Merge branch 'for-5.15-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup fixes from Tejun Heo:
"All documentation / comment updates"
* 'for-5.15-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroupv2, docs: fix misinformation in "device controller" section
cgroup/cpuset: Change references of cpuset_mutex to cpuset_rwsem
docs/cgroup: remove some duplicate words
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index babbe04..4d8c27e 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1226,7 +1226,7 @@
Note that all fields in this file are hierarchical and the
file modified event can be generated due to an event down the
- hierarchy. For for the local events at the cgroup level see
+ hierarchy. For the local events at the cgroup level see
memory.events.local.
low
@@ -2170,19 +2170,19 @@
Cgroup v2 device controller has no interface files and is implemented
on top of cgroup BPF. To control access to device files, a user may
-create bpf programs of the BPF_CGROUP_DEVICE type and attach them
-to cgroups. On an attempt to access a device file, corresponding
-BPF programs will be executed, and depending on the return value
-the attempt will succeed or fail with -EPERM.
+create bpf programs of type BPF_PROG_TYPE_CGROUP_DEVICE and attach
+them to cgroups with BPF_CGROUP_DEVICE flag. On an attempt to access a
+device file, corresponding BPF programs will be executed, and depending
+on the return value the attempt will succeed or fail with -EPERM.
-A BPF_CGROUP_DEVICE program takes a pointer to the bpf_cgroup_dev_ctx
-structure, which describes the device access attempt: access type
-(mknod/read/write) and device (type, major and minor numbers).
-If the program returns 0, the attempt fails with -EPERM, otherwise
-it succeeds.
+A BPF_PROG_TYPE_CGROUP_DEVICE program takes a pointer to the
+bpf_cgroup_dev_ctx structure, which describes the device access attempt:
+access type (mknod/read/write) and device (type, major and minor numbers).
+If the program returns 0, the attempt fails with -EPERM, otherwise it
+succeeds.
-An example of BPF_CGROUP_DEVICE program may be found in the kernel
-source tree in the tools/testing/selftests/bpf/progs/dev_cgroup.c file.
+An example of BPF_PROG_TYPE_CGROUP_DEVICE program may be found in
+tools/testing/selftests/bpf/progs/dev_cgroup.c in the kernel source tree.
RDMA
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index df1ccf4..2a9695c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -311,17 +311,19 @@
if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))
/*
- * There are two global locks guarding cpuset structures - cpuset_mutex and
+ * There are two global locks guarding cpuset structures - cpuset_rwsem and
* callback_lock. We also require taking task_lock() when dereferencing a
* task's cpuset pointer. See "The task_lock() exception", at the end of this
- * comment.
+ * comment. The cpuset code uses only cpuset_rwsem write lock. Other
+ * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to
+ * prevent change to cpuset structures.
*
* A task must hold both locks to modify cpusets. If a task holds
- * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it
+ * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it
* is the only task able to also acquire callback_lock and be able to
* modify cpusets. It can perform various checks on the cpuset structure
* first, knowing nothing will change. It can also allocate memory while
- * just holding cpuset_mutex. While it is performing these checks, various
+ * just holding cpuset_rwsem. While it is performing these checks, various
* callback routines can briefly acquire callback_lock to query cpusets.
* Once it is ready to make the changes, it takes callback_lock, blocking
* everyone else.
@@ -393,7 +395,7 @@
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_mask.
*
- * Call with callback_lock or cpuset_mutex held.
+ * Call with callback_lock or cpuset_rwsem held.
*/
static void guarantee_online_cpus(struct task_struct *tsk,
struct cpumask *pmask)
@@ -435,7 +437,7 @@
* One way or another, we guarantee to return some non-empty subset
* of node_states[N_MEMORY].
*
- * Call with callback_lock or cpuset_mutex held.
+ * Call with callback_lock or cpuset_rwsem held.
*/
static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
{
@@ -447,7 +449,7 @@
/*
* update task's spread flag if cpuset's page/slab spread flag is set
*
- * Call with callback_lock or cpuset_mutex held.
+ * Call with callback_lock or cpuset_rwsem held.
*/
static void cpuset_update_task_spread_flag(struct cpuset *cs,
struct task_struct *tsk)
@@ -468,7 +470,7 @@
*
* One cpuset is a subset of another if all its allowed CPUs and
* Memory Nodes are a subset of the other, and its exclusive flags
- * are only set if the other's are set. Call holding cpuset_mutex.
+ * are only set if the other's are set. Call holding cpuset_rwsem.
*/
static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
@@ -577,7 +579,7 @@
* If we replaced the flag and mask values of the current cpuset
* (cur) with those values in the trial cpuset (trial), would
* our various subset and exclusive rules still be valid? Presumes
- * cpuset_mutex held.
+ * cpuset_rwsem held.
*
* 'cur' is the address of an actual, in-use cpuset. Operations
* such as list traversal that depend on the actual address of the
@@ -700,7 +702,7 @@
rcu_read_unlock();
}
-/* Must be called with cpuset_mutex held. */
+/* Must be called with cpuset_rwsem held. */
static inline int nr_cpusets(void)
{
/* jump label reference count + the top-level cpuset */
@@ -726,7 +728,7 @@
* domains when operating in the severe memory shortage situations
* that could cause allocation failures below.
*
- * Must be called with cpuset_mutex held.
+ * Must be called with cpuset_rwsem held.
*
* The three key local variables below are:
* cp - cpuset pointer, used (together with pos_css) to perform a
@@ -1005,7 +1007,7 @@
* 'cpus' is removed, then call this routine to rebuild the
* scheduler's dynamic sched domains.
*
- * Call with cpuset_mutex held. Takes cpus_read_lock().
+ * Call with cpuset_rwsem held. Takes cpus_read_lock().
*/
static void rebuild_sched_domains_locked(void)
{
@@ -1078,7 +1080,7 @@
* @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
*
* Iterate through each task of @cs updating its cpus_allowed to the
- * effective cpuset's. As this function is called with cpuset_mutex held,
+ * effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
static void update_tasks_cpumask(struct cpuset *cs)
@@ -1347,7 +1349,7 @@
*
* On legacy hierarchy, effective_cpus will be the same with cpu_allowed.
*
- * Called with cpuset_mutex held
+ * Called with cpuset_rwsem held
*/
static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
{
@@ -1704,12 +1706,12 @@
* @cs: the cpuset in which each task's mems_allowed mask needs to be changed
*
* Iterate through each task of @cs updating its mems_allowed to the
- * effective cpuset's. As this function is called with cpuset_mutex held,
+ * effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
static void update_tasks_nodemask(struct cpuset *cs)
{
- static nodemask_t newmems; /* protected by cpuset_mutex */
+ static nodemask_t newmems; /* protected by cpuset_rwsem */
struct css_task_iter it;
struct task_struct *task;
@@ -1722,7 +1724,7 @@
* take while holding tasklist_lock. Forks can happen - the
* mpol_dup() cpuset_being_rebound check will catch such forks,
* and rebind their vma mempolicies too. Because we still hold
- * the global cpuset_mutex, we know that no other rebind effort
+ * the global cpuset_rwsem, we know that no other rebind effort
* will be contending for the global variable cpuset_being_rebound.
* It's ok if we rebind the same mm twice; mpol_rebind_mm()
* is idempotent. Also migrate pages in each mm to new nodes.
@@ -1768,7 +1770,7 @@
*
* On legacy hierarchy, effective_mems will be the same with mems_allowed.
*
- * Called with cpuset_mutex held
+ * Called with cpuset_rwsem held
*/
static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
{
@@ -1821,7 +1823,7 @@
* mempolicies and if the cpuset is marked 'memory_migrate',
* migrate the tasks pages to the new memory.
*
- * Call with cpuset_mutex held. May take callback_lock during call.
+ * Call with cpuset_rwsem held. May take callback_lock during call.
* Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
* lock each such tasks mm->mmap_lock, scan its vma's and rebind
* their mempolicies to the cpusets new mems_allowed.
@@ -1911,7 +1913,7 @@
* @cs: the cpuset in which each task's spread flags needs to be changed
*
* Iterate through each task of @cs updating its spread flags. As this
- * function is called with cpuset_mutex held, cpuset membership stays
+ * function is called with cpuset_rwsem held, cpuset membership stays
* stable.
*/
static void update_tasks_flags(struct cpuset *cs)
@@ -1931,7 +1933,7 @@
* cs: the cpuset to update
* turning_on: whether the flag is being set or cleared
*
- * Call with cpuset_mutex held.
+ * Call with cpuset_rwsem held.
*/
static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
@@ -1980,7 +1982,7 @@
* cs: the cpuset to update
* new_prs: new partition root state
*
- * Call with cpuset_mutex held.
+ * Call with cpuset_rwsem held.
*/
static int update_prstate(struct cpuset *cs, int new_prs)
{
@@ -2167,7 +2169,7 @@
static struct cpuset *cpuset_attach_old_cs;
-/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
+/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */
static int cpuset_can_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
@@ -2219,7 +2221,7 @@
}
/*
- * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach()
+ * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach()
* but we can't allocate it dynamically there. Define it global and
* allocate from cpuset_init().
*/
@@ -2227,7 +2229,7 @@
static void cpuset_attach(struct cgroup_taskset *tset)
{
- /* static buf protected by cpuset_mutex */
+ /* static buf protected by cpuset_rwsem */
static nodemask_t cpuset_attach_nodemask_to;
struct task_struct *task;
struct task_struct *leader;
@@ -2417,7 +2419,7 @@
* operation like this one can lead to a deadlock through kernfs
* active_ref protection. Let's break the protection. Losing the
* protection is okay as we check whether @cs is online after
- * grabbing cpuset_mutex anyway. This only happens on the legacy
+ * grabbing cpuset_rwsem anyway. This only happens on the legacy
* hierarchies.
*/
css_get(&cs->css);
@@ -3672,7 +3674,7 @@
* - Used for /proc/<pid>/cpuset.
* - No need to task_lock(tsk) on this tsk->cpuset reference, as it
* doesn't really matter if tsk->cpuset changes after we read it,
- * and we take cpuset_mutex, keeping cpuset_attach() from changing it
+ * and we take cpuset_rwsem, keeping cpuset_attach() from changing it
* anyway.
*/
int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
