Resguardo inicial

linux-7.2.3/kernel/cgroup/Makefile

@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y := cgroup.o rstat.o namespace.o cgroup-v1.o freezer.o
+
+obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o
+obj-$(CONFIG_CGROUP_PIDS) += pids.o
+obj-$(CONFIG_CGROUP_RDMA) += rdma.o
+obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CPUSETS_V1) += cpuset-v1.o
+obj-$(CONFIG_CGROUP_MISC) += misc.o
+obj-$(CONFIG_CGROUP_DMEM) += dmem.o
+obj-$(CONFIG_CGROUP_DEBUG) += debug.o

linux-7.2.3/kernel/cgroup/cgroup-internal.h

@@ -0,0 +1,296 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __CGROUP_INTERNAL_H
+#define __CGROUP_INTERNAL_H
+
+#include <linux/cgroup.h>
+#include <linux/kernfs.h>
+#include <linux/workqueue.h>
+#include <linux/list.h>
+#include <linux/refcount.h>
+#include <linux/fs_parser.h>
+
+#define TRACE_CGROUP_PATH_LEN 1024
+extern spinlock_t trace_cgroup_path_lock;
+extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+extern void __init enable_debug_cgroup(void);
+
+/*
+ * cgroup_path() takes a spin lock. It is good practice not to take
+ * spin locks within trace point handlers, as they are mostly hidden
+ * from normal view. As cgroup_path() can take the kernfs_rename_lock
+ * spin lock, it is best to not call that function from the trace event
+ * handler.
+ *
+ * Note: trace_cgroup_##type##_enabled() is a static branch that will only
+ *       be set when the trace event is enabled.
+ */
+#define TRACE_CGROUP_PATH(type, cgrp, ...)				\
+	do {								\
+		if (trace_cgroup_##type##_enabled()) {			\
+			unsigned long flags;				\
+			spin_lock_irqsave(&trace_cgroup_path_lock,	\
+					  flags);			\
+			cgroup_path(cgrp, trace_cgroup_path,		\
+				    TRACE_CGROUP_PATH_LEN);		\
+			trace_cgroup_##type(cgrp, trace_cgroup_path,	\
+					    ##__VA_ARGS__);		\
+			spin_unlock_irqrestore(&trace_cgroup_path_lock, \
+					       flags);			\
+		}							\
+	} while (0)
+
+/*
+ * The cgroup filesystem superblock creation/mount context.
+ */
+struct cgroup_fs_context {
+	struct kernfs_fs_context kfc;
+	struct cgroup_root	*root;
+	struct cgroup_namespace	*ns;
+	unsigned int	flags;			/* CGRP_ROOT_* flags */
+
+	/* cgroup1 bits */
+	bool		cpuset_clone_children;
+	bool		none;			/* User explicitly requested empty subsystem */
+	bool		all_ss;			/* Seen 'all' option */
+	u32		subsys_mask;		/* Selected subsystems */
+	char		*name;			/* Hierarchy name */
+	char		*release_agent;		/* Path for release notifications */
+};
+
+static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	return container_of(kfc, struct cgroup_fs_context, kfc);
+}
+
+struct cgroup_pidlist;
+
+struct cgroup_file_ctx {
+	struct cgroup_namespace	*ns;
+
+	struct {
+		void			*trigger;
+	} psi;
+
+	struct {
+		bool			started;
+		struct css_task_iter	iter;
+	} procs;
+
+	struct {
+		struct cgroup_pidlist	*pidlist;
+	} procs1;
+
+	struct cgroup_of_peak peak;
+};
+
+/*
+ * A cgroup can be associated with multiple css_sets as different tasks may
+ * belong to different cgroups on different hierarchies.  In the other
+ * direction, a css_set is naturally associated with multiple cgroups.
+ * This M:N relationship is represented by the following link structure
+ * which exists for each association and allows traversing the associations
+ * from both sides.
+ */
+struct cgrp_cset_link {
+	/* the cgroup and css_set this link associates */
+	struct cgroup		*cgrp;
+	struct css_set		*cset;
+
+	/* list of cgrp_cset_links anchored at cgrp->cset_links */
+	struct list_head	cset_link;
+
+	/* list of cgrp_cset_links anchored at css_set->cgrp_links */
+	struct list_head	cgrp_link;
+};
+
+/* used to track tasks and csets during migration */
+struct cgroup_taskset {
+	/* the src and dst cset list running through cset->mg_node */
+	struct list_head	src_csets;
+	struct list_head	dst_csets;
+
+	/* the number of tasks in the set */
+	int			nr_tasks;
+
+	/* the subsys currently being processed */
+	int			ssid;
+
+	/*
+	 * Fields for cgroup_taskset_*() iteration.
+	 *
+	 * Before migration is committed, the target migration tasks are on
+	 * ->mg_tasks of the csets on ->src_csets.  After, on ->mg_tasks of
+	 * the csets on ->dst_csets.  ->csets point to either ->src_csets
+	 * or ->dst_csets depending on whether migration is committed.
+	 *
+	 * ->cur_csets and ->cur_task point to the current task position
+	 * during iteration.
+	 */
+	struct list_head	*csets;
+	struct css_set		*cur_cset;
+	struct task_struct	*cur_task;
+};
+
+/* migration context also tracks preloading */
+struct cgroup_mgctx {
+	/*
+	 * Preloaded source and destination csets.  Used to guarantee
+	 * atomic success or failure on actual migration.
+	 */
+	struct list_head	preloaded_src_csets;
+	struct list_head	preloaded_dst_csets;
+
+	/* tasks and csets to migrate */
+	struct cgroup_taskset	tset;
+
+	/* subsystems affected by migration */
+	u32			ss_mask;
+};
+
+#define CGROUP_TASKSET_INIT(tset)						\
+{										\
+	.src_csets		= LIST_HEAD_INIT(tset.src_csets),		\
+	.dst_csets		= LIST_HEAD_INIT(tset.dst_csets),		\
+	.csets			= &tset.src_csets,				\
+}
+
+#define CGROUP_MGCTX_INIT(name)							\
+{										\
+	LIST_HEAD_INIT(name.preloaded_src_csets),				\
+	LIST_HEAD_INIT(name.preloaded_dst_csets),				\
+	CGROUP_TASKSET_INIT(name.tset),						\
+}
+
+#define DEFINE_CGROUP_MGCTX(name)						\
+	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
+
+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)						\
+	list_for_each_entry_rcu((root), &cgroup_roots, root_list,	\
+				lockdep_is_held(&cgroup_mutex))
+
+/**
+ * for_each_subsys - iterate all enabled cgroup subsystems
+ * @ss: the iteration cursor
+ * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
+ */
+#define for_each_subsys(ss, ssid)					\
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT &&		\
+	     (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
+
+static inline bool notify_on_release(const struct cgroup *cgrp)
+{
+	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+}
+
+void put_css_set_locked(struct css_set *cset);
+
+static inline void put_css_set(struct css_set *cset)
+{
+	unsigned long flags;
+
+	/*
+	 * Ensure that the refcount doesn't hit zero while any readers
+	 * can see it. Similar to atomic_dec_and_lock(), but for an
+	 * rwlock
+	 */
+	if (refcount_dec_not_one(&cset->refcount))
+		return;
+
+	spin_lock_irqsave(&css_set_lock, flags);
+	put_css_set_locked(cset);
+	spin_unlock_irqrestore(&css_set_lock, flags);
+}
+
+/*
+ * refcounted get/put for css_set objects
+ */
+static inline void get_css_set(struct css_set *cset)
+{
+	refcount_inc(&cset->refcount);
+}
+
+bool cgroup_ssid_enabled(int ssid);
+
+struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root);
+struct cgroup *task_cgroup_from_root(struct task_struct *task,
+				     struct cgroup_root *root);
+struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline);
+void cgroup_kn_unlock(struct kernfs_node *kn);
+int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
+			  struct cgroup_namespace *ns);
+
+void cgroup_favor_dynmods(struct cgroup_root *root, bool favor);
+void cgroup_free_root(struct cgroup_root *root);
+void init_cgroup_root(struct cgroup_fs_context *ctx);
+int cgroup_setup_root(struct cgroup_root *root, u32 ss_mask);
+int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask);
+int cgroup_do_get_tree(struct fs_context *fc);
+
+int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp);
+void cgroup_migrate_finish(struct cgroup_mgctx *mgctx);
+void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp,
+			    struct cgroup_mgctx *mgctx);
+int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx);
+int cgroup_migrate(struct task_struct *leader, bool threadgroup,
+		   struct cgroup_mgctx *mgctx);
+
+int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
+		       bool threadgroup);
+void cgroup_attach_lock(enum cgroup_attach_lock_mode lock_mode,
+			struct task_struct *tsk);
+void cgroup_attach_unlock(enum cgroup_attach_lock_mode lock_mode,
+			  struct task_struct *tsk);
+struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
+					     enum cgroup_attach_lock_mode *lock_mode)
+	__acquires(&cgroup_threadgroup_rwsem);
+void cgroup_procs_write_finish(struct task_struct *task,
+			       enum cgroup_attach_lock_mode lock_mode)
+	__releases(&cgroup_threadgroup_rwsem);
+
+void cgroup_lock_and_drain_offline(struct cgroup *cgrp);
+
+int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode);
+int cgroup_rmdir(struct kernfs_node *kn);
+int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
+		     struct kernfs_root *kf_root);
+
+int __cgroup_task_count(const struct cgroup *cgrp);
+int cgroup_task_count(const struct cgroup *cgrp);
+
+/*
+ * rstat.c
+ */
+int css_rstat_init(struct cgroup_subsys_state *css);
+void css_rstat_exit(struct cgroup_subsys_state *css);
+int ss_rstat_init(struct cgroup_subsys *ss);
+void cgroup_base_stat_cputime_show(struct seq_file *seq);
+
+/*
+ * namespace.c
+ */
+extern const struct proc_ns_operations cgroupns_operations;
+
+/*
+ * cgroup-v1.c
+ */
+extern struct cftype cgroup1_base_files[];
+extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
+extern const struct fs_parameter_spec cgroup1_fs_parameters[];
+
+int proc_cgroupstats_show(struct seq_file *m, void *v);
+bool cgroup1_ssid_disabled(int ssid);
+void cgroup1_pidlist_destroy_all(struct cgroup *cgrp);
+void cgroup1_release_agent(struct work_struct *work);
+void cgroup1_check_for_release(struct cgroup *cgrp);
+int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param);
+int cgroup1_get_tree(struct fs_context *fc);
+int cgroup1_reconfigure(struct fs_context *ctx);
+
+#endif /* __CGROUP_INTERNAL_H */

linux-7.2.3/kernel/cgroup/cpuset-internal.h

@@ -0,0 +1,354 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __CPUSET_INTERNAL_H
+#define __CPUSET_INTERNAL_H
+
+#include <linux/cgroup.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/cpuset.h>
+#include <linux/spinlock.h>
+#include <linux/union_find.h>
+#include <linux/sched/isolation.h>
+
+/* See "Frequency meter" comments, below. */
+
+struct fmeter {
+	int cnt;		/* unprocessed events count */
+	int val;		/* most recent output value */
+	time64_t time;		/* clock (secs) when val computed */
+	spinlock_t lock;	/* guards read or write of above */
+};
+
+/*
+ * Invalid partition error code
+ */
+enum prs_errcode {
+	PERR_NONE = 0,
+	PERR_INVCPUS,
+	PERR_INVPARENT,
+	PERR_NOTPART,
+	PERR_NOTEXCL,
+	PERR_NOCPUS,
+	PERR_HOTPLUG,
+	PERR_CPUSEMPTY,
+	PERR_HKEEPING,
+	PERR_ACCESS,
+	PERR_REMOTE,
+};
+
+/* bits in struct cpuset flags field */
+typedef enum {
+	CS_CPU_EXCLUSIVE,
+	CS_MEM_EXCLUSIVE,
+	CS_MEM_HARDWALL,
+	CS_MEMORY_MIGRATE,
+	CS_SCHED_LOAD_BALANCE,
+	CS_SPREAD_PAGE,
+	CS_SPREAD_SLAB,
+} cpuset_flagbits_t;
+
+/* The various types of files and directories in a cpuset file system */
+
+typedef enum {
+	FILE_MEMORY_MIGRATE,
+	FILE_CPULIST,
+	FILE_MEMLIST,
+	FILE_EFFECTIVE_CPULIST,
+	FILE_EFFECTIVE_MEMLIST,
+	FILE_SUBPARTS_CPULIST,
+	FILE_EXCLUSIVE_CPULIST,
+	FILE_EFFECTIVE_XCPULIST,
+	FILE_ISOLATED_CPULIST,
+	FILE_CPU_EXCLUSIVE,
+	FILE_MEM_EXCLUSIVE,
+	FILE_MEM_HARDWALL,
+	FILE_SCHED_LOAD_BALANCE,
+	FILE_PARTITION_ROOT,
+	FILE_SCHED_RELAX_DOMAIN_LEVEL,
+	FILE_MEMORY_PRESSURE_ENABLED,
+	FILE_MEMORY_PRESSURE,
+	FILE_SPREAD_PAGE,
+	FILE_SPREAD_SLAB,
+} cpuset_filetype_t;
+
+struct cpuset {
+	struct cgroup_subsys_state css;
+
+	unsigned long flags;		/* "unsigned long" so bitops work */
+
+	/*
+	 * On default hierarchy:
+	 *
+	 * The user-configured masks can only be changed by writing to
+	 * cpuset.cpus and cpuset.mems, and won't be limited by the
+	 * parent masks.
+	 *
+	 * The effective masks is the real masks that apply to the tasks
+	 * in the cpuset. They may be changed if the configured masks are
+	 * changed or hotplug happens.
+	 *
+	 * effective_mask == configured_mask & parent's effective_mask,
+	 * and if it ends up empty, it will inherit the parent's mask.
+	 *
+	 *
+	 * On legacy hierarchy:
+	 *
+	 * The user-configured masks are always the same with effective masks.
+	 */
+
+	/* user-configured CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t cpus_allowed;
+	nodemask_t mems_allowed;
+
+	/* effective CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t effective_cpus;
+	nodemask_t effective_mems;
+
+	/*
+	 * Exclusive CPUs dedicated to current cgroup (default hierarchy only)
+	 *
+	 * The effective_cpus of a valid partition root comes solely from its
+	 * effective_xcpus and some of the effective_xcpus may be distributed
+	 * to sub-partitions below & hence excluded from its effective_cpus.
+	 * For a valid partition root, its effective_cpus have no relationship
+	 * with cpus_allowed unless its exclusive_cpus isn't set.
+	 *
+	 * This value will only be set if either exclusive_cpus is set or
+	 * when this cpuset becomes a local partition root.
+	 */
+	cpumask_var_t effective_xcpus;
+
+	/*
+	 * Exclusive CPUs as requested by the user (default hierarchy only)
+	 *
+	 * Its value is independent of cpus_allowed and designates the set of
+	 * CPUs that can be granted to the current cpuset or its children when
+	 * it becomes a valid partition root. The effective set of exclusive
+	 * CPUs granted (effective_xcpus) depends on whether those exclusive
+	 * CPUs are passed down by its ancestors and not yet taken up by
+	 * another sibling partition root along the way.
+	 *
+	 * If its value isn't set, it defaults to cpus_allowed.
+	 */
+	cpumask_var_t exclusive_cpus;
+
+	/*
+	 * This is old Memory Nodes tasks took on.
+	 *
+	 * - top_cpuset.old_mems_allowed is initialized to mems_allowed.
+	 * - A new cpuset's old_mems_allowed is initialized when some
+	 *   task is moved into it.
+	 * - old_mems_allowed is used in cpuset_migrate_mm() when we change
+	 *   cpuset.mems_allowed and have tasks' nodemask updated, and
+	 *   then old_mems_allowed is updated to mems_allowed.
+	 */
+	nodemask_t old_mems_allowed;
+
+	/*
+	 * Tasks are being attached to this cpuset.  Used to prevent
+	 * zeroing cpus/mems_allowed between ->can_attach() and ->attach().
+	 */
+	int attach_in_progress;
+
+	/* partition root state */
+	int partition_root_state;
+
+	/*
+	 * Whether cpuset is a remote partition.
+	 * It used to be a list anchoring all remote partitions — we can switch back
+	 * to a list if we need to iterate over the remote partitions.
+	 */
+	bool remote_partition;
+
+	/*
+	 * number of SCHED_DEADLINE tasks attached to this cpuset, so that we
+	 * know when to rebuild associated root domain bandwidth information.
+	 */
+	int nr_deadline_tasks;
+	int nr_migrate_dl_tasks;
+	/* DL bandwidth that needs destination reservation for this attach. */
+	u64 sum_migrate_dl_bw;
+	/*
+	 * CPU used for temporary DL bandwidth allocation during attach;
+	 * -1 if no DL bandwidth was allocated in the current attach.
+	 */
+	int dl_bw_cpu;
+
+	/* Invalid partition error code, not lock protected */
+	enum prs_errcode prs_err;
+
+	/* Handle for cpuset.cpus.partition */
+	struct cgroup_file partition_file;
+
+#ifdef CONFIG_CPUSETS_V1
+	struct fmeter fmeter;		/* memory_pressure filter */
+
+	/* for custom sched domain */
+	int relax_domain_level;
+
+	/* Used to merge intersecting subsets for generate_sched_domains */
+	struct uf_node node;
+#endif
+};
+
+extern struct cpuset top_cpuset;
+
+static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct cpuset, css) : NULL;
+}
+
+/* Retrieve the cpuset for a task */
+static inline struct cpuset *task_cs(struct task_struct *task)
+{
+	return css_cs(task_css(task, cpuset_cgrp_id));
+}
+
+static inline struct cpuset *parent_cs(struct cpuset *cs)
+{
+	return css_cs(cs->css.parent);
+}
+
+/* convenient tests for these bits */
+static inline bool is_cpuset_online(struct cpuset *cs)
+{
+	return css_is_online(&cs->css) && !css_is_dying(&cs->css);
+}
+
+static inline int is_cpu_exclusive(const struct cpuset *cs)
+{
+	return test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
+}
+
+static inline int is_mem_exclusive(const struct cpuset *cs)
+{
+	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
+}
+
+static inline int is_mem_hardwall(const struct cpuset *cs)
+{
+	return test_bit(CS_MEM_HARDWALL, &cs->flags);
+}
+
+static inline int is_sched_load_balance(const struct cpuset *cs)
+{
+	return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+}
+
+static inline int is_memory_migrate(const struct cpuset *cs)
+{
+	return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
+}
+
+static inline int is_spread_page(const struct cpuset *cs)
+{
+	return test_bit(CS_SPREAD_PAGE, &cs->flags);
+}
+
+static inline int is_spread_slab(const struct cpuset *cs)
+{
+	return test_bit(CS_SPREAD_SLAB, &cs->flags);
+}
+
+/*
+ * Helper routine for generate_sched_domains().
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
+ */
+static inline int cpusets_overlap(struct cpuset *a, struct cpuset *b)
+{
+	return cpumask_intersects(a->effective_cpus, b->effective_cpus);
+}
+
+static inline int nr_cpusets(void)
+{
+	/* jump label reference count + the top-level cpuset */
+	return static_key_count(&cpusets_enabled_key.key) + 1;
+}
+
+static inline bool cpuset_is_populated(struct cpuset *cs)
+{
+	lockdep_assert_cpuset_lock_held();
+
+	/* Cpusets in the process of attaching should be considered as populated */
+	return cgroup_is_populated(cs->css.cgroup) ||
+		cs->attach_in_progress;
+}
+
+/**
+ * cpuset_for_each_child - traverse online children of a cpuset
+ * @child_cs: loop cursor pointing to the current child
+ * @pos_css: used for iteration
+ * @parent_cs: target cpuset to walk children of
+ *
+ * Walk @child_cs through the online children of @parent_cs.  Must be used
+ * with RCU read locked.
+ */
+#define cpuset_for_each_child(child_cs, pos_css, parent_cs)		\
+	css_for_each_child((pos_css), &(parent_cs)->css)		\
+		if (is_cpuset_online(((child_cs) = css_cs((pos_css)))))
+
+/**
+ * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants
+ * @des_cs: loop cursor pointing to the current descendant
+ * @pos_css: used for iteration
+ * @root_cs: target cpuset to walk ancestor of
+ *
+ * Walk @des_cs through the online descendants of @root_cs.  Must be used
+ * with RCU read locked.  The caller may modify @pos_css by calling
+ * css_rightmost_descendant() to skip subtree.  @root_cs is included in the
+ * iteration and the first node to be visited.
+ */
+#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs)	\
+	css_for_each_descendant_pre((pos_css), &(root_cs)->css)		\
+		if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))
+
+void rebuild_sched_domains_locked(void);
+void cpuset_callback_lock_irq(void);
+void cpuset_callback_unlock_irq(void);
+void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus);
+void cpuset_update_tasks_nodemask(struct cpuset *cs);
+int cpuset_update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on);
+ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off);
+int cpuset_common_seq_show(struct seq_file *sf, void *v);
+void cpuset_full_lock(void);
+void cpuset_full_unlock(void);
+
+/*
+ * cpuset-v1.c
+ */
+#ifdef CONFIG_CPUSETS_V1
+extern struct cftype cpuset1_files[];
+void cpuset1_update_task_spread_flags(struct cpuset *cs,
+					struct task_struct *tsk);
+void cpuset1_update_tasks_flags(struct cpuset *cs);
+void cpuset1_hotplug_update_tasks(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated);
+int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial);
+bool cpuset1_cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2);
+void cpuset1_init(struct cpuset *cs);
+void cpuset1_online_css(struct cgroup_subsys_state *css);
+int cpuset1_generate_sched_domains(cpumask_var_t **domains,
+			struct sched_domain_attr **attributes);
+
+#else
+static inline void cpuset1_update_task_spread_flags(struct cpuset *cs,
+					struct task_struct *tsk) {}
+static inline void cpuset1_update_tasks_flags(struct cpuset *cs) {}
+static inline void cpuset1_hotplug_update_tasks(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated) {}
+static inline int cpuset1_validate_change(struct cpuset *cur,
+				struct cpuset *trial) { return 0; }
+static inline bool cpuset1_cpus_excl_conflict(struct cpuset *cs1,
+					struct cpuset *cs2) { return false; }
+static inline void cpuset1_init(struct cpuset *cs) {}
+static inline void cpuset1_online_css(struct cgroup_subsys_state *css) {}
+static inline int cpuset1_generate_sched_domains(cpumask_var_t **domains,
+			struct sched_domain_attr **attributes) { return 0; };
+
+#endif /* CONFIG_CPUSETS_V1 */
+
+#endif /* __CPUSET_INTERNAL_H */

linux-7.2.3/kernel/cgroup/cpuset-v1.c

@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "cgroup-internal.h"
+#include "cpuset-internal.h"
+
+/*
+ * Legacy hierarchy call to cgroup_transfer_tasks() is handled asynchrously
+ */
+struct cpuset_remove_tasks_struct {
+	struct work_struct work;
+	struct cpuset *cs;
+};
+
+/*
+ * Frequency meter - How fast is some event occurring?
+ *
+ * These routines manage a digitally filtered, constant time based,
+ * event frequency meter.  There are four routines:
+ *   fmeter_init() - initialize a frequency meter.
+ *   fmeter_markevent() - called each time the event happens.
+ *   fmeter_getrate() - returns the recent rate of such events.
+ *   fmeter_update() - internal routine used to update fmeter.
+ *
+ * A common data structure is passed to each of these routines,
+ * which is used to keep track of the state required to manage the
+ * frequency meter and its digital filter.
+ *
+ * The filter works on the number of events marked per unit time.
+ * The filter is single-pole low-pass recursive (IIR).  The time unit
+ * is 1 second.  Arithmetic is done using 32-bit integers scaled to
+ * simulate 3 decimal digits of precision (multiplied by 1000).
+ *
+ * With an FM_COEF of 933, and a time base of 1 second, the filter
+ * has a half-life of 10 seconds, meaning that if the events quit
+ * happening, then the rate returned from the fmeter_getrate()
+ * will be cut in half each 10 seconds, until it converges to zero.
+ *
+ * It is not worth doing a real infinitely recursive filter.  If more
+ * than FM_MAXTICKS ticks have elapsed since the last filter event,
+ * just compute FM_MAXTICKS ticks worth, by which point the level
+ * will be stable.
+ *
+ * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
+ * arithmetic overflow in the fmeter_update() routine.
+ *
+ * Given the simple 32 bit integer arithmetic used, this meter works
+ * best for reporting rates between one per millisecond (msec) and
+ * one per 32 (approx) seconds.  At constant rates faster than one
+ * per msec it maxes out at values just under 1,000,000.  At constant
+ * rates between one per msec, and one per second it will stabilize
+ * to a value N*1000, where N is the rate of events per second.
+ * At constant rates between one per second and one per 32 seconds,
+ * it will be choppy, moving up on the seconds that have an event,
+ * and then decaying until the next event.  At rates slower than
+ * about one in 32 seconds, it decays all the way back to zero between
+ * each event.
+ */
+
+#define FM_COEF 933		/* coefficient for half-life of 10 secs */
+#define FM_MAXTICKS ((u32)99)   /* useless computing more ticks than this */
+#define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
+#define FM_SCALE 1000		/* faux fixed point scale */
+
+/* Initialize a frequency meter */
+static void fmeter_init(struct fmeter *fmp)
+{
+	fmp->cnt = 0;
+	fmp->val = 0;
+	fmp->time = 0;
+	spin_lock_init(&fmp->lock);
+}
+
+/* Internal meter update - process cnt events and update value */
+static void fmeter_update(struct fmeter *fmp)
+{
+	time64_t now;
+	u32 ticks;
+
+	now = ktime_get_seconds();
+	ticks = now - fmp->time;
+
+	if (ticks == 0)
+		return;
+
+	ticks = min(FM_MAXTICKS, ticks);
+	while (ticks-- > 0)
+		fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
+	fmp->time = now;
+
+	fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
+	fmp->cnt = 0;
+}
+
+/* Process any previous ticks, then bump cnt by one (times scale). */
+static void fmeter_markevent(struct fmeter *fmp)
+{
+	spin_lock(&fmp->lock);
+	fmeter_update(fmp);
+	fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
+	spin_unlock(&fmp->lock);
+}
+
+/* Process any previous ticks, then return current value. */
+static int fmeter_getrate(struct fmeter *fmp)
+{
+	int val;
+
+	spin_lock(&fmp->lock);
+	fmeter_update(fmp);
+	val = fmp->val;
+	spin_unlock(&fmp->lock);
+	return val;
+}
+
+/*
+ * Collection of memory_pressure is suppressed unless
+ * this flag is enabled by writing "1" to the special
+ * cpuset file 'memory_pressure_enabled' in the root cpuset.
+ */
+
+int cpuset_memory_pressure_enabled __read_mostly;
+
+/*
+ * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+ *
+ * Keep a running average of the rate of synchronous (direct)
+ * page reclaim efforts initiated by tasks in each cpuset.
+ *
+ * This represents the rate at which some task in the cpuset
+ * ran low on memory on all nodes it was allowed to use, and
+ * had to enter the kernels page reclaim code in an effort to
+ * create more free memory by tossing clean pages or swapping
+ * or writing dirty pages.
+ *
+ * Display to user space in the per-cpuset read-only file
+ * "memory_pressure".  Value displayed is an integer
+ * representing the recent rate of entry into the synchronous
+ * (direct) page reclaim by any task attached to the cpuset.
+ */
+
+void __cpuset_memory_pressure_bump(void)
+{
+	rcu_read_lock();
+	fmeter_markevent(&task_cs(current)->fmeter);
+	rcu_read_unlock();
+}
+
+static int update_relax_domain_level(struct cpuset *cs, s64 val)
+{
+#ifdef CONFIG_SMP
+	if (val < -1 || val > sched_domain_level_max + 1)
+		return -EINVAL;
+#endif
+
+	if (val != cs->relax_domain_level) {
+		cs->relax_domain_level = val;
+		if (!cpumask_empty(cs->cpus_allowed) &&
+		    is_sched_load_balance(cs))
+			rebuild_sched_domains_locked();
+	}
+
+	return 0;
+}
+
+static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
+			    s64 val)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+	int retval = -ENODEV;
+
+	cpuset_full_lock();
+	if (!is_cpuset_online(cs))
+		goto out_unlock;
+
+	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:
+		retval = -EINVAL;
+		break;
+	}
+out_unlock:
+	cpuset_full_unlock();
+	return retval;
+}
+
+static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+
+	switch (type) {
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		return cs->relax_domain_level;
+	default:
+		BUG();
+	}
+
+	/* Unreachable but makes gcc happy */
+	return 0;
+}
+
+/*
+ * update task's spread flag if cpuset's page/slab spread flag is set
+ *
+ * Call with callback_lock or cpuset_mutex held. The check can be skipped
+ * if on default hierarchy.
+ */
+void cpuset1_update_task_spread_flags(struct cpuset *cs,
+					struct task_struct *tsk)
+{
+	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
+		return;
+
+	if (is_spread_page(cs))
+		task_set_spread_page(tsk);
+	else
+		task_clear_spread_page(tsk);
+
+	if (is_spread_slab(cs))
+		task_set_spread_slab(tsk);
+	else
+		task_clear_spread_slab(tsk);
+}
+
+/**
+ * cpuset1_update_tasks_flags - update the spread flags of tasks in the cpuset.
+ * @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
+ * stable.
+ */
+void cpuset1_update_tasks_flags(struct cpuset *cs)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&cs->css, 0, &it);
+	while ((task = css_task_iter_next(&it)))
+		cpuset1_update_task_spread_flags(cs, task);
+	css_task_iter_end(&it);
+}
+
+/*
+ * If CPU and/or memory hotplug handlers, below, unplug any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then move the tasks in the empty
+ * cpuset to its next-highest non-empty parent.
+ */
+static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
+{
+	struct cpuset *parent;
+
+	/*
+	 * Find its next-highest non-empty parent, (top cpuset
+	 * has online cpus, so can't be empty).
+	 */
+	parent = parent_cs(cs);
+	while (cpumask_empty(parent->cpus_allowed) ||
+			nodes_empty(parent->mems_allowed))
+		parent = parent_cs(parent);
+
+	if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
+		pr_err("cpuset: failed to transfer tasks out of empty cpuset ");
+		pr_cont_cgroup_name(cs->css.cgroup);
+		pr_cont("\n");
+	}
+}
+
+static void cpuset_migrate_tasks_workfn(struct work_struct *work)
+{
+	struct cpuset_remove_tasks_struct *s;
+
+	s = container_of(work, struct cpuset_remove_tasks_struct, work);
+	remove_tasks_in_empty_cpuset(s->cs);
+	css_put(&s->cs->css);
+	kfree(s);
+}
+
+void cpuset1_hotplug_update_tasks(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated)
+{
+	bool is_empty;
+
+	cpuset_callback_lock_irq();
+	cpumask_copy(cs->cpus_allowed, new_cpus);
+	cpumask_copy(cs->effective_cpus, new_cpus);
+	cs->mems_allowed = *new_mems;
+	cs->effective_mems = *new_mems;
+	cpuset_callback_unlock_irq();
+
+	/*
+	 * Don't call cpuset_update_tasks_cpumask() if the cpuset becomes empty,
+	 * as the tasks will be migrated to an ancestor.
+	 */
+	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
+		cpuset_update_tasks_cpumask(cs, new_cpus);
+	if (mems_updated && !nodes_empty(cs->mems_allowed))
+		cpuset_update_tasks_nodemask(cs);
+
+	is_empty = cpumask_empty(cs->cpus_allowed) ||
+		   nodes_empty(cs->mems_allowed);
+
+	/*
+	 * Move tasks to the nearest ancestor with execution resources,
+	 * This is full cgroup operation which will also call back into
+	 * cpuset. Execute it asynchronously using workqueue.
+	 */
+	if (is_empty && cgroup_has_tasks(cs->css.cgroup) &&
+	    css_tryget_online(&cs->css)) {
+		struct cpuset_remove_tasks_struct *s;
+
+		s = kzalloc_obj(*s);
+		if (WARN_ON_ONCE(!s)) {
+			css_put(&cs->css);
+			return;
+		}
+
+		s->cs = cs;
+		INIT_WORK(&s->work, cpuset_migrate_tasks_workfn);
+		schedule_work(&s->work);
+	}
+}
+
+/*
+ * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
+ *
+ * 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.
+ */
+
+static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
+{
+	return	cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
+		nodes_subset(p->mems_allowed, q->mems_allowed) &&
+		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
+		is_mem_exclusive(p) <= is_mem_exclusive(q);
+}
+
+/*
+ * cpuset1_validate_change() - Validate conditions specific to legacy (v1)
+ *                            behavior.
+ */
+int cpuset1_validate_change(struct cpuset *cur, struct cpuset *trial)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *c, *par;
+	int ret;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* Each of our child cpusets must be a subset of us */
+	ret = -EBUSY;
+	cpuset_for_each_child(c, css, cur)
+		if (!is_cpuset_subset(c, trial))
+			goto out;
+
+	/* On legacy hierarchy, we must be a subset of our parent cpuset. */
+	ret = -EACCES;
+	par = parent_cs(cur);
+	if (par && !is_cpuset_subset(trial, par))
+		goto out;
+
+	/*
+	 * Cpusets with tasks - existing or newly being attached - can't
+	 * be changed to have empty cpus_allowed or mems_allowed.
+	 */
+	ret = -ENOSPC;
+	if (cpuset_is_populated(cur)) {
+		if (!cpumask_empty(cur->cpus_allowed) &&
+		    cpumask_empty(trial->cpus_allowed))
+			goto out;
+		if (!nodes_empty(cur->mems_allowed) &&
+		    nodes_empty(trial->mems_allowed))
+			goto out;
+	}
+
+	ret = 0;
+out:
+	return ret;
+}
+
+/*
+ * cpuset1_cpus_excl_conflict() - Check if two cpusets have exclusive CPU conflicts
+ *                                to legacy (v1)
+ * @cs1: first cpuset to check
+ * @cs2: second cpuset to check
+ *
+ * Returns: true if CPU exclusivity conflict exists, false otherwise
+ *
+ * If either cpuset is CPU exclusive, their allowed CPUs cannot intersect.
+ */
+bool cpuset1_cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
+{
+	if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
+		return cpumask_intersects(cs1->cpus_allowed,
+					  cs2->cpus_allowed);
+
+	return false;
+}
+
+#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);
+	cpuset_filetype_t type = cft->private;
+
+	switch (type) {
+	case FILE_CPU_EXCLUSIVE:
+		return is_cpu_exclusive(cs);
+	case FILE_MEM_EXCLUSIVE:
+		return is_mem_exclusive(cs);
+	case FILE_MEM_HARDWALL:
+		return is_mem_hardwall(cs);
+	case FILE_SCHED_LOAD_BALANCE:
+		return is_sched_load_balance(cs);
+	case FILE_MEMORY_MIGRATE:
+		return is_memory_migrate(cs);
+	case FILE_MEMORY_PRESSURE_ENABLED:
+		return cpuset_memory_pressure_enabled;
+	case FILE_MEMORY_PRESSURE:
+		return fmeter_getrate(&cs->fmeter);
+	case FILE_SPREAD_PAGE:
+		return is_spread_page(cs);
+	case FILE_SPREAD_SLAB:
+		return is_spread_slab(cs);
+	default:
+		BUG();
+	}
+
+	/* Unreachable but makes gcc happy */
+	return 0;
+}
+
+static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
+			    u64 val)
+{
+	struct cpuset *cs = css_cs(css);
+	cpuset_filetype_t type = cft->private;
+	int retval = 0;
+
+	cpuset_full_lock();
+	if (!is_cpuset_online(cs)) {
+		retval = -ENODEV;
+		goto out_unlock;
+	}
+
+	switch (type) {
+	case FILE_CPU_EXCLUSIVE:
+		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:
+		retval = -EINVAL;
+		break;
+	}
+out_unlock:
+	cpuset_full_unlock();
+	return retval;
+}
+
+void cpuset1_init(struct cpuset *cs)
+{
+	fmeter_init(&cs->fmeter);
+	cs->relax_domain_level = -1;
+}
+
+void cpuset1_online_css(struct cgroup_subsys_state *css)
+{
+	struct cpuset *tmp_cs;
+	struct cgroup_subsys_state *pos_css;
+	struct cpuset *cs = css_cs(css);
+	struct cpuset *parent = parent_cs(cs);
+
+	lockdep_assert_cpus_held();
+	lockdep_assert_cpuset_lock_held();
+
+	if (is_spread_page(parent))
+		set_bit(CS_SPREAD_PAGE, &cs->flags);
+	if (is_spread_slab(parent))
+		set_bit(CS_SPREAD_SLAB, &cs->flags);
+
+	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
+		return;
+
+	/*
+	 * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
+	 * set.  This flag handling is implemented in cgroup core for
+	 * historical reasons - the flag may be specified during mount.
+	 *
+	 * Currently, if any sibling cpusets have exclusive cpus or mem, we
+	 * refuse to clone the configuration - thereby refusing the task to
+	 * be entered, and as a result refusing the sys_unshare() or
+	 * clone() which initiated it.  If this becomes a problem for some
+	 * users who wish to allow that scenario, then this could be
+	 * changed to grant parent->cpus_allowed-sibling_cpus_exclusive
+	 * (and likewise for mems) to the new cgroup.
+	 */
+	rcu_read_lock();
+	cpuset_for_each_child(tmp_cs, pos_css, parent) {
+		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+
+	cpuset_callback_lock_irq();
+	cs->mems_allowed = parent->mems_allowed;
+	cs->effective_mems = parent->mems_allowed;
+	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
+	cpuset_callback_unlock_irq();
+}
+
+static void
+update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
+{
+	if (dattr->relax_domain_level < c->relax_domain_level)
+		dattr->relax_domain_level = c->relax_domain_level;
+}
+
+static void update_domain_attr_tree(struct sched_domain_attr *dattr,
+				    struct cpuset *root_cs)
+{
+	struct cpuset *cp;
+	struct cgroup_subsys_state *pos_css;
+
+	rcu_read_lock();
+	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
+		/* skip the whole subtree if @cp doesn't have any CPU */
+		if (cpumask_empty(cp->cpus_allowed)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
+		}
+
+		if (is_sched_load_balance(cp))
+			update_domain_attr(dattr, cp);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * cpuset1_generate_sched_domains()
+ *
+ * Finding the best partition (set of domains):
+ *	The double nested loops below over i, j scan over the load
+ *	balanced cpusets (using the array of cpuset pointers in csa[])
+ *	looking for pairs of cpusets that have overlapping cpus_allowed
+ *	and merging them using a union-find algorithm.
+ *
+ *	The union of the cpus_allowed masks from the set of all cpusets
+ *	having the same root then form the one element of the partition
+ *	(one sched domain) to be passed to partition_sched_domains().
+ */
+int cpuset1_generate_sched_domains(cpumask_var_t **domains,
+			struct sched_domain_attr **attributes)
+{
+	struct cpuset *cp;	/* top-down scan of cpusets */
+	struct cpuset **csa;	/* array of all cpuset ptrs */
+	int csn;		/* how many cpuset ptrs in csa so far */
+	int i, j;		/* indices for partition finding loops */
+	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
+	struct sched_domain_attr *dattr;  /* attributes for custom domains */
+	int ndoms = 0;		/* number of sched domains in result */
+	int nslot;		/* next empty doms[] struct cpumask slot */
+	struct cgroup_subsys_state *pos_css;
+	int nslot_update;
+
+	lockdep_assert_cpuset_lock_held();
+
+	doms = NULL;
+	dattr = NULL;
+	csa = NULL;
+
+	/* Special case for the 99% of systems with one, full, sched domain */
+	if (is_sched_load_balance(&top_cpuset)) {
+		ndoms = 1;
+		doms = alloc_sched_domains(ndoms);
+		if (!doms)
+			goto done;
+
+		dattr = kmalloc_obj(struct sched_domain_attr);
+		if (dattr) {
+			*dattr = SD_ATTR_INIT;
+			update_domain_attr_tree(dattr, &top_cpuset);
+		}
+		cpumask_and(doms[0], top_cpuset.effective_cpus,
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
+
+		goto done;
+	}
+
+	csa = kmalloc_objs(cp, nr_cpusets());
+	if (!csa)
+		goto done;
+	csn = 0;
+
+	rcu_read_lock();
+	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
+		if (cp == &top_cpuset)
+			continue;
+
+		/*
+		 * Continue traversing beyond @cp iff @cp has some CPUs and
+		 * isn't load balancing.  The former is obvious.  The
+		 * latter: All child cpusets contain a subset of the
+		 * parent's cpus, so just skip them, and then we call
+		 * update_domain_attr_tree() to calc relax_domain_level of
+		 * the corresponding sched domain.
+		 */
+		if (!cpumask_empty(cp->cpus_allowed) &&
+		    !(is_sched_load_balance(cp) &&
+		      cpumask_intersects(cp->cpus_allowed,
+					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
+			continue;
+
+		if (is_sched_load_balance(cp) &&
+		    !cpumask_empty(cp->effective_cpus))
+			csa[csn++] = cp;
+
+		/* skip @cp's subtree */
+		pos_css = css_rightmost_descendant(pos_css);
+		continue;
+	}
+	rcu_read_unlock();
+
+	for (i = 0; i < csn; i++)
+		uf_node_init(&csa[i]->node);
+
+	/* Merge overlapping cpusets */
+	for (i = 0; i < csn; i++) {
+		for (j = i + 1; j < csn; j++) {
+			if (cpusets_overlap(csa[i], csa[j]))
+				uf_union(&csa[i]->node, &csa[j]->node);
+		}
+	}
+
+	/* Count the total number of domains */
+	for (i = 0; i < csn; i++) {
+		if (uf_find(&csa[i]->node) == &csa[i]->node)
+			ndoms++;
+	}
+
+	/*
+	 * Now we know how many domains to create.
+	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
+	 */
+	doms = alloc_sched_domains(ndoms);
+	if (!doms)
+		goto done;
+
+	/*
+	 * The rest of the code, including the scheduler, can deal with
+	 * dattr==NULL case. No need to abort if alloc fails.
+	 */
+	dattr = kmalloc_objs(struct sched_domain_attr, ndoms);
+
+	for (nslot = 0, i = 0; i < csn; i++) {
+		nslot_update = 0;
+		for (j = i; j < csn; j++) {
+			if (uf_find(&csa[j]->node) == &csa[i]->node) {
+				struct cpumask *dp = doms[nslot];
+
+				if (i == j) {
+					nslot_update = 1;
+					cpumask_clear(dp);
+					if (dattr)
+						*(dattr + nslot) = SD_ATTR_INIT;
+				}
+				cpumask_or(dp, dp, csa[j]->effective_cpus);
+				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
+				if (dattr)
+					update_domain_attr_tree(dattr + nslot, csa[j]);
+			}
+		}
+		if (nslot_update)
+			nslot++;
+	}
+	BUG_ON(nslot != ndoms);
+
+done:
+	kfree(csa);
+
+	/*
+	 * Fallback to the default domain if kmalloc() failed.
+	 * See comments in partition_sched_domains().
+	 */
+	if (doms == NULL)
+		ndoms = 1;
+
+	*domains    = doms;
+	*attributes = dattr;
+	return ndoms;
+}
+
+/*
+ * for the common functions, 'private' gives the type of file
+ */
+
+struct cftype cpuset1_files[] = {
+	{
+		.name = "cpus",
+		.seq_show = cpuset_common_seq_show,
+		.write = cpuset_write_resmask,
+		.max_write_len = (100U + 6 * NR_CPUS),
+		.private = FILE_CPULIST,
+	},
+
+	{
+		.name = "mems",
+		.seq_show = cpuset_common_seq_show,
+		.write = cpuset_write_resmask,
+		.max_write_len = (100U + 6 * MAX_NUMNODES),
+		.private = FILE_MEMLIST,
+	},
+
+	{
+		.name = "effective_cpus",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_CPULIST,
+	},
+
+	{
+		.name = "effective_mems",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_MEMLIST,
+	},
+
+	{
+		.name = "cpu_exclusive",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_CPU_EXCLUSIVE,
+	},
+
+	{
+		.name = "mem_exclusive",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEM_EXCLUSIVE,
+	},
+
+	{
+		.name = "mem_hardwall",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEM_HARDWALL,
+	},
+
+	{
+		.name = "sched_load_balance",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SCHED_LOAD_BALANCE,
+	},
+
+	{
+		.name = "sched_relax_domain_level",
+		.read_s64 = cpuset_read_s64,
+		.write_s64 = cpuset_write_s64,
+		.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
+	},
+
+	{
+		.name = "memory_migrate",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEMORY_MIGRATE,
+	},
+
+	{
+		.name = "memory_pressure",
+		.read_u64 = cpuset_read_u64,
+		.private = FILE_MEMORY_PRESSURE,
+	},
+
+	{
+		.name = "memory_spread_page",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SPREAD_PAGE,
+	},
+
+	{
+		/* obsolete, may be removed in the future */
+		.name = "memory_spread_slab",
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_SPREAD_SLAB,
+	},
+
+	{
+		.name = "memory_pressure_enabled",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.read_u64 = cpuset_read_u64,
+		.write_u64 = cpuset_write_u64,
+		.private = FILE_MEMORY_PRESSURE_ENABLED,
+	},
+
+	{ }	/* terminate */
+};

linux-7.2.3/kernel/cgroup/debug.c

@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Debug controller
+ *
+ * WARNING: This controller is for cgroup core debugging only.
+ * Its interfaces are unstable and subject to changes at any time.
+ */
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include "cgroup-internal.h"
+
+static struct cgroup_subsys_state *
+debug_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cgroup_subsys_state *css = kzalloc_obj(*css);
+
+	if (!css)
+		return ERR_PTR(-ENOMEM);
+
+	return css;
+}
+
+static void debug_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css);
+}
+
+/*
+ * debug_taskcount_read - return the number of tasks in a cgroup.
+ * @cgrp: the cgroup in question
+ */
+static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
+				struct cftype *cft)
+{
+	return cgroup_task_count(css->cgroup);
+}
+
+static int current_css_set_read(struct seq_file *seq, void *v)
+{
+	struct kernfs_open_file *of = seq->private;
+	struct css_set *cset;
+	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
+	int i, refcnt;
+
+	if (!cgroup_kn_lock_live(of->kn, false))
+		return -ENODEV;
+
+	spin_lock_irq(&css_set_lock);
+	cset = task_css_set(current);
+	refcnt = refcount_read(&cset->refcount);
+	seq_printf(seq, "css_set %pK %d", cset, refcnt);
+	if (refcnt > cset->nr_tasks)
+		seq_printf(seq, " +%d", refcnt - cset->nr_tasks);
+	seq_puts(seq, "\n");
+
+	/*
+	 * Print the css'es stored in the current css_set.
+	 */
+	for_each_subsys(ss, i) {
+		css = cset->subsys[ss->id];
+		if (!css)
+			continue;
+		seq_printf(seq, "%2d: %-4s\t- %p[%d]\n", ss->id, ss->name,
+			  css, css->id);
+	}
+	spin_unlock_irq(&css_set_lock);
+	cgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
+					 struct cftype *cft)
+{
+	u64 count;
+
+	rcu_read_lock();
+	count = refcount_read(&task_css_set(current)->refcount);
+	rcu_read_unlock();
+	return count;
+}
+
+static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
+{
+	struct cgrp_cset_link *link;
+	struct css_set *cset;
+	char *name_buf;
+
+	name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+	if (!name_buf)
+		return -ENOMEM;
+
+	spin_lock_irq(&css_set_lock);
+	cset = task_css_set(current);
+	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
+		struct cgroup *c = link->cgrp;
+
+		cgroup_name(c, name_buf, NAME_MAX + 1);
+		seq_printf(seq, "Root %d group %s\n",
+			   c->root->hierarchy_id, name_buf);
+	}
+	spin_unlock_irq(&css_set_lock);
+	kfree(name_buf);
+	return 0;
+}
+
+#define MAX_TASKS_SHOWN_PER_CSS 25
+static int cgroup_css_links_read(struct seq_file *seq, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(seq);
+	struct cgrp_cset_link *link;
+	int dead_cnt = 0, extra_refs = 0, threaded_csets = 0;
+
+	spin_lock_irq(&css_set_lock);
+
+	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
+		struct css_set *cset = link->cset;
+		struct task_struct *task;
+		int count = 0;
+		int refcnt = refcount_read(&cset->refcount);
+
+		/*
+		 * Print out the proc_cset and threaded_cset relationship
+		 * and highlight difference between refcount and task_count.
+		 */
+		seq_printf(seq, "css_set %pK", cset);
+		if (rcu_dereference_protected(cset->dom_cset, 1) != cset) {
+			threaded_csets++;
+			seq_printf(seq, "=>%pK", cset->dom_cset);
+		}
+		if (!list_empty(&cset->threaded_csets)) {
+			struct css_set *tcset;
+			int idx = 0;
+
+			list_for_each_entry(tcset, &cset->threaded_csets,
+					    threaded_csets_node) {
+				seq_puts(seq, idx ? "," : "<=");
+				seq_printf(seq, "%pK", tcset);
+				idx++;
+			}
+		} else {
+			seq_printf(seq, " %d", refcnt);
+			if (refcnt - cset->nr_tasks > 0) {
+				int extra = refcnt - cset->nr_tasks;
+
+				seq_printf(seq, " +%d", extra);
+				/*
+				 * Take out the one additional reference in
+				 * init_css_set.
+				 */
+				if (cset == &init_css_set)
+					extra--;
+				extra_refs += extra;
+			}
+		}
+		seq_puts(seq, "\n");
+
+		list_for_each_entry(task, &cset->tasks, cg_list) {
+			if (count++ <= MAX_TASKS_SHOWN_PER_CSS)
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
+		}
+
+		list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+			if (count++ <= MAX_TASKS_SHOWN_PER_CSS)
+				seq_printf(seq, "  task %d\n",
+					   task_pid_vnr(task));
+		}
+		/* show # of overflowed tasks */
+		if (count > MAX_TASKS_SHOWN_PER_CSS)
+			seq_printf(seq, "  ... (%d)\n",
+				   count - MAX_TASKS_SHOWN_PER_CSS);
+
+		if (cset->dead) {
+			seq_puts(seq, "    [dead]\n");
+			dead_cnt++;
+		}
+
+		WARN_ON(count != cset->nr_tasks);
+	}
+	spin_unlock_irq(&css_set_lock);
+
+	if (!dead_cnt && !extra_refs && !threaded_csets)
+		return 0;
+
+	seq_puts(seq, "\n");
+	if (threaded_csets)
+		seq_printf(seq, "threaded css_sets = %d\n", threaded_csets);
+	if (extra_refs)
+		seq_printf(seq, "extra references = %d\n", extra_refs);
+	if (dead_cnt)
+		seq_printf(seq, "dead css_sets = %d\n", dead_cnt);
+
+	return 0;
+}
+
+static int cgroup_subsys_states_read(struct seq_file *seq, void *v)
+{
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp;
+	struct cgroup_subsys *ss;
+	struct cgroup_subsys_state *css;
+	char pbuf[16];
+	int i;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
+
+	for_each_subsys(ss, i) {
+		css = rcu_dereference_check(cgrp->subsys[ss->id], true);
+		if (!css)
+			continue;
+
+		pbuf[0] = '\0';
+
+		/* Show the parent CSS if applicable*/
+		if (css->parent)
+			snprintf(pbuf, sizeof(pbuf) - 1, " P=%d",
+				 css->parent->id);
+		seq_printf(seq, "%2d: %-4s\t- %p[%d] %d%s\n", ss->id, ss->name,
+			  css, css->id,
+			  atomic_read(&css->online_cnt), pbuf);
+	}
+
+	cgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static void cgroup_masks_read_one(struct seq_file *seq, const char *name,
+				  u32 mask)
+{
+	struct cgroup_subsys *ss;
+	int ssid;
+	bool first = true;
+
+	seq_printf(seq, "%-17s: ", name);
+	for_each_subsys(ss, ssid) {
+		if (!(mask & (1 << ssid)))
+			continue;
+		if (!first)
+			seq_puts(seq, ", ");
+		seq_puts(seq, ss->name);
+		first = false;
+	}
+	seq_putc(seq, '\n');
+}
+
+static int cgroup_masks_read(struct seq_file *seq, void *v)
+{
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
+
+	cgroup_masks_read_one(seq, "subtree_control", cgrp->subtree_control);
+	cgroup_masks_read_one(seq, "subtree_ss_mask", cgrp->subtree_ss_mask);
+
+	cgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return (!cgroup_is_populated(css->cgroup) &&
+		!css_has_online_children(&css->cgroup->self));
+}
+
+static struct cftype debug_legacy_files[] =  {
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.seq_show = current_css_set_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.seq_show = current_css_set_cg_links_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "cgroup_css_links",
+		.seq_show = cgroup_css_links_read,
+	},
+
+	{
+		.name = "cgroup_subsys_states",
+		.seq_show = cgroup_subsys_states_read,
+	},
+
+	{
+		.name = "cgroup_masks",
+		.seq_show = cgroup_masks_read,
+	},
+
+	{
+		.name = "releasable",
+		.read_u64 = releasable_read,
+	},
+
+	{ }	/* terminate */
+};
+
+static struct cftype debug_files[] =  {
+	{
+		.name = "taskcount",
+		.read_u64 = debug_taskcount_read,
+	},
+
+	{
+		.name = "current_css_set",
+		.seq_show = current_css_set_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_refcount",
+		.read_u64 = current_css_set_refcount_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "current_css_set_cg_links",
+		.seq_show = current_css_set_cg_links_read,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+
+	{
+		.name = "css_links",
+		.seq_show = cgroup_css_links_read,
+	},
+
+	{
+		.name = "csses",
+		.seq_show = cgroup_subsys_states_read,
+	},
+
+	{
+		.name = "masks",
+		.seq_show = cgroup_masks_read,
+	},
+
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys debug_cgrp_subsys = {
+	.css_alloc	= debug_css_alloc,
+	.css_free	= debug_css_free,
+	.legacy_cftypes	= debug_legacy_files,
+};
+
+/*
+ * On v2, debug is an implicit controller enabled by "cgroup_debug" boot
+ * parameter.
+ */
+void __init enable_debug_cgroup(void)
+{
+	debug_cgrp_subsys.dfl_cftypes = debug_files;
+	debug_cgrp_subsys.implicit_on_dfl = true;
+	debug_cgrp_subsys.threaded = true;
+}

linux-7.2.3/kernel/cgroup/dmem.c

@@ -0,0 +1,886 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023-2024 Intel Corporation (Maarten Lankhorst <dev@lankhorst.se>)
+ * Copyright 2024 Red Hat (Maxime Ripard <mripard@kernel.org>)
+ * Partially based on the rdma and misc controllers, which bear the following copyrights:
+ *
+ * Copyright 2020 Google LLC
+ * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
+ */
+
+#include <linux/cgroup.h>
+#include <linux/cgroup_dmem.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/page_counter.h>
+#include <linux/parser.h>
+#include <linux/refcount.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+
+struct dmem_cgroup_region {
+	/**
+	 * @ref: References keeping the region alive.
+	 * Keeps the region reference alive after a succesful RCU lookup.
+	 */
+	struct kref ref;
+
+	/** @rcu: RCU head for freeing */
+	struct rcu_head rcu;
+
+	/**
+	 * @region_node: Linked into &dmem_cgroup_regions list.
+	 * Protected by RCU and global spinlock.
+	 */
+	struct list_head region_node;
+
+	/**
+	 * @pools: List of pools linked to this region.
+	 * Protected by global spinlock only
+	 */
+	struct list_head pools;
+
+	/** @size: Size of region, in bytes */
+	u64 size;
+
+	/** @name: Name describing the node, set by dmem_cgroup_register_region */
+	char *name;
+
+	/**
+	 * @unregistered: Whether the region is unregistered by its caller.
+	 * No new pools should be added to the region afterwards.
+	 */
+	bool unregistered;
+};
+
+struct dmemcg_state {
+	struct cgroup_subsys_state css;
+
+	struct list_head pools;
+};
+
+struct dmem_cgroup_pool_state {
+	struct dmem_cgroup_region *region;
+	struct dmemcg_state *cs;
+
+	/* css node, RCU protected against region teardown */
+	struct list_head	css_node;
+
+	/* dev node, no RCU protection required */
+	struct list_head	region_node;
+
+	struct rcu_head rcu;
+
+	struct page_counter cnt;
+	struct dmem_cgroup_pool_state *parent;
+
+	refcount_t ref;
+	bool inited;
+};
+
+/*
+ * 3 operations require locking protection:
+ * - Registering and unregistering region to/from list, requires global lock.
+ * - Adding a dmem_cgroup_pool_state to a CSS, removing when CSS is freed.
+ * - Adding a dmem_cgroup_pool_state to a region list.
+ *
+ * Since for the most common operations RCU provides enough protection, I
+ * do not think more granular locking makes sense. Most protection is offered
+ * by RCU and the lockless operating page_counter.
+ */
+static DEFINE_SPINLOCK(dmemcg_lock);
+static LIST_HEAD(dmem_cgroup_regions);
+
+static void dmemcg_free_region(struct kref *ref);
+static void dmemcg_pool_free_rcu(struct rcu_head *rcu);
+
+static inline struct dmemcg_state *
+css_to_dmemcs(struct cgroup_subsys_state *css)
+{
+	return container_of(css, struct dmemcg_state, css);
+}
+
+static inline struct dmemcg_state *get_current_dmemcs(void)
+{
+	return css_to_dmemcs(task_get_css(current, dmem_cgrp_id));
+}
+
+static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg)
+{
+	return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL;
+}
+
+static void dmemcg_pool_get(struct dmem_cgroup_pool_state *pool)
+{
+	refcount_inc(&pool->ref);
+}
+
+static bool dmemcg_pool_tryget(struct dmem_cgroup_pool_state *pool)
+{
+	return refcount_inc_not_zero(&pool->ref);
+}
+
+static void dmemcg_pool_put(struct dmem_cgroup_pool_state *pool)
+{
+	if (!refcount_dec_and_test(&pool->ref))
+		return;
+
+	call_rcu(&pool->rcu, dmemcg_pool_free_rcu);
+}
+
+static void dmemcg_pool_free_rcu(struct rcu_head *rcu)
+{
+	struct dmem_cgroup_pool_state *pool = container_of(rcu, typeof(*pool), rcu);
+
+	if (pool->parent)
+		dmemcg_pool_put(pool->parent);
+	kref_put(&pool->region->ref, dmemcg_free_region);
+	kfree(pool);
+}
+
+static void free_cg_pool(struct dmem_cgroup_pool_state *pool)
+{
+	list_del(&pool->region_node);
+	dmemcg_pool_put(pool);
+}
+
+static void
+set_resource_min(struct dmem_cgroup_pool_state *pool, u64 val)
+{
+	page_counter_set_min(&pool->cnt, val);
+}
+
+static void
+set_resource_low(struct dmem_cgroup_pool_state *pool, u64 val)
+{
+	page_counter_set_low(&pool->cnt, val);
+}
+
+static void
+set_resource_max(struct dmem_cgroup_pool_state *pool, u64 val)
+{
+	page_counter_set_max(&pool->cnt, val);
+}
+
+static u64 get_resource_low(struct dmem_cgroup_pool_state *pool)
+{
+	return pool ? READ_ONCE(pool->cnt.low) : 0;
+}
+
+static u64 get_resource_min(struct dmem_cgroup_pool_state *pool)
+{
+	return pool ? READ_ONCE(pool->cnt.min) : 0;
+}
+
+static u64 get_resource_max(struct dmem_cgroup_pool_state *pool)
+{
+	return pool ? READ_ONCE(pool->cnt.max) : PAGE_COUNTER_MAX;
+}
+
+static u64 get_resource_current(struct dmem_cgroup_pool_state *pool)
+{
+	return pool ? page_counter_read(&pool->cnt) : 0;
+}
+
+static void reset_all_resource_limits(struct dmem_cgroup_pool_state *rpool)
+{
+	set_resource_min(rpool, 0);
+	set_resource_low(rpool, 0);
+	set_resource_max(rpool, PAGE_COUNTER_MAX);
+}
+
+static void dmemcs_offline(struct cgroup_subsys_state *css)
+{
+	struct dmemcg_state *dmemcs = css_to_dmemcs(css);
+	struct dmem_cgroup_pool_state *pool;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pool, &dmemcs->pools, css_node)
+		reset_all_resource_limits(pool);
+	rcu_read_unlock();
+}
+
+static void dmemcs_free(struct cgroup_subsys_state *css)
+{
+	struct dmemcg_state *dmemcs = css_to_dmemcs(css);
+	struct dmem_cgroup_pool_state *pool, *next;
+
+	spin_lock(&dmemcg_lock);
+	list_for_each_entry_safe(pool, next, &dmemcs->pools, css_node) {
+		/*
+		 *The pool is dead and all references are 0,
+		 * no need for RCU protection with list_del_rcu or freeing.
+		 */
+		list_del(&pool->css_node);
+		free_cg_pool(pool);
+	}
+	spin_unlock(&dmemcg_lock);
+
+	kfree(dmemcs);
+}
+
+static struct cgroup_subsys_state *
+dmemcs_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct dmemcg_state *dmemcs = kzalloc_obj(*dmemcs);
+	if (!dmemcs)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&dmemcs->pools);
+	return &dmemcs->css;
+}
+
+static struct dmem_cgroup_pool_state *
+find_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region)
+{
+	struct dmem_cgroup_pool_state *pool;
+
+	list_for_each_entry_rcu(pool, &dmemcs->pools, css_node, spin_is_locked(&dmemcg_lock))
+		if (pool->region == region)
+			return pool;
+
+	return NULL;
+}
+
+static struct dmem_cgroup_pool_state *pool_parent(struct dmem_cgroup_pool_state *pool)
+{
+	if (!pool->cnt.parent)
+		return NULL;
+
+	return container_of(pool->cnt.parent, typeof(*pool), cnt);
+}
+
+static void
+dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool,
+				 struct dmem_cgroup_pool_state *test_pool)
+{
+	struct page_counter *climit;
+	struct cgroup_subsys_state *css;
+	struct dmemcg_state *dmemcg_iter;
+	struct dmem_cgroup_pool_state *pool, *found_pool;
+
+	climit = &limit_pool->cnt;
+
+	rcu_read_lock();
+
+	css_for_each_descendant_pre(css, &limit_pool->cs->css) {
+		dmemcg_iter = container_of(css, struct dmemcg_state, css);
+		found_pool = NULL;
+
+		list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) {
+			if (pool->region == limit_pool->region) {
+				found_pool = pool;
+				break;
+			}
+		}
+		if (!found_pool)
+			continue;
+
+		page_counter_calculate_protection(
+			climit, &found_pool->cnt, true);
+
+		if (found_pool == test_pool)
+			break;
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * dmem_cgroup_state_evict_valuable() - Check if we should evict from test_pool
+ * @limit_pool: The pool for which we hit limits
+ * @test_pool: The pool for which to test
+ * @ignore_low: Whether we have to respect low watermarks.
+ * @ret_hit_low: Pointer to whether it makes sense to consider low watermark.
+ *
+ * This function returns true if we can evict from @test_pool, false if not.
+ * When returning false and @ignore_low is false, @ret_hit_low may
+ * be set to true to indicate this function can be retried with @ignore_low
+ * set to true.
+ *
+ * Return: bool
+ */
+bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
+				      struct dmem_cgroup_pool_state *test_pool,
+				      bool ignore_low, bool *ret_hit_low)
+{
+	struct dmem_cgroup_pool_state *pool = test_pool;
+	struct page_counter *ctest;
+	u64 used, min, low;
+
+	/* Can always evict from current pool, despite limits */
+	if (limit_pool == test_pool)
+		return true;
+
+	if (limit_pool) {
+		if (!parent_dmemcs(limit_pool->cs))
+			return true;
+
+		for (pool = test_pool; pool && limit_pool != pool; pool = pool_parent(pool))
+			{}
+
+		if (!pool)
+			return false;
+	} else {
+		/*
+		 * If there is no cgroup limiting memory usage, use the root
+		 * cgroup instead for limit calculations.
+		 */
+		for (limit_pool = test_pool; pool_parent(limit_pool); limit_pool = pool_parent(limit_pool))
+			{}
+	}
+
+	ctest = &test_pool->cnt;
+
+	dmem_cgroup_calculate_protection(limit_pool, test_pool);
+
+	used = page_counter_read(ctest);
+	min = READ_ONCE(ctest->emin);
+
+	if (used <= min)
+		return false;
+
+	if (!ignore_low) {
+		low = READ_ONCE(ctest->elow);
+		if (used > low)
+			return true;
+
+		*ret_hit_low = true;
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_state_evict_valuable);
+
+static struct dmem_cgroup_pool_state *
+alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region,
+		  struct dmem_cgroup_pool_state **allocpool)
+{
+	struct dmemcg_state *parent = parent_dmemcs(dmemcs);
+	struct dmem_cgroup_pool_state *pool, *ppool = NULL;
+
+	if (!*allocpool) {
+		pool = kzalloc_obj(*pool, GFP_NOWAIT);
+		if (!pool)
+			return ERR_PTR(-ENOMEM);
+	} else {
+		pool = *allocpool;
+		*allocpool = NULL;
+	}
+
+	pool->region = region;
+	pool->cs = dmemcs;
+
+	if (parent)
+		ppool = find_cg_pool_locked(parent, region);
+
+	page_counter_init(&pool->cnt,
+			  ppool ? &ppool->cnt : NULL, true);
+	reset_all_resource_limits(pool);
+	refcount_set(&pool->ref, 1);
+	kref_get(&region->ref);
+	if (ppool && !pool->parent) {
+		pool->parent = ppool;
+		dmemcg_pool_get(ppool);
+	}
+
+	list_add_tail_rcu(&pool->css_node, &dmemcs->pools);
+	list_add_tail(&pool->region_node, &region->pools);
+
+	if (!parent)
+		pool->inited = true;
+	else
+		pool->inited = ppool ? ppool->inited : false;
+	return pool;
+}
+
+static struct dmem_cgroup_pool_state *
+get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region,
+		   struct dmem_cgroup_pool_state **allocpool)
+{
+	struct dmem_cgroup_pool_state *pool, *ppool, *retpool;
+	struct dmemcg_state *p, *pp;
+
+	/*
+	 * Recursively create pool, we may not initialize yet on
+	 * recursion, this is done as a separate step.
+	 */
+	for (p = dmemcs; p; p = parent_dmemcs(p)) {
+		pool = find_cg_pool_locked(p, region);
+		if (!pool)
+			pool = alloc_pool_single(p, region, allocpool);
+
+		if (IS_ERR(pool))
+			return pool;
+
+		if (p == dmemcs && pool->inited)
+			return pool;
+
+		if (pool->inited)
+			break;
+	}
+
+	retpool = pool = find_cg_pool_locked(dmemcs, region);
+	for (p = dmemcs, pp = parent_dmemcs(dmemcs); pp; p = pp, pp = parent_dmemcs(p)) {
+		if (pool->inited)
+			break;
+
+		/* ppool was created if it didn't exist by above loop. */
+		ppool = find_cg_pool_locked(pp, region);
+
+		/* Fix up parent links, mark as inited. */
+		pool->cnt.parent = &ppool->cnt;
+		if (ppool && !pool->parent) {
+			pool->parent = ppool;
+			dmemcg_pool_get(ppool);
+		}
+		pool->inited = true;
+
+		pool = ppool;
+	}
+
+	return retpool;
+}
+
+static void dmemcg_free_rcu(struct rcu_head *rcu)
+{
+	struct dmem_cgroup_region *region = container_of(rcu, typeof(*region), rcu);
+	struct dmem_cgroup_pool_state *pool, *next;
+
+	list_for_each_entry_safe(pool, next, &region->pools, region_node)
+		free_cg_pool(pool);
+	kfree(region->name);
+	kfree(region);
+}
+
+static void dmemcg_free_region(struct kref *ref)
+{
+	struct dmem_cgroup_region *cgregion = container_of(ref, typeof(*cgregion), ref);
+
+	call_rcu(&cgregion->rcu, dmemcg_free_rcu);
+}
+
+/**
+ * dmem_cgroup_unregister_region() - Unregister a previously registered region.
+ * @region: The region to unregister.
+ *
+ * This function undoes dmem_cgroup_register_region.
+ */
+void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region)
+{
+	struct dmem_cgroup_pool_state *pool, *next;
+
+	if (!region)
+		return;
+
+	spin_lock(&dmemcg_lock);
+
+	/* Remove from global region list */
+	list_del_rcu(&region->region_node);
+
+	list_for_each_entry_safe(pool, next, &region->pools, region_node) {
+		list_del_rcu(&pool->css_node);
+		list_del(&pool->region_node);
+		dmemcg_pool_put(pool);
+	}
+
+	/*
+	 * Ensure any RCU based lookups fail. Additionally,
+	 * no new pools should be added to the dead region
+	 * by get_cg_pool_unlocked.
+	 */
+	region->unregistered = true;
+	spin_unlock(&dmemcg_lock);
+
+	kref_put(&region->ref, dmemcg_free_region);
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_unregister_region);
+
+/**
+ * dmem_cgroup_register_region() - Register a regions for dev cgroup.
+ * @size: Size of region to register, in bytes.
+ * @fmt: Region parameters to register
+ *
+ * This function registers a node in the dmem cgroup with the
+ * name given. After calling this function, the region can be
+ * used for allocations.
+ *
+ * Return: NULL or a struct on success, PTR_ERR on failure.
+ */
+struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *fmt, ...)
+{
+	struct dmem_cgroup_region *ret;
+	char *region_name;
+	va_list ap;
+
+	if (!size)
+		return NULL;
+
+	va_start(ap, fmt);
+	region_name = kvasprintf(GFP_KERNEL, fmt, ap);
+	va_end(ap);
+	if (!region_name)
+		return ERR_PTR(-ENOMEM);
+
+	ret = kzalloc_obj(*ret);
+	if (!ret) {
+		kfree(region_name);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	INIT_LIST_HEAD(&ret->pools);
+	ret->name = region_name;
+	ret->size = size;
+	kref_init(&ret->ref);
+
+	spin_lock(&dmemcg_lock);
+	list_add_tail_rcu(&ret->region_node, &dmem_cgroup_regions);
+	spin_unlock(&dmemcg_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_register_region);
+
+static struct dmem_cgroup_region *dmemcg_get_region_by_name(const char *name)
+{
+	struct dmem_cgroup_region *region;
+
+	list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node, spin_is_locked(&dmemcg_lock))
+		if (!strcmp(name, region->name) &&
+		    kref_get_unless_zero(&region->ref))
+			return region;
+
+	return NULL;
+}
+
+/**
+ * dmem_cgroup_pool_state_put() - Drop a reference to a dmem_cgroup_pool_state
+ * @pool: &dmem_cgroup_pool_state
+ *
+ * Called to drop a reference to the limiting pool returned by
+ * dmem_cgroup_try_charge().
+ */
+void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool)
+{
+	if (pool) {
+		css_put(&pool->cs->css);
+		dmemcg_pool_put(pool);
+	}
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_pool_state_put);
+
+static struct dmem_cgroup_pool_state *
+get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region)
+{
+	struct dmem_cgroup_pool_state *pool, *allocpool = NULL;
+
+	/* fastpath lookup? */
+	rcu_read_lock();
+	pool = find_cg_pool_locked(cg, region);
+	if (pool && !READ_ONCE(pool->inited))
+		pool = NULL;
+	if (pool && !dmemcg_pool_tryget(pool))
+		pool = NULL;
+	rcu_read_unlock();
+
+	while (!pool) {
+		spin_lock(&dmemcg_lock);
+		if (!region->unregistered)
+			pool = get_cg_pool_locked(cg, region, &allocpool);
+		else
+			pool = ERR_PTR(-ENODEV);
+		if (!IS_ERR(pool))
+			dmemcg_pool_get(pool);
+		spin_unlock(&dmemcg_lock);
+
+		if (pool == ERR_PTR(-ENOMEM)) {
+			pool = NULL;
+			if (WARN_ON(allocpool))
+				continue;
+
+			allocpool = kzalloc_obj(*allocpool);
+			if (allocpool) {
+				pool = NULL;
+				continue;
+			}
+			pool = ERR_PTR(-ENOMEM);
+		}
+	}
+
+	kfree(allocpool);
+	return pool;
+}
+
+/**
+ * dmem_cgroup_uncharge() - Uncharge a pool.
+ * @pool: Pool to uncharge.
+ * @size: Size to uncharge.
+ *
+ * Undoes the effects of dmem_cgroup_try_charge.
+ * Must be called with the returned pool as argument,
+ * and same @index and @size.
+ */
+void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size)
+{
+	if (!pool)
+		return;
+
+	page_counter_uncharge(&pool->cnt, size);
+	css_put(&pool->cs->css);
+	dmemcg_pool_put(pool);
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_uncharge);
+
+/**
+ * dmem_cgroup_try_charge() - Try charging a new allocation to a region.
+ * @region: dmem region to charge
+ * @size: Size (in bytes) to charge.
+ * @ret_pool: On succesfull allocation, the pool that is charged.
+ * @ret_limit_pool: On a failed allocation, the limiting pool.
+ *
+ * This function charges the @region region for a size of @size bytes.
+ *
+ * If the function succeeds, @ret_pool is set, which must be passed to
+ * dmem_cgroup_uncharge() when undoing the allocation.
+ *
+ * When this function fails with -EAGAIN and @ret_limit_pool is non-null, it
+ * will be set to the pool for which the limit is hit. This can be used for
+ * eviction as argument to dmem_cgroup_evict_valuable(). This reference must be freed
+ * with @dmem_cgroup_pool_state_put().
+ *
+ * Return: 0 on success, -EAGAIN on hitting a limit, or a negative errno on failure.
+ */
+int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
+			  struct dmem_cgroup_pool_state **ret_pool,
+			  struct dmem_cgroup_pool_state **ret_limit_pool)
+{
+	struct dmemcg_state *cg;
+	struct dmem_cgroup_pool_state *pool;
+	struct page_counter *fail;
+	int ret;
+
+	*ret_pool = NULL;
+	if (ret_limit_pool)
+		*ret_limit_pool = NULL;
+
+	/*
+	 * hold on to css, as cgroup can be removed but resource
+	 * accounting happens on css.
+	 */
+	cg = get_current_dmemcs();
+
+	pool = get_cg_pool_unlocked(cg, region);
+	if (IS_ERR(pool)) {
+		ret = PTR_ERR(pool);
+		goto err;
+	}
+
+	if (!page_counter_try_charge(&pool->cnt, size, &fail)) {
+		if (ret_limit_pool) {
+			*ret_limit_pool = container_of(fail, struct dmem_cgroup_pool_state, cnt);
+			css_get(&(*ret_limit_pool)->cs->css);
+			dmemcg_pool_get(*ret_limit_pool);
+		}
+		dmemcg_pool_put(pool);
+		ret = -EAGAIN;
+		goto err;
+	}
+
+	/* On success, reference from get_current_dmemcs is transferred to *ret_pool */
+	*ret_pool = pool;
+	return 0;
+
+err:
+	css_put(&cg->css);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_try_charge);
+
+static int dmem_cgroup_region_capacity_show(struct seq_file *sf, void *v)
+{
+	struct dmem_cgroup_region *region;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node) {
+		seq_puts(sf, region->name);
+		seq_printf(sf, " %llu\n", region->size);
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+static int dmemcg_parse_limit(char *options, u64 *new_limit)
+{
+	char *end;
+
+	if (!strcmp(options, "max")) {
+		*new_limit = PAGE_COUNTER_MAX;
+		return 0;
+	}
+
+	*new_limit = memparse(options, &end);
+	if (*end != '\0')
+		return -EINVAL;
+
+	return 0;
+}
+
+static ssize_t dmemcg_limit_write(struct kernfs_open_file *of,
+				 char *buf, size_t nbytes, loff_t off,
+				 void (*apply)(struct dmem_cgroup_pool_state *, u64))
+{
+	struct dmemcg_state *dmemcs = css_to_dmemcs(of_css(of));
+	int err = 0;
+
+	while (buf && !err) {
+		struct dmem_cgroup_pool_state *pool = NULL;
+		char *options, *region_name;
+		struct dmem_cgroup_region *region;
+		u64 new_limit;
+
+		options = buf;
+		buf = strchr(buf, '\n');
+		if (buf)
+			*buf++ = '\0';
+
+		options = strstrip(options);
+
+		/* eat empty lines */
+		if (!options[0])
+			continue;
+
+		region_name = strsep(&options, " \t");
+		if (!region_name[0])
+			continue;
+
+		if (!options || !*options)
+			return -EINVAL;
+
+		rcu_read_lock();
+		region = dmemcg_get_region_by_name(region_name);
+		rcu_read_unlock();
+
+		if (!region)
+			return -EINVAL;
+
+		err = dmemcg_parse_limit(options, &new_limit);
+		if (err < 0)
+			goto out_put;
+
+		pool = get_cg_pool_unlocked(dmemcs, region);
+		if (IS_ERR(pool)) {
+			err = PTR_ERR(pool);
+			goto out_put;
+		}
+
+		/* And commit */
+		apply(pool, new_limit);
+		dmemcg_pool_put(pool);
+
+out_put:
+		kref_put(&region->ref, dmemcg_free_region);
+	}
+
+
+	return err ?: nbytes;
+}
+
+static int dmemcg_limit_show(struct seq_file *sf, void *v,
+			    u64 (*fn)(struct dmem_cgroup_pool_state *))
+{
+	struct dmemcg_state *dmemcs = css_to_dmemcs(seq_css(sf));
+	struct dmem_cgroup_region *region;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(region, &dmem_cgroup_regions, region_node) {
+		struct dmem_cgroup_pool_state *pool = find_cg_pool_locked(dmemcs, region);
+		u64 val;
+
+		seq_puts(sf, region->name);
+
+		val = fn(pool);
+		if (val < PAGE_COUNTER_MAX)
+			seq_printf(sf, " %lld\n", val);
+		else
+			seq_puts(sf, " max\n");
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int dmem_cgroup_region_current_show(struct seq_file *sf, void *v)
+{
+	return dmemcg_limit_show(sf, v, get_resource_current);
+}
+
+static int dmem_cgroup_region_min_show(struct seq_file *sf, void *v)
+{
+	return dmemcg_limit_show(sf, v, get_resource_min);
+}
+
+static ssize_t dmem_cgroup_region_min_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	return dmemcg_limit_write(of, buf, nbytes, off, set_resource_min);
+}
+
+static int dmem_cgroup_region_low_show(struct seq_file *sf, void *v)
+{
+	return dmemcg_limit_show(sf, v, get_resource_low);
+}
+
+static ssize_t dmem_cgroup_region_low_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	return dmemcg_limit_write(of, buf, nbytes, off, set_resource_low);
+}
+
+static int dmem_cgroup_region_max_show(struct seq_file *sf, void *v)
+{
+	return dmemcg_limit_show(sf, v, get_resource_max);
+}
+
+static ssize_t dmem_cgroup_region_max_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	return dmemcg_limit_write(of, buf, nbytes, off, set_resource_max);
+}
+
+static struct cftype files[] = {
+	{
+		.name = "capacity",
+		.seq_show = dmem_cgroup_region_capacity_show,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.seq_show = dmem_cgroup_region_current_show,
+	},
+	{
+		.name = "min",
+		.write = dmem_cgroup_region_min_write,
+		.seq_show = dmem_cgroup_region_min_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "low",
+		.write = dmem_cgroup_region_low_write,
+		.seq_show = dmem_cgroup_region_low_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "max",
+		.write = dmem_cgroup_region_max_write,
+		.seq_show = dmem_cgroup_region_max_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ } /* Zero entry terminates. */
+};
+
+struct cgroup_subsys dmem_cgrp_subsys = {
+	.css_alloc	= dmemcs_alloc,
+	.css_free	= dmemcs_free,
+	.css_offline	= dmemcs_offline,
+	.legacy_cftypes	= files,
+	.dfl_cftypes	= files,
+};

linux-7.2.3/kernel/cgroup/freezer.c

@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cgroup.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/signal.h>
+
+#include "cgroup-internal.h"
+
+#include <trace/events/cgroup.h>
+
+/*
+ * Update CGRP_FROZEN of cgroup.flag
+ * Return true if flags is updated; false if flags has no change
+ */
+static bool cgroup_update_frozen_flag(struct cgroup *cgrp, bool frozen)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	/* Already there? */
+	if (test_bit(CGRP_FROZEN, &cgrp->flags) == frozen)
+		return false;
+
+	if (frozen)
+		set_bit(CGRP_FROZEN, &cgrp->flags);
+	else
+		clear_bit(CGRP_FROZEN, &cgrp->flags);
+
+	cgroup_file_notify(&cgrp->events_file);
+	TRACE_CGROUP_PATH(notify_frozen, cgrp, frozen);
+	return true;
+}
+
+/*
+ * Propagate the cgroup frozen state upwards by the cgroup tree.
+ */
+static void cgroup_propagate_frozen(struct cgroup *cgrp, bool frozen)
+{
+	int desc = 1;
+
+	/*
+	 * If the new state is frozen, some freezing ancestor cgroups may change
+	 * their state too, depending on if all their descendants are frozen.
+	 *
+	 * Otherwise, all ancestor cgroups are forced into the non-frozen state.
+	 */
+	while ((cgrp = cgroup_parent(cgrp))) {
+		if (frozen) {
+			cgrp->freezer.nr_frozen_descendants += desc;
+			if (!test_bit(CGRP_FREEZE, &cgrp->flags) ||
+			    (cgrp->freezer.nr_frozen_descendants !=
+			    cgrp->nr_descendants))
+				continue;
+		} else {
+			cgrp->freezer.nr_frozen_descendants -= desc;
+		}
+
+		if (cgroup_update_frozen_flag(cgrp, frozen))
+			desc++;
+	}
+}
+
+/*
+ * Revisit the cgroup frozen state.
+ * Checks if the cgroup is really frozen and perform all state transitions.
+ */
+void cgroup_update_frozen(struct cgroup *cgrp)
+{
+	bool frozen;
+
+	/*
+	 * If the cgroup has to be frozen (CGRP_FREEZE bit set),
+	 * and all tasks are frozen and/or stopped, let's consider
+	 * the cgroup frozen. Otherwise it's not frozen.
+	 */
+	frozen = test_bit(CGRP_FREEZE, &cgrp->flags) &&
+		cgrp->freezer.nr_frozen_tasks == __cgroup_task_count(cgrp);
+
+	/* If flags is updated, update the state of ancestor cgroups. */
+	if (cgroup_update_frozen_flag(cgrp, frozen))
+		cgroup_propagate_frozen(cgrp, frozen);
+}
+
+/*
+ * Increment cgroup's nr_frozen_tasks.
+ */
+static void cgroup_inc_frozen_cnt(struct cgroup *cgrp)
+{
+	cgrp->freezer.nr_frozen_tasks++;
+}
+
+/*
+ * Decrement cgroup's nr_frozen_tasks.
+ */
+static void cgroup_dec_frozen_cnt(struct cgroup *cgrp)
+{
+	cgrp->freezer.nr_frozen_tasks--;
+	WARN_ON_ONCE(cgrp->freezer.nr_frozen_tasks < 0);
+}
+
+/*
+ * Enter frozen/stopped state, if not yet there. Update cgroup's counters,
+ * and revisit the state of the cgroup, if necessary.
+ */
+void cgroup_enter_frozen(void)
+{
+	struct cgroup *cgrp;
+
+	if (current->frozen)
+		return;
+
+	spin_lock_irq(&css_set_lock);
+	current->frozen = true;
+	cgrp = task_dfl_cgroup(current);
+	cgroup_inc_frozen_cnt(cgrp);
+	cgroup_update_frozen(cgrp);
+	spin_unlock_irq(&css_set_lock);
+}
+
+/*
+ * Conditionally leave frozen/stopped state. Update cgroup's counters,
+ * and revisit the state of the cgroup, if necessary.
+ *
+ * If always_leave is not set, and the cgroup is freezing,
+ * we're racing with the cgroup freezing. In this case, we don't
+ * drop the frozen counter to avoid a transient switch to
+ * the unfrozen state.
+ */
+void cgroup_leave_frozen(bool always_leave)
+{
+	struct cgroup *cgrp;
+
+	spin_lock_irq(&css_set_lock);
+	cgrp = task_dfl_cgroup(current);
+	if (always_leave || !test_bit(CGRP_FREEZE, &cgrp->flags)) {
+		cgroup_dec_frozen_cnt(cgrp);
+		cgroup_update_frozen(cgrp);
+		WARN_ON_ONCE(!current->frozen);
+		current->frozen = false;
+	} else if (!(current->jobctl & JOBCTL_TRAP_FREEZE)) {
+		spin_lock(&current->sighand->siglock);
+		current->jobctl |= JOBCTL_TRAP_FREEZE;
+		set_thread_flag(TIF_SIGPENDING);
+		spin_unlock(&current->sighand->siglock);
+	}
+	spin_unlock_irq(&css_set_lock);
+}
+
+/*
+ * Freeze or unfreeze the task by setting or clearing the JOBCTL_TRAP_FREEZE
+ * jobctl bit.
+ */
+static void cgroup_freeze_task(struct task_struct *task, bool freeze)
+{
+	unsigned long flags;
+
+	/* If the task is about to die, don't bother with freezing it. */
+	if (!lock_task_sighand(task, &flags))
+		return;
+
+	if (freeze) {
+		task->jobctl |= JOBCTL_TRAP_FREEZE;
+		signal_wake_up(task, false);
+	} else {
+		task->jobctl &= ~JOBCTL_TRAP_FREEZE;
+		wake_up_process(task);
+	}
+
+	unlock_task_sighand(task, &flags);
+}
+
+/*
+ * Freeze or unfreeze all tasks in the given cgroup.
+ */
+static void cgroup_do_freeze(struct cgroup *cgrp, bool freeze, u64 ts_nsec)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	spin_lock_irq(&css_set_lock);
+	write_seqcount_begin(&cgrp->freezer.freeze_seq);
+	if (freeze) {
+		set_bit(CGRP_FREEZE, &cgrp->flags);
+		cgrp->freezer.freeze_start_nsec = ts_nsec;
+	} else {
+		clear_bit(CGRP_FREEZE, &cgrp->flags);
+		cgrp->freezer.frozen_nsec += (ts_nsec -
+			cgrp->freezer.freeze_start_nsec);
+	}
+	write_seqcount_end(&cgrp->freezer.freeze_seq);
+	spin_unlock_irq(&css_set_lock);
+
+	if (freeze)
+		TRACE_CGROUP_PATH(freeze, cgrp);
+	else
+		TRACE_CGROUP_PATH(unfreeze, cgrp);
+
+	css_task_iter_start(&cgrp->self, 0, &it);
+	while ((task = css_task_iter_next(&it))) {
+		/*
+		 * Ignore kernel threads here. Freezing cgroups containing
+		 * kthreads isn't supported.
+		 */
+		if (task->flags & PF_KTHREAD)
+			continue;
+		cgroup_freeze_task(task, freeze);
+	}
+	css_task_iter_end(&it);
+
+	/*
+	 * Cgroup state should be revisited here to cover empty leaf cgroups
+	 * and cgroups which descendants are already in the desired state.
+	 */
+	spin_lock_irq(&css_set_lock);
+	if (cgrp->nr_descendants == cgrp->freezer.nr_frozen_descendants)
+		cgroup_update_frozen(cgrp);
+	spin_unlock_irq(&css_set_lock);
+}
+
+/*
+ * Adjust the task state (freeze or unfreeze) and revisit the state of
+ * source and destination cgroups.
+ */
+void cgroup_freezer_migrate_task(struct task_struct *task,
+				 struct cgroup *src, struct cgroup *dst)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	/*
+	 * Kernel threads are not supposed to be frozen at all.
+	 */
+	if (task->flags & PF_KTHREAD)
+		return;
+
+	/*
+	 * It's not necessary to do changes if both of the src and dst cgroups
+	 * are not freezing and task is not frozen.
+	 */
+	if (!test_bit(CGRP_FREEZE, &src->flags) &&
+	    !test_bit(CGRP_FREEZE, &dst->flags) &&
+	    !task->frozen)
+		return;
+
+	/*
+	 * Adjust counters of freezing and frozen tasks.
+	 * Note, that if the task is frozen, but the destination cgroup is not
+	 * frozen, we bump both counters to keep them balanced.
+	 */
+	if (task->frozen) {
+		cgroup_inc_frozen_cnt(dst);
+		cgroup_dec_frozen_cnt(src);
+	}
+	cgroup_update_frozen(dst);
+	cgroup_update_frozen(src);
+
+	/*
+	 * Force the task to the desired state.
+	 */
+	cgroup_freeze_task(task, test_bit(CGRP_FREEZE, &dst->flags));
+}
+
+void cgroup_freeze(struct cgroup *cgrp, bool freeze)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *parent;
+	struct cgroup *dsct;
+	bool applied = false;
+	u64 ts_nsec;
+	bool old_e;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	/*
+	 * Nothing changed? Just exit.
+	 */
+	if (cgrp->freezer.freeze == freeze)
+		return;
+
+	cgrp->freezer.freeze = freeze;
+	ts_nsec = ktime_get_ns();
+
+	/*
+	 * Propagate changes downwards the cgroup tree.
+	 */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		dsct = css->cgroup;
+
+		if (cgroup_is_dead(dsct))
+			continue;
+
+		/*
+		 * e_freeze is affected by parent's e_freeze and dst's freeze.
+		 * If old e_freeze eq new e_freeze, no change, its children
+		 * will not be affected. So do nothing and skip the subtree
+		 */
+		old_e = dsct->freezer.e_freeze;
+		parent = cgroup_parent(dsct);
+		dsct->freezer.e_freeze = (dsct->freezer.freeze ||
+					  parent->freezer.e_freeze);
+		if (dsct->freezer.e_freeze == old_e) {
+			css = css_rightmost_descendant(css);
+			continue;
+		}
+
+		/*
+		 * Do change actual state: freeze or unfreeze.
+		 */
+		cgroup_do_freeze(dsct, freeze, ts_nsec);
+		applied = true;
+	}
+
+	/*
+	 * Even if the actual state hasn't changed, let's notify a user.
+	 * The state can be enforced by an ancestor cgroup: the cgroup
+	 * can already be in the desired state or it can be locked in the
+	 * opposite state, so that the transition will never happen.
+	 * In both cases it's better to notify a user, that there is
+	 * nothing to wait for.
+	 */
+	if (!applied) {
+		TRACE_CGROUP_PATH(notify_frozen, cgrp,
+				  test_bit(CGRP_FROZEN, &cgrp->flags));
+		cgroup_file_notify(&cgrp->events_file);
+	}
+}

linux-7.2.3/kernel/cgroup/legacy_freezer.c

@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * cgroup_freezer.c -  control group freezer subsystem
+ *
+ * Copyright IBM Corporation, 2007
+ *
+ * Author : Cedric Le Goater <clg@fr.ibm.com>
+ */
+
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/freezer.h>
+#include <linux/seq_file.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+/*
+ * A cgroup is freezing if any FREEZING flags are set.  FREEZING_SELF is
+ * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared
+ * for "THAWED".  FREEZING_PARENT is set if the parent freezer is FREEZING
+ * for whatever reason.  IOW, a cgroup has FREEZING_PARENT set if one of
+ * its ancestors has FREEZING_SELF set.
+ */
+enum freezer_state_flags {
+	CGROUP_FREEZER_ONLINE	= (1 << 0), /* freezer is fully online */
+	CGROUP_FREEZING_SELF	= (1 << 1), /* this freezer is freezing */
+	CGROUP_FREEZING_PARENT	= (1 << 2), /* the parent freezer is freezing */
+	CGROUP_FROZEN		= (1 << 3), /* this and its descendants frozen */
+
+	/* mask for all FREEZING flags */
+	CGROUP_FREEZING		= CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT,
+};
+
+struct freezer {
+	struct cgroup_subsys_state	css;
+	unsigned int			state;
+};
+
+static DEFINE_MUTEX(freezer_mutex);
+
+static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct freezer, css) : NULL;
+}
+
+static inline struct freezer *task_freezer(struct task_struct *task)
+{
+	return css_freezer(task_css(task, freezer_cgrp_id));
+}
+
+static struct freezer *parent_freezer(struct freezer *freezer)
+{
+	return css_freezer(freezer->css.parent);
+}
+
+bool cgroup1_freezing(struct task_struct *task)
+{
+	bool ret;
+
+	rcu_read_lock();
+	ret = task_freezer(task)->state & CGROUP_FREEZING;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static const char *freezer_state_strs(unsigned int state)
+{
+	if (state & CGROUP_FROZEN)
+		return "FROZEN";
+	if (state & CGROUP_FREEZING)
+		return "FREEZING";
+	return "THAWED";
+};
+
+static struct cgroup_subsys_state *
+freezer_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct freezer *freezer;
+
+	freezer = kzalloc_obj(struct freezer);
+	if (!freezer)
+		return ERR_PTR(-ENOMEM);
+
+	return &freezer->css;
+}
+
+/**
+ * freezer_css_online - commit creation of a freezer css
+ * @css: css being created
+ *
+ * We're committing to creation of @css.  Mark it online and inherit
+ * parent's freezing state while holding cpus read lock and freezer_mutex.
+ */
+static int freezer_css_online(struct cgroup_subsys_state *css)
+{
+	struct freezer *freezer = css_freezer(css);
+	struct freezer *parent = parent_freezer(freezer);
+
+	cpus_read_lock();
+	mutex_lock(&freezer_mutex);
+
+	freezer->state |= CGROUP_FREEZER_ONLINE;
+
+	if (parent && (parent->state & CGROUP_FREEZING)) {
+		freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
+		static_branch_inc_cpuslocked(&freezer_active);
+	}
+
+	mutex_unlock(&freezer_mutex);
+	cpus_read_unlock();
+	return 0;
+}
+
+/**
+ * freezer_css_offline - initiate destruction of a freezer css
+ * @css: css being destroyed
+ *
+ * @css is going away.  Mark it dead and decrement freezer_active if
+ * it was holding one.
+ */
+static void freezer_css_offline(struct cgroup_subsys_state *css)
+{
+	struct freezer *freezer = css_freezer(css);
+
+	cpus_read_lock();
+	mutex_lock(&freezer_mutex);
+
+	if (freezer->state & CGROUP_FREEZING)
+		static_branch_dec_cpuslocked(&freezer_active);
+
+	freezer->state = 0;
+
+	mutex_unlock(&freezer_mutex);
+	cpus_read_unlock();
+}
+
+static void freezer_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_freezer(css));
+}
+
+/*
+ * Tasks can be migrated into a different freezer anytime regardless of its
+ * current state.  freezer_attach() is responsible for making new tasks
+ * conform to the current state.
+ *
+ * Freezer state changes and task migration are synchronized via
+ * @freezer->lock.  freezer_attach() makes the new tasks conform to the
+ * current state and all following state changes can see the new tasks.
+ */
+static void freezer_attach(struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct cgroup_subsys_state *new_css;
+
+	mutex_lock(&freezer_mutex);
+
+	/*
+	 * Make the new tasks conform to the current state of @new_css.
+	 * For simplicity, when migrating any task to a FROZEN cgroup, we
+	 * revert it to FREEZING and let update_if_frozen() determine the
+	 * correct state later.
+	 *
+	 * Tasks in @tset are on @new_css but may not conform to its
+	 * current state before executing the following - !frozen tasks may
+	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
+	 */
+	cgroup_taskset_for_each(task, new_css, tset) {
+		struct freezer *freezer = css_freezer(new_css);
+
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			__thaw_task(task);
+		} else {
+			/* clear FROZEN and propagate upwards */
+			while (freezer && (freezer->state & CGROUP_FROZEN)) {
+				freezer->state &= ~CGROUP_FROZEN;
+				freezer = parent_freezer(freezer);
+			}
+			freeze_task(task);
+		}
+	}
+
+	mutex_unlock(&freezer_mutex);
+}
+
+/**
+ * freezer_fork - cgroup post fork callback
+ * @task: a task which has just been forked
+ *
+ * @task has just been created and should conform to the current state of
+ * the cgroup_freezer it belongs to.  This function may race against
+ * freezer_attach().  Losing to freezer_attach() means that we don't have
+ * to do anything as freezer_attach() will put @task into the appropriate
+ * state.
+ */
+static void freezer_fork(struct task_struct *task)
+{
+	struct freezer *freezer;
+
+	/*
+	 * The root cgroup is non-freezable, so we can skip locking the
+	 * freezer.  This is safe regardless of race with task migration.
+	 * If we didn't race or won, skipping is obviously the right thing
+	 * to do.  If we lost and root is the new cgroup, noop is still the
+	 * right thing to do.
+	 */
+	if (task_css_is_root(task, freezer_cgrp_id))
+		return;
+
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+
+	freezer = task_freezer(task);
+	if (freezer->state & CGROUP_FREEZING)
+		freeze_task(task);
+
+	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
+}
+
+/**
+ * update_if_frozen - update whether a cgroup finished freezing
+ * @css: css of interest
+ *
+ * Once FREEZING is initiated, transition to FROZEN is lazily updated by
+ * calling this function.  If the current state is FREEZING but not FROZEN,
+ * this function checks whether all tasks of this cgroup and the descendant
+ * cgroups finished freezing and, if so, sets FROZEN.
+ *
+ * The caller is responsible for grabbing RCU read lock and calling
+ * update_if_frozen() on all descendants prior to invoking this function.
+ *
+ * Task states and freezer state might disagree while tasks are being
+ * migrated into or out of @css, so we can't verify task states against
+ * @freezer state here.  See freezer_attach() for details.
+ */
+static void update_if_frozen(struct cgroup_subsys_state *css)
+{
+	struct freezer *freezer = css_freezer(css);
+	struct cgroup_subsys_state *pos;
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	lockdep_assert_held(&freezer_mutex);
+
+	if (!(freezer->state & CGROUP_FREEZING) ||
+	    (freezer->state & CGROUP_FROZEN))
+		return;
+
+	/* are all (live) children frozen? */
+	rcu_read_lock();
+	css_for_each_child(pos, css) {
+		struct freezer *child = css_freezer(pos);
+
+		if ((child->state & CGROUP_FREEZER_ONLINE) &&
+		    !(child->state & CGROUP_FROZEN)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+
+	/* are all tasks frozen? */
+	css_task_iter_start(css, 0, &it);
+
+	while ((task = css_task_iter_next(&it))) {
+		if (freezing(task) && !frozen(task))
+			goto out_iter_end;
+	}
+
+	freezer->state |= CGROUP_FROZEN;
+out_iter_end:
+	css_task_iter_end(&it);
+}
+
+static int freezer_read(struct seq_file *m, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(m), *pos;
+
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+
+	/* update states bottom-up */
+	css_for_each_descendant_post(pos, css) {
+		if (!css_tryget_online(pos))
+			continue;
+		rcu_read_unlock();
+
+		update_if_frozen(pos);
+
+		rcu_read_lock();
+		css_put(pos);
+	}
+
+	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
+
+	seq_puts(m, freezer_state_strs(css_freezer(css)->state));
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void freeze_cgroup(struct freezer *freezer)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&freezer->css, 0, &it);
+	while ((task = css_task_iter_next(&it)))
+		freeze_task(task);
+	css_task_iter_end(&it);
+}
+
+static void unfreeze_cgroup(struct freezer *freezer)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&freezer->css, 0, &it);
+	while ((task = css_task_iter_next(&it)))
+		__thaw_task(task);
+	css_task_iter_end(&it);
+}
+
+/**
+ * freezer_apply_state - apply state change to a single cgroup_freezer
+ * @freezer: freezer to apply state change to
+ * @freeze: whether to freeze or unfreeze
+ * @state: CGROUP_FREEZING_* flag to set or clear
+ *
+ * Set or clear @state on @cgroup according to @freeze, and perform
+ * freezing or thawing as necessary.
+ */
+static void freezer_apply_state(struct freezer *freezer, bool freeze,
+				unsigned int state)
+{
+	/* also synchronizes against task migration, see freezer_attach() */
+	lockdep_assert_held(&freezer_mutex);
+
+	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
+		return;
+
+	if (freeze) {
+		if (!(freezer->state & CGROUP_FREEZING))
+			static_branch_inc_cpuslocked(&freezer_active);
+		freezer->state |= state;
+		freeze_cgroup(freezer);
+	} else {
+		bool was_freezing = freezer->state & CGROUP_FREEZING;
+
+		freezer->state &= ~state;
+
+		if (!(freezer->state & CGROUP_FREEZING)) {
+			freezer->state &= ~CGROUP_FROZEN;
+			if (was_freezing)
+				static_branch_dec_cpuslocked(&freezer_active);
+			unfreeze_cgroup(freezer);
+		}
+	}
+}
+
+/**
+ * freezer_change_state - change the freezing state of a cgroup_freezer
+ * @freezer: freezer of interest
+ * @freeze: whether to freeze or thaw
+ *
+ * Freeze or thaw @freezer according to @freeze.  The operations are
+ * recursive - all descendants of @freezer will be affected.
+ */
+static void freezer_change_state(struct freezer *freezer, bool freeze)
+{
+	struct cgroup_subsys_state *pos;
+
+	cpus_read_lock();
+	/*
+	 * Update all its descendants in pre-order traversal.  Each
+	 * descendant will try to inherit its parent's FREEZING state as
+	 * CGROUP_FREEZING_PARENT.
+	 */
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+	css_for_each_descendant_pre(pos, &freezer->css) {
+		struct freezer *pos_f = css_freezer(pos);
+		struct freezer *parent = parent_freezer(pos_f);
+
+		if (!css_tryget_online(pos))
+			continue;
+		rcu_read_unlock();
+
+		if (pos_f == freezer)
+			freezer_apply_state(pos_f, freeze,
+					    CGROUP_FREEZING_SELF);
+		else
+			freezer_apply_state(pos_f,
+					    parent->state & CGROUP_FREEZING,
+					    CGROUP_FREEZING_PARENT);
+
+		rcu_read_lock();
+		css_put(pos);
+	}
+	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
+	cpus_read_unlock();
+}
+
+static ssize_t freezer_write(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
+{
+	bool freeze;
+
+	buf = strstrip(buf);
+
+	if (strcmp(buf, freezer_state_strs(0)) == 0)
+		freeze = false;
+	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
+		return -EINVAL;
+
+	freezer_change_state(css_freezer(of_css(of)), freeze);
+	return nbytes;
+}
+
+static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css,
+				      struct cftype *cft)
+{
+	struct freezer *freezer = css_freezer(css);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_SELF);
+}
+
+static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css,
+					struct cftype *cft)
+{
+	struct freezer *freezer = css_freezer(css);
+
+	return (bool)(freezer->state & CGROUP_FREEZING_PARENT);
+}
+
+static struct cftype files[] = {
+	{
+		.name = "state",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = freezer_read,
+		.write = freezer_write,
+	},
+	{
+		.name = "self_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_self_freezing_read,
+	},
+	{
+		.name = "parent_freezing",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = freezer_parent_freezing_read,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys freezer_cgrp_subsys = {
+	.css_alloc	= freezer_css_alloc,
+	.css_online	= freezer_css_online,
+	.css_offline	= freezer_css_offline,
+	.css_free	= freezer_css_free,
+	.attach		= freezer_attach,
+	.fork		= freezer_fork,
+	.legacy_cftypes	= files,
+};

linux-7.2.3/kernel/cgroup/misc.c

@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Miscellaneous cgroup controller
+ *
+ * Copyright 2020 Google LLC
+ * Author: Vipin Sharma <vipinsh@google.com>
+ */
+
+#include <linux/limits.h>
+#include <linux/cgroup.h>
+#include <linux/errno.h>
+#include <linux/atomic.h>
+#include <linux/slab.h>
+#include <linux/misc_cgroup.h>
+
+#define MAX_STR "max"
+#define MAX_NUM U64_MAX
+
+/* Miscellaneous res name, keep it in sync with enum misc_res_type */
+static const char *const misc_res_name[] = {
+#ifdef CONFIG_KVM_AMD_SEV
+	/* AMD SEV ASIDs resource */
+	"sev",
+	/* AMD SEV-ES ASIDs resource */
+	"sev_es",
+#endif
+#ifdef CONFIG_INTEL_TDX_HOST
+	/* Intel TDX HKIDs resource */
+	"tdx",
+#endif
+};
+
+/* Root misc cgroup */
+static struct misc_cg root_cg;
+
+/*
+ * Miscellaneous resources capacity for the entire machine. 0 capacity means
+ * resource is not initialized or not present in the host.
+ *
+ * root_cg.max and capacity are independent of each other. root_cg.max can be
+ * more than the actual capacity. We are using Limits resource distribution
+ * model of cgroup for miscellaneous controller.
+ */
+static u64 misc_res_capacity[MISC_CG_RES_TYPES];
+
+/**
+ * parent_misc() - Get the parent of the passed misc cgroup.
+ * @cgroup: cgroup whose parent needs to be fetched.
+ *
+ * Context: Any context.
+ * Return:
+ * * struct misc_cg* - Parent of the @cgroup.
+ * * %NULL - If @cgroup is null or the passed cgroup does not have a parent.
+ */
+static struct misc_cg *parent_misc(struct misc_cg *cgroup)
+{
+	return cgroup ? css_misc(cgroup->css.parent) : NULL;
+}
+
+/**
+ * valid_type() - Check if @type is valid or not.
+ * @type: misc res type.
+ *
+ * Context: Any context.
+ * Return:
+ * * true - If valid type.
+ * * false - If not valid type.
+ */
+static inline bool valid_type(enum misc_res_type type)
+{
+	return type >= 0 && type < MISC_CG_RES_TYPES;
+}
+
+/**
+ * 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.
+ *
+ * If capacity is 0 then the charging a misc cgroup fails for that type.
+ *
+ * Context: Any context.
+ * Return:
+ * * %0 - Successfully registered the capacity.
+ * * %-EINVAL - If @type is invalid.
+ */
+int misc_cg_set_capacity(enum misc_res_type type, u64 capacity)
+{
+	if (!valid_type(type))
+		return -EINVAL;
+
+	WRITE_ONCE(misc_res_capacity[type], capacity);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(misc_cg_set_capacity);
+
+/**
+ * misc_cg_cancel_charge() - Cancel the charge from the misc cgroup.
+ * @type: Misc res type in misc cg to cancel the charge from.
+ * @cg: Misc cgroup to cancel charge from.
+ * @amount: Amount to cancel.
+ *
+ * Context: Any context.
+ */
+static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg,
+				  u64 amount)
+{
+	WARN_ONCE(atomic64_add_negative(-amount, &cg->res[type].usage),
+		  "misc cgroup resource %s became less than 0",
+		  misc_res_name[type]);
+}
+
+static void misc_cg_update_watermark(struct misc_res *res, u64 new_usage)
+{
+	u64 old;
+
+	while (true) {
+		old = atomic64_read(&res->watermark);
+		if (new_usage <= old)
+			break;
+		if (atomic64_cmpxchg(&res->watermark, old, new_usage) == old)
+			break;
+	}
+}
+
+static void misc_cg_event(enum misc_res_type type, struct misc_cg *cg)
+{
+	atomic64_inc(&cg->res[type].events_local);
+	cgroup_file_notify(&cg->events_local_file);
+
+	for (; parent_misc(cg); cg = parent_misc(cg)) {
+		atomic64_inc(&cg->res[type].events);
+		cgroup_file_notify(&cg->events_file);
+	}
+}
+
+/**
+ * misc_cg_try_charge() - Try charging the misc cgroup.
+ * @type: Misc res type to charge.
+ * @cg: Misc cgroup which will be charged.
+ * @amount: Amount to charge.
+ *
+ * Charge @amount to the misc cgroup. Caller must use the same cgroup during
+ * the uncharge call.
+ *
+ * Context: Any context.
+ * Return:
+ * * %0 - If successfully charged.
+ * * -EINVAL - If @type is invalid or misc res has 0 capacity.
+ * * -EBUSY - If max limit will be crossed or total usage will be more than the
+ *	      capacity.
+ */
+int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount)
+{
+	struct misc_cg *i, *j;
+	int ret;
+	struct misc_res *res;
+	u64 new_usage;
+
+	if (!(valid_type(type) && cg && READ_ONCE(misc_res_capacity[type])))
+		return -EINVAL;
+
+	if (!amount)
+		return 0;
+
+	for (i = cg; i; i = parent_misc(i)) {
+		res = &i->res[type];
+
+		new_usage = atomic64_add_return(amount, &res->usage);
+		if (new_usage > READ_ONCE(res->max) ||
+		    new_usage > READ_ONCE(misc_res_capacity[type])) {
+			ret = -EBUSY;
+			goto err_charge;
+		}
+		misc_cg_update_watermark(res, new_usage);
+	}
+	return 0;
+
+err_charge:
+	misc_cg_event(type, i);
+
+	for (j = cg; j != i; j = parent_misc(j))
+		misc_cg_cancel_charge(type, j, amount);
+	misc_cg_cancel_charge(type, i, amount);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(misc_cg_try_charge);
+
+/**
+ * misc_cg_uncharge() - Uncharge the misc cgroup.
+ * @type: Misc res type which was charged.
+ * @cg: Misc cgroup which will be uncharged.
+ * @amount: Charged amount.
+ *
+ * Context: Any context.
+ */
+void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg, u64 amount)
+{
+	struct misc_cg *i;
+
+	if (!(amount && valid_type(type) && cg))
+		return;
+
+	for (i = cg; i; i = parent_misc(i))
+		misc_cg_cancel_charge(type, i, amount);
+}
+EXPORT_SYMBOL_GPL(misc_cg_uncharge);
+
+/**
+ * misc_cg_max_show() - Show the misc cgroup max limit.
+ * @sf: Interface file
+ * @v: Arguments passed
+ *
+ * Context: Any context.
+ * Return: 0 to denote successful print.
+ */
+static int misc_cg_max_show(struct seq_file *sf, void *v)
+{
+	int i;
+	struct misc_cg *cg = css_misc(seq_css(sf));
+	u64 max;
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		if (READ_ONCE(misc_res_capacity[i])) {
+			max = READ_ONCE(cg->res[i].max);
+			if (max == MAX_NUM)
+				seq_printf(sf, "%s max\n", misc_res_name[i]);
+			else
+				seq_printf(sf, "%s %llu\n", misc_res_name[i],
+					   max);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * misc_cg_max_write() - Update the maximum limit of the cgroup.
+ * @of: Handler for the file.
+ * @buf: Data from the user. It should be either "max", 0, or a positive
+ *	 integer.
+ * @nbytes: Number of bytes of the data.
+ * @off: Offset in the file.
+ *
+ * User can pass data like:
+ * echo sev 23 > misc.max, OR
+ * echo sev max > misc.max
+ *
+ * Context: Any context.
+ * Return:
+ * * >= 0 - Number of bytes processed in the input.
+ * * -EINVAL - If buf is not valid.
+ * * -ERANGE - If number is bigger than the u64 capacity.
+ */
+static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf,
+				 size_t nbytes, loff_t off)
+{
+	struct misc_cg *cg;
+	u64 max;
+	int ret = 0, i;
+	enum misc_res_type type = MISC_CG_RES_TYPES;
+	char *token;
+
+	buf = strstrip(buf);
+	token = strsep(&buf, " ");
+
+	if (!token || !buf)
+		return -EINVAL;
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		if (!strcmp(misc_res_name[i], token)) {
+			type = i;
+			break;
+		}
+	}
+
+	if (type == MISC_CG_RES_TYPES)
+		return -EINVAL;
+
+	if (!strcmp(MAX_STR, buf)) {
+		max = MAX_NUM;
+	} else {
+		ret = kstrtou64(buf, 0, &max);
+		if (ret)
+			return ret;
+	}
+
+	cg = css_misc(of_css(of));
+
+	if (READ_ONCE(misc_res_capacity[type]))
+		WRITE_ONCE(cg->res[type].max, max);
+	else
+		ret = -EINVAL;
+
+	return ret ? ret : nbytes;
+}
+
+/**
+ * misc_cg_current_show() - Show the current usage of the misc cgroup.
+ * @sf: Interface file
+ * @v: Arguments passed
+ *
+ * Context: Any context.
+ * Return: 0 to denote successful print.
+ */
+static int misc_cg_current_show(struct seq_file *sf, void *v)
+{
+	int i;
+	u64 usage;
+	struct misc_cg *cg = css_misc(seq_css(sf));
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		usage = atomic64_read(&cg->res[i].usage);
+		if (READ_ONCE(misc_res_capacity[i]) || usage)
+			seq_printf(sf, "%s %llu\n", misc_res_name[i], usage);
+	}
+
+	return 0;
+}
+
+/**
+ * misc_cg_peak_show() - Show the peak usage of the misc cgroup.
+ * @sf: Interface file
+ * @v: Arguments passed
+ *
+ * Context: Any context.
+ * Return: 0 to denote successful print.
+ */
+static int misc_cg_peak_show(struct seq_file *sf, void *v)
+{
+	int i;
+	u64 watermark;
+	struct misc_cg *cg = css_misc(seq_css(sf));
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		watermark = atomic64_read(&cg->res[i].watermark);
+		if (READ_ONCE(misc_res_capacity[i]) || watermark)
+			seq_printf(sf, "%s %llu\n", misc_res_name[i], watermark);
+	}
+
+	return 0;
+}
+
+/**
+ * misc_cg_capacity_show() - Show the total capacity of misc res on the host.
+ * @sf: Interface file
+ * @v: Arguments passed
+ *
+ * Only present in the root cgroup directory.
+ *
+ * Context: Any context.
+ * Return: 0 to denote successful print.
+ */
+static int misc_cg_capacity_show(struct seq_file *sf, void *v)
+{
+	int i;
+	u64 cap;
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		cap = READ_ONCE(misc_res_capacity[i]);
+		if (cap)
+			seq_printf(sf, "%s %llu\n", misc_res_name[i], cap);
+	}
+
+	return 0;
+}
+
+static int __misc_events_show(struct seq_file *sf, bool local)
+{
+	struct misc_cg *cg = css_misc(seq_css(sf));
+	u64 events;
+	int i;
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		if (local)
+			events = atomic64_read(&cg->res[i].events_local);
+		else
+			events = atomic64_read(&cg->res[i].events);
+		if (READ_ONCE(misc_res_capacity[i]) || events)
+			seq_printf(sf, "%s.max %llu\n", misc_res_name[i], events);
+	}
+	return 0;
+}
+
+static int misc_events_show(struct seq_file *sf, void *v)
+{
+	return __misc_events_show(sf, false);
+}
+
+static int misc_events_local_show(struct seq_file *sf, void *v)
+{
+	return __misc_events_show(sf, true);
+}
+
+/* Misc cgroup interface files */
+static struct cftype misc_cg_files[] = {
+	{
+		.name = "max",
+		.write = misc_cg_max_write,
+		.seq_show = misc_cg_max_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.seq_show = misc_cg_current_show,
+	},
+	{
+		.name = "peak",
+		.seq_show = misc_cg_peak_show,
+	},
+	{
+		.name = "capacity",
+		.seq_show = misc_cg_capacity_show,
+		.flags = CFTYPE_ONLY_ON_ROOT,
+	},
+	{
+		.name = "events",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct misc_cg, events_file),
+		.seq_show = misc_events_show,
+	},
+	{
+		.name = "events.local",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct misc_cg, events_local_file),
+		.seq_show = misc_events_local_show,
+	},
+	{}
+};
+
+/**
+ * misc_cg_alloc() - Allocate misc cgroup.
+ * @parent_css: Parent cgroup.
+ *
+ * Context: Process context.
+ * Return:
+ * * struct cgroup_subsys_state* - css of the allocated cgroup.
+ * * ERR_PTR(-ENOMEM) - No memory available to allocate.
+ */
+static struct cgroup_subsys_state *
+misc_cg_alloc(struct cgroup_subsys_state *parent_css)
+{
+	enum misc_res_type i;
+	struct misc_cg *cg;
+
+	if (!parent_css) {
+		cg = &root_cg;
+	} else {
+		cg = kzalloc_obj(*cg);
+		if (!cg)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		WRITE_ONCE(cg->res[i].max, MAX_NUM);
+		atomic64_set(&cg->res[i].usage, 0);
+	}
+
+	return &cg->css;
+}
+
+/**
+ * misc_cg_free() - Free the misc cgroup.
+ * @css: cgroup subsys object.
+ *
+ * Context: Any context.
+ */
+static void misc_cg_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_misc(css));
+}
+
+/* Cgroup controller callbacks */
+struct cgroup_subsys misc_cgrp_subsys = {
+	.css_alloc = misc_cg_alloc,
+	.css_free = misc_cg_free,
+	.legacy_cftypes = misc_cg_files,
+	.dfl_cftypes = misc_cg_files,
+};

linux-7.2.3/kernel/cgroup/namespace.c

@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "cgroup-internal.h"
+
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/nsproxy.h>
+#include <linux/proc_ns.h>
+#include <linux/nstree.h>
+
+/* cgroup namespaces */
+
+static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns)
+{
+	return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES);
+}
+
+static void dec_cgroup_namespaces(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES);
+}
+
+static struct cgroup_namespace *alloc_cgroup_ns(void)
+{
+	struct cgroup_namespace *new_ns __free(kfree) = NULL;
+	int ret;
+
+	new_ns = kzalloc_obj(struct cgroup_namespace, GFP_KERNEL_ACCOUNT);
+	if (!new_ns)
+		return ERR_PTR(-ENOMEM);
+	ret = ns_common_init(new_ns);
+	if (ret)
+		return ERR_PTR(ret);
+	return no_free_ptr(new_ns);
+}
+
+void free_cgroup_ns(struct cgroup_namespace *ns)
+{
+	ns_tree_remove(ns);
+	put_css_set(ns->root_cset);
+	dec_cgroup_namespaces(ns->ucounts);
+	put_user_ns(ns->user_ns);
+	ns_common_free(ns);
+	/* Concurrent nstree traversal depends on a grace period. */
+	kfree_rcu(ns, ns.ns_rcu);
+}
+EXPORT_SYMBOL(free_cgroup_ns);
+
+struct cgroup_namespace *copy_cgroup_ns(u64 flags,
+					struct user_namespace *user_ns,
+					struct cgroup_namespace *old_ns)
+{
+	struct cgroup_namespace *new_ns;
+	struct ucounts *ucounts;
+	struct css_set *cset;
+
+	BUG_ON(!old_ns);
+
+	if (!(flags & CLONE_NEWCGROUP)) {
+		get_cgroup_ns(old_ns);
+		return old_ns;
+	}
+
+	/* Allow only sysadmin to create cgroup namespace. */
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	ucounts = inc_cgroup_namespaces(user_ns);
+	if (!ucounts)
+		return ERR_PTR(-ENOSPC);
+
+	/* It is not safe to take cgroup_mutex here */
+	spin_lock_irq(&css_set_lock);
+	cset = task_css_set(current);
+	get_css_set(cset);
+	spin_unlock_irq(&css_set_lock);
+
+	new_ns = alloc_cgroup_ns();
+	if (IS_ERR(new_ns)) {
+		put_css_set(cset);
+		dec_cgroup_namespaces(ucounts);
+		return new_ns;
+	}
+
+	new_ns->user_ns = get_user_ns(user_ns);
+	new_ns->ucounts = ucounts;
+	new_ns->root_cset = cset;
+
+	ns_tree_add(new_ns);
+	return new_ns;
+}
+
+static int cgroupns_install(struct nsset *nsset, struct ns_common *ns)
+{
+	struct nsproxy *nsproxy = nsset->nsproxy;
+	struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
+
+	if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Don't need to do anything if we are attaching to our own cgroupns. */
+	if (cgroup_ns == nsproxy->cgroup_ns)
+		return 0;
+
+	get_cgroup_ns(cgroup_ns);
+	put_cgroup_ns(nsproxy->cgroup_ns);
+	nsproxy->cgroup_ns = cgroup_ns;
+
+	return 0;
+}
+
+static struct ns_common *cgroupns_get(struct task_struct *task)
+{
+	struct cgroup_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy) {
+		ns = nsproxy->cgroup_ns;
+		get_cgroup_ns(ns);
+	}
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static void cgroupns_put(struct ns_common *ns)
+{
+	put_cgroup_ns(to_cg_ns(ns));
+}
+
+static struct user_namespace *cgroupns_owner(struct ns_common *ns)
+{
+	return to_cg_ns(ns)->user_ns;
+}
+
+const struct proc_ns_operations cgroupns_operations = {
+	.name		= "cgroup",
+	.get		= cgroupns_get,
+	.put		= cgroupns_put,
+	.install	= cgroupns_install,
+	.owner		= cgroupns_owner,
+};

linux-7.2.3/kernel/cgroup/pids.c

@@ -0,0 +1,460 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Process number limiting controller for cgroups.
+ *
+ * Used to allow a cgroup hierarchy to stop any new processes from fork()ing
+ * after a certain limit is reached.
+ *
+ * Since it is trivial to hit the task limit without hitting any kmemcg limits
+ * in place, PIDs are a fundamental resource. As such, PID exhaustion must be
+ * preventable in the scope of a cgroup hierarchy by allowing resource limiting
+ * of the number of tasks in a cgroup.
+ *
+ * In order to use the `pids` controller, set the maximum number of tasks in
+ * pids.max (this is not available in the root cgroup for obvious reasons). The
+ * number of processes currently in the cgroup is given by pids.current.
+ * Organisational operations are not blocked by cgroup policies, so it is
+ * possible to have pids.current > pids.max. However, it is not possible to
+ * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking
+ * would cause a cgroup policy to be violated.
+ *
+ * To set a cgroup to have no limit, set pids.max to "max". This is the default
+ * for all new cgroups (N.B. that PID limits are hierarchical, so the most
+ * stringent limit in the hierarchy is followed).
+ *
+ * pids.current tracks all child cgroup hierarchies, so parent/pids.current is
+ * a superset of parent/child/pids.current.
+ *
+ * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/atomic.h>
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/sched/task.h>
+
+#define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
+#define PIDS_MAX_STR "max"
+
+enum pidcg_event {
+	/* Fork failed in subtree because this pids_cgroup limit was hit. */
+	PIDCG_MAX,
+	/* Fork failed in this pids_cgroup because ancestor limit was hit. */
+	PIDCG_FORKFAIL,
+	NR_PIDCG_EVENTS,
+};
+
+struct pids_cgroup {
+	struct cgroup_subsys_state	css;
+
+	/*
+	 * Use 64-bit types so that we can safely represent "max" as
+	 * %PIDS_MAX = (%PID_MAX_LIMIT + 1).
+	 */
+	atomic64_t			counter;
+	atomic64_t			limit;
+	int64_t				watermark;
+
+	/* Handles for pids.events[.local] */
+	struct cgroup_file		events_file;
+	struct cgroup_file		events_local_file;
+
+	atomic64_t			events[NR_PIDCG_EVENTS];
+	atomic64_t			events_local[NR_PIDCG_EVENTS];
+};
+
+static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
+{
+	return container_of(css, struct pids_cgroup, css);
+}
+
+static struct pids_cgroup *parent_pids(struct pids_cgroup *pids)
+{
+	return css_pids(pids->css.parent);
+}
+
+static struct cgroup_subsys_state *
+pids_css_alloc(struct cgroup_subsys_state *parent)
+{
+	struct pids_cgroup *pids;
+
+	pids = kzalloc_obj(struct pids_cgroup);
+	if (!pids)
+		return ERR_PTR(-ENOMEM);
+
+	atomic64_set(&pids->limit, PIDS_MAX);
+	return &pids->css;
+}
+
+static void pids_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_pids(css));
+}
+
+static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids)
+{
+	/*
+	 * This is racy, but we don't need perfectly accurate tallying of
+	 * the watermark, and this lets us avoid extra atomic overhead.
+	 */
+	if (nr_pids > READ_ONCE(p->watermark))
+		WRITE_ONCE(p->watermark, nr_pids);
+}
+
+/**
+ * pids_cancel - uncharge the local pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to cancel
+ *
+ * This function will WARN if the pid count goes under 0, because such a case is
+ * a bug in the pids controller proper.
+ */
+static void pids_cancel(struct pids_cgroup *pids, int num)
+{
+	/*
+	 * A negative count (or overflow for that matter) is invalid,
+	 * and indicates a bug in the `pids` controller proper.
+	 */
+	WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter));
+}
+
+/**
+ * pids_uncharge - hierarchically uncharge the pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to uncharge
+ */
+static void pids_uncharge(struct pids_cgroup *pids, int num)
+{
+	struct pids_cgroup *p;
+
+	for (p = pids; parent_pids(p); p = parent_pids(p))
+		pids_cancel(p, num);
+}
+
+/**
+ * pids_charge - hierarchically charge the pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to charge
+ *
+ * This function does *not* follow the pid limit set. It cannot fail and the new
+ * pid count may exceed the limit. This is only used for reverting failed
+ * attaches, where there is no other way out than violating the limit.
+ */
+static void pids_charge(struct pids_cgroup *pids, int num)
+{
+	struct pids_cgroup *p;
+
+	for (p = pids; parent_pids(p); p = parent_pids(p)) {
+		int64_t new = atomic64_add_return(num, &p->counter);
+
+		pids_update_watermark(p, new);
+	}
+}
+
+/**
+ * pids_try_charge - hierarchically try to charge the pid count
+ * @pids: the pid cgroup state
+ * @num: the number of pids to charge
+ * @fail: storage of pid cgroup causing the fail
+ *
+ * This function follows the set limit. It will fail if the charge would cause
+ * the new value to exceed the hierarchical limit. Returns 0 if the charge
+ * succeeded, otherwise -EAGAIN.
+ */
+static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail)
+{
+	struct pids_cgroup *p, *q;
+
+	for (p = pids; parent_pids(p); p = parent_pids(p)) {
+		int64_t new = atomic64_add_return(num, &p->counter);
+		int64_t limit = atomic64_read(&p->limit);
+
+		/*
+		 * Since new is capped to the maximum number of pid_t, if
+		 * p->limit is %PIDS_MAX then we know that this test will never
+		 * fail.
+		 */
+		if (new > limit) {
+			*fail = p;
+			goto revert;
+		}
+		/*
+		 * Not technically accurate if we go over limit somewhere up
+		 * the hierarchy, but that's tolerable for the watermark.
+		 */
+		pids_update_watermark(p, new);
+	}
+
+	return 0;
+
+revert:
+	for (q = pids; q != p; q = parent_pids(q))
+		pids_cancel(q, num);
+	pids_cancel(p, num);
+
+	return -EAGAIN;
+}
+
+static int pids_can_attach(struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
+
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
+		struct cgroup_subsys_state *old_css;
+		struct pids_cgroup *old_pids;
+
+		/*
+		 * No need to pin @old_css between here and cancel_attach()
+		 * because cgroup core protects it from being freed before
+		 * the migration completes or fails.
+		 */
+		old_css = task_css(task, pids_cgrp_id);
+		old_pids = css_pids(old_css);
+
+		pids_charge(pids, 1);
+		pids_uncharge(old_pids, 1);
+	}
+
+	return 0;
+}
+
+static void pids_cancel_attach(struct cgroup_taskset *tset)
+{
+	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
+
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
+		struct cgroup_subsys_state *old_css;
+		struct pids_cgroup *old_pids;
+
+		old_css = task_css(task, pids_cgrp_id);
+		old_pids = css_pids(old_css);
+
+		pids_charge(old_pids, 1);
+		pids_uncharge(pids, 1);
+	}
+}
+
+static void pids_event(struct pids_cgroup *pids_forking,
+		       struct pids_cgroup *pids_over_limit)
+{
+	struct pids_cgroup *p = pids_forking;
+
+	/* Only log the first time limit is hit. */
+	if (atomic64_inc_return(&p->events_local[PIDCG_FORKFAIL]) == 1) {
+		pr_info("cgroup: fork rejected by pids controller in ");
+		pr_cont_cgroup_path(p->css.cgroup);
+		pr_cont("\n");
+	}
+	if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) ||
+	    cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) {
+		cgroup_file_notify(&p->events_local_file);
+		return;
+	}
+
+	atomic64_inc(&pids_over_limit->events_local[PIDCG_MAX]);
+	cgroup_file_notify(&pids_over_limit->events_local_file);
+
+	for (p = pids_over_limit; parent_pids(p); p = parent_pids(p)) {
+		atomic64_inc(&p->events[PIDCG_MAX]);
+		cgroup_file_notify(&p->events_file);
+	}
+}
+
+/*
+ * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
+ * on cgroup_threadgroup_change_begin() held by the copy_process().
+ */
+static int pids_can_fork(struct task_struct *task, struct css_set *cset)
+{
+	struct pids_cgroup *pids, *pids_over_limit;
+	int err;
+
+	pids = css_pids(cset->subsys[pids_cgrp_id]);
+	err = pids_try_charge(pids, 1, &pids_over_limit);
+	if (err)
+		pids_event(pids, pids_over_limit);
+
+	return err;
+}
+
+static void pids_cancel_fork(struct task_struct *task, struct css_set *cset)
+{
+	struct pids_cgroup *pids;
+
+	pids = css_pids(cset->subsys[pids_cgrp_id]);
+	pids_uncharge(pids, 1);
+}
+
+static void pids_release(struct task_struct *task)
+{
+	struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));
+
+	pids_uncharge(pids, 1);
+}
+
+static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, loff_t off)
+{
+	struct cgroup_subsys_state *css = of_css(of);
+	struct pids_cgroup *pids = css_pids(css);
+	int64_t limit;
+	int err;
+
+	buf = strstrip(buf);
+	if (!strcmp(buf, PIDS_MAX_STR)) {
+		limit = PIDS_MAX;
+		goto set_limit;
+	}
+
+	err = kstrtoll(buf, 0, &limit);
+	if (err)
+		return err;
+
+	if (limit < 0 || limit >= PIDS_MAX)
+		return -EINVAL;
+
+set_limit:
+	/*
+	 * Limit updates don't need to be mutex'd, since it isn't
+	 * critical that any racing fork()s follow the new limit.
+	 */
+	atomic64_set(&pids->limit, limit);
+	return nbytes;
+}
+
+static int pids_max_show(struct seq_file *sf, void *v)
+{
+	struct cgroup_subsys_state *css = seq_css(sf);
+	struct pids_cgroup *pids = css_pids(css);
+	int64_t limit = atomic64_read(&pids->limit);
+
+	if (limit >= PIDS_MAX)
+		seq_printf(sf, "%s\n", PIDS_MAX_STR);
+	else
+		seq_printf(sf, "%lld\n", limit);
+
+	return 0;
+}
+
+static s64 pids_current_read(struct cgroup_subsys_state *css,
+			     struct cftype *cft)
+{
+	struct pids_cgroup *pids = css_pids(css);
+
+	return atomic64_read(&pids->counter);
+}
+
+static s64 pids_peak_read(struct cgroup_subsys_state *css,
+			  struct cftype *cft)
+{
+	struct pids_cgroup *pids = css_pids(css);
+
+	return READ_ONCE(pids->watermark);
+}
+
+static int __pids_events_show(struct seq_file *sf, bool local)
+{
+	struct pids_cgroup *pids = css_pids(seq_css(sf));
+	enum pidcg_event pe = PIDCG_MAX;
+	atomic64_t *events;
+
+	if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) ||
+	    cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) {
+		pe = PIDCG_FORKFAIL;
+		local = true;
+	}
+	events = local ? pids->events_local : pids->events;
+
+	seq_printf(sf, "max %lld\n", (s64)atomic64_read(&events[pe]));
+	return 0;
+}
+
+static int pids_events_show(struct seq_file *sf, void *v)
+{
+	__pids_events_show(sf, false);
+	return 0;
+}
+
+static int pids_events_local_show(struct seq_file *sf, void *v)
+{
+	__pids_events_show(sf, true);
+	return 0;
+}
+
+static struct cftype pids_files[] = {
+	{
+		.name = "max",
+		.write = pids_max_write,
+		.seq_show = pids_max_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.read_s64 = pids_current_read,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "peak",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = pids_peak_read,
+	},
+	{
+		.name = "events",
+		.seq_show = pids_events_show,
+		.file_offset = offsetof(struct pids_cgroup, events_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "events.local",
+		.seq_show = pids_events_local_show,
+		.file_offset = offsetof(struct pids_cgroup, events_local_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ }	/* terminate */
+};
+
+static struct cftype pids_files_legacy[] = {
+	{
+		.name = "max",
+		.write = pids_max_write,
+		.seq_show = pids_max_show,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.read_s64 = pids_current_read,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "peak",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = pids_peak_read,
+	},
+	{
+		.name = "events",
+		.seq_show = pids_events_show,
+		.file_offset = offsetof(struct pids_cgroup, events_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ }	/* terminate */
+};
+
+
+struct cgroup_subsys pids_cgrp_subsys = {
+	.css_alloc	= pids_css_alloc,
+	.css_free	= pids_css_free,
+	.can_attach 	= pids_can_attach,
+	.cancel_attach 	= pids_cancel_attach,
+	.can_fork	= pids_can_fork,
+	.cancel_fork	= pids_cancel_fork,
+	.release	= pids_release,
+	.legacy_cftypes = pids_files_legacy,
+	.dfl_cftypes	= pids_files,
+	.threaded	= true,
+};

linux-7.2.3/kernel/cgroup/rdma.c

@@ -0,0 +1,789 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RDMA resource limiting controller for cgroups.
+ *
+ * Used to allow a cgroup hierarchy to stop processes from consuming
+ * additional RDMA resources after a certain limit is reached.
+ *
+ * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/limits.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/cgroup.h>
+#include <linux/parser.h>
+#include <linux/cgroup_rdma.h>
+
+#define RDMACG_MAX_STR "max"
+
+enum rdmacg_limit_tokens {
+	RDMACG_HCA_HANDLE_VAL,
+	RDMACG_HCA_HANDLE_MAX,
+	RDMACG_HCA_OBJECT_VAL,
+	RDMACG_HCA_OBJECT_MAX,
+	NR_RDMACG_LIMIT_TOKENS,
+};
+
+static const match_table_t rdmacg_limit_tokens = {
+	{ RDMACG_HCA_HANDLE_VAL,	"hca_handle=%d"	},
+	{ RDMACG_HCA_HANDLE_MAX,	"hca_handle=max"	},
+	{ RDMACG_HCA_OBJECT_VAL,	"hca_object=%d"	},
+	{ RDMACG_HCA_OBJECT_MAX,	"hca_object=max"	},
+	{ NR_RDMACG_LIMIT_TOKENS,	NULL			},
+};
+
+/*
+ * Protects list of resource pools maintained on per cgroup basis
+ * and rdma device list.
+ */
+static DEFINE_MUTEX(rdmacg_mutex);
+static LIST_HEAD(rdmacg_devices);
+
+enum rdmacg_file_type {
+	RDMACG_RESOURCE_TYPE_MAX,
+	RDMACG_RESOURCE_TYPE_STAT,
+	RDMACG_RESOURCE_TYPE_PEAK,
+};
+
+/*
+ * resource table definition as to be seen by the user.
+ * Need to add entries to it when more resources are
+ * added/defined at IB verb/core layer.
+ */
+static char const *rdmacg_resource_names[] = {
+	[RDMACG_RESOURCE_HCA_HANDLE]	= "hca_handle",
+	[RDMACG_RESOURCE_HCA_OBJECT]	= "hca_object",
+};
+
+/* resource tracker for each resource of rdma cgroup */
+struct rdmacg_resource {
+	int max;
+	int usage;
+	int peak;
+};
+
+/*
+ * resource pool object which represents per cgroup, per device
+ * resources. There are multiple instances of this object per cgroup,
+ * therefore it cannot be embedded within rdma_cgroup structure. It
+ * is maintained as list.
+ */
+struct rdmacg_resource_pool {
+	struct rdmacg_device	*device;
+	struct rdmacg_resource	resources[RDMACG_RESOURCE_MAX];
+
+	struct list_head	cg_node;
+	struct list_head	dev_node;
+
+	/* count active user tasks of this pool */
+	u64			usage_sum;
+	/* total number counts which are set to max */
+	int			num_max_cnt;
+
+	/* per-resource event counters */
+	u64			events_max[RDMACG_RESOURCE_MAX];
+	u64			events_alloc_fail[RDMACG_RESOURCE_MAX];
+	u64			events_local_max[RDMACG_RESOURCE_MAX];
+	u64			events_local_alloc_fail[RDMACG_RESOURCE_MAX];
+};
+
+static struct rdma_cgroup *css_rdmacg(struct cgroup_subsys_state *css)
+{
+	return container_of(css, struct rdma_cgroup, css);
+}
+
+static struct rdma_cgroup *parent_rdmacg(struct rdma_cgroup *cg)
+{
+	return css_rdmacg(cg->css.parent);
+}
+
+static inline struct rdma_cgroup *get_current_rdmacg(void)
+{
+	return css_rdmacg(task_get_css(current, rdma_cgrp_id));
+}
+
+static void set_resource_limit(struct rdmacg_resource_pool *rpool,
+			       int index, int new_max)
+{
+	if (new_max == S32_MAX) {
+		if (rpool->resources[index].max != S32_MAX)
+			rpool->num_max_cnt++;
+	} else {
+		if (rpool->resources[index].max == S32_MAX)
+			rpool->num_max_cnt--;
+	}
+	rpool->resources[index].max = new_max;
+}
+
+static void set_all_resource_max_limit(struct rdmacg_resource_pool *rpool)
+{
+	int i;
+
+	for (i = 0; i < RDMACG_RESOURCE_MAX; i++)
+		set_resource_limit(rpool, i, S32_MAX);
+}
+
+static void free_cg_rpool_locked(struct rdmacg_resource_pool *rpool)
+{
+	lockdep_assert_held(&rdmacg_mutex);
+
+	list_del(&rpool->cg_node);
+	list_del(&rpool->dev_node);
+	kfree(rpool);
+}
+
+static bool rpool_has_persistent_state(struct rdmacg_resource_pool *rpool)
+{
+	int i;
+
+	/*
+	 * Keep the rpool alive if any peak value is non-zero,
+	 * so that rdma.peak persists as a historical high-
+	 * watermark even after all resources are freed.
+	 */
+	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
+		if (rpool->resources[i].peak ||
+		    rpool->events_max[i] ||
+		    rpool->events_local_max[i] ||
+		    rpool->events_alloc_fail[i] ||
+		    rpool->events_local_alloc_fail[i])
+			return true;
+	}
+	return false;
+}
+
+static struct rdmacg_resource_pool *
+find_cg_rpool_locked(struct rdma_cgroup *cg,
+		     struct rdmacg_device *device)
+
+{
+	struct rdmacg_resource_pool *pool;
+
+	lockdep_assert_held(&rdmacg_mutex);
+
+	list_for_each_entry(pool, &cg->rpools, cg_node)
+		if (pool->device == device)
+			return pool;
+
+	return NULL;
+}
+
+static struct rdmacg_resource_pool *
+get_cg_rpool_locked(struct rdma_cgroup *cg, struct rdmacg_device *device)
+{
+	struct rdmacg_resource_pool *rpool;
+
+	rpool = find_cg_rpool_locked(cg, device);
+	if (rpool)
+		return rpool;
+
+	rpool = kzalloc_obj(*rpool);
+	if (!rpool)
+		return ERR_PTR(-ENOMEM);
+
+	rpool->device = device;
+	set_all_resource_max_limit(rpool);
+
+	INIT_LIST_HEAD(&rpool->cg_node);
+	INIT_LIST_HEAD(&rpool->dev_node);
+	list_add_tail(&rpool->cg_node, &cg->rpools);
+	list_add_tail(&rpool->dev_node, &device->rpools);
+	return rpool;
+}
+
+/**
+ * uncharge_cg_locked - uncharge resource for rdma cgroup
+ * @cg: pointer to cg to uncharge and all parents in hierarchy
+ * @device: pointer to rdmacg device
+ * @index: index of the resource to uncharge in cg (resource pool)
+ *
+ * It also frees the resource pool which was created as part of
+ * charging operation when there are no resources attached to
+ * resource pool.
+ */
+static void
+uncharge_cg_locked(struct rdma_cgroup *cg,
+		   struct rdmacg_device *device,
+		   enum rdmacg_resource_type index)
+{
+	struct rdmacg_resource_pool *rpool;
+
+	rpool = find_cg_rpool_locked(cg, device);
+
+	/*
+	 * rpool cannot be null at this stage. Let kernel operate in case
+	 * if there a bug in IB stack or rdma controller, instead of crashing
+	 * the system.
+	 */
+	if (unlikely(!rpool)) {
+		pr_warn("Invalid device %p or rdma cgroup %p\n", device, cg);
+		return;
+	}
+
+	rpool->resources[index].usage--;
+
+	/*
+	 * A negative count (or overflow) is invalid,
+	 * it indicates a bug in the rdma controller.
+	 */
+	WARN_ON_ONCE(rpool->resources[index].usage < 0);
+	rpool->usage_sum--;
+	if (rpool->usage_sum == 0 &&
+	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
+		if (!rpool_has_persistent_state(rpool)) {
+			/*
+			 * No user of the rpool and all entries are set to max, so
+			 * safe to delete this rpool.
+			 */
+			free_cg_rpool_locked(rpool);
+		}
+	}
+}
+
+/**
+ * rdmacg_event_locked - fire event when resource allocation exceeds limit
+ * @cg: requesting cgroup
+ * @over_cg: cgroup whose limit was exceeded
+ * @device: rdma device
+ * @index: resource type index
+ *
+ * Must be called under rdmacg_mutex. Updates event counters in the
+ * resource pools of @cg and @over_cg, propagates hierarchical max
+ * events from @over_cg (including itself) upward, and notifies
+ * userspace via cgroup_file_notify().
+ */
+static void rdmacg_event_locked(struct rdma_cgroup *cg,
+				struct rdma_cgroup *over_cg,
+				struct rdmacg_device *device,
+				enum rdmacg_resource_type index)
+{
+	struct rdmacg_resource_pool *rpool;
+	struct rdma_cgroup *p;
+
+	lockdep_assert_held(&rdmacg_mutex);
+
+	/* Increment local alloc_fail in requesting cgroup */
+	rpool = find_cg_rpool_locked(cg, device);
+	if (rpool) {
+		rpool->events_local_alloc_fail[index]++;
+		cgroup_file_notify(&cg->events_local_file);
+	}
+
+	/* Increment local max in the over-limit cgroup */
+	rpool = find_cg_rpool_locked(over_cg, device);
+	if (rpool) {
+		rpool->events_local_max[index]++;
+		cgroup_file_notify(&over_cg->events_local_file);
+	}
+
+	/* Propagate hierarchical max events upward */
+	for (p = over_cg; parent_rdmacg(p); p = parent_rdmacg(p)) {
+		rpool = get_cg_rpool_locked(p, device);
+		if (!IS_ERR(rpool)) {
+			rpool->events_max[index]++;
+			cgroup_file_notify(&p->events_file);
+		}
+	}
+	/* Propagate hierarchical alloc_fail from requesting cgroup upward */
+	for (p = cg; parent_rdmacg(p); p = parent_rdmacg(p)) {
+		rpool = get_cg_rpool_locked(p, device);
+		if (!IS_ERR(rpool)) {
+			rpool->events_alloc_fail[index]++;
+			cgroup_file_notify(&p->events_file);
+		}
+	}
+}
+
+/**
+ * rdmacg_uncharge_hierarchy - hierarchically uncharge rdma resource count
+ * @cg: pointer to cg to uncharge and all parents in hierarchy
+ * @device: pointer to rdmacg device
+ * @stop_cg: while traversing hirerchy, when meet with stop_cg cgroup
+ *           stop uncharging
+ * @index: index of the resource to uncharge in cg in given resource pool
+ */
+static void rdmacg_uncharge_hierarchy(struct rdma_cgroup *cg,
+				     struct rdmacg_device *device,
+				     struct rdma_cgroup *stop_cg,
+				     enum rdmacg_resource_type index)
+{
+	struct rdma_cgroup *p;
+
+	mutex_lock(&rdmacg_mutex);
+
+	for (p = cg; p != stop_cg; p = parent_rdmacg(p))
+		uncharge_cg_locked(p, device, index);
+
+	mutex_unlock(&rdmacg_mutex);
+
+	css_put(&cg->css);
+}
+
+/**
+ * rdmacg_uncharge - hierarchically uncharge rdma resource count
+ * @cg: pointer to cg to uncharge and all parents in hierarchy
+ * @device: pointer to rdmacg device
+ * @index: index of the resource to uncharge in cgroup in given resource pool
+ */
+void rdmacg_uncharge(struct rdma_cgroup *cg,
+		     struct rdmacg_device *device,
+		     enum rdmacg_resource_type index)
+{
+	if (index >= RDMACG_RESOURCE_MAX)
+		return;
+
+	rdmacg_uncharge_hierarchy(cg, device, NULL, index);
+}
+EXPORT_SYMBOL(rdmacg_uncharge);
+
+/**
+ * rdmacg_try_charge - hierarchically try to charge the rdma resource
+ * @rdmacg: pointer to rdma cgroup which will own this resource
+ * @device: pointer to rdmacg device
+ * @index: index of the resource to charge in cgroup (resource pool)
+ *
+ * This function follows charging resource in hierarchical way.
+ * It will fail if the charge would cause the new value to exceed the
+ * hierarchical limit.
+ * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL.
+ * Returns pointer to rdmacg for this resource when charging is successful.
+ *
+ * Charger needs to account resources on two criteria.
+ * (a) per cgroup & (b) per device resource usage.
+ * Per cgroup resource usage ensures that tasks of cgroup doesn't cross
+ * the configured limits. Per device provides granular configuration
+ * in multi device usage. It allocates resource pool in the hierarchy
+ * for each parent it come across for first resource. Later on resource
+ * pool will be available. Therefore it will be much faster thereon
+ * to charge/uncharge.
+ */
+int rdmacg_try_charge(struct rdma_cgroup **rdmacg,
+		      struct rdmacg_device *device,
+		      enum rdmacg_resource_type index)
+{
+	struct rdma_cgroup *cg, *p;
+	struct rdmacg_resource_pool *rpool;
+	s64 new;
+	int ret = 0;
+
+	if (index >= RDMACG_RESOURCE_MAX)
+		return -EINVAL;
+
+	/*
+	 * hold on to css, as cgroup can be removed but resource
+	 * accounting happens on css.
+	 */
+	cg = get_current_rdmacg();
+
+	mutex_lock(&rdmacg_mutex);
+	for (p = cg; p; p = parent_rdmacg(p)) {
+		rpool = get_cg_rpool_locked(p, device);
+		if (IS_ERR(rpool)) {
+			ret = PTR_ERR(rpool);
+			goto err;
+		} else {
+			new = (s64)rpool->resources[index].usage + 1;
+			if (new > rpool->resources[index].max) {
+				ret = -EAGAIN;
+				goto err;
+			} else {
+				rpool->resources[index].usage = new;
+				rpool->usage_sum++;
+			}
+		}
+	}
+	/* Update peak only after all charges succeed */
+	for (p = cg; p; p = parent_rdmacg(p)) {
+		rpool = find_cg_rpool_locked(p, device);
+		if (rpool && rpool->resources[index].usage > rpool->resources[index].peak)
+			rpool->resources[index].peak = rpool->resources[index].usage;
+	}
+	mutex_unlock(&rdmacg_mutex);
+
+	*rdmacg = cg;
+	return 0;
+
+err:
+	if (ret == -EAGAIN)
+		rdmacg_event_locked(cg, p, device, index);
+	mutex_unlock(&rdmacg_mutex);
+	rdmacg_uncharge_hierarchy(cg, device, p, index);
+	return ret;
+}
+EXPORT_SYMBOL(rdmacg_try_charge);
+
+/**
+ * rdmacg_register_device - register rdmacg device to rdma controller.
+ * @device: pointer to rdmacg device whose resources need to be accounted.
+ *
+ * If IB stack wish a device to participate in rdma cgroup resource
+ * tracking, it must invoke this API to register with rdma cgroup before
+ * any user space application can start using the RDMA resources.
+ */
+void rdmacg_register_device(struct rdmacg_device *device)
+{
+	INIT_LIST_HEAD(&device->dev_node);
+	INIT_LIST_HEAD(&device->rpools);
+
+	mutex_lock(&rdmacg_mutex);
+	list_add_tail(&device->dev_node, &rdmacg_devices);
+	mutex_unlock(&rdmacg_mutex);
+}
+EXPORT_SYMBOL(rdmacg_register_device);
+
+/**
+ * rdmacg_unregister_device - unregister rdmacg device from rdma controller.
+ * @device: pointer to rdmacg device which was previously registered with rdma
+ *          controller using rdmacg_register_device().
+ *
+ * IB stack must invoke this after all the resources of the IB device
+ * are destroyed and after ensuring that no more resources will be created
+ * when this API is invoked.
+ */
+void rdmacg_unregister_device(struct rdmacg_device *device)
+{
+	struct rdmacg_resource_pool *rpool, *tmp;
+
+	/*
+	 * Synchronize with any active resource settings,
+	 * usage query happening via configfs.
+	 */
+	mutex_lock(&rdmacg_mutex);
+	list_del_init(&device->dev_node);
+
+	/*
+	 * Now that this device is off the cgroup list, its safe to free
+	 * all the rpool resources.
+	 */
+	list_for_each_entry_safe(rpool, tmp, &device->rpools, dev_node)
+		free_cg_rpool_locked(rpool);
+
+	mutex_unlock(&rdmacg_mutex);
+}
+EXPORT_SYMBOL(rdmacg_unregister_device);
+
+static struct rdmacg_device *rdmacg_get_device_locked(const char *name)
+{
+	struct rdmacg_device *device;
+
+	lockdep_assert_held(&rdmacg_mutex);
+
+	list_for_each_entry(device, &rdmacg_devices, dev_node)
+		if (!strcmp(name, device->name))
+			return device;
+
+	return NULL;
+}
+
+static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
+				       char *buf, size_t nbytes, loff_t off)
+{
+	struct rdma_cgroup *cg = css_rdmacg(of_css(of));
+	const char *dev_name;
+	struct rdmacg_resource_pool *rpool;
+	struct rdmacg_device *device;
+	char *options = strstrip(buf);
+	char *p;
+	int *new_limits;
+	unsigned long enables = 0;
+	int i = 0, ret = 0;
+
+	/* extract the device name first */
+	dev_name = strsep(&options, " ");
+	if (!dev_name) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	new_limits = kzalloc_objs(int, RDMACG_RESOURCE_MAX);
+	if (!new_limits) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	/* parse resource limit tokens */
+	while ((p = strsep(&options, " \t\n"))) {
+		substring_t args[MAX_OPT_ARGS];
+		int tok, intval;
+
+		if (!*p)
+			continue;
+
+		tok = match_token(p, rdmacg_limit_tokens, args);
+		switch (tok) {
+		case RDMACG_HCA_HANDLE_VAL:
+			if (match_int(&args[0], &intval) || intval < 0) {
+				ret = -EINVAL;
+				goto parse_err;
+			}
+			new_limits[RDMACG_RESOURCE_HCA_HANDLE] = intval;
+			enables |= BIT(RDMACG_RESOURCE_HCA_HANDLE);
+			break;
+		case RDMACG_HCA_HANDLE_MAX:
+			new_limits[RDMACG_RESOURCE_HCA_HANDLE] = S32_MAX;
+			enables |= BIT(RDMACG_RESOURCE_HCA_HANDLE);
+			break;
+		case RDMACG_HCA_OBJECT_VAL:
+			if (match_int(&args[0], &intval) || intval < 0) {
+				ret = -EINVAL;
+				goto parse_err;
+			}
+			new_limits[RDMACG_RESOURCE_HCA_OBJECT] = intval;
+			enables |= BIT(RDMACG_RESOURCE_HCA_OBJECT);
+			break;
+		case RDMACG_HCA_OBJECT_MAX:
+			new_limits[RDMACG_RESOURCE_HCA_OBJECT] = S32_MAX;
+			enables |= BIT(RDMACG_RESOURCE_HCA_OBJECT);
+			break;
+		default:
+			ret = -EINVAL;
+			goto parse_err;
+		}
+	}
+
+	/* acquire lock to synchronize with hot plug devices */
+	mutex_lock(&rdmacg_mutex);
+
+	device = rdmacg_get_device_locked(dev_name);
+	if (!device) {
+		ret = -ENODEV;
+		goto dev_err;
+	}
+
+	rpool = get_cg_rpool_locked(cg, device);
+	if (IS_ERR(rpool)) {
+		ret = PTR_ERR(rpool);
+		goto dev_err;
+	}
+
+	/* now set the new limits of the rpool */
+	for_each_set_bit(i, &enables, RDMACG_RESOURCE_MAX)
+		set_resource_limit(rpool, i, new_limits[i]);
+
+	if (rpool->usage_sum == 0 &&
+	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
+		if (!rpool_has_persistent_state(rpool)) {
+			/*
+			 * No user of the rpool and all entries are set to max, so
+			 * safe to delete this rpool.
+			 */
+			free_cg_rpool_locked(rpool);
+		}
+	}
+
+dev_err:
+	mutex_unlock(&rdmacg_mutex);
+
+parse_err:
+	kfree(new_limits);
+
+err:
+	return ret ?: nbytes;
+}
+
+static void print_rpool_values(struct seq_file *sf,
+			       struct rdmacg_resource_pool *rpool)
+{
+	enum rdmacg_file_type sf_type;
+	int i;
+	u32 value;
+
+	sf_type = seq_cft(sf)->private;
+
+	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
+		seq_puts(sf, rdmacg_resource_names[i]);
+		seq_putc(sf, '=');
+		if (sf_type == RDMACG_RESOURCE_TYPE_MAX) {
+			if (rpool)
+				value = rpool->resources[i].max;
+			else
+				value = S32_MAX;
+		} else if (sf_type == RDMACG_RESOURCE_TYPE_PEAK) {
+			value = rpool ? rpool->resources[i].peak : 0;
+		} else {
+			if (rpool)
+				value = rpool->resources[i].usage;
+			else
+				value = 0;
+		}
+
+		if (value == S32_MAX)
+			seq_puts(sf, RDMACG_MAX_STR);
+		else
+			seq_printf(sf, "%d", value);
+		seq_putc(sf, ' ');
+	}
+}
+
+static int rdmacg_resource_read(struct seq_file *sf, void *v)
+{
+	struct rdmacg_device *device;
+	struct rdmacg_resource_pool *rpool;
+	struct rdma_cgroup *cg = css_rdmacg(seq_css(sf));
+
+	mutex_lock(&rdmacg_mutex);
+
+	list_for_each_entry(device, &rdmacg_devices, dev_node) {
+		seq_printf(sf, "%s ", device->name);
+
+		rpool = find_cg_rpool_locked(cg, device);
+		print_rpool_values(sf, rpool);
+
+		seq_putc(sf, '\n');
+	}
+
+	mutex_unlock(&rdmacg_mutex);
+	return 0;
+}
+
+static int rdmacg_events_show(struct seq_file *sf, void *v)
+{
+	struct rdma_cgroup *cg = css_rdmacg(seq_css(sf));
+	struct rdmacg_resource_pool *rpool;
+	struct rdmacg_device *device;
+	int i;
+
+	mutex_lock(&rdmacg_mutex);
+
+	list_for_each_entry(device, &rdmacg_devices, dev_node) {
+		rpool = find_cg_rpool_locked(cg, device);
+
+		seq_printf(sf, "%s ", device->name);
+		for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
+			seq_printf(sf, "%s.max=%llu %s.alloc_fail=%llu",
+				   rdmacg_resource_names[i],
+				   rpool ? rpool->events_max[i] : 0ULL,
+				   rdmacg_resource_names[i],
+				   rpool ? rpool->events_alloc_fail[i] : 0ULL);
+			if (i < RDMACG_RESOURCE_MAX - 1)
+				seq_putc(sf, ' ');
+		}
+		seq_putc(sf, '\n');
+	}
+
+	mutex_unlock(&rdmacg_mutex);
+	return 0;
+}
+
+static int rdmacg_events_local_show(struct seq_file *sf, void *v)
+{
+	struct rdma_cgroup *cg = css_rdmacg(seq_css(sf));
+	struct rdmacg_resource_pool *rpool;
+	struct rdmacg_device *device;
+	int i;
+
+	mutex_lock(&rdmacg_mutex);
+
+	list_for_each_entry(device, &rdmacg_devices, dev_node) {
+		rpool = find_cg_rpool_locked(cg, device);
+
+		seq_printf(sf, "%s ", device->name);
+		for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
+			seq_printf(sf, "%s.max=%llu %s.alloc_fail=%llu",
+				   rdmacg_resource_names[i],
+				   rpool ? rpool->events_local_max[i] : 0ULL,
+				   rdmacg_resource_names[i],
+				   rpool ? rpool->events_local_alloc_fail[i] : 0ULL);
+			if (i < RDMACG_RESOURCE_MAX - 1)
+				seq_putc(sf, ' ');
+		}
+		seq_putc(sf, '\n');
+	}
+
+	mutex_unlock(&rdmacg_mutex);
+	return 0;
+}
+
+static struct cftype rdmacg_files[] = {
+	{
+		.name = "max",
+		.write = rdmacg_resource_set_max,
+		.seq_show = rdmacg_resource_read,
+		.private = RDMACG_RESOURCE_TYPE_MAX,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "current",
+		.seq_show = rdmacg_resource_read,
+		.private = RDMACG_RESOURCE_TYPE_STAT,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "peak",
+		.seq_show = rdmacg_resource_read,
+		.private = RDMACG_RESOURCE_TYPE_PEAK,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "events",
+		.seq_show = rdmacg_events_show,
+		.file_offset = offsetof(struct rdma_cgroup, events_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{
+		.name = "events.local",
+		.seq_show = rdmacg_events_local_show,
+		.file_offset = offsetof(struct rdma_cgroup, events_local_file),
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+	{ }	/* terminate */
+};
+
+static struct cgroup_subsys_state *
+rdmacg_css_alloc(struct cgroup_subsys_state *parent)
+{
+	struct rdma_cgroup *cg;
+
+	cg = kzalloc_obj(*cg);
+	if (!cg)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&cg->rpools);
+	return &cg->css;
+}
+
+static void rdmacg_css_free(struct cgroup_subsys_state *css)
+{
+	struct rdma_cgroup *cg = css_rdmacg(css);
+	struct rdmacg_resource_pool *rpool, *tmp;
+
+	/* Clean up rpools kept alive by non-zero peak values */
+	mutex_lock(&rdmacg_mutex);
+	list_for_each_entry_safe(rpool, tmp, &cg->rpools, cg_node)
+		free_cg_rpool_locked(rpool);
+	mutex_unlock(&rdmacg_mutex);
+
+	kfree(cg);
+}
+
+/**
+ * rdmacg_css_offline - cgroup css_offline callback
+ * @css: css of interest
+ *
+ * This function is called when @css is about to go away and responsible
+ * for shooting down all rdmacg associated with @css. As part of that it
+ * marks all the resource pool entries to max value, so that when resources are
+ * uncharged, associated resource pool can be freed as well.
+ */
+static void rdmacg_css_offline(struct cgroup_subsys_state *css)
+{
+	struct rdma_cgroup *cg = css_rdmacg(css);
+	struct rdmacg_resource_pool *rpool;
+
+	mutex_lock(&rdmacg_mutex);
+
+	list_for_each_entry(rpool, &cg->rpools, cg_node)
+		set_all_resource_max_limit(rpool);
+
+	mutex_unlock(&rdmacg_mutex);
+}
+
+struct cgroup_subsys rdma_cgrp_subsys = {
+	.css_alloc	= rdmacg_css_alloc,
+	.css_free	= rdmacg_css_free,
+	.css_offline	= rdmacg_css_offline,
+	.legacy_cftypes	= rdmacg_files,
+	.dfl_cftypes	= rdmacg_files,
+};

linux-7.2.3/kernel/cgroup/rstat.c

@@ -0,0 +1,771 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "cgroup-internal.h"
+
+#include <linux/cpumask.h>
+#include <linux/sched/cputime.h>
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+
+#include <trace/events/cgroup.h>
+
+static DEFINE_SPINLOCK(rstat_base_lock);
+static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list);
+
+static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
+
+/*
+ * Determines whether a given css can participate in rstat.
+ * css's that are cgroup::self use rstat for base stats.
+ * Other css's associated with a subsystem use rstat only when
+ * they define the ss->css_rstat_flush callback.
+ */
+static inline bool css_uses_rstat(struct cgroup_subsys_state *css)
+{
+	return css_is_self(css) || css->ss->css_rstat_flush != NULL;
+}
+
+static struct css_rstat_cpu *css_rstat_cpu(
+		struct cgroup_subsys_state *css, int cpu)
+{
+	return per_cpu_ptr(css->rstat_cpu, cpu);
+}
+
+static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu(
+		struct cgroup *cgrp, int cpu)
+{
+	return per_cpu_ptr(cgrp->rstat_base_cpu, cpu);
+}
+
+static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
+{
+	if (ss)
+		return &ss->rstat_ss_lock;
+
+	return &rstat_base_lock;
+}
+
+static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu)
+{
+	if (ss)
+		return per_cpu_ptr(ss->lhead, cpu);
+	return per_cpu_ptr(&rstat_backlog_list, cpu);
+}
+
+/**
+ * __css_rstat_updated - keep track of updated rstat_cpu
+ * @css: target cgroup subsystem state
+ * @cpu: cpu on which rstat_cpu was updated
+ *
+ * Atomically inserts the css in the ss's llist for the given cpu. This is
+ * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist
+ * will be processed at the flush time to create the update tree.
+ *
+ * NOTE: if the user needs the guarantee that the updater either add itself in
+ * the lockless list or the concurrent flusher flushes its updated stats, a
+ * memory barrier is needed before the call to __css_rstat_updated() i.e. a
+ * barrier after updating the per-cpu stats and before calling
+ * __css_rstat_updated().
+ */
+void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
+{
+	struct llist_head *lhead;
+	struct css_rstat_cpu *rstatc;
+	struct llist_node *self;
+
+	/* Prevent access to uninitialized rstat pointers. */
+	if (!css_uses_rstat(css))
+		return;
+
+	lockdep_assert_preemption_disabled();
+
+	/*
+	 * The lockless insertion below relies on NMI-safe cmpxchg;
+	 * bail out in NMI on archs that don't provide it.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && in_nmi())
+		return;
+
+	rstatc = css_rstat_cpu(css, cpu);
+	/*
+	 * If already on list return. This check is racy and smp_mb() is needed
+	 * to pair it with the smp_mb() in css_process_update_tree() if the
+	 * guarantee that the updated stats are visible to concurrent flusher is
+	 * needed.
+	 */
+	if (llist_on_list(&rstatc->lnode))
+		return;
+
+	/*
+	 * This function can be renentered by irqs and nmis for the same cgroup
+	 * and may try to insert the same per-cpu lnode into the llist. Note
+	 * that llist_add() does not protect against such scenarios. In addition
+	 * this same per-cpu lnode can be modified through init_llist_node()
+	 * from css_rstat_flush() running on a different CPU.
+	 *
+	 * To protect against such stacked contexts of irqs/nmis, we use the
+	 * fact that lnode points to itself when not on a list and then use
+	 * try_cmpxchg() to atomically set to NULL to select the winner
+	 * which will call llist_add(). The losers can assume the insertion is
+	 * successful and the winner will eventually add the per-cpu lnode to
+	 * the llist.
+	 *
+	 * Please note that we can not use this_cpu_cmpxchg() here as on some
+	 * archs it is not safe against modifications from multiple CPUs.
+	 */
+	self = &rstatc->lnode;
+	if (!try_cmpxchg(&rstatc->lnode.next, &self, NULL))
+		return;
+
+	lhead = ss_lhead_cpu(css->ss, cpu);
+	llist_add(&rstatc->lnode, lhead);
+}
+
+/*
+ * BPF-facing wrapper for __css_rstat_updated(). Validate the caller-provided
+ * CPU before passing it to the internal rstat updater.
+ */
+__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
+{
+	if (unlikely(cpu < 0 || cpu >= nr_cpu_ids || !cpu_possible(cpu)))
+		return;
+
+	__css_rstat_updated(css, cpu);
+}
+
+static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu)
+{
+	/* put @css and all ancestors on the corresponding updated lists */
+	while (true) {
+		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
+		struct cgroup_subsys_state *parent = css->parent;
+		struct css_rstat_cpu *prstatc;
+
+		/*
+		 * Both additions and removals are bottom-up.  If a cgroup
+		 * is already in the tree, all ancestors are.
+		 */
+		if (rstatc->updated_next)
+			break;
+
+		/* Root has no parent to link it to, but mark it busy */
+		if (!parent) {
+			rstatc->updated_next = css;
+			break;
+		}
+
+		prstatc = css_rstat_cpu(parent, cpu);
+		rstatc->updated_next = prstatc->updated_children;
+		prstatc->updated_children = css;
+
+		css = parent;
+	}
+}
+
+static void css_process_update_tree(struct cgroup_subsys *ss, int cpu)
+{
+	struct llist_head *lhead = ss_lhead_cpu(ss, cpu);
+	struct llist_node *lnode;
+
+	while ((lnode = llist_del_first_init(lhead))) {
+		struct css_rstat_cpu *rstatc;
+
+		/*
+		 * smp_mb() is needed here (more specifically in between
+		 * init_llist_node() and per-cpu stats flushing) if the
+		 * guarantee is required by a rstat user where etiher the
+		 * updater should add itself on the lockless list or the
+		 * flusher flush the stats updated by the updater who have
+		 * observed that they are already on the list. The
+		 * corresponding barrier pair for this one should be before
+		 * __css_rstat_updated() by the user.
+		 *
+		 * For now, there aren't any such user, so not adding the
+		 * barrier here but if such a use-case arise, please add
+		 * smp_mb() here.
+		 */
+
+		rstatc = container_of(lnode, struct css_rstat_cpu, lnode);
+		__css_process_update_tree(rstatc->owner, cpu);
+	}
+}
+
+/**
+ * css_rstat_push_children - push children css's into the given list
+ * @head: current head of the list (= subtree root)
+ * @child: first child of the root
+ * @cpu: target cpu
+ * Return: A new singly linked list of css's to be flushed
+ *
+ * Iteratively traverse down the css_rstat_cpu updated tree level by
+ * level and push all the parents first before their next level children
+ * into a singly linked list via the rstat_flush_next pointer built from the
+ * tail backward like "pushing" css's into a stack. The root is pushed by
+ * the caller.
+ */
+static struct cgroup_subsys_state *css_rstat_push_children(
+		struct cgroup_subsys_state *head,
+		struct cgroup_subsys_state *child, int cpu)
+{
+	struct cgroup_subsys_state *cnext = child;	/* Next head of child css level */
+	struct cgroup_subsys_state *ghead = NULL;	/* Head of grandchild css level */
+	struct cgroup_subsys_state *parent, *grandchild;
+	struct css_rstat_cpu *crstatc;
+
+	child->rstat_flush_next = NULL;
+
+	/*
+	 * The subsystem rstat lock must be held for the whole duration from
+	 * here as the rstat_flush_next list is being constructed to when
+	 * it is consumed later in css_rstat_flush().
+	 */
+	lockdep_assert_held(ss_rstat_lock(head->ss));
+
+	/*
+	 * Notation: -> updated_next pointer
+	 *	     => rstat_flush_next pointer
+	 *
+	 * Assuming the following sample updated_children lists:
+	 *  P: C1 -> C2 -> P
+	 *  C1: G11 -> G12 -> C1
+	 *  C2: G21 -> G22 -> C2
+	 *
+	 * After 1st iteration:
+	 *  head => C2 => C1 => NULL
+	 *  ghead => G21 => G11 => NULL
+	 *
+	 * After 2nd iteration:
+	 *  head => G12 => G11 => G22 => G21 => C2 => C1 => NULL
+	 */
+next_level:
+	while (cnext) {
+		child = cnext;
+		cnext = child->rstat_flush_next;
+		parent = child->parent;
+
+		/* updated_next is parent cgroup terminated if !NULL */
+		while (child != parent) {
+			child->rstat_flush_next = head;
+			head = child;
+			crstatc = css_rstat_cpu(child, cpu);
+			grandchild = crstatc->updated_children;
+			if (grandchild != child) {
+				/* Push the grand child to the next level */
+				crstatc->updated_children = child;
+				grandchild->rstat_flush_next = ghead;
+				ghead = grandchild;
+			}
+			child = crstatc->updated_next;
+			crstatc->updated_next = NULL;
+		}
+	}
+
+	if (ghead) {
+		cnext = ghead;
+		ghead = NULL;
+		goto next_level;
+	}
+	return head;
+}
+
+/**
+ * css_rstat_updated_list - build a list of updated css's to be flushed
+ * @root: root of the css subtree to traverse
+ * @cpu: target cpu
+ * Return: A singly linked list of css's to be flushed
+ *
+ * Walks the updated rstat_cpu tree on @cpu from @root.  During traversal,
+ * each returned css is unlinked from the updated tree.
+ *
+ * The only ordering guarantee is that, for a parent and a child pair
+ * covered by a given traversal, the child is before its parent in
+ * the list.
+ *
+ * Note that updated_children is self terminated and points to a list of
+ * child css's if not empty. Whereas updated_next is like a sibling link
+ * within the children list and terminated by the parent css. An exception
+ * here is the css root whose updated_next can be self terminated.
+ */
+static struct cgroup_subsys_state *css_rstat_updated_list(
+		struct cgroup_subsys_state *root, int cpu)
+{
+	struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu);
+	struct cgroup_subsys_state *head = NULL, *parent, *child;
+
+	css_process_update_tree(root->ss, cpu);
+
+	/* Return NULL if this subtree is not on-list */
+	if (!rstatc->updated_next)
+		return NULL;
+
+	/*
+	 * Unlink @root from its parent. As the updated_children list is
+	 * singly linked, we have to walk it to find the removal point.
+	 */
+	parent = root->parent;
+	if (parent) {
+		struct css_rstat_cpu *prstatc;
+		struct cgroup_subsys_state **nextp;
+
+		prstatc = css_rstat_cpu(parent, cpu);
+		nextp = &prstatc->updated_children;
+		while (*nextp != root) {
+			struct css_rstat_cpu *nrstatc;
+
+			nrstatc = css_rstat_cpu(*nextp, cpu);
+			WARN_ON_ONCE(*nextp == parent);
+			nextp = &nrstatc->updated_next;
+		}
+		*nextp = rstatc->updated_next;
+	}
+
+	rstatc->updated_next = NULL;
+
+	/* Push @root to the list first before pushing the children */
+	head = root;
+	root->rstat_flush_next = NULL;
+	child = rstatc->updated_children;
+	rstatc->updated_children = root;
+	if (child != root)
+		head = css_rstat_push_children(head, child, cpu);
+
+	return head;
+}
+
+/*
+ * A hook for bpf stat collectors to attach to and flush their stats.
+ * Together with providing bpf kfuncs for css_rstat_updated() and
+ * css_rstat_flush(), this enables a complete workflow where bpf progs that
+ * collect cgroup stats can integrate with rstat for efficient flushing.
+ *
+ * A static noinline declaration here could cause the compiler to optimize away
+ * the function. A global noinline declaration will keep the definition, but may
+ * optimize away the callsite. Therefore, __weak is needed to ensure that the
+ * call is still emitted, by telling the compiler that we don't know what the
+ * function might eventually be.
+ */
+
+__bpf_hook_start();
+
+__weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
+				     struct cgroup *parent, int cpu)
+{
+}
+
+__bpf_hook_end();
+
+/*
+ * Helper functions for locking.
+ *
+ * This makes it easier to diagnose locking issues and contention in
+ * production environments.  The parameter @cpu_in_loop indicate lock
+ * was released and re-taken when collection data from the CPUs. The
+ * value -1 is used when obtaining the main lock else this is the CPU
+ * number processed last.
+ */
+static inline void __css_rstat_lock(struct cgroup_subsys_state *css,
+		int cpu_in_loop)
+	__acquires(ss_rstat_lock(css->ss))
+{
+	struct cgroup *cgrp = css->cgroup;
+	spinlock_t *lock;
+	bool contended;
+
+	lock = ss_rstat_lock(css->ss);
+	contended = !spin_trylock_irq(lock);
+	if (contended) {
+		trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended);
+		spin_lock_irq(lock);
+	}
+	trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended);
+}
+
+static inline void __css_rstat_unlock(struct cgroup_subsys_state *css,
+				      int cpu_in_loop)
+	__releases(ss_rstat_lock(css->ss))
+{
+	struct cgroup *cgrp = css->cgroup;
+	spinlock_t *lock;
+
+	lock = ss_rstat_lock(css->ss);
+	trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false);
+	spin_unlock_irq(lock);
+}
+
+/**
+ * css_rstat_flush - flush stats in @css's rstat subtree
+ * @css: target cgroup subsystem state
+ *
+ * Collect all per-cpu stats in @css's subtree into the global counters
+ * and propagate them upwards. After this function returns, all rstat
+ * nodes in the subtree have up-to-date ->stat.
+ *
+ * This also gets all rstat nodes in the subtree including @css off the
+ * ->updated_children lists.
+ *
+ * This function may block.
+ */
+__bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css)
+{
+	int cpu;
+	bool is_self = css_is_self(css);
+
+	/*
+	 * Since bpf programs can call this function, prevent access to
+	 * uninitialized rstat pointers.
+	 */
+	if (!css_uses_rstat(css))
+		return;
+
+	might_sleep();
+	for_each_possible_cpu(cpu) {
+		struct cgroup_subsys_state *pos;
+
+		/* Reacquire for each CPU to avoid disabling IRQs too long */
+		__css_rstat_lock(css, cpu);
+		pos = css_rstat_updated_list(css, cpu);
+		for (; pos; pos = pos->rstat_flush_next) {
+			if (is_self) {
+				cgroup_base_stat_flush(pos->cgroup, cpu);
+				bpf_rstat_flush(pos->cgroup,
+						cgroup_parent(pos->cgroup), cpu);
+			} else
+				pos->ss->css_rstat_flush(pos, cpu);
+		}
+		__css_rstat_unlock(css, cpu);
+		if (!cond_resched())
+			cpu_relax();
+	}
+}
+
+int css_rstat_init(struct cgroup_subsys_state *css)
+{
+	struct cgroup *cgrp = css->cgroup;
+	int cpu;
+	bool is_self = css_is_self(css);
+
+	if (is_self) {
+		/* the root cgrp has rstat_base_cpu preallocated */
+		if (!cgrp->rstat_base_cpu) {
+			cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu);
+			if (!cgrp->rstat_base_cpu)
+				return -ENOMEM;
+		}
+	} else if (css->ss->css_rstat_flush == NULL)
+		return 0;
+
+	/* the root cgrp's self css has rstat_cpu preallocated */
+	if (!css->rstat_cpu) {
+		css->rstat_cpu = alloc_percpu(struct css_rstat_cpu);
+		if (!css->rstat_cpu) {
+			if (is_self)
+				free_percpu(cgrp->rstat_base_cpu);
+
+			return -ENOMEM;
+		}
+	}
+
+	/* ->updated_children list is self terminated */
+	for_each_possible_cpu(cpu) {
+		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
+
+		rstatc->owner = rstatc->updated_children = css;
+		init_llist_node(&rstatc->lnode);
+
+		if (is_self) {
+			struct cgroup_rstat_base_cpu *rstatbc;
+
+			rstatbc = cgroup_rstat_base_cpu(cgrp, cpu);
+			u64_stats_init(&rstatbc->bsync);
+		}
+	}
+
+	return 0;
+}
+
+void css_rstat_exit(struct cgroup_subsys_state *css)
+{
+	int cpu;
+
+	if (!css_uses_rstat(css))
+		return;
+
+	if (!css->rstat_cpu)
+		return;
+
+	css_rstat_flush(css);
+
+	/* sanity check */
+	for_each_possible_cpu(cpu) {
+		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
+
+		if (WARN_ON_ONCE(rstatc->updated_children != css) ||
+		    WARN_ON_ONCE(rstatc->updated_next))
+			return;
+	}
+
+	if (css_is_self(css)) {
+		struct cgroup *cgrp = css->cgroup;
+
+		free_percpu(cgrp->rstat_base_cpu);
+		cgrp->rstat_base_cpu = NULL;
+	}
+
+	free_percpu(css->rstat_cpu);
+	css->rstat_cpu = NULL;
+}
+
+/**
+ * ss_rstat_init - subsystem-specific rstat initialization
+ * @ss: target subsystem
+ *
+ * If @ss is NULL, the static locks associated with the base stats
+ * are initialized. If @ss is non-NULL, the subsystem-specific locks
+ * are initialized.
+ */
+int __init ss_rstat_init(struct cgroup_subsys *ss)
+{
+	int cpu;
+
+	if (ss) {
+		ss->lhead = alloc_percpu(struct llist_head);
+		if (!ss->lhead)
+			return -ENOMEM;
+	}
+
+	spin_lock_init(ss_rstat_lock(ss));
+	for_each_possible_cpu(cpu)
+		init_llist_head(ss_lhead_cpu(ss, cpu));
+
+	return 0;
+}
+
+/*
+ * Functions for cgroup basic resource statistics implemented on top of
+ * rstat.
+ */
+static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
+				 struct cgroup_base_stat *src_bstat)
+{
+	dst_bstat->cputime.utime += src_bstat->cputime.utime;
+	dst_bstat->cputime.stime += src_bstat->cputime.stime;
+	dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
+#ifdef CONFIG_SCHED_CORE
+	dst_bstat->forceidle_sum += src_bstat->forceidle_sum;
+#endif
+	dst_bstat->ntime += src_bstat->ntime;
+}
+
+static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
+				 struct cgroup_base_stat *src_bstat)
+{
+	dst_bstat->cputime.utime -= src_bstat->cputime.utime;
+	dst_bstat->cputime.stime -= src_bstat->cputime.stime;
+	dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime;
+#ifdef CONFIG_SCHED_CORE
+	dst_bstat->forceidle_sum -= src_bstat->forceidle_sum;
+#endif
+	dst_bstat->ntime -= src_bstat->ntime;
+}
+
+static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
+{
+	struct cgroup_rstat_base_cpu *rstatbc = cgroup_rstat_base_cpu(cgrp, cpu);
+	struct cgroup *parent = cgroup_parent(cgrp);
+	struct cgroup_rstat_base_cpu *prstatbc;
+	struct cgroup_base_stat delta;
+	unsigned seq;
+
+	/* Root-level stats are sourced from system-wide CPU stats */
+	if (!parent)
+		return;
+
+	/* fetch the current per-cpu values */
+	do {
+		seq = __u64_stats_fetch_begin(&rstatbc->bsync);
+		delta = rstatbc->bstat;
+	} while (__u64_stats_fetch_retry(&rstatbc->bsync, seq));
+
+	/* propagate per-cpu delta to cgroup and per-cpu global statistics */
+	cgroup_base_stat_sub(&delta, &rstatbc->last_bstat);
+	cgroup_base_stat_add(&cgrp->bstat, &delta);
+	cgroup_base_stat_add(&rstatbc->last_bstat, &delta);
+	cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta);
+
+	/* propagate cgroup and per-cpu global delta to parent (unless that's root) */
+	if (cgroup_parent(parent)) {
+		delta = cgrp->bstat;
+		cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
+		cgroup_base_stat_add(&parent->bstat, &delta);
+		cgroup_base_stat_add(&cgrp->last_bstat, &delta);
+
+		delta = rstatbc->subtree_bstat;
+		prstatbc = cgroup_rstat_base_cpu(parent, cpu);
+		cgroup_base_stat_sub(&delta, &rstatbc->last_subtree_bstat);
+		cgroup_base_stat_add(&prstatbc->subtree_bstat, &delta);
+		cgroup_base_stat_add(&rstatbc->last_subtree_bstat, &delta);
+	}
+}
+
+static struct cgroup_rstat_base_cpu *
+cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags)
+{
+	struct cgroup_rstat_base_cpu *rstatbc;
+
+	rstatbc = get_cpu_ptr(cgrp->rstat_base_cpu);
+	*flags = u64_stats_update_begin_irqsave(&rstatbc->bsync);
+	return rstatbc;
+}
+
+static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
+						 struct cgroup_rstat_base_cpu *rstatbc,
+						 unsigned long flags)
+{
+	u64_stats_update_end_irqrestore(&rstatbc->bsync, flags);
+	__css_rstat_updated(&cgrp->self, smp_processor_id());
+	put_cpu_ptr(rstatbc);
+}
+
+void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
+{
+	struct cgroup_rstat_base_cpu *rstatbc;
+	unsigned long flags;
+
+	rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
+	rstatbc->bstat.cputime.sum_exec_runtime += delta_exec;
+	cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags);
+}
+
+void __cgroup_account_cputime_field(struct cgroup *cgrp,
+				    enum cpu_usage_stat index, u64 delta_exec)
+{
+	struct cgroup_rstat_base_cpu *rstatbc;
+	unsigned long flags;
+
+	rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
+
+	switch (index) {
+	case CPUTIME_NICE:
+		rstatbc->bstat.ntime += delta_exec;
+		fallthrough;
+	case CPUTIME_USER:
+		rstatbc->bstat.cputime.utime += delta_exec;
+		break;
+	case CPUTIME_SYSTEM:
+	case CPUTIME_IRQ:
+	case CPUTIME_SOFTIRQ:
+		rstatbc->bstat.cputime.stime += delta_exec;
+		break;
+#ifdef CONFIG_SCHED_CORE
+	case CPUTIME_FORCEIDLE:
+		rstatbc->bstat.forceidle_sum += delta_exec;
+		break;
+#endif
+	default:
+		break;
+	}
+
+	cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags);
+}
+
+/*
+ * compute the cputime for the root cgroup by getting the per cpu data
+ * at a global level, then categorizing the fields in a manner consistent
+ * with how it is done by __cgroup_account_cputime_field for each bit of
+ * cpu time attributed to a cgroup.
+ */
+static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
+{
+	struct task_cputime *cputime = &bstat->cputime;
+	int i;
+
+	memset(bstat, 0, sizeof(*bstat));
+	for_each_possible_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+		u64 user = 0;
+		u64 sys = 0;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user += cpustat[CPUTIME_USER];
+		user += cpustat[CPUTIME_NICE];
+		cputime->utime += user;
+
+		sys += cpustat[CPUTIME_SYSTEM];
+		sys += cpustat[CPUTIME_IRQ];
+		sys += cpustat[CPUTIME_SOFTIRQ];
+		cputime->stime += sys;
+
+		cputime->sum_exec_runtime += user;
+		cputime->sum_exec_runtime += sys;
+
+#ifdef CONFIG_SCHED_CORE
+		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
+#endif
+		bstat->ntime += cpustat[CPUTIME_NICE];
+	}
+}
+
+
+static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat)
+{
+#ifdef CONFIG_SCHED_CORE
+	u64 forceidle_time = bstat->forceidle_sum;
+
+	do_div(forceidle_time, NSEC_PER_USEC);
+	seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
+#endif
+}
+
+void cgroup_base_stat_cputime_show(struct seq_file *seq)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct cgroup_base_stat bstat;
+
+	if (cgroup_parent(cgrp)) {
+		css_rstat_flush(&cgrp->self);
+		__css_rstat_lock(&cgrp->self, -1);
+		bstat = cgrp->bstat;
+		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
+			       &bstat.cputime.utime, &bstat.cputime.stime);
+		__css_rstat_unlock(&cgrp->self, -1);
+	} else {
+		root_cgroup_cputime(&bstat);
+	}
+
+	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",
+			bstat.cputime.sum_exec_runtime,
+			bstat.cputime.utime,
+			bstat.cputime.stime,
+			bstat.ntime);
+
+	cgroup_force_idle_show(seq, &bstat);
+}
+
+/* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */
+BTF_KFUNCS_START(bpf_rstat_kfunc_ids)
+BTF_ID_FLAGS(func, css_rstat_updated)
+BTF_ID_FLAGS(func, css_rstat_flush, KF_SLEEPABLE)
+BTF_KFUNCS_END(bpf_rstat_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = {
+	.owner          = THIS_MODULE,
+	.set            = &bpf_rstat_kfunc_ids,
+};
+
+static int __init bpf_rstat_kfunc_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+					 &bpf_rstat_kfunc_set);
+}
+late_initcall(bpf_rstat_kfunc_init);