Merge tag 'cgroup-for-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

torvalds · torvalds · commit 94dc216ad848 · 2025-03-24T16:49:40.000-07:00
Pull cgroup updates from Tejun Heo:

 - Add deprecation info messages to cgroup1-only features

 - rstat updates including a bug fix and breaking up a critical section
   to reduce interrupt latency impact

 - Other misc and doc updates

* tag 'cgroup-for-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: rstat: Cleanup flushing functions and locking
  cgroup/rstat: avoid disabling irqs for O(num_cpu)
  mm: Fix a build breakage in memcontrol-v1.c
  blk-cgroup: Simplify policy files registration
  cgroup: Update file naming comment
  cgroup: Add deprecation message to legacy freezer controller
  mm: Add transformation message for per-memcg swappiness
  RFC cgroup/cpuset-v1: Add deprecation messages to sched_relax_domain_level
  cgroup/cpuset-v1: Add deprecation messages to memory_migrate
  cgroup/cpuset-v1: Add deprecation messages to mem_exclusive and mem_hardwall
  cgroup: Print message when /proc/cgroups is read on v2-only system
  cgroup/blkio: Add deprecation messages to reset_stats
  cgroup/cpuset-v1: Add deprecation messages to memory_spread_page and memory_spread_slab
  cgroup/cpuset-v1: Add deprecation messages to sched_load_balance and memory_pressure_enabled
  cgroup, docs: Be explicit about independence of RT_GROUP_SCHED and non-cpu controllers
  cgroup/rstat: Fix forceidle time in cpu.stat
  cgroup/misc: Remove unused misc_cg_res_total_usage
  cgroup/cpuset: Move procfs cpuset attribute under cgroup-v1.c
  cgroup: update comment about dropping cgroup kn refs
diff --git a/Documentation/admin-guide/cgroup-v1/freezer-subsystem.rst b/Documentation/admin-guide/cgroup-v1/freezer-subsystem.rst
@@ -125,3 +125,7 @@ to unfreeze all tasks in the container::
 
 This is the basic mechanism which should do the right thing for user space task
 in a simple scenario.
+
+This freezer implementation is affected by shortcomings (see commit
+76f969e8948d8 ("cgroup: cgroup v2 freezer")) and cgroup v2 freezer is
+recommended.
diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst
@@ -90,6 +90,7 @@ Brief summary of control files.
                                      used.
  memory.swappiness		     set/show swappiness parameter of vmscan
 				     (See sysctl's vm.swappiness)
+				     Per memcg knob does not exist in cgroup v2.
  memory.move_charge_at_immigrate     This knob is deprecated.
  memory.oom_control		     set/show oom controls.
                                      This knob is deprecated and shouldn't be
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
@@ -1076,15 +1076,20 @@ cpufreq governor about the minimum desired frequency which should always be
 provided by a CPU, as well as the maximum desired frequency, which should not
 be exceeded by a CPU.
 
-WARNING: cgroup2 doesn't yet support control of realtime processes. For
-a kernel built with the CONFIG_RT_GROUP_SCHED option enabled for group
-scheduling of realtime processes, the cpu controller can only be enabled
-when all RT processes are in the root cgroup.  This limitation does
-not apply if CONFIG_RT_GROUP_SCHED is disabled.  Be aware that system
-management software may already have placed RT processes into nonroot
-cgroups during the system boot process, and these processes may need
-to be moved to the root cgroup before the cpu controller can be enabled
-with a CONFIG_RT_GROUP_SCHED enabled kernel.
+WARNING: cgroup2 cpu controller doesn't yet fully support the control of
+realtime processes. For a kernel built with the CONFIG_RT_GROUP_SCHED option
+enabled for group scheduling of realtime processes, the cpu controller can only
+be enabled when all RT processes are in the root cgroup. Be aware that system
+management software may already have placed RT processes into non-root cgroups
+during the system boot process, and these processes may need to be moved to the
+root cgroup before the cpu controller can be enabled with a
+CONFIG_RT_GROUP_SCHED enabled kernel.
+
+With CONFIG_RT_GROUP_SCHED disabled, this limitation does not apply and some of
+the interface files either affect realtime processes or account for them. See
+the following section for details. Only the cpu controller is affected by
+CONFIG_RT_GROUP_SCHED. Other controllers can be used for the resource control of
+realtime processes irrespective of CONFIG_RT_GROUP_SCHED.
 
 
 CPU Interface Files
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
@@ -659,6 +659,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	struct blkcg_gq *blkg;
 	int i;
 
+	pr_info_once("blkio.%s is deprecated\n", cftype->name);
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
 
@@ -1770,12 +1771,15 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 	mutex_unlock(&blkcg_pol_mutex);
 
 	/* everything is in place, add intf files for the new policy */
-	if (pol->dfl_cftypes)
+	if (pol->dfl_cftypes == pol->legacy_cftypes) {
+		WARN_ON(cgroup_add_cftypes(&io_cgrp_subsys,
+					   pol->dfl_cftypes));
+	} else {
 		WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
 					       pol->dfl_cftypes));
-	if (pol->legacy_cftypes)
 		WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
 						  pol->legacy_cftypes));
+	}
 	mutex_unlock(&blkcg_pol_register_mutex);
 	return 0;
 
diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c
@@ -113,27 +113,18 @@ static void ioprio_free_cpd(struct blkcg_policy_data *cpd)
 	kfree(blkcg);
 }
 
-#define IOPRIO_ATTRS						\
-	{							\
-		.name		= "prio.class",			\
-		.seq_show	= ioprio_show_prio_policy,	\
-		.write		= ioprio_set_prio_policy,	\
-	},							\
-	{ } /* sentinel */
-
-/* cgroup v2 attributes */
 static struct cftype ioprio_files[] = {
-	IOPRIO_ATTRS
-};
-
-/* cgroup v1 attributes */
-static struct cftype ioprio_legacy_files[] = {
-	IOPRIO_ATTRS
+	{
+		.name		= "prio.class",
+		.seq_show	= ioprio_show_prio_policy,
+		.write		= ioprio_set_prio_policy,
+	},
+	{ } /* sentinel */
 };
 
 static struct blkcg_policy ioprio_policy = {
 	.dfl_cftypes	= ioprio_files,
-	.legacy_cftypes = ioprio_legacy_files,
+	.legacy_cftypes = ioprio_files,
 
 	.cpd_alloc_fn	= ioprio_alloc_cpd,
 	.cpd_free_fn	= ioprio_free_cpd,
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
@@ -619,9 +619,8 @@ struct cgroup_root {
  */
 struct cftype {
 	/*
-	 * By convention, the name should begin with the name of the
-	 * subsystem, followed by a period.  Zero length string indicates
-	 * end of cftype array.
+	 * Name of the subsystem is prepended in cgroup_file_name().
+	 * Zero length string indicates end of cftype array.
 	 */
 	char name[MAX_CFTYPE_NAME];
 	unsigned long private;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
@@ -113,6 +113,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
 int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 void cgroup_file_notify(struct cgroup_file *cfile);
 void cgroup_file_show(struct cgroup_file *cfile, bool show);
@@ -689,8 +690,6 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
  */
 void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
 void cgroup_rstat_flush(struct cgroup *cgrp);
-void cgroup_rstat_flush_hold(struct cgroup *cgrp);
-void cgroup_rstat_flush_release(struct cgroup *cgrp);
 
 /*
  * Basic resource stats.
diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h
@@ -60,7 +60,6 @@ struct misc_cg {
 	struct misc_res res[MISC_CG_RES_TYPES];
 };
 
-u64 misc_cg_res_total_usage(enum misc_res_type type);
 int misc_cg_set_capacity(enum misc_res_type type, u64 capacity);
 int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount);
 void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg, u64 amount);
@@ -104,11 +103,6 @@ static inline void put_misc_cg(struct misc_cg *cg)
 
 #else /* !CONFIG_CGROUP_MISC */
 
-static inline u64 misc_cg_res_total_usage(enum misc_res_type type)
-{
-	return 0;
-}
-
 static inline int misc_cg_set_capacity(enum misc_res_type type, u64 capacity)
 {
 	return 0;
diff --git a/init/Kconfig b/init/Kconfig
@@ -1198,15 +1198,16 @@ config CPUSETS_V1
 	help
 	  Legacy cgroup v1 cpusets controller which has been deprecated by
 	  cgroup v2 implementation. The v1 is there for legacy applications
-	  which haven't migrated to the new cgroup v2 interface yet. If you
+	  which haven't migrated to the new cgroup v2 interface yet. Legacy
+	  interface includes cpuset filesystem and /proc/<pid>/cpuset. If you
 	  do not have any such application then you are completely fine leaving
 	  this option disabled.
 
 	  Say N if unsure.
 
 config PROC_PID_CPUSET
 	bool "Include legacy /proc/<pid>/cpuset file"
-	depends on CPUSETS
+	depends on CPUSETS_V1
 	default y
 
 config CGROUP_DEVICE
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
@@ -168,6 +168,7 @@ struct cgroup_mgctx {
 
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
+extern bool cgrp_dfl_visible;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
@@ -673,6 +673,7 @@ struct cftype cgroup1_base_files[] = {
 int proc_cgroupstats_show(struct seq_file *m, void *v)
 {
 	struct cgroup_subsys *ss;
+	bool cgrp_v1_visible = false;
 	int i;
 
 	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
@@ -684,12 +685,18 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 	for_each_subsys(ss, i) {
 		if (cgroup1_subsys_absent(ss))
 			continue;
+		cgrp_v1_visible |= ss->root != &cgrp_dfl_root;
+
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps),
 			   cgroup_ssid_enabled(i));
 	}
 
+	if (cgrp_dfl_visible && !cgrp_v1_visible)
+		pr_info_once("/proc/cgroups lists only v1 controllers, use cgroup.controllers of root cgroup for v2 info\n");
+
+
 	return 0;
 }
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
@@ -171,7 +171,7 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root);
  * The default hierarchy always exists but is hidden until mounted for the
  * first time.  This is for backward compatibility.
  */
-static bool cgrp_dfl_visible;
+bool cgrp_dfl_visible;
 
 /* some controllers are not supported in the default hierarchy */
 static u16 cgrp_dfl_inhibit_ss_mask;
@@ -4447,7 +4447,7 @@ int cgroup_rm_cftypes(struct cftype *cfts)
  * function currently returns 0 as long as @cfts registration is successful
  * even if some file creation attempts on existing cgroups fail.
  */
-static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	int ret;
 
@@ -5831,7 +5831,7 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
 	}
 
 	/*
-	 * This extra ref will be put in cgroup_free_fn() and guarantees
+	 * This extra ref will be put in css_free_rwork_fn() and guarantees
 	 * that @cgrp->kn is always accessible.
 	 */
 	kernfs_get(cgrp->kn);
diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include "cgroup-internal.h"
 #include "cpuset-internal.h"
 
 /*
@@ -175,6 +176,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	switch (type) {
 	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = update_relax_domain_level(cs, val);
 		break;
 	default:
@@ -373,6 +375,46 @@ int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial)
 	return ret;
 }
 
+#ifdef CONFIG_PROC_PID_CPUSET
+/*
+ * proc_cpuset_show()
+ *  - Print tasks cpuset path into seq_file.
+ *  - Used for /proc/<pid>/cpuset.
+ */
+int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
+{
+	char *buf;
+	struct cgroup_subsys_state *css;
+	int retval;
+
+	retval = -ENOMEM;
+	buf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	rcu_read_lock();
+	spin_lock_irq(&css_set_lock);
+	css = task_css(tsk, cpuset_cgrp_id);
+	retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
+				       current->nsproxy->cgroup_ns);
+	spin_unlock_irq(&css_set_lock);
+	rcu_read_unlock();
+
+	if (retval == -E2BIG)
+		retval = -ENAMETOOLONG;
+	if (retval < 0)
+		goto out_free;
+	seq_puts(m, buf);
+	seq_putc(m, '\n');
+	retval = 0;
+out_free:
+	kfree(buf);
+out:
+	return retval;
+}
+#endif /* CONFIG_PROC_PID_CPUSET */
+
 static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct cpuset *cs = css_cs(css);
@@ -424,24 +466,31 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 		retval = cpuset_update_flag(CS_CPU_EXCLUSIVE, cs, val);
 		break;
 	case FILE_MEM_EXCLUSIVE:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_MEM_EXCLUSIVE, cs, val);
 		break;
 	case FILE_MEM_HARDWALL:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_MEM_HARDWALL, cs, val);
 		break;
 	case FILE_SCHED_LOAD_BALANCE:
+		pr_info_once("cpuset.%s is deprecated, use cpuset.cpus.partition instead\n", cft->name);
 		retval = cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
 		break;
 	case FILE_MEMORY_MIGRATE:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_MEMORY_MIGRATE, cs, val);
 		break;
 	case FILE_MEMORY_PRESSURE_ENABLED:
+		pr_info_once("cpuset.%s is deprecated, use memory.pressure with CONFIG_PSI instead\n", cft->name);
 		cpuset_memory_pressure_enabled = !!val;
 		break;
 	case FILE_SPREAD_PAGE:
+		pr_info_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_SPREAD_PAGE, cs, val);
 		break;
 	case FILE_SPREAD_SLAB:
+		pr_warn_once("cpuset.%s is deprecated\n", cft->name);
 		retval = cpuset_update_flag(CS_SPREAD_SLAB, cs, val);
 		break;
 	default:
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
@@ -21,7 +21,6 @@
  *  License.  See the file COPYING in the main directory of the Linux
  *  distribution for more details.
  */
-#include "cgroup-internal.h"
 #include "cpuset-internal.h"
 
 #include <linux/init.h>
@@ -4244,50 +4243,6 @@ void cpuset_print_current_mems_allowed(void)
 	rcu_read_unlock();
 }
 
-#ifdef CONFIG_PROC_PID_CPUSET
-/*
- * proc_cpuset_show()
- *  - Print tasks cpuset path into seq_file.
- *  - 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
- *    anyway.
- */
-int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
-		     struct pid *pid, struct task_struct *tsk)
-{
-	char *buf;
-	struct cgroup_subsys_state *css;
-	int retval;
-
-	retval = -ENOMEM;
-	buf = kmalloc(PATH_MAX, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	rcu_read_lock();
-	spin_lock_irq(&css_set_lock);
-	css = task_css(tsk, cpuset_cgrp_id);
-	retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
-				       current->nsproxy->cgroup_ns);
-	spin_unlock_irq(&css_set_lock);
-	rcu_read_unlock();
-
-	if (retval == -E2BIG)
-		retval = -ENAMETOOLONG;
-	if (retval < 0)
-		goto out_free;
-	seq_puts(m, buf);
-	seq_putc(m, '\n');
-	retval = 0;
-out_free:
-	kfree(buf);
-out:
-	return retval;
-}
-#endif /* CONFIG_PROC_PID_CPUSET */
-
 /* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
