--- /dev/null
+From 2bd110339288c18823dcace602b63b0d8627e520 Mon Sep 17 00:00:00 2001
+From: John Sperbeck <jsperbeck@google.com>
+Date: Sun, 21 May 2023 19:29:53 +0000
+Subject: cgroup: always put cset in cgroup_css_set_put_fork
+
+From: John Sperbeck <jsperbeck@google.com>
+
+commit 2bd110339288c18823dcace602b63b0d8627e520 upstream.
+
+A successful call to cgroup_css_set_fork() will always have taken
+a ref on kargs->cset (regardless of CLONE_INTO_CGROUP), so always
+do a corresponding put in cgroup_css_set_put_fork().
+
+Without this, a cset and its contained css structures will be
+leaked for some fork failures. The following script reproduces
+the leak for a fork failure due to exceeding pids.max in the
+pids controller. A similar thing can happen if we jump to the
+bad_fork_cancel_cgroup label in copy_process().
+
+[ -z "$1" ] && echo "Usage $0 pids-root" && exit 1
+PID_ROOT=$1
+CGROUP=$PID_ROOT/foo
+
+[ -e $CGROUP ] && rmdir -f $CGROUP
+mkdir $CGROUP
+echo 5 > $CGROUP/pids.max
+echo $$ > $CGROUP/cgroup.procs
+
+fork_bomb()
+{
+ set -e
+ for i in $(seq 10); do
+ /bin/sleep 3600 &
+ done
+}
+
+(fork_bomb) &
+wait
+echo $$ > $PID_ROOT/cgroup.procs
+kill $(cat $CGROUP/cgroup.procs)
+rmdir $CGROUP
+
+Fixes: ef2c41cf38a7 ("clone3: allow spawning processes into cgroups")
+Cc: stable@vger.kernel.org # v5.7+
+Signed-off-by: John Sperbeck <jsperbeck@google.com>
+Signed-off-by: Tejun Heo <tj@kernel.org>
+[TJM: This backport accommodates the lack of cgroup_unlock]
+Signed-off-by: T.J. Mercier <tjmercier@google.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/cgroup/cgroup.c | 17 ++++++++---------
+ 1 file changed, 8 insertions(+), 9 deletions(-)
+
+--- a/kernel/cgroup/cgroup.c
++++ b/kernel/cgroup/cgroup.c
+@@ -6259,19 +6259,18 @@ err:
+ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
+ __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
+ {
++ struct cgroup *cgrp = kargs->cgrp;
++ struct css_set *cset = kargs->cset;
++
+ cgroup_threadgroup_change_end(current);
+
+- if (kargs->flags & CLONE_INTO_CGROUP) {
+- struct cgroup *cgrp = kargs->cgrp;
+- struct css_set *cset = kargs->cset;
++ if (cset) {
++ put_css_set(cset);
++ kargs->cset = NULL;
++ }
+
++ if (kargs->flags & CLONE_INTO_CGROUP) {
+ mutex_unlock(&cgroup_mutex);
+-
+- if (cset) {
+- put_css_set(cset);
+- kargs->cset = NULL;
+- }
+-
+ if (cgrp) {
+ cgroup_put(cgrp);
+ kargs->cgrp = NULL;
--- /dev/null
+From 5da7cb193db32da783a3f3e77d8b639989321d48 Mon Sep 17 00:00:00 2001
+From: Ziwei Dai <ziwei.dai@unisoc.com>
+Date: Fri, 31 Mar 2023 20:42:09 +0800
+Subject: rcu/kvfree: Avoid freeing new kfree_rcu() memory after old grace period
+
+From: Ziwei Dai <ziwei.dai@unisoc.com>
+
+commit 5da7cb193db32da783a3f3e77d8b639989321d48 upstream.
+
+Memory passed to kvfree_rcu() that is to be freed is tracked by a
+per-CPU kfree_rcu_cpu structure, which in turn contains pointers
+to kvfree_rcu_bulk_data structures that contain pointers to memory
+that has not yet been handed to RCU, along with an kfree_rcu_cpu_work
+structure that tracks the memory that has already been handed to RCU.
+These structures track three categories of memory: (1) Memory for
+kfree(), (2) Memory for kvfree(), and (3) Memory for both that arrived
+during an OOM episode. The first two categories are tracked in a
+cache-friendly manner involving a dynamically allocated page of pointers
+(the aforementioned kvfree_rcu_bulk_data structures), while the third
+uses a simple (but decidedly cache-unfriendly) linked list through the
+rcu_head structures in each block of memory.
+
+On a given CPU, these three categories are handled as a unit, with that
+CPU's kfree_rcu_cpu_work structure having one pointer for each of the
+three categories. Clearly, new memory for a given category cannot be
+placed in the corresponding kfree_rcu_cpu_work structure until any old
+memory has had its grace period elapse and thus has been removed. And
+the kfree_rcu_monitor() function does in fact check for this.
+
+Except that the kfree_rcu_monitor() function checks these pointers one
+at a time. This means that if the previous kfree_rcu() memory passed
+to RCU had only category 1 and the current one has only category 2, the
+kfree_rcu_monitor() function will send that current category-2 memory
+along immediately. This can result in memory being freed too soon,
+that is, out from under unsuspecting RCU readers.
+
+To see this, consider the following sequence of events, in which:
+
+o Task A on CPU 0 calls rcu_read_lock(), then uses "from_cset",
+ then is preempted.
+
+o CPU 1 calls kfree_rcu(cset, rcu_head) in order to free "from_cset"
+ after a later grace period. Except that "from_cset" is freed
+ right after the previous grace period ended, so that "from_cset"
+ is immediately freed. Task A resumes and references "from_cset"'s
+ member, after which nothing good happens.
+
+In full detail:
+
+CPU 0 CPU 1
+---------------------- ----------------------
+count_memcg_event_mm()
+|rcu_read_lock() <---
+|mem_cgroup_from_task()
+ |// css_set_ptr is the "from_cset" mentioned on CPU 1
+ |css_set_ptr = rcu_dereference((task)->cgroups)
+ |// Hard irq comes, current task is scheduled out.
+
+ cgroup_attach_task()
+ |cgroup_migrate()
+ |cgroup_migrate_execute()
+ |css_set_move_task(task, from_cset, to_cset, true)
+ |cgroup_move_task(task, to_cset)
+ |rcu_assign_pointer(.., to_cset)
+ |...
+ |cgroup_migrate_finish()
+ |put_css_set_locked(from_cset)
+ |from_cset->refcount return 0
+ |kfree_rcu(cset, rcu_head) // free from_cset after new gp
+ |add_ptr_to_bulk_krc_lock()
+ |schedule_delayed_work(&krcp->monitor_work, ..)
+
+ kfree_rcu_monitor()
+ |krcp->bulk_head[0]'s work attached to krwp->bulk_head_free[]
+ |queue_rcu_work(system_wq, &krwp->rcu_work)
+ |if rwork->rcu.work is not in WORK_STRUCT_PENDING_BIT state,
+ |call_rcu(&rwork->rcu, rcu_work_rcufn) <--- request new gp
+
+ // There is a perious call_rcu(.., rcu_work_rcufn)
+ // gp end, rcu_work_rcufn() is called.
+ rcu_work_rcufn()
+ |__queue_work(.., rwork->wq, &rwork->work);
+
+ |kfree_rcu_work()
+ |krwp->bulk_head_free[0] bulk is freed before new gp end!!!
+ |The "from_cset" is freed before new gp end.
+
+// the task resumes some time later.
+ |css_set_ptr->subsys[(subsys_id) <--- Caused kernel crash, because css_set_ptr is freed.
+
+This commit therefore causes kfree_rcu_monitor() to refrain from moving
+kfree_rcu() memory to the kfree_rcu_cpu_work structure until the RCU
+grace period has completed for all three categories.
+
+v2: Use helper function instead of inserted code block at kfree_rcu_monitor().
+
+Fixes: 34c881745549 ("rcu: Support kfree_bulk() interface in kfree_rcu()")
+Fixes: 5f3c8d620447 ("rcu/tree: Maintain separate array for vmalloc ptrs")
+Reported-by: Mukesh Ojha <quic_mojha@quicinc.com>
+Signed-off-by: Ziwei Dai <ziwei.dai@unisoc.com>
+Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
+Tested-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
+Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
+Signed-off-by: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ kernel/rcu/tree.c | 39 +++++++++++++++++++++++++++++++--------
+ 1 file changed, 31 insertions(+), 8 deletions(-)
+
+--- a/kernel/rcu/tree.c
++++ b/kernel/rcu/tree.c
+@@ -3328,6 +3328,30 @@ static void kfree_rcu_work(struct work_s
+ }
+ }
+
++static bool
++need_offload_krc(struct kfree_rcu_cpu *krcp)
++{
++ int i;
++
++ for (i = 0; i < FREE_N_CHANNELS; i++)
++ if (krcp->bkvhead[i])
++ return true;
++
++ return !!krcp->head;
++}
++
++static bool
++need_wait_for_krwp_work(struct kfree_rcu_cpu_work *krwp)
++{
++ int i;
++
++ for (i = 0; i < FREE_N_CHANNELS; i++)
++ if (krwp->bkvhead_free[i])
++ return true;
++
++ return !!krwp->head_free;
++}
++
+ /*
+ * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
+ */
+@@ -3344,14 +3368,13 @@ static void kfree_rcu_monitor(struct wor
+ for (i = 0; i < KFREE_N_BATCHES; i++) {
+ struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]);
+
+- // Try to detach bkvhead or head and attach it over any
+- // available corresponding free channel. It can be that
+- // a previous RCU batch is in progress, it means that
+- // immediately to queue another one is not possible so
+- // in that case the monitor work is rearmed.
+- if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
+- (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
+- (krcp->head && !krwp->head_free)) {
++ // Try to detach bulk_head or head and attach it, only when
++ // all channels are free. Any channel is not free means at krwp
++ // there is on-going rcu work to handle krwp's free business.
++ if (need_wait_for_krwp_work(krwp))
++ continue;
++
++ if (need_offload_krc(krcp)) {
+ // Channel 1 corresponds to the SLAB-pointer bulk path.
+ // Channel 2 corresponds to vmalloc-pointer bulk path.
+ for (j = 0; j < FREE_N_CHANNELS; j++) {
projects / thirdparty / kernel / stable-queue.git / commitdiff
