Merge: cgroup: Backport upstream cgroup commits up to v6.12

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6581

JIRA: https://issues.redhat.com/browse/RHEL-80382

This MR backports upstream cgroup commits up to v6.12 with relevant fixes, if applicable.

Signed-off-by: Radostin Stoyanov <rstoyano@redhat.com>

Approved-by: Waiman Long <longman@redhat.com>
Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Jan Stancek <jstancek@redhat.com>

Documentation/admin-guide/cgroup-v2.rst

@@ -533,10 +533,12 @@ cgroup namespace on namespace creation.
 Because the resource control interface files in a given directory
 control the distribution of the parent's resources, the delegatee
 shouldn't be allowed to write to them.  For the first method, this is
-achieved by not granting access to these files.  For the second, the
-kernel rejects writes to all files other than "cgroup.procs" and
-"cgroup.subtree_control" on a namespace root from inside the
-namespace.
+achieved by not granting access to these files.  For the second, files
+outside the namespace should be hidden from the delegatee by the means
+of at least mount namespacing, and the kernel rejects writes to all
+files on a namespace root from inside the cgroup namespace, except for
+those files listed in "/sys/kernel/cgroup/delegate" (including
+"cgroup.procs", "cgroup.threads", "cgroup.subtree_control", etc.).
 
 The end results are equivalent for both delegation types.  Once
 delegated, the user can build sub-hierarchy under the directory,
@@ -1708,6 +1710,8 @@ PAGE_SIZE multiple when read back.
 
 	Note that this is subtly different from setting memory.swap.max to
 	0, as it still allows for pages to be written to the zswap pool.
+	This setting has no effect if zswap is disabled, and swapping
+	is allowed unless memory.swap.max is set to 0.
 
   memory.pressure
 	A read-only nested-keyed file.

MAINTAINERS

@@ -4928,9 +4928,12 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
 F:	Documentation/admin-guide/cgroup-v1/cpusets.rst
 F:	include/linux/cpuset.h
+F:	kernel/cgroup/cpuset-internal.h
+F:	kernel/cgroup/cpuset-v1.c
 F:	kernel/cgroup/cpuset.c
 F:	tools/testing/selftests/cgroup/test_cpuset.c
 F:	tools/testing/selftests/cgroup/test_cpuset_prs.sh
+F:	tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
 
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>

include/linux/cgroup-defs.h

@@ -172,7 +172,11 @@ struct cgroup_subsys_state {
 	/* reference count - access via css_[try]get() and css_put() */
 	struct percpu_ref refcnt;
 
-	/* siblings list anchored at the parent's ->children */
+	/*
+	 * siblings list anchored at the parent's ->children
+	 *
+	 * linkage is protected by cgroup_mutex or RCU
+	 */
 	struct list_head sibling;
 	struct list_head children;
 
@@ -323,6 +327,7 @@ struct cgroup_base_stat {
 #ifdef CONFIG_SCHED_CORE
 	u64 forceidle_sum;
 #endif
+	u64 ntime;
 };
 
 /*

include/linux/cpuset.h

@@ -99,6 +99,7 @@ static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 					  const struct task_struct *tsk2);
 
+#ifdef CONFIG_CPUSETS_V1
 #define cpuset_memory_pressure_bump() 				\
 	do {							\
 		if (cpuset_memory_pressure_enabled)		\
@@ -106,6 +107,9 @@ extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 	} while (0)
 extern int cpuset_memory_pressure_enabled;
 extern void __cpuset_memory_pressure_bump(void);
+#else
+static inline void cpuset_memory_pressure_bump(void) { }
+#endif
 
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
@@ -113,7 +117,6 @@ extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
 			    struct pid *pid, struct task_struct *tsk);
 
 extern int cpuset_mem_spread_node(void);
-extern int cpuset_slab_spread_node(void);
 
 static inline int cpuset_do_page_mem_spread(void)
 {
@@ -251,11 +254,6 @@ static inline int cpuset_mem_spread_node(void)
 	return 0;
 }
 
-static inline int cpuset_slab_spread_node(void)
-{
-	return 0;
-}
-
 static inline int cpuset_do_page_mem_spread(void)
 {
 	return 0;

include/linux/mm.h

@@ -1433,7 +1433,6 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
 		struct page *page, unsigned int nr, unsigned long addr);
 
 vm_fault_t finish_fault(struct vm_fault *vmf);
-vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 #endif
 
 /*
@@ -1783,26 +1782,26 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
 
 #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid)
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
-static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
+static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
 {
-	return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
+	return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK);
 }
 
-static inline int page_cpupid_last(struct page *page)
+static inline int folio_last_cpupid(struct folio *folio)
 {
-	return page->_last_cpupid;
+	return folio->_last_cpupid;
 }
 static inline void page_cpupid_reset_last(struct page *page)
 {
 	page->_last_cpupid = -1 & LAST_CPUPID_MASK;
 }
 #else
-static inline int page_cpupid_last(struct page *page)
+static inline int folio_last_cpupid(struct folio *folio)
 {
-	return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
+	return (folio->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
 }
 
-extern int page_cpupid_xchg_last(struct page *page, int cpupid);
+int folio_xchg_last_cpupid(struct folio *folio, int cpupid);
 
 static inline void page_cpupid_reset_last(struct page *page)
 {
@@ -1810,11 +1809,12 @@ static inline void page_cpupid_reset_last(struct page *page)
 }
 #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */
 
-static inline int xchg_page_access_time(struct page *page, int time)
+static inline int folio_xchg_access_time(struct folio *folio, int time)
 {
 	int last_time;
 
-	last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS);
+	last_time = folio_xchg_last_cpupid(folio,
+					   time >> PAGE_ACCESS_TIME_BUCKETS);
 	return last_time << PAGE_ACCESS_TIME_BUCKETS;
 }
 
@@ -1828,19 +1828,19 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 	}
 }
 #else /* !CONFIG_NUMA_BALANCING */
-static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
+static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
 {
-	return page_to_nid(page); /* XXX */
+	return folio_nid(folio); /* XXX */
 }
 
-static inline int xchg_page_access_time(struct page *page, int time)
+static inline int folio_xchg_access_time(struct folio *folio, int time)
 {
 	return 0;
 }
 
-static inline int page_cpupid_last(struct page *page)
+static inline int folio_last_cpupid(struct folio *folio)
 {
-	return page_to_nid(page); /* XXX */
+	return folio_nid(folio); /* XXX */
 }
 
 static inline int cpupid_to_nid(int cpupid)

include/linux/mm_types.h

@@ -190,6 +190,10 @@ struct page {
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
 
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+	int _last_cpupid;
+#endif
+
 #ifdef CONFIG_KMSAN
 	/*
 	 * KMSAN metadata for this page:
@@ -201,10 +205,6 @@ struct page {
 	struct page *kmsan_shadow;
 	struct page *kmsan_origin;
 #endif
-
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
-	int _last_cpupid;
-#endif
 } _struct_page_alignment;
 
 /*
@@ -263,6 +263,8 @@ typedef struct {
  * @_refcount: Do not access this member directly.  Use folio_ref_count()
  *    to find how many references there are to this folio.
  * @memcg_data: Memory Control Group data.
+ * @virtual: Virtual address in the kernel direct map.
+ * @_last_cpupid: IDs of last CPU and last process that accessed the folio.
  * @_entire_mapcount: Do not use directly, call folio_entire_mapcount().
  * @_nr_pages_mapped: Do not use directly, call folio_mapcount().
  * @_pincount: Do not use directly, call folio_maybe_dma_pinned().
@@ -308,6 +310,12 @@ struct folio {
 			atomic_t _refcount;
 #ifdef CONFIG_MEMCG
 			unsigned long memcg_data;
+#endif
+#if defined(WANT_PAGE_VIRTUAL)
+			void *virtual;
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+			int _last_cpupid;
 #endif
 	/* private: the union with struct page is transitional */
 		};
@@ -364,6 +372,12 @@ FOLIO_MATCH(_refcount, _refcount);
 #ifdef CONFIG_MEMCG
 FOLIO_MATCH(memcg_data, memcg_data);
 #endif
+#if defined(WANT_PAGE_VIRTUAL)
+FOLIO_MATCH(virtual, virtual);
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+FOLIO_MATCH(_last_cpupid, _last_cpupid);
+#endif
 #undef FOLIO_MATCH
 #define FOLIO_MATCH(pg, fl)						\
 	static_assert(offsetof(struct folio, fl) ==			\

include/linux/sched.h

@@ -1244,7 +1244,6 @@ struct task_struct {
 	/* Sequence number to catch updates: */
 	seqcount_spinlock_t		mems_allowed_seq;
 	int				cpuset_mem_spread_rotor;
-	int				cpuset_slab_spread_rotor;
 #endif
 #ifdef CONFIG_CGROUPS
 	/* Control Group info protected by css_set_lock: */

init/Kconfig

@@ -1123,9 +1123,23 @@ config CPUSETS
 
 	  Say N if unsure.
 
+config CPUSETS_V1
+	bool "Legacy cgroup v1 cpusets controller"
+	depends on CPUSETS
+	default n
+	help
+	  Legacy cgroup v1 cpusets controller which has been deprecated by
+	  cgroup v2 implementation. The v1 is there for legacy applications
+	  which haven't migrated to the new cgroup v2 interface yet. Legacy
+	  interface includes cpuset filesystem and /proc/<pid>/cpuset. If you
+	  do not have any such application then you are completely fine leaving
+	  this option disabled.
+
+	  Say N if unsure.
+
 config PROC_PID_CPUSET
 	bool "Include legacy /proc/<pid>/cpuset file"
-	depends on CPUSETS
+	depends on CPUSETS_V1
 	default y
 
 config CGROUP_DEVICE

kernel/cgroup/Makefile

@@ -5,5 +5,6 @@ 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_DEBUG) += debug.o

kernel/cgroup/cgroup-v1.c

@@ -46,6 +46,12 @@ bool cgroup1_ssid_disabled(int ssid)
 	return cgroup_no_v1_mask & (1 << ssid);
 }
 
+static bool cgroup1_subsys_absent(struct cgroup_subsys *ss)
+{
+	/* Check also dfl_cftypes for file-less controllers, i.e. perf_event */
+	return ss->legacy_cftypes == NULL && ss->dfl_cftypes;
+}
+
 /**
  * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
  * @from: attach to all cgroups of a given task
@@ -675,11 +681,14 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
 	 * cgroup_mutex contention.
 	 */
 
-	for_each_subsys(ss, i)
+	for_each_subsys(ss, i) {
+		if (cgroup1_subsys_absent(ss))
+			continue;
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->legacy_name, ss->root->hierarchy_id,
 			   atomic_read(&ss->root->nr_cgrps),
 			   cgroup_ssid_enabled(i));
+	}
 
 	return 0;
 }
@@ -932,7 +941,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		if (ret != -ENOPARAM)
 			return ret;
 		for_each_subsys(ss, i) {
-			if (strcmp(param->key, ss->legacy_name))
+			if (strcmp(param->key, ss->legacy_name) ||
+			    cgroup1_subsys_absent(ss))
 				continue;
 			if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i))
 				return invalfc(fc, "Disabled controller '%s'",
@@ -1024,7 +1034,8 @@ static int check_cgroupfs_options(struct fs_context *fc)
 	mask = ~((u16)1 << cpuset_cgrp_id);
 #endif
 	for_each_subsys(ss, i)
-		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
+		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i) &&
+		    !cgroup1_subsys_absent(ss))
 			enabled |= 1 << i;
 
 	ctx->subsys_mask &= enabled;

kernel/cgroup/cgroup.c

@@ -2331,7 +2331,7 @@ static struct file_system_type cgroup2_fs_type = {
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CPUSETS_V1
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
@@ -4124,7 +4124,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	 * If namespaces are delegation boundaries, disallow writes to
 	 * files in an non-init namespace root from inside the namespace
 	 * except for the files explicitly marked delegatable -
-	 * cgroup.procs and cgroup.subtree_control.
+	 * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control.
 	 */
 	if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
 	    !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
@@ -4623,8 +4623,9 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
  *
  * While this function requires cgroup_mutex or RCU read locking, it
  * doesn't require the whole traversal to be contained in a single critical
- * section.  This function will return the correct next descendant as long
- * as both @pos and @root are accessible and @pos is a descendant of @root.
+ * section. Additionally, it isn't necessary to hold onto a reference to @pos.
+ * This function will return the correct next descendant as long as both @pos
+ * and @root are accessible and @pos is a descendant of @root.
  *
  * If a subsystem synchronizes ->css_online() and the start of iteration, a
  * css which finished ->css_online() is guaranteed to be visible in the
@@ -4672,8 +4673,9 @@ EXPORT_SYMBOL_GPL(css_next_descendant_pre);
  *
  * While this function requires cgroup_mutex or RCU read locking, it
  * doesn't require the whole traversal to be contained in a single critical
- * section.  This function will return the correct rightmost descendant as
- * long as @pos is accessible.
+ * section. Additionally, it isn't necessary to hold onto a reference to @pos.
+ * This function will return the correct rightmost descendant as long as @pos
+ * is accessible.
  */
 struct cgroup_subsys_state *
 css_rightmost_descendant(struct cgroup_subsys_state *pos)
@@ -4717,9 +4719,9 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos)
  *
  * While this function requires cgroup_mutex or RCU read locking, it
  * doesn't require the whole traversal to be contained in a single critical
- * section.  This function will return the correct next descendant as long
- * as both @pos and @cgroup are accessible and @pos is a descendant of
- * @cgroup.
+ * section. Additionally, it isn't necessary to hold onto a reference to @pos.
+ * This function will return the correct next descendant as long as both @pos
+ * and @cgroup are accessible and @pos is a descendant of @cgroup.
  *
  * If a subsystem synchronizes ->css_online() and the start of iteration, a
  * css which finished ->css_online() is guaranteed to be visible in the
@@ -5780,7 +5782,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
 {
 	struct cgroup *cgroup;
 	int ret = false;
-	int level = 1;
+	int level = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -5788,7 +5790,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent)
 		if (cgroup->nr_descendants >= cgroup->max_descendants)
 			goto fail;
 
-		if (level > cgroup->max_depth)
+		if (level >= cgroup->max_depth)
 			goto fail;
 
 		level++;
@@ -6242,7 +6244,7 @@ int __init cgroup_init(void)
 	WARN_ON(register_filesystem(&cgroup_fs_type));
 	WARN_ON(register_filesystem(&cgroup2_fs_type));
 	WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show));
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CPUSETS_V1
 	WARN_ON(register_filesystem(&cpuset_fs_type));
 #endif
 

kernel/cgroup/cpuset-internal.h

@@ -0,0 +1,305 @@
+/* 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>
+
+/* 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,
+};
+
+/* bits in struct cpuset flags field */
+typedef enum {
+	CS_ONLINE,
+	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;
+
+	struct fmeter fmeter;		/* memory_pressure filter */
+
+	/*
+	 * Tasks are being attached to this cpuset.  Used to prevent
+	 * zeroing cpus/mems_allowed between ->can_attach() and ->attach().
+	 */
+	int attach_in_progress;
+
+	/* for custom sched domain */
+	int relax_domain_level;
+
+	/* number of valid local child partitions */
+	int nr_subparts;
+
+	/* partition root state */
+	int partition_root_state;
+
+	/*
+	 * 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;
+	u64 sum_migrate_dl_bw;
+
+	/* Invalid partition error code, not lock protected */
+	enum prs_errcode prs_err;
+
+	/* Handle for cpuset.cpus.partition */
+	struct cgroup_file partition_file;
+
+	/* Remote partition silbling list anchored at remote_children */
+	struct list_head remote_sibling;
+
+	/* Used to merge intersecting subsets for generate_sched_domains */
+	struct uf_node node;
+};
+
+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 test_bit(CS_ONLINE, &cs->flags) && !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);
+}
+
+/**
+ * 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);
+
+/*
+ * cpuset-v1.c
+ */
+#ifdef CONFIG_CPUSETS_V1
+extern struct cftype cpuset1_files[];
+void fmeter_init(struct fmeter *fmp);
+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);
+#else
+static inline void fmeter_init(struct fmeter *fmp) {}
+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; }
+#endif /* CONFIG_CPUSETS_V1 */
+
+#endif /* __CPUSET_INTERNAL_H */

kernel/cgroup/cpuset-v1.c

@@ -0,0 +1,603 @@
+// 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 */
+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;
+
+	cpus_read_lock();
+	cpuset_lock();
+	if (!is_cpuset_online(cs))
+		goto out_unlock;
+
+	switch (type) {
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		retval = update_relax_domain_level(cs, val);
+		break;
+	default:
+		retval = -EINVAL;
+		break;
+	}
+out_unlock:
+	cpuset_unlock();
+	cpus_read_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 && cs->css.cgroup->nr_populated_csets &&
+	    css_tryget_online(&cs->css)) {
+		struct cpuset_remove_tasks_struct *s;
+
+		s = kzalloc(sizeof(*s), GFP_KERNEL);
+		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;
+
+	ret = 0;
+out:
+	return ret;
+}
+
+#ifdef CONFIG_PROC_PID_CPUSET
+/*
+ * proc_cpuset_show()
+ *  - Print tasks cpuset path into seq_file.
+ *  - Used for /proc/<pid>/cpuset.
+ */
+int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
+{
+	char *buf;
+	struct cgroup_subsys_state *css;
+	int retval;
+
+	retval = -ENOMEM;
+	buf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	rcu_read_lock();
+	spin_lock_irq(&css_set_lock);
+	css = task_css(tsk, cpuset_cgrp_id);
+	retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
+				       current->nsproxy->cgroup_ns);
+	spin_unlock_irq(&css_set_lock);
+	rcu_read_unlock();
+
+	if (retval == -E2BIG)
+		retval = -ENAMETOOLONG;
+	if (retval < 0)
+		goto out_free;
+	seq_puts(m, buf);
+	seq_putc(m, '\n');
+	retval = 0;
+out_free:
+	kfree(buf);
+out:
+	return retval;
+}
+#endif /* CONFIG_PROC_PID_CPUSET */
+
+static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct cpuset *cs = css_cs(css);
+	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;
+
+	cpus_read_lock();
+	cpuset_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:
+		retval = cpuset_update_flag(CS_MEM_EXCLUSIVE, cs, val);
+		break;
+	case FILE_MEM_HARDWALL:
+		retval = cpuset_update_flag(CS_MEM_HARDWALL, cs, val);
+		break;
+	case FILE_SCHED_LOAD_BALANCE:
+		retval = cpuset_update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
+		break;
+	case FILE_MEMORY_MIGRATE:
+		retval = cpuset_update_flag(CS_MEMORY_MIGRATE, cs, val);
+		break;
+	case FILE_MEMORY_PRESSURE_ENABLED:
+		cpuset_memory_pressure_enabled = !!val;
+		break;
+	case FILE_SPREAD_PAGE:
+		retval = cpuset_update_flag(CS_SPREAD_PAGE, cs, val);
+		break;
+	case FILE_SPREAD_SLAB:
+		retval = cpuset_update_flag(CS_SPREAD_SLAB, cs, val);
+		break;
+	default:
+		retval = -EINVAL;
+		break;
+	}
+out_unlock:
+	cpuset_unlock();
+	cpus_read_unlock();
+	return retval;
+}
+
+/*
+ * 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 */
+};

kernel/cgroup/pids.c

@@ -272,15 +272,10 @@ static void pids_event(struct pids_cgroup *pids_forking,
  */
 static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 {
-	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids, *pids_over_limit;
 	int err;
 
-	if (cset)
-		css = cset->subsys[pids_cgrp_id];
-	else
-		css = task_css_check(current, pids_cgrp_id, true);
-	pids = css_pids(css);
+	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);
@@ -290,14 +285,9 @@ static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 
 static void pids_cancel_fork(struct task_struct *task, struct css_set *cset)
 {
-	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
 
-	if (cset)
-		css = cset->subsys[pids_cgrp_id];
-	else
-		css = task_css_check(current, pids_cgrp_id, true);
-	pids = css_pids(css);
+	pids = css_pids(cset->subsys[pids_cgrp_id]);
 	pids_uncharge(pids, 1);
 }
 

kernel/cgroup/rstat.c

@@ -444,6 +444,7 @@ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
 #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,
@@ -455,6 +456,7 @@ static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
 #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)
@@ -534,8 +536,10 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
 	rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
 
 	switch (index) {
-	case CPUTIME_USER:
 	case CPUTIME_NICE:
+		rstatc->bstat.ntime += delta_exec;
+		fallthrough;
+	case CPUTIME_USER:
 		rstatc->bstat.cputime.utime += delta_exec;
 		break;
 	case CPUTIME_SYSTEM:
@@ -590,6 +594,7 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 #ifdef CONFIG_SCHED_CORE
 		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
 #endif
+		bstat->ntime += cpustat[CPUTIME_NICE];
 	}
 }
 
@@ -607,13 +612,14 @@ static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime;
+	u64 usage, utime, stime, ntime;
 
 	if (cgroup_parent(cgrp)) {
 		cgroup_rstat_flush_hold(cgrp);
 		usage = cgrp->bstat.cputime.sum_exec_runtime;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
 			       &utime, &stime);
+		ntime = cgrp->bstat.ntime;
 		cgroup_rstat_flush_release(cgrp);
 	} else {
 		/* cgrp->bstat of root is not actually used, reuse it */
@@ -621,16 +627,19 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 		usage = cgrp->bstat.cputime.sum_exec_runtime;
 		utime = cgrp->bstat.cputime.utime;
 		stime = cgrp->bstat.cputime.stime;
+		ntime = cgrp->bstat.ntime;
 	}
 
 	do_div(usage, NSEC_PER_USEC);
 	do_div(utime, NSEC_PER_USEC);
 	do_div(stime, NSEC_PER_USEC);
+	do_div(ntime, NSEC_PER_USEC);
 
 	seq_printf(seq, "usage_usec %llu\n"
-		   "user_usec %llu\n"
-		   "system_usec %llu\n",
-		   usage, utime, stime);
+			"user_usec %llu\n"
+			"system_usec %llu\n"
+			"nice_usec %llu\n",
+			usage, utime, stime, ntime);
 
 	cgroup_force_idle_show(seq, &cgrp->bstat);
 }

kernel/fork.c

@@ -2377,7 +2377,6 @@ static __latent_entropy struct task_struct *copy_process(
 #endif
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
-	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
 	seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS

kernel/sched/fair.c

@@ -1535,7 +1535,7 @@ static int numa_hint_fault_latency(struct folio *folio)
 	int last_time, time;
 
 	time = jiffies_to_msecs(jiffies);
-	last_time = xchg_page_access_time(&folio->page, time);
+	last_time = folio_xchg_access_time(folio, time);
 
 	return (time - last_time) & PAGE_ACCESS_TIME_MASK;
 }
@@ -1637,7 +1637,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
 	}
 
 	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
-	last_cpupid = page_cpupid_xchg_last(&folio->page, this_cpupid);
+	last_cpupid = folio_xchg_last_cpupid(folio, this_cpupid);
 
 	if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) &&
 	    !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid))

mm/Makefile

@@ -29,6 +29,7 @@ KCOV_INSTRUMENT_page_alloc.o := n
 KCOV_INSTRUMENT_debug-pagealloc.o := n
 KCOV_INSTRUMENT_kmemleak.o := n
 KCOV_INSTRUMENT_memcontrol.o := n
+KCOV_INSTRUMENT_memcontrol-v1.o := n
 KCOV_INSTRUMENT_mmzone.o := n
 KCOV_INSTRUMENT_vmstat.o := n
 KCOV_INSTRUMENT_failslab.o := n
@@ -96,7 +97,7 @@ obj-$(CONFIG_NUMA) += memory-tiers.o
 obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
 obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
-obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
+obj-$(CONFIG_MEMCG) += memcontrol.o memcontrol-v1.o vmpressure.o
 ifdef CONFIG_SWAP
 obj-$(CONFIG_MEMCG) += swap_cgroup.o
 endif

mm/huge_memory.c

@@ -1560,7 +1560,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	 */
 	if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) ||
 	    node_is_toptier(nid))
-		last_cpupid = page_cpupid_last(&folio->page);
+		last_cpupid = folio_last_cpupid(folio);
 	target_nid = numa_migrate_prep(folio, vma, haddr, nid, &flags);
 	if (target_nid == NUMA_NO_NODE) {
 		folio_put(folio);
@@ -1863,7 +1863,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 	if (is_swap_pmd(*pmd)) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
-		struct page *page = pfn_swap_entry_to_page(entry);
+		struct folio *folio = page_folio(pfn_swap_entry_to_page(entry));
 		pmd_t newpmd;
 
 		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
@@ -1872,7 +1872,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			 * A protection check is difficult so
 			 * just be safe and disable write
 			 */
-			if (PageAnon(page))
+			if (folio_test_anon(folio))
 				entry = make_readable_exclusive_migration_entry(swp_offset(entry));
 			else
 				entry = make_readable_migration_entry(swp_offset(entry));
@@ -1894,7 +1894,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 #endif
 
 	if (prot_numa) {
-		struct page *page;
+		struct folio *folio;
 		bool toptier;
 		/*
 		 * Avoid trapping faults against the zero page. The read-only
@@ -1907,8 +1907,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		if (pmd_protnone(*pmd))
 			goto unlock;
 
-		page = pmd_page(*pmd);
-		toptier = node_is_toptier(page_to_nid(page));
+		folio = page_folio(pmd_page(*pmd));
+		toptier = node_is_toptier(folio_nid(folio));
 		/*
 		 * Skip scanning top tier node if normal numa
 		 * balancing is disabled
@@ -1919,7 +1919,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
 		    !toptier)
-			xchg_page_access_time(page, jiffies_to_msecs(jiffies));
+			folio_xchg_access_time(folio,
+					       jiffies_to_msecs(jiffies));
 	}
 	/*
 	 * In case prot_numa, we are under mmap_read_lock(mm). It's critical
@@ -2526,7 +2527,7 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
 	if (page_is_idle(head))
 		set_page_idle(page_tail);
 
-	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
+	folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio));
 
 	/*
 	 * always add to the tail because some iterators expect new

mm/memcontrol-v1.c

@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/memcontrol.h>
+#include <linux/swap.h>
+#include <linux/mm_inline.h>
+
+#include "memcontrol-v1.h"
+
+/*
+ * Cgroups above their limits are maintained in a RB-Tree, independent of
+ * their hierarchy representation
+ */
+
+struct mem_cgroup_tree_per_node {
+	struct rb_root rb_root;
+	struct rb_node *rb_rightmost;
+	spinlock_t lock;
+};
+
+struct mem_cgroup_tree {
+	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
+};
+
+static struct mem_cgroup_tree soft_limit_tree __read_mostly;
+
+/*
+ * Maximum loops in mem_cgroup_soft_reclaim(), used for soft
+ * limit reclaim to prevent infinite loops, if they ever occur.
+ */
+#define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
+#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2
+
+static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz,
+					 unsigned long new_usage_in_excess)
+{
+	struct rb_node **p = &mctz->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct mem_cgroup_per_node *mz_node;
+	bool rightmost = true;
+
+	if (mz->on_tree)
+		return;
+
+	mz->usage_in_excess = new_usage_in_excess;
+	if (!mz->usage_in_excess)
+		return;
+	while (*p) {
+		parent = *p;
+		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
+					tree_node);
+		if (mz->usage_in_excess < mz_node->usage_in_excess) {
+			p = &(*p)->rb_left;
+			rightmost = false;
+		} else {
+			p = &(*p)->rb_right;
+		}
+	}
+
+	if (rightmost)
+		mctz->rb_rightmost = &mz->tree_node;
+
+	rb_link_node(&mz->tree_node, parent, p);
+	rb_insert_color(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = true;
+}
+
+static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz)
+{
+	if (!mz->on_tree)
+		return;
+
+	if (&mz->tree_node == mctz->rb_rightmost)
+		mctz->rb_rightmost = rb_prev(&mz->tree_node);
+
+	rb_erase(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = false;
+}
+
+static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+				       struct mem_cgroup_tree_per_node *mctz)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&mctz->lock, flags);
+	__mem_cgroup_remove_exceeded(mz, mctz);
+	spin_unlock_irqrestore(&mctz->lock, flags);
+}
+
+static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
+{
+	unsigned long nr_pages = page_counter_read(&memcg->memory);
+	unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
+	unsigned long excess = 0;
+
+	if (nr_pages > soft_limit)
+		excess = nr_pages - soft_limit;
+
+	return excess;
+}
+
+void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
+{
+	unsigned long excess;
+	struct mem_cgroup_per_node *mz;
+	struct mem_cgroup_tree_per_node *mctz;
+
+	if (lru_gen_enabled()) {
+		if (soft_limit_excess(memcg))
+			lru_gen_soft_reclaim(memcg, nid);
+		return;
+	}
+
+	mctz = soft_limit_tree.rb_tree_per_node[nid];
+	if (!mctz)
+		return;
+	/*
+	 * Necessary to update all ancestors when hierarchy is used.
+	 * because their event counter is not touched.
+	 */
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		mz = memcg->nodeinfo[nid];
+		excess = soft_limit_excess(memcg);
+		/*
+		 * We have to update the tree if mz is on RB-tree or
+		 * mem is over its softlimit.
+		 */
+		if (excess || mz->on_tree) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&mctz->lock, flags);
+			/* if on-tree, remove it */
+			if (mz->on_tree)
+				__mem_cgroup_remove_exceeded(mz, mctz);
+			/*
+			 * Insert again. mz->usage_in_excess will be updated.
+			 * If excess is 0, no tree ops.
+			 */
+			__mem_cgroup_insert_exceeded(mz, mctz, excess);
+			spin_unlock_irqrestore(&mctz->lock, flags);
+		}
+	}
+}
+
+void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_tree_per_node *mctz;
+	struct mem_cgroup_per_node *mz;
+	int nid;
+
+	for_each_node(nid) {
+		mz = memcg->nodeinfo[nid];
+		mctz = soft_limit_tree.rb_tree_per_node[nid];
+		if (mctz)
+			mem_cgroup_remove_exceeded(mz, mctz);
+	}
+}
+
+static struct mem_cgroup_per_node *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
+{
+	struct mem_cgroup_per_node *mz;
+
+retry:
+	mz = NULL;
+	if (!mctz->rb_rightmost)
+		goto done;		/* Nothing to reclaim from */
+
+	mz = rb_entry(mctz->rb_rightmost,
+		      struct mem_cgroup_per_node, tree_node);
+	/*
+	 * Remove the node now but someone else can add it back,
+	 * we will to add it back at the end of reclaim to its correct
+	 * position in the tree.
+	 */
+	__mem_cgroup_remove_exceeded(mz, mctz);
+	if (!soft_limit_excess(mz->memcg) ||
+	    !css_tryget(&mz->memcg->css))
+		goto retry;
+done:
+	return mz;
+}
+
+static struct mem_cgroup_per_node *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
+{
+	struct mem_cgroup_per_node *mz;
+
+	spin_lock_irq(&mctz->lock);
+	mz = __mem_cgroup_largest_soft_limit_node(mctz);
+	spin_unlock_irq(&mctz->lock);
+	return mz;
+}
+
+static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
+				   pg_data_t *pgdat,
+				   gfp_t gfp_mask,
+				   unsigned long *total_scanned)
+{
+	struct mem_cgroup *victim = NULL;
+	int total = 0;
+	int loop = 0;
+	unsigned long excess;
+	unsigned long nr_scanned;
+	struct mem_cgroup_reclaim_cookie reclaim = {
+		.pgdat = pgdat,
+	};
+
+	excess = soft_limit_excess(root_memcg);
+
+	while (1) {
+		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
+		if (!victim) {
+			loop++;
+			if (loop >= 2) {
+				/*
+				 * If we have not been able to reclaim
+				 * anything, it might because there are
+				 * no reclaimable pages under this hierarchy
+				 */
+				if (!total)
+					break;
+				/*
+				 * We want to do more targeted reclaim.
+				 * excess >> 2 is not to excessive so as to
+				 * reclaim too much, nor too less that we keep
+				 * coming back to reclaim from this cgroup
+				 */
+				if (total >= (excess >> 2) ||
+					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
+					break;
+			}
+			continue;
+		}
+		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
+					pgdat, &nr_scanned);
+		*total_scanned += nr_scanned;
+		if (!soft_limit_excess(root_memcg))
+			break;
+	}
+	mem_cgroup_iter_break(root_memcg, victim);
+	return total;
+}
+
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					    gfp_t gfp_mask,
+					    unsigned long *total_scanned)
+{
+	unsigned long nr_reclaimed = 0;
+	struct mem_cgroup_per_node *mz, *next_mz = NULL;
+	unsigned long reclaimed;
+	int loop = 0;
+	struct mem_cgroup_tree_per_node *mctz;
+	unsigned long excess;
+
+	if (lru_gen_enabled())
+		return 0;
+
+	if (order > 0)
+		return 0;
+
+	mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id];
+
+	/*
+	 * Do not even bother to check the largest node if the root
+	 * is empty. Do it lockless to prevent lock bouncing. Races
+	 * are acceptable as soft limit is best effort anyway.
+	 */
+	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
+		return 0;
+
+	/*
+	 * This loop can run a while, specially if mem_cgroup's continuously
+	 * keep exceeding their soft limit and putting the system under
+	 * pressure
+	 */
+	do {
+		if (next_mz)
+			mz = next_mz;
+		else
+			mz = mem_cgroup_largest_soft_limit_node(mctz);
+		if (!mz)
+			break;
+
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
+						    gfp_mask, total_scanned);
+		nr_reclaimed += reclaimed;
+		spin_lock_irq(&mctz->lock);
+
+		/*
+		 * If we failed to reclaim anything from this memory cgroup
+		 * it is time to move on to the next cgroup
+		 */
+		next_mz = NULL;
+		if (!reclaimed)
+			next_mz = __mem_cgroup_largest_soft_limit_node(mctz);
+
+		excess = soft_limit_excess(mz->memcg);
+		/*
+		 * One school of thought says that we should not add
+		 * back the node to the tree if reclaim returns 0.
+		 * But our reclaim could return 0, simply because due
+		 * to priority we are exposing a smaller subset of
+		 * memory to reclaim from. Consider this as a longer
+		 * term TODO.
+		 */
+		/* If excess == 0, no tree ops */
+		__mem_cgroup_insert_exceeded(mz, mctz, excess);
+		spin_unlock_irq(&mctz->lock);
+		css_put(&mz->memcg->css);
+		loop++;
+		/*
+		 * Could not reclaim anything and there are no more
+		 * mem cgroups to try or we seem to be looping without
+		 * reclaiming anything.
+		 */
+		if (!nr_reclaimed &&
+			(next_mz == NULL ||
+			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
+			break;
+	} while (!nr_reclaimed);
+	if (next_mz)
+		css_put(&next_mz->memcg->css);
+	return nr_reclaimed;
+}
+
+static int __init memcg1_init(void)
+{
+	int node;
+
+	for_each_node(node) {
+		struct mem_cgroup_tree_per_node *rtpn;
+
+		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, node);
+
+		rtpn->rb_root = RB_ROOT;
+		rtpn->rb_rightmost = NULL;
+		spin_lock_init(&rtpn->lock);
+		soft_limit_tree.rb_tree_per_node[node] = rtpn;
+	}
+
+	return 0;
+}
+subsys_initcall(memcg1_init);

mm/memcontrol-v1.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __MM_MEMCONTROL_V1_H
+#define __MM_MEMCONTROL_V1_H
+
+void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid);
+void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg);
+
+static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg)
+{
+	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
+}
+
+#endif	/* __MM_MEMCONTROL_V1_H */

mm/memcontrol.c

@@ -70,6 +70,7 @@
 #include <net/ip.h>
 #include "slab.h"
 #include "swap.h"
+#include "memcontrol-v1.h"
 #include <linux/zswap.h>
 
 #include <linux/uaccess.h>
@@ -107,23 +108,6 @@ static bool do_memsw_account(void)
 #define THRESHOLDS_EVENTS_TARGET 128
 #define SOFTLIMIT_EVENTS_TARGET 1024
 
-/*
- * Cgroups above their limits are maintained in a RB-Tree, independent of
- * their hierarchy representation
- */
-
-struct mem_cgroup_tree_per_node {
-	struct rb_root rb_root;
-	struct rb_node *rb_rightmost;
-	spinlock_t lock;
-};
-
-struct mem_cgroup_tree {
-	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
-};
-
-static struct mem_cgroup_tree soft_limit_tree __read_mostly;
-
 /* for OOM */
 struct mem_cgroup_eventfd_list {
 	struct list_head list;
@@ -198,13 +182,6 @@ static struct move_charge_struct {
 	.waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq),
 };
 
-/*
- * Maximum loops in mem_cgroup_soft_reclaim(), used for soft
- * limit reclaim to prevent infinite loops, if they ever occur.
- */
-#define	MEM_CGROUP_MAX_RECLAIM_LOOPS		100
-#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	2
-
 /* for encoding cft->private value on file */
 enum res_type {
 	_MEM,
@@ -420,169 +397,6 @@ ino_t page_cgroup_ino(struct page *page)
 	return ino;
 }
 
-static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
-					 struct mem_cgroup_tree_per_node *mctz,
-					 unsigned long new_usage_in_excess)
-{
-	struct rb_node **p = &mctz->rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct mem_cgroup_per_node *mz_node;
-	bool rightmost = true;
-
-	if (mz->on_tree)
-		return;
-
-	mz->usage_in_excess = new_usage_in_excess;
-	if (!mz->usage_in_excess)
-		return;
-	while (*p) {
-		parent = *p;
-		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
-					tree_node);
-		if (mz->usage_in_excess < mz_node->usage_in_excess) {
-			p = &(*p)->rb_left;
-			rightmost = false;
-		} else {
-			p = &(*p)->rb_right;
-		}
-	}
-
-	if (rightmost)
-		mctz->rb_rightmost = &mz->tree_node;
-
-	rb_link_node(&mz->tree_node, parent, p);
-	rb_insert_color(&mz->tree_node, &mctz->rb_root);
-	mz->on_tree = true;
-}
-
-static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
-					 struct mem_cgroup_tree_per_node *mctz)
-{
-	if (!mz->on_tree)
-		return;
-
-	if (&mz->tree_node == mctz->rb_rightmost)
-		mctz->rb_rightmost = rb_prev(&mz->tree_node);
-
-	rb_erase(&mz->tree_node, &mctz->rb_root);
-	mz->on_tree = false;
-}
-
-static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
-				       struct mem_cgroup_tree_per_node *mctz)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&mctz->lock, flags);
-	__mem_cgroup_remove_exceeded(mz, mctz);
-	spin_unlock_irqrestore(&mctz->lock, flags);
-}
-
-static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
-{
-	unsigned long nr_pages = page_counter_read(&memcg->memory);
-	unsigned long soft_limit = READ_ONCE(memcg->soft_limit);
-	unsigned long excess = 0;
-
-	if (nr_pages > soft_limit)
-		excess = nr_pages - soft_limit;
-
-	return excess;
-}
-
-static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
-{
-	unsigned long excess;
-	struct mem_cgroup_per_node *mz;
-	struct mem_cgroup_tree_per_node *mctz;
-
-	if (lru_gen_enabled()) {
-		if (soft_limit_excess(memcg))
-			lru_gen_soft_reclaim(memcg, nid);
-		return;
-	}
-
-	mctz = soft_limit_tree.rb_tree_per_node[nid];
-	if (!mctz)
-		return;
-	/*
-	 * Necessary to update all ancestors when hierarchy is used.
-	 * because their event counter is not touched.
-	 */
-	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		mz = memcg->nodeinfo[nid];
-		excess = soft_limit_excess(memcg);
-		/*
-		 * We have to update the tree if mz is on RB-tree or
-		 * mem is over its softlimit.
-		 */
-		if (excess || mz->on_tree) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&mctz->lock, flags);
-			/* if on-tree, remove it */
-			if (mz->on_tree)
-				__mem_cgroup_remove_exceeded(mz, mctz);
-			/*
-			 * Insert again. mz->usage_in_excess will be updated.
-			 * If excess is 0, no tree ops.
-			 */
-			__mem_cgroup_insert_exceeded(mz, mctz, excess);
-			spin_unlock_irqrestore(&mctz->lock, flags);
-		}
-	}
-}
-
-static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
-{
-	struct mem_cgroup_tree_per_node *mctz;
-	struct mem_cgroup_per_node *mz;
-	int nid;
-
-	for_each_node(nid) {
-		mz = memcg->nodeinfo[nid];
-		mctz = soft_limit_tree.rb_tree_per_node[nid];
-		if (mctz)
-			mem_cgroup_remove_exceeded(mz, mctz);
-	}
-}
-
-static struct mem_cgroup_per_node *
-__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
-{
-	struct mem_cgroup_per_node *mz;
-
-retry:
-	mz = NULL;
-	if (!mctz->rb_rightmost)
-		goto done;		/* Nothing to reclaim from */
-
-	mz = rb_entry(mctz->rb_rightmost,
-		      struct mem_cgroup_per_node, tree_node);
-	/*
-	 * Remove the node now but someone else can add it back,
-	 * we will to add it back at the end of reclaim to its correct
-	 * position in the tree.
-	 */
-	__mem_cgroup_remove_exceeded(mz, mctz);
-	if (!soft_limit_excess(mz->memcg) ||
-	    !css_tryget(&mz->memcg->css))
-		goto retry;
-done:
-	return mz;
-}
-
-static struct mem_cgroup_per_node *
-mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
-{
-	struct mem_cgroup_per_node *mz;
-
-	spin_lock_irq(&mctz->lock);
-	mz = __mem_cgroup_largest_soft_limit_node(mctz);
-	spin_unlock_irq(&mctz->lock);
-	return mz;
-}
-
 /*
  * memcg and lruvec stats flushing
  *
@@ -1846,56 +1660,6 @@ unlock:
 	return ret;
 }
 
-static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
-				   pg_data_t *pgdat,
-				   gfp_t gfp_mask,
-				   unsigned long *total_scanned)
-{
-	struct mem_cgroup *victim = NULL;
-	int total = 0;
-	int loop = 0;
-	unsigned long excess;
-	unsigned long nr_scanned;
-	struct mem_cgroup_reclaim_cookie reclaim = {
-		.pgdat = pgdat,
-	};
-
-	excess = soft_limit_excess(root_memcg);
-
-	while (1) {
-		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
-		if (!victim) {
-			loop++;
-			if (loop >= 2) {
-				/*
-				 * If we have not been able to reclaim
-				 * anything, it might because there are
-				 * no reclaimable pages under this hierarchy
-				 */
-				if (!total)
-					break;
-				/*
-				 * We want to do more targeted reclaim.
-				 * excess >> 2 is not to excessive so as to
-				 * reclaim too much, nor too less that we keep
-				 * coming back to reclaim from this cgroup
-				 */
-				if (total >= (excess >> 2) ||
-					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS))
-					break;
-			}
-			continue;
-		}
-		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
-					pgdat, &nr_scanned);
-		*total_scanned += nr_scanned;
-		if (!soft_limit_excess(root_memcg))
-			break;
-	}
-	mem_cgroup_iter_break(root_memcg, victim);
-	return total;
-}
-
 #ifdef CONFIG_LOCKDEP
 static struct lockdep_map memcg_oom_lock_dep_map = {
 	.name = "memcg_oom_lock",
@@ -3744,88 +3508,6 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
 	return ret;
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-					    gfp_t gfp_mask,
-					    unsigned long *total_scanned)
-{
-	unsigned long nr_reclaimed = 0;
-	struct mem_cgroup_per_node *mz, *next_mz = NULL;
-	unsigned long reclaimed;
-	int loop = 0;
-	struct mem_cgroup_tree_per_node *mctz;
-	unsigned long excess;
-
-	if (lru_gen_enabled())
-		return 0;
-
-	if (order > 0)
-		return 0;
-
-	mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id];
-
-	/*
-	 * Do not even bother to check the largest node if the root
-	 * is empty. Do it lockless to prevent lock bouncing. Races
-	 * are acceptable as soft limit is best effort anyway.
-	 */
-	if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
-		return 0;
-
-	/*
-	 * This loop can run a while, specially if mem_cgroup's continuously
-	 * keep exceeding their soft limit and putting the system under
-	 * pressure
-	 */
-	do {
-		if (next_mz)
-			mz = next_mz;
-		else
-			mz = mem_cgroup_largest_soft_limit_node(mctz);
-		if (!mz)
-			break;
-
-		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
-						    gfp_mask, total_scanned);
-		nr_reclaimed += reclaimed;
-		spin_lock_irq(&mctz->lock);
-
-		/*
-		 * If we failed to reclaim anything from this memory cgroup
-		 * it is time to move on to the next cgroup
-		 */
-		next_mz = NULL;
-		if (!reclaimed)
-			next_mz = __mem_cgroup_largest_soft_limit_node(mctz);
-
-		excess = soft_limit_excess(mz->memcg);
-		/*
-		 * One school of thought says that we should not add
-		 * back the node to the tree if reclaim returns 0.
-		 * But our reclaim could return 0, simply because due
-		 * to priority we are exposing a smaller subset of
-		 * memory to reclaim from. Consider this as a longer
-		 * term TODO.
-		 */
-		/* If excess == 0, no tree ops */
-		__mem_cgroup_insert_exceeded(mz, mctz, excess);
-		spin_unlock_irq(&mctz->lock);
-		css_put(&mz->memcg->css);
-		loop++;
-		/*
-		 * Could not reclaim anything and there are no more
-		 * mem cgroups to try or we seem to be looping without
-		 * reclaiming anything.
-		 */
-		if (!nr_reclaimed &&
-			(next_mz == NULL ||
-			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
-			break;
-	} while (!nr_reclaimed);
-	if (next_mz)
-		css_put(&next_mz->memcg->css);
-	return nr_reclaimed;
-}
-
 /*
  * Reclaims as many pages from the given memcg as possible.
  *
@@ -5668,7 +5350,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 		return ERR_CAST(memcg);
 
 	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
-	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
+	memcg1_soft_limit_reset(memcg);
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	memcg->zswap_max = PAGE_COUNTER_MAX;
 	WRITE_ONCE(memcg->zswap_writeback, true);
@@ -5841,7 +5523,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
 	page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX);
-	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
+	memcg1_soft_limit_reset(memcg);
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	memcg_wb_domain_size_changed(memcg);
 }
@@ -7810,7 +7492,7 @@ __setup("cgroup.memory=", cgroup_memory);
  */
 static int __init mem_cgroup_init(void)
 {
-	int cpu, node;
+	int cpu;
 
 	/*
 	 * Currently s32 type (can refer to struct batched_lruvec_stat) is
@@ -7827,17 +7509,6 @@ static int __init mem_cgroup_init(void)
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
 			  drain_local_stock);
 
-	for_each_node(node) {
-		struct mem_cgroup_tree_per_node *rtpn;
-
-		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, node);
-
-		rtpn->rb_root = RB_ROOT;
-		rtpn->rb_rightmost = NULL;
-		spin_lock_init(&rtpn->lock);
-		soft_limit_tree.rb_tree_per_node[node] = rtpn;
-	}
-
 	return 0;
 }
 subsys_initcall(mem_cgroup_init);

mm/memory.c

@@ -3036,23 +3036,24 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf)
  * case, all we need to do here is to mark the page as writable and update
  * any related book-keeping.
  */
-static inline void wp_page_reuse(struct vm_fault *vmf)
+static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio)
 	__releases(vmf->ptl)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = vmf->page;
 	pte_t entry;
 
 	VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE));
-	VM_BUG_ON(page && PageAnon(page) && !PageAnonExclusive(page));
 
-	/*
-	 * Clear the pages cpupid information as the existing
-	 * information potentially belongs to a now completely
-	 * unrelated process.
-	 */
-	if (page)
-		page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1);
+	if (folio) {
+		VM_BUG_ON(folio_test_anon(folio) &&
+			  !PageAnonExclusive(vmf->page));
+		/*
+		 * Clear the folio's cpupid information as the existing
+		 * information potentially belongs to a now completely
+		 * unrelated process.
+		 */
+		folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1);
+	}
 
 	flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 	entry = pte_mkyoung(vmf->orig_pte);
@@ -3245,6 +3246,7 @@ oom:
  *			  writeable once the page is prepared
  *
  * @vmf: structure describing the fault
+ * @folio: the folio of vmf->page
  *
  * This function handles all that is needed to finish a write page fault in a
  * shared mapping due to PTE being read-only once the mapped page is prepared.
@@ -3256,7 +3258,7 @@ oom:
  * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before
  * we acquired PTE lock.
  */
-vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
+static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio)
 {
 	WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
 	vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address,
@@ -3272,7 +3274,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return VM_FAULT_NOPAGE;
 	}
-	wp_page_reuse(vmf);
+	wp_page_reuse(vmf, folio);
 	return 0;
 }
 
@@ -3297,9 +3299,9 @@ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf)
 		ret = vma->vm_ops->pfn_mkwrite(vmf);
 		if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
 			return ret;
-		return finish_mkwrite_fault(vmf);
+		return finish_mkwrite_fault(vmf, NULL);
 	}
-	wp_page_reuse(vmf);
+	wp_page_reuse(vmf, NULL);
 	return 0;
 }
 
@@ -3327,14 +3329,14 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio)
 			folio_put(folio);
 			return tmp;
 		}
-		tmp = finish_mkwrite_fault(vmf);
+		tmp = finish_mkwrite_fault(vmf, folio);
 		if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
 			folio_unlock(folio);
 			folio_put(folio);
 			return tmp;
 		}
 	} else {
-		wp_page_reuse(vmf);
+		wp_page_reuse(vmf, folio);
 		folio_lock(folio);
 	}
 	ret |= fault_dirty_shared_page(vmf);
@@ -3458,7 +3460,7 @@ reuse:
 			pte_unmap_unlock(vmf->pte, vmf->ptl);
 			return 0;
 		}
-		wp_page_reuse(vmf);
+		wp_page_reuse(vmf, folio);
 		return 0;
 	}
 copy:
@@ -4866,7 +4868,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	    !node_is_toptier(nid))
 		last_cpupid = (-1 & LAST_CPUPID_MASK);
 	else
-		last_cpupid = page_cpupid_last(&folio->page);
+		last_cpupid = folio_last_cpupid(folio);
 	target_nid = numa_migrate_prep(folio, vma, vmf->address, nid, &flags);
 	if (target_nid == NUMA_NO_NODE) {
 		folio_put(folio);

mm/migrate.c

@@ -606,20 +606,20 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
 	 * Copy NUMA information to the new page, to prevent over-eager
 	 * future migrations of this same page.
 	 */
-	cpupid = page_cpupid_xchg_last(&folio->page, -1);
+	cpupid = folio_xchg_last_cpupid(folio, -1);
 	/*
 	 * For memory tiering mode, when migrate between slow and fast
 	 * memory node, reset cpupid, because that is used to record
 	 * page access time in slow memory node.
 	 */
 	if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) {
-		bool f_toptier = node_is_toptier(page_to_nid(&folio->page));
-		bool t_toptier = node_is_toptier(page_to_nid(&newfolio->page));
+		bool f_toptier = node_is_toptier(folio_nid(folio));
+		bool t_toptier = node_is_toptier(folio_nid(newfolio));
 
 		if (f_toptier != t_toptier)
 			cpupid = -1;
 	}
-	page_cpupid_xchg_last(&newfolio->page, cpupid);
+	folio_xchg_last_cpupid(newfolio, cpupid);
 
 	folio_migrate_ksm(newfolio, folio);
 	/*

mm/mmzone.c

@@ -94,19 +94,19 @@ void lruvec_init(struct lruvec *lruvec)
 }
 
 #if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
-int page_cpupid_xchg_last(struct page *page, int cpupid)
+int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
 {
 	unsigned long old_flags, flags;
 	int last_cpupid;
 
-	old_flags = READ_ONCE(page->flags);
+	old_flags = READ_ONCE(folio->flags);
 	do {
 		flags = old_flags;
 		last_cpupid = (flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
 
 		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
 		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
-	} while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags)));
+	} while (unlikely(!try_cmpxchg(&folio->flags, &old_flags, flags)));
 
 	return last_cpupid;
 }

mm/mprotect.c

@@ -114,7 +114,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 			 * pages. See similar comment in change_huge_pmd.
 			 */
 			if (prot_numa) {
-				struct page *page;
+				struct folio *folio;
 				int nid;
 				bool toptier;
 
@@ -122,13 +122,14 @@ static long change_pte_range(struct mmu_gather *tlb,
 				if (pte_protnone(oldpte))
 					continue;
 
-				page = vm_normal_page(vma, addr, oldpte);
-				if (!page || is_zone_device_page(page) || PageKsm(page))
+				folio = vm_normal_folio(vma, addr, oldpte);
+				if (!folio || folio_is_zone_device(folio) ||
+				    folio_test_ksm(folio))
 					continue;
 
 				/* Also skip shared copy-on-write pages */
 				if (is_cow_mapping(vma->vm_flags) &&
-				    page_count(page) != 1)
+				    folio_ref_count(folio) != 1)
 					continue;
 
 				/*
@@ -136,14 +137,15 @@ static long change_pte_range(struct mmu_gather *tlb,
 				 * it cannot move them all from MIGRATE_ASYNC
 				 * context.
 				 */
-				if (page_is_file_lru(page) && PageDirty(page))
+				if (folio_is_file_lru(folio) &&
+				    folio_test_dirty(folio))
 					continue;
 
 				/*
 				 * Don't mess with PTEs if page is already on the node
 				 * a single-threaded process is running on.
 				 */
-				nid = page_to_nid(page);
+				nid = folio_nid(folio);
 				if (target_node == nid)
 					continue;
 				toptier = node_is_toptier(nid);
@@ -157,7 +159,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 					continue;
 				if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
 				    !toptier)
-					xchg_page_access_time(page,
+					folio_xchg_access_time(folio,
 						jiffies_to_msecs(jiffies));
 			}
 

redhat/configs/rhel/generic/CONFIG_CPUSETS_V1

@@ -0,0 +1 @@
+CONFIG_CPUSETS_V1=y

tools/testing/selftests/cgroup/test_cpu.c

@@ -8,6 +8,7 @@
 #include <pthread.h>
 #include <stdio.h>
 #include <time.h>
+#include <unistd.h>
 
 #include "../kselftest.h"
 #include "cgroup_util.h"
@@ -229,6 +230,79 @@ cleanup:
 	return ret;
 }
 
+/*
+ * Creates a nice process that consumes CPU and checks that the elapsed
+ * usertime in the cgroup is close to the expected time.
+ */
+static int test_cpucg_nice(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int status;
+	long user_usec, nice_usec;
+	long usage_seconds = 2;
+	long expected_nice_usec = usage_seconds * USEC_PER_SEC;
+	char *cpucg;
+	pid_t pid;
+
+	cpucg = cg_name(root, "cpucg_test");
+	if (!cpucg)
+		goto cleanup;
+
+	if (cg_create(cpucg))
+		goto cleanup;
+
+	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+	nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+	if (nice_usec == -1)
+		ret = KSFT_SKIP;
+	if (user_usec != 0 || nice_usec != 0)
+		goto cleanup;
+
+	/*
+	 * We fork here to create a new process that can be niced without
+	 * polluting the nice value of other selftests
+	 */
+	pid = fork();
+	if (pid < 0) {
+		goto cleanup;
+	} else if (pid == 0) {
+		struct cpu_hog_func_param param = {
+			.nprocs = 1,
+			.ts = {
+				.tv_sec = usage_seconds,
+				.tv_nsec = 0,
+			},
+			.clock_type = CPU_HOG_CLOCK_PROCESS,
+		};
+		char buf[64];
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cpucg, "cgroup.procs", buf))
+			goto cleanup;
+
+		/* Try to keep niced CPU usage as constrained to hog_cpu as possible */
+		nice(1);
+		hog_cpus_timed(cpucg, &param);
+		exit(0);
+	} else {
+		waitpid(pid, &status, 0);
+		if (!WIFEXITED(status))
+			goto cleanup;
+
+		user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+		nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+		if (!values_close(nice_usec, expected_nice_usec, 1))
+			goto cleanup;
+
+		ret = KSFT_PASS;
+	}
+
+cleanup:
+	cg_destroy(cpucg);
+	free(cpucg);
+
+	return ret;
+}
+
 static int
 run_cpucg_weight_test(
 		const char *root,
@@ -686,6 +760,7 @@ struct cpucg_test {
 } tests[] = {
 	T(test_cpucg_subtree_control),
 	T(test_cpucg_stats),
+	T(test_cpucg_nice),
 	T(test_cpucg_weight_overprovisioned),
 	T(test_cpucg_weight_underprovisioned),
 	T(test_cpucg_nested_weight_overprovisioned),

tools/testing/selftests/cgroup/test_cpuset_v1_base.sh

@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Basc test for cpuset v1 interfaces write/read
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+write_test() {
+	dir=$1
+	interface=$2
+	value=$3
+	original=$(cat $dir/$interface)
+	echo "testing $interface $value"
+	echo $value > $dir/$interface
+	new=$(cat $dir/$interface)
+	[[ $value -ne $(cat $dir/$interface) ]] && {
+		echo "$interface write $value failed: new:$new"
+		exit 1
+	}
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, read write test
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+
+ITF_MATRIX=(
+	#interface			value		expect 	root_only
+	'cpuset.cpus			0-1		0-1	0'
+	'cpuset.mem_exclusive		1		1	0'
+	'cpuset.mem_exclusive		0		0	0'
+	'cpuset.mem_hardwall		1		1	0'
+	'cpuset.mem_hardwall		0		0	0'
+	'cpuset.memory_migrate		1		1	0'
+	'cpuset.memory_migrate		0		0	0'
+	'cpuset.memory_spread_page	1		1	0'
+	'cpuset.memory_spread_page	0		0	0'
+	'cpuset.memory_spread_slab	1		1	0'
+	'cpuset.memory_spread_slab	0		0	0'
+	'cpuset.mems			0		0	0'
+	'cpuset.sched_load_balance	1		1	0'
+	'cpuset.sched_load_balance	0		0	0'
+	'cpuset.sched_relax_domain_level	2	2	0'
+	'cpuset.memory_pressure_enabled	1		1	1'
+	'cpuset.memory_pressure_enabled	0		0	1'
+)
+
+run_test()
+{
+	cnt="${ITF_MATRIX[@]}"
+	for i in "${ITF_MATRIX[@]}" ; do
+		args=($i)
+		root_only=${args[3]}
+		[[ $root_only -eq 1 ]] && {
+			write_test "$CPUSET" "${args[0]}" "${args[1]}" "${args[2]}"
+			continue
+		}
+		write_test "$CPUSET/$TDIR" "${args[0]}" "${args[1]}" "${args[2]}"
+	done
+}
+
+run_test
+rmdir $CPUSET/$TDIR
+echo "Test PASSED"
+exit 0

tools/testing/selftests/cgroup/test_zswap.c

@@ -50,9 +50,35 @@ static int get_zswap_stored_pages(size_t *value)
 	return read_int("/sys/kernel/debug/zswap/stored_pages", value);
 }
 
-static int get_zswap_written_back_pages(size_t *value)
+static long get_cg_wb_count(const char *cg)
 {
-	return read_int("/sys/kernel/debug/zswap/written_back_pages", value);
+	return cg_read_key_long(cg, "memory.stat", "zswpwb");
+}
+
+static long get_zswpout(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "memory.stat", "zswpout ");
+}
+
+static int allocate_and_read_bytes(const char *cgroup, void *arg)
+{
+	size_t size = (size_t)arg;
+	char *mem = (char *)malloc(size);
+	int ret = 0;
+
+	if (!mem)
+		return -1;
+	for (int i = 0; i < size; i += 4095)
+		mem[i] = 'a';
+
+	/* Go through the allocated memory to (z)swap in and out pages */
+	for (int i = 0; i < size; i += 4095) {
+		if (mem[i] != 'a')
+			ret = -1;
+	}
+
+	free(mem);
+	return ret;
 }
 
 static int allocate_bytes(const char *cgroup, void *arg)
@@ -68,21 +94,33 @@ static int allocate_bytes(const char *cgroup, void *arg)
 	return 0;
 }
 
-/*
- * When trying to store a memcg page in zswap, if the memcg hits its memory
- * limit in zswap, writeback should not be triggered.
- *
- * This was fixed with commit 0bdf0efa180a("zswap: do not shrink if cgroup may
- * not zswap"). Needs to be revised when a per memcg writeback mechanism is
- * implemented.
- */
-static int test_no_invasive_cgroup_shrink(const char *root)
+static char *setup_test_group_1M(const char *root, const char *name)
 {
-	size_t written_back_before, written_back_after;
+	char *group_name = cg_name(root, name);
+
+	if (!group_name)
+		return NULL;
+	if (cg_create(group_name))
+		goto fail;
+	if (cg_write(group_name, "memory.max", "1M")) {
+		cg_destroy(group_name);
+		goto fail;
+	}
+	return group_name;
+fail:
+	free(group_name);
+	return NULL;
+}
+
+/*
+ * Sanity test to check that pages are written into zswap.
+ */
+static int test_zswap_usage(const char *root)
+{
+	long zswpout_before, zswpout_after;
 	int ret = KSFT_FAIL;
 	char *test_group;
 
-	/* Set up */
 	test_group = cg_name(root, "no_shrink_test");
 	if (!test_group)
 		goto out;
@@ -90,26 +128,334 @@ static int test_no_invasive_cgroup_shrink(const char *root)
 		goto out;
 	if (cg_write(test_group, "memory.max", "1M"))
 		goto out;
-	if (cg_write(test_group, "memory.zswap.max", "10K"))
+
+	zswpout_before = get_zswpout(test_group);
+	if (zswpout_before < 0) {
+		ksft_print_msg("Failed to get zswpout\n");
 		goto out;
-	if (get_zswap_written_back_pages(&written_back_before))
+	}
+
+	/* Allocate more than memory.max to push memory into zswap */
+	if (cg_run(test_group, allocate_bytes, (void *)MB(4)))
 		goto out;
 
-	/* Allocate 10x memory.max to push memory into zswap */
-	if (cg_run(test_group, allocate_bytes, (void *)MB(10)))
+	/* Verify that pages come into zswap */
+	zswpout_after = get_zswpout(test_group);
+	if (zswpout_after <= zswpout_before) {
+		ksft_print_msg("zswpout does not increase after test program\n");
 		goto out;
+	}
+	ret = KSFT_PASS;
 
-	/* Verify that no writeback happened because of the memcg allocation */
-	if (get_zswap_written_back_pages(&written_back_after))
-		goto out;
-	if (written_back_after == written_back_before)
-		ret = KSFT_PASS;
 out:
 	cg_destroy(test_group);
 	free(test_group);
 	return ret;
 }
 
+/*
+ * Check that when memory.zswap.max = 0, no pages can go to the zswap pool for
+ * the cgroup.
+ */
+static int test_swapin_nozswap(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+	long swap_peak, zswpout;
+
+	test_group = cg_name(root, "no_zswap_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "8M"))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.max", "0"))
+		goto out;
+
+	/* Allocate and read more than memory.max to trigger swapin */
+	if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32)))
+		goto out;
+
+	/* Verify that pages are swapped out, but no zswap happened */
+	swap_peak = cg_read_long(test_group, "memory.swap.peak");
+	if (swap_peak < 0) {
+		ksft_print_msg("failed to get cgroup's swap_peak\n");
+		goto out;
+	}
+
+	if (swap_peak < MB(24)) {
+		ksft_print_msg("at least 24MB of memory should be swapped out\n");
+		goto out;
+	}
+
+	zswpout = get_zswpout(test_group);
+	if (zswpout < 0) {
+		ksft_print_msg("failed to get zswpout\n");
+		goto out;
+	}
+
+	if (zswpout > 0) {
+		ksft_print_msg("zswapout > 0 when memory.zswap.max = 0\n");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/* Simple test to verify the (z)swapin code paths */
+static int test_zswapin(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+	long zswpin;
+
+	test_group = cg_name(root, "zswapin_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "8M"))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.max", "max"))
+		goto out;
+
+	/* Allocate and read more than memory.max to trigger (z)swap in */
+	if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32)))
+		goto out;
+
+	zswpin = cg_read_key_long(test_group, "memory.stat", "zswpin ");
+	if (zswpin < 0) {
+		ksft_print_msg("failed to get zswpin\n");
+		goto out;
+	}
+
+	if (zswpin < MB(24) / PAGE_SIZE) {
+		ksft_print_msg("at least 24MB should be brought back from zswap\n");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/*
+ * Attempt writeback with the following steps:
+ * 1. Allocate memory.
+ * 2. Reclaim memory equal to the amount that was allocated in step 1.
+      This will move it into zswap.
+ * 3. Save current zswap usage.
+ * 4. Move the memory allocated in step 1 back in from zswap.
+ * 5. Set zswap.max to half the amount that was recorded in step 3.
+ * 6. Attempt to reclaim memory equal to the amount that was allocated,
+      this will either trigger writeback if it's enabled, or reclamation
+      will fail if writeback is disabled as there isn't enough zswap space.
+ */
+static int attempt_writeback(const char *cgroup, void *arg)
+{
+	long pagesize = sysconf(_SC_PAGESIZE);
+	size_t memsize = MB(4);
+	char buf[pagesize];
+	long zswap_usage;
+	bool wb_enabled = *(bool *) arg;
+	int ret = -1;
+	char *mem;
+
+	mem = (char *)malloc(memsize);
+	if (!mem)
+		return ret;
+
+	/*
+	 * Fill half of each page with increasing data, and keep other
+	 * half empty, this will result in data that is still compressible
+	 * and ends up in zswap, with material zswap usage.
+	 */
+	for (int i = 0; i < pagesize; i++)
+		buf[i] = i < pagesize/2 ? (char) i : 0;
+
+	for (int i = 0; i < memsize; i += pagesize)
+		memcpy(&mem[i], buf, pagesize);
+
+	/* Try and reclaim allocated memory */
+	if (cg_write_numeric(cgroup, "memory.reclaim", memsize)) {
+		ksft_print_msg("Failed to reclaim all of the requested memory\n");
+		goto out;
+	}
+
+	zswap_usage = cg_read_long(cgroup, "memory.zswap.current");
+
+	/* zswpin */
+	for (int i = 0; i < memsize; i += pagesize) {
+		if (memcmp(&mem[i], buf, pagesize)) {
+			ksft_print_msg("invalid memory\n");
+			goto out;
+		}
+	}
+
+	if (cg_write_numeric(cgroup, "memory.zswap.max", zswap_usage/2))
+		goto out;
+
+	/*
+	 * If writeback is enabled, trying to reclaim memory now will trigger a
+	 * writeback as zswap.max is half of what was needed when reclaim ran the first time.
+	 * If writeback is disabled, memory reclaim will fail as zswap is limited and
+	 * it can't writeback to swap.
+	 */
+	ret = cg_write_numeric(cgroup, "memory.reclaim", memsize);
+	if (!wb_enabled)
+		ret = (ret == -EAGAIN) ? 0 : -1;
+
+out:
+	free(mem);
+	return ret;
+}
+
+static int test_zswap_writeback_one(const char *cgroup, bool wb)
+{
+	long zswpwb_before, zswpwb_after;
+
+	zswpwb_before = get_cg_wb_count(cgroup);
+	if (zswpwb_before != 0) {
+		ksft_print_msg("zswpwb_before = %ld instead of 0\n", zswpwb_before);
+		return -1;
+	}
+
+	if (cg_run(cgroup, attempt_writeback, (void *) &wb))
+		return -1;
+
+	/* Verify that zswap writeback occurred only if writeback was enabled */
+	zswpwb_after = get_cg_wb_count(cgroup);
+	if (zswpwb_after < 0)
+		return -1;
+
+	if (wb != !!zswpwb_after) {
+		ksft_print_msg("zswpwb_after is %ld while wb is %s",
+				zswpwb_after, wb ? "enabled" : "disabled");
+		return -1;
+	}
+
+	return 0;
+}
+
+/* Test to verify the zswap writeback path */
+static int test_zswap_writeback(const char *root, bool wb)
+{
+	int ret = KSFT_FAIL;
+	char *test_group, *test_group_child = NULL;
+
+	if (cg_read_strcmp(root, "memory.zswap.writeback", "1"))
+		return KSFT_SKIP;
+
+	test_group = cg_name(root, "zswap_writeback_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.writeback", wb ? "1" : "0"))
+		goto out;
+
+	if (test_zswap_writeback_one(test_group, wb))
+		goto out;
+
+	/* Reset memory.zswap.max to max (modified by attempt_writeback), and
+	 * set up child cgroup, whose memory.zswap.writeback is hardcoded to 1.
+	 * Thus, the parent's setting shall be what's in effect. */
+	if (cg_write(test_group, "memory.zswap.max", "max"))
+		goto out;
+	if (cg_write(test_group, "cgroup.subtree_control", "+memory"))
+		goto out;
+
+	test_group_child = cg_name(test_group, "zswap_writeback_test_child");
+	if (!test_group_child)
+		goto out;
+	if (cg_create(test_group_child))
+		goto out;
+	if (cg_write(test_group_child, "memory.zswap.writeback", "1"))
+		goto out;
+
+	if (test_zswap_writeback_one(test_group_child, wb))
+		goto out;
+
+	ret = KSFT_PASS;
+
+out:
+	if (test_group_child) {
+		cg_destroy(test_group_child);
+		free(test_group_child);
+	}
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+static int test_zswap_writeback_enabled(const char *root)
+{
+	return test_zswap_writeback(root, true);
+}
+
+static int test_zswap_writeback_disabled(const char *root)
+{
+	return test_zswap_writeback(root, false);
+}
+
+/*
+ * When trying to store a memcg page in zswap, if the memcg hits its memory
+ * limit in zswap, writeback should affect only the zswapped pages of that
+ * memcg.
+ */
+static int test_no_invasive_cgroup_shrink(const char *root)
+{
+	int ret = KSFT_FAIL;
+	size_t control_allocation_size = MB(10);
+	char *control_allocation, *wb_group = NULL, *control_group = NULL;
+
+	wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
+	if (!wb_group)
+		return KSFT_FAIL;
+	if (cg_write(wb_group, "memory.zswap.max", "10K"))
+		goto out;
+	control_group = setup_test_group_1M(root, "per_memcg_wb_test2");
+	if (!control_group)
+		goto out;
+
+	/* Push some test_group2 memory into zswap */
+	if (cg_enter_current(control_group))
+		goto out;
+	control_allocation = malloc(control_allocation_size);
+	for (int i = 0; i < control_allocation_size; i += 4095)
+		control_allocation[i] = 'a';
+	if (cg_read_key_long(control_group, "memory.stat", "zswapped") < 1)
+		goto out;
+
+	/* Allocate 10x memory.max to push wb_group memory into zswap and trigger wb */
+	if (cg_run(wb_group, allocate_bytes, (void *)MB(10)))
+		goto out;
+
+	/* Verify that only zswapped memory from gwb_group has been written back */
+	if (get_cg_wb_count(wb_group) > 0 && get_cg_wb_count(control_group) == 0)
+		ret = KSFT_PASS;
+out:
+	cg_enter_current(root);
+	if (control_group) {
+		cg_destroy(control_group);
+		free(control_group);
+	}
+	cg_destroy(wb_group);
+	free(wb_group);
+	if (control_allocation)
+		free(control_allocation);
+	return ret;
+}
+
 struct no_kmem_bypass_child_args {
 	size_t target_alloc_bytes;
 	size_t child_allocated;
@@ -177,8 +523,6 @@ static int test_no_kmem_bypass(const char *root)
 	trigger_allocation_size = sys_info.totalram / 20;
 
 	/* Set up test memcg */
-	if (cg_write(root, "cgroup.subtree_control", "+memory"))
-		goto out;
 	test_group = cg_name(root, "kmem_bypass_test");
 	if (!test_group)
 		goto out;
@@ -235,6 +579,11 @@ struct zswap_test {
 	int (*fn)(const char *root);
 	const char *name;
 } tests[] = {
+	T(test_zswap_usage),
+	T(test_swapin_nozswap),
+	T(test_zswapin),
+	T(test_zswap_writeback_enabled),
+	T(test_zswap_writeback_disabled),
 	T(test_no_kmem_bypass),
 	T(test_no_invasive_cgroup_shrink),
 };