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

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

8 files changed, 100 insertions, 146 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c964dd7ff967..95ab39e1ec8f 100644
--- 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
index e28d5f0d20ed..11ea8d24ac72 100644
--- 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
index afc665b7b1fe..f231fe3a0744 100644
--- 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
index 25c1d7b77e2f..b69a7db67090 100644
--- 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 @@ out:
 	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
index 0f910c828973..5a637292faa2 100644
--- 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
index 074653f964c1..039d1eb2f215 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -430,9 +430,11 @@ static ssize_t freezer_write(struct kernfs_open_file *of,
 
 	if (strcmp(buf, freezer_state_strs(0)) == 0)
 		freeze = false;
-	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0)
+	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0) {
+		pr_info_once("Freezing with imperfect legacy cgroup freezer. "
+			     "See cgroup.freeze of cgroup v2\n");
 		freeze = true;
-	else
+	} else
 		return -EINVAL;
 
 	freezer_change_state(css_freezer(of_css(of)), freeze);
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
index 0e26068995a6..2fa3a4fb2aaf 100644
--- a/kernel/cgroup/misc.c
+++ b/kernel/cgroup/misc.c
@@ -68,22 +68,6 @@ static inline bool valid_type(enum misc_res_type type)
 }
 
 /**
- * misc_cg_res_total_usage() - Get the current total usage of the resource.
- * @type: misc res type.
- *
- * Context: Any context.
- * Return: Current total usage of the resource.
- */
-u64 misc_cg_res_total_usage(enum misc_res_type type)
-{
-	if (valid_type(type))
-		return atomic64_read(&root_cg.res[type].usage);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(misc_cg_res_total_usage);
-
-/**
  * misc_cg_set_capacity() - Set the capacity of the misc cgroup res.
  * @type: Type of the misc res.
  * @capacity: Supported capacity of the misc res on the host.
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index aac91466279f..4bb587d5d34f 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -299,40 +299,6 @@ static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
 	spin_unlock_irq(&cgroup_rstat_lock);
 }
 
-/* see cgroup_rstat_flush() */
-static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
-	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
-{
-	int cpu;
-
-	lockdep_assert_held(&cgroup_rstat_lock);
-
-	for_each_possible_cpu(cpu) {
-		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
-
-		for (; pos; pos = pos->rstat_flush_next) {
-			struct cgroup_subsys_state *css;
-
-			cgroup_base_stat_flush(pos, cpu);
-			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
-
-			rcu_read_lock();
-			list_for_each_entry_rcu(css, &pos->rstat_css_list,
-						rstat_css_node)
-				css->ss->css_rstat_flush(css, cpu);
-			rcu_read_unlock();
-		}
-
-		/* play nice and yield if necessary */
-		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
-			__cgroup_rstat_unlock(cgrp, cpu);
-			if (!cond_resched())
-				cpu_relax();
-			__cgroup_rstat_lock(cgrp, cpu);
-		}
-	}
-}
-
 /**
  * cgroup_rstat_flush - flush stats in @cgrp's subtree
  * @cgrp: target cgroup
@@ -348,38 +314,30 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
  */
 __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
 {
+	int cpu;
+
 	might_sleep();
+	for_each_possible_cpu(cpu) {
+		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
 
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
-	__cgroup_rstat_unlock(cgrp, -1);
-}
+		/* Reacquire for each CPU to avoid disabling IRQs too long */
+		__cgroup_rstat_lock(cgrp, cpu);
+		for (; pos; pos = pos->rstat_flush_next) {
+			struct cgroup_subsys_state *css;
 
-/**
- * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold
- * @cgrp: target cgroup
- *
- * Flush stats in @cgrp's subtree and prevent further flushes.  Must be
- * paired with cgroup_rstat_flush_release().
- *
- * This function may block.
- */
-void cgroup_rstat_flush_hold(struct cgroup *cgrp)
-	__acquires(&cgroup_rstat_lock)
-{
-	might_sleep();
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
-}
+			cgroup_base_stat_flush(pos, cpu);
+			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
 
-/**
- * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
- * @cgrp: cgroup used by tracepoint
- */
-void cgroup_rstat_flush_release(struct cgroup *cgrp)
-	__releases(&cgroup_rstat_lock)
-{
-	__cgroup_rstat_unlock(cgrp, -1);
+			rcu_read_lock();
+			list_for_each_entry_rcu(css, &pos->rstat_css_list,
+						rstat_css_node)
+				css->ss->css_rstat_flush(css, cpu);
+			rcu_read_unlock();
+		}
+		__cgroup_rstat_unlock(cgrp, cpu);
+		if (!cond_resched())
+			cpu_relax();
+	}
 }
 
 int cgroup_rstat_init(struct cgroup *cgrp)
@@ -612,36 +570,34 @@ static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime, ntime;
+	struct cgroup_base_stat bstat;
 
 	if (cgroup_parent(cgrp)) {
-		cgroup_rstat_flush_hold(cgrp);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
+		cgroup_rstat_flush(cgrp);
+		__cgroup_rstat_lock(cgrp, -1);
+		bstat = cgrp->bstat;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
-			       &utime, &stime);
-		ntime = cgrp->bstat.ntime;
-		cgroup_rstat_flush_release(cgrp);
+			       &bstat.cputime.utime, &bstat.cputime.stime);
+		__cgroup_rstat_unlock(cgrp, -1);
 	} else {
-		/* cgrp->bstat of root is not actually used, reuse it */
-		root_cgroup_cputime(&cgrp->bstat);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
-		utime = cgrp->bstat.cputime.utime;
-		stime = cgrp->bstat.cputime.stime;
-		ntime = cgrp->bstat.ntime;
+		root_cgroup_cputime(&bstat);
 	}
 
-	do_div(usage, NSEC_PER_USEC);
-	do_div(utime, NSEC_PER_USEC);
-	do_div(stime, NSEC_PER_USEC);
-	do_div(ntime, NSEC_PER_USEC);
+	do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC);
+	do_div(bstat.cputime.utime, NSEC_PER_USEC);
+	do_div(bstat.cputime.stime, NSEC_PER_USEC);
+	do_div(bstat.ntime, NSEC_PER_USEC);
 
 	seq_printf(seq, "usage_usec %llu\n"
 			"user_usec %llu\n"
 			"system_usec %llu\n"
 			"nice_usec %llu\n",
-			usage, utime, stime, ntime);
+			bstat.cputime.sum_exec_runtime,
+			bstat.cputime.utime,
+			bstat.cputime.stime,
+			bstat.ntime);
 
-	cgroup_force_idle_show(seq, &cgrp->bstat);
+	cgroup_force_idle_show(seq, &bstat);
 }
 
 /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */