/cg1/A/B echo 1 > /tmp/cg1/A/B/cpuset.cpus echo 1 > /tmp/cg1/A/B/cpuset.cpus.exclusive echo "+cpuset" > /tmp/cg1/A/B/cgroup.subtree_control mkdir /tmp/cg1/A/B/D echo 1 > /tmp/cg1/A/B/D/cpuset.cpus echo 1 > /tmp/cg1/A/B/D/cpuset.cpus.exclusive echo root > /tmp/cg1/A/B/D/cpuset.cpus.partition which triggers: WARNING: kernel/cgroup/cpuset.c:1594 at remote_partition_enable+0x1c1/0x300 and leaves both /tmp/cg1/A and /tmp/cg1/A/B/D as active root partitions claiming exclusive CPU 1. Fix this by returning PERR_NOCPUS when tmp->new_cpus intersects subpartitions_cpus in remote_partition_enable(), matching the error code used by remote_cpus_update() for the same subpartitions_cpus conflict, and add a regression test case to tools/testing/selftests/cgroup/test_cpuset_prs.sh. Tested in QEMU on Linux 7.3.0-rc3 using the reproducer above and tools/testing/selftests/cgroup/test_cpuset_prs.sh. Fixes: 86888c7bd117 ("cgroup/cpuset: Add warnings to catch inconsistency in exclusive CPUs") Suggested-by: Guopeng Zhang Cc: stable@vger.kernel.org Assisted-by: LLM Signed-off-by: Hui Peng Reviewed-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 3 ++- tools/testing/selftests/cgroup/test_cpuset_prs.sh | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 8f24171b6055..1fcec89a28b9 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1591,10 +1591,11 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, * above it or remote partition root underneath it is not allowed. */ compute_excpus(cs, tmp->new_cpus); - WARN_ON_ONCE(cpumask_intersects(tmp->new_cpus, subpartitions_cpus)); if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) || cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus)) return PERR_INVCPUS; + if (cpumask_intersects(tmp->new_cpus, subpartitions_cpus)) + return PERR_NOCPUS; if (((new_prs == PRS_ISOLATED) && !isolated_cpus_can_update(tmp->new_cpus, NULL)) || prstate_housekeeping_conflict(new_prs, tmp->new_cpus)) diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 131d8b4551ef..7efd5e645767 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -298,6 +298,8 @@ TEST_MATRIX=( " 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" + " 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" # Remote partition offline tests " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" -- knotmirror 0.0.1 From e06b678e3b4e12fdaa0b51a7a5a54abc5dbd6469 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 29 Sep 2026 23:18:33 -0400 Subject: [PATCH 5/7] cgroup/cpuset: Don't access cpuset_cgrp_subsys.root in is_in_v2_mode() After seeing the patch [1] to guard is_in_v2_mode() with RCU, it makes me realize that is_in_v2_mode() may be called in a context where a new cgroup filesystem is being rebound with stale cpuset_cgrp_subsys.root pointer. Avoid this potential UaF situation by adding a new cpuset_v2_mode flag which is set when the cpuset_v2_mode mount option is used. This flag is written into only when cpuset_bind() is being called with a stable cpuset_cgrp_subsys.root value. The is_in_v2_mode() helper is modified to read the new cpuset_v2_mode flag instead of accessing cpuset_cgrp_subsys.root directly. [1] https://lore.kernel.org/lkml/20260929084124.626693-2-arighi@nvidia.com Fixes: b8d1b8ee93df ("cpuset: Allow v2 behavior in v1 cgroup") Signed-off-by: Waiman Long Reviewed-by: Ridong Chen Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 1fcec89a28b9..98af44a7f399 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -152,6 +152,12 @@ static cpumask_var_t isolated_cpus; /* CSCB */ */ static bool update_housekeeping; /* RWCS */ +/* + * Set if "cpuset_v2_mode" mount option is used + * Cached at bind time and not lock protected; accessed via {READ,WRITE}_ONCE + */ +static bool cpuset_v2_mode; + /* * Copy of isolated_cpus to be passed to housekeeping_update() */ @@ -439,8 +445,7 @@ static inline bool cpuset_v2(void) */ static inline bool is_in_v2_mode(void) { - return cpuset_v2() || - (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); + return cpuset_v2() || READ_ONCE(cpuset_v2_mode); } /** @@ -3727,6 +3732,8 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); + WRITE_ONCE(cpuset_v2_mode, + !!(cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE)); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); cpumask_copy(top_cpuset.effective_xcpus, cpu_possible_mask); -- knotmirror 0.0.1 From 23b1ab15ca91f2cffaf149d9bb0fafeb700c7db2 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 2 Oct 2026 12:54:38 -0400 Subject: [PATCH 6/7] cgroup/cpuset: Handle cpu hotplug race in guarantee_active_cpus() With commit 2125c0034c5d ("cgroup/cpuset: Make cpuset hotplug processing synchronous"), the cpuset hotplug operation becomes synchronous. That commit also removes the code that handles race between cpuset_hotplug_work and cpu hotplug notifier with the assumption that race is now gone. Later commit 7a0aabd9ce69 ("cgroup/cpuset: Always use cpu_active_mask") updates the cpuset code to always use cpu_active_mask instead of cpu_online_mask in some places including guarantee_online_cpus() which is renamed to guarantee_active_cpus() in that commit. In the case of CPU offline operation, cpu_active_mask is updated first in sched_cpu_deactivate() to remove the offline CPU before cpuset_handle_hotplug() is called to update the effective_cpus of the affected cpusets. The cpu_online_mask is updated after that near the end of the offline operation to remove the offline CPU. As a result, the race comes back and the top cpuset may not have any active CPU leading to NULL pointer dereference during the race window when guarantee_active_cpus() is called after cpu_active_mask is updated to remove the CPU to be torn down but before cpuset_handle_hotplug() is able to properly update the effective_cpus of the top cpuset. Fix this by adding back the NULL cs check to avoid this problem. Fixes: 7a0aabd9ce69 ("cgroup/cpuset: Always use cpu_active_mask") Cc: stable@vger.kernel.org # v6.16+ Reported-by: Farhad Alemi Link: https://lore.kernel.org/lkml/CA+0ovChh3VjsKN1g+ZGjwwY2fGTpP7uD+aCCByLj5Qbymw=bfQ@mail.gmail.com Signed-off-by: Waiman Long Tested-by: Farhad Alemi Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 98af44a7f399..d2ec7b128960 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -518,10 +518,26 @@ static void guarantee_active_cpus(struct task_struct *tsk, rcu_read_lock(); cs = task_cs(tsk); - while (!cpumask_intersects(cs->effective_cpus, pmask)) + while (!cpumask_intersects(cs->effective_cpus, pmask)) { cs = parent_cs(cs); - + if (unlikely(!cs)) { + /* + * The top cpuset doesn't have any active cpu as a + * consequence of a race between its caller and the cpu + * hotplug operation where cpu_active_mask is updated + * asynchronously before cpuset_handle_hotplug() is + * being called to adjust the effective_cpus of the + * affected cpusets. But we know the top cpuset's + * effective_cpus is on its way to be identical to + * cpu_active_mask minus the exclusive CPUs dedicated + * to other valid cpuset partitions. Just pass back + * the filtered cpu_active_mask in this case. + */ + goto out_unlock; + } + } cpumask_and(pmask, pmask, cs->effective_cpus); +out_unlock: rcu_read_unlock(); } -- knotmirror 0.0.1 From b8eb5fd5bdb4c03758b056c70e5e1d962ca89757 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 5 Oct 2026 06:43:10 -0400 Subject: [PATCH 7/7] cgroup/cpuset: Call is_in_v2_mode() after acquiring cpuset_mutex in cpuset_handle_hotplug() It is reported by sashiko that calling is_in_v2_mode() outside of cpuset_mutex critical section in cpuset_handle_hotplug() can introduce a TOCTOU race where cgroup hierarchy may have changed from v1 to v2 or vice versa after is_in_v2_mode() is called leading to erroneously skip the allocation of tmpmasks or incorrectly modify cpus_allowed masks, resulting in cpuset state corruption. Fix that by calling is_in_v2_mode() after acquiring the cpuset_mutex. Fixes: b8d1b8ee93df ("cpuset: Allow v2 behavior in v1 cgroup") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d2ec7b128960..b61bc3ed1037 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -4062,15 +4062,16 @@ static void cpuset_handle_hotplug(void) static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; - bool on_dfl = is_in_v2_mode(); + bool on_dfl; struct tmpmasks tmp, *ptmp = NULL; - if (on_dfl && !alloc_tmpmasks(&tmp)) - ptmp = &tmp; - lockdep_assert_cpus_held(); mutex_lock(&cpuset_mutex); + on_dfl = is_in_v2_mode(); + if (on_dfl && !alloc_tmpmasks(&tmp)) + ptmp = &tmp; + /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY];