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>

Author: jstancek

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

@@ -99,21 +99,24 @@ 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)		\
 			__cpuset_memory_pressure_bump();	\
 	} 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);
 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
 
 /*
@@ -1783,38 +1782,39 @@ 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)
 {
 	page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT;
 }
 #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;