Merge tag 'cgroup-for-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - cpuset now support isolated cpus.partition type, which will enable
   dynamic CPU isolation

 - pids.peak added to remember the max number of pids used

 - holes in cgroup namespace plugged

 - internal cleanups

* tag 'cgroup-for-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (25 commits)
  cgroup: use strscpy() is more robust and safer
  iocost_monitor: reorder BlkgIterator
  cgroup: simplify code in cgroup_apply_control
  cgroup: Make cgroup_get_from_id() prettier
  cgroup/cpuset: remove unreachable code
  cgroup: Remove CFTYPE_PRESSURE
  cgroup: Improve cftype add/rm error handling
  kselftest/cgroup: Add cpuset v2 partition root state test
  cgroup/cpuset: Update description of cpuset.cpus.partition in cgroup-v2.rst
  cgroup/cpuset: Make partition invalid if cpumask change violates exclusivity rule
  cgroup/cpuset: Relocate a code block in validate_change()
  cgroup/cpuset: Show invalid partition reason string
  cgroup/cpuset: Add a new isolated cpus.partition type
  cgroup/cpuset: Relax constraints to partition & cpus changes
  cgroup/cpuset: Allow no-task partition to have empty cpuset.cpus.effective
  cgroup/cpuset: Miscellaneous cleanups & add helper functions
  cgroup/cpuset: Enable update_tasks_cpumask() on top_cpuset
  cgroup: add pids.peak interface for pids controller
  cgroup: Remove data-race around cgrp_dfl_visible
  cgroup: Fix build failure when CONFIG_SHRINKER_DEBUG
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -2190,75 +2190,93 @@ Cpuset Interface Files
 
 	It accepts only the following input values when written to.
 
-	  ========	================================
-	  "root"	a partition root
-	  "member"	a non-root member of a partition
-	  ========	================================
-
-	When set to be a partition root, the current cgroup is the
-	root of a new partition or scheduling domain that comprises
-	itself and all its descendants except those that are separate
-	partition roots themselves and their descendants.  The root
-	cgroup is always a partition root.
-
-	There are constraints on where a partition root can be set.
-	It can only be set in a cgroup if all the following conditions
-	are true.
-
-	1) The "cpuset.cpus" is not empty and the list of CPUs are
-	   exclusive, i.e. they are not shared by any of its siblings.
-	2) The parent cgroup is a partition root.
-	3) The "cpuset.cpus" is also a proper subset of the parent's
-	   "cpuset.cpus.effective".
-	4) There is no child cgroups with cpuset enabled.  This is for
-	   eliminating corner cases that have to be handled if such a
-	   condition is allowed.
-
-	Setting it to partition root will take the CPUs away from the
-	effective CPUs of the parent cgroup.  Once it is set, this
-	file cannot be reverted back to "member" if there are any child
-	cgroups with cpuset enabled.
-
-	A parent partition cannot distribute all its CPUs to its
-	child partitions.  There must be at least one cpu left in the
-	parent partition.
-
-	Once becoming a partition root, changes to "cpuset.cpus" is
-	generally allowed as long as the first condition above is true,
-	the change will not take away all the CPUs from the parent
-	partition and the new "cpuset.cpus" value is a superset of its
-	children's "cpuset.cpus" values.
-
-	Sometimes, external factors like changes to ancestors'
-	"cpuset.cpus" or cpu hotplug can cause the state of the partition
-	root to change.  On read, the "cpuset.sched.partition" file
-	can show the following values.
-
-	  ==============	==============================
-	  "member"		Non-root member of a partition
-	  "root"		Partition root
-	  "root invalid"	Invalid partition root
-	  ==============	==============================
-
-	It is a partition root if the first 2 partition root conditions
-	above are true and at least one CPU from "cpuset.cpus" is
-	granted by the parent cgroup.
-
-	A partition root can become invalid if none of CPUs requested
-	in "cpuset.cpus" can be granted by the parent cgroup or the
-	parent cgroup is no longer a partition root itself.  In this
-	case, it is not a real partition even though the restriction
-	of the first partition root condition above will still apply.
-	The cpu affinity of all the tasks in the cgroup will then be
-	associated with CPUs in the nearest ancestor partition.
-
-	An invalid partition root can be transitioned back to a
-	real partition root if at least one of the requested CPUs
-	can now be granted by its parent.  In this case, the cpu
-	affinity of all the tasks in the formerly invalid partition
-	will be associated to the CPUs of the newly formed partition.
-	Changing the partition state of an invalid partition root to
-	"member" is always allowed even if child cpusets are present.
+	  ==========	=====================================
+	  "member"	Non-root member of a partition
+	  "root"	Partition root
+	  "isolated"	Partition root without load balancing
+	  ==========	=====================================
+
+	The root cgroup is always a partition root and its state
+	cannot be changed.  All other non-root cgroups start out as
+	"member".
+
+	When set to "root", the current cgroup is the root of a new
+	partition or scheduling domain that comprises itself and all
+	its descendants except those that are separate partition roots
+	themselves and their descendants.
+
+	When set to "isolated", the CPUs in that partition root will
+	be in an isolated state without any load balancing from the
+	scheduler.  Tasks placed in such a partition with multiple
+	CPUs should be carefully distributed and bound to each of the
+	individual CPUs for optimal performance.
+
+	The value shown in "cpuset.cpus.effective" of a partition root
+	is the CPUs that the partition root can dedicate to a potential
+	new child partition root. The new child subtracts available
+	CPUs from its parent "cpuset.cpus.effective".
+
+	A partition root ("root" or "isolated") can be in one of the
+	two possible states - valid or invalid.  An invalid partition
+	root is in a degraded state where some state information may
+	be retained, but behaves more like a "member".
+
+	All possible state transitions among "member", "root" and
+	"isolated" are allowed.
+
+	On read, the "cpuset.cpus.partition" file can show the following
+	values.
+
+	  =============================	=====================================
+	  "member"			Non-root member of a partition
+	  "root"			Partition root
+	  "isolated"			Partition root without load balancing
+	  "root invalid (<reason>)"	Invalid partition root
+	  "isolated invalid (<reason>)"	Invalid isolated partition root
+	  =============================	=====================================
+
+	In the case of an invalid partition root, a descriptive string on
+	why the partition is invalid is included within parentheses.
+
+	For a partition root to become valid, the following conditions
+	must be met.
+
+	1) The "cpuset.cpus" is exclusive with its siblings , i.e. they
+	   are not shared by any of its siblings (exclusivity rule).
+	2) The parent cgroup is a valid partition root.
+	3) The "cpuset.cpus" is not empty and must contain at least
+	   one of the CPUs from parent's "cpuset.cpus", i.e. they overlap.
+	4) The "cpuset.cpus.effective" cannot be empty unless there is
+	   no task associated with this partition.
+
+	External events like hotplug or changes to "cpuset.cpus" can
+	cause a valid partition root to become invalid and vice versa.
+	Note that a task cannot be moved to a cgroup with empty
+	"cpuset.cpus.effective".
+
+	For a valid partition root with the sibling cpu exclusivity
+	rule enabled, changes made to "cpuset.cpus" that violate the
+	exclusivity rule will invalidate the partition as well as its
+	sibiling partitions with conflicting cpuset.cpus values. So
+	care must be taking in changing "cpuset.cpus".
+
+	A valid non-root parent partition may distribute out all its CPUs
+	to its child partitions when there is no task associated with it.
+
+	Care must be taken to change a valid partition root to
+	"member" as all its child partitions, if present, will become
+	invalid causing disruption to tasks running in those child
+	partitions. These inactivated partitions could be recovered if
+	their parent is switched back to a partition root with a proper
+	set of "cpuset.cpus".
+
+	Poll and inotify events are triggered whenever the state of
+	"cpuset.cpus.partition" changes.  That includes changes caused
+	by write to "cpuset.cpus.partition", cpu hotplug or other
+	changes that modify the validity status of the partition.
+	This will allow user space agents to monitor unexpected changes
+	to "cpuset.cpus.partition" without the need to do continuous
+	polling.
 
 
 Device controller

block/blk-cgroup-fc-appid.c

@@ -19,8 +19,8 @@ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len)
 		return -EINVAL;
 
 	cgrp = cgroup_get_from_id(cgrp_id);
-	if (!cgrp)
-		return -ENOENT;
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
 	css = cgroup_get_e_css(cgrp, &io_cgrp_subsys);
 	if (!css) {
 		ret = -ENOENT;

include/linux/cgroup-defs.h

@@ -126,11 +126,11 @@ enum {
 	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
 	CFTYPE_WORLD_WRITABLE	= (1 << 4),	/* (DON'T USE FOR NEW FILES) S_IWUGO */
 	CFTYPE_DEBUG		= (1 << 5),	/* create when cgroup_debug */
-	CFTYPE_PRESSURE		= (1 << 6),	/* only if pressure feature is enabled */
 
 	/* internal flags, do not use outside cgroup core proper */
 	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */
 	__CFTYPE_NOT_ON_DFL	= (1 << 17),	/* not on default hierarchy */
+	__CFTYPE_ADDED		= (1 << 18),
 };
 
 /*
@@ -384,7 +384,7 @@ struct cgroup {
 	/*
 	 * The depth this cgroup is at.  The root is at depth zero and each
 	 * step down the hierarchy increments the level.  This along with
-	 * ancestor_ids[] can determine whether a given cgroup is a
+	 * ancestors[] can determine whether a given cgroup is a
 	 * descendant of another without traversing the hierarchy.
 	 */
 	int level;
@@ -504,8 +504,8 @@ struct cgroup {
 	/* Used to store internal freezer state */
 	struct cgroup_freezer_state freezer;
 
-	/* ids of the ancestors at each level including self */
-	u64 ancestor_ids[];
+	/* All ancestors including self */
+	struct cgroup *ancestors[];
 };
 
 /*
@@ -522,11 +522,15 @@ struct cgroup_root {
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
-	/* The root cgroup.  Root is destroyed on its release. */
+	/*
+	 * The root cgroup. The containing cgroup_root will be destroyed on its
+	 * release. cgrp->ancestors[0] will be used overflowing into the
+	 * following field. cgrp_ancestor_storage must immediately follow.
+	 */
 	struct cgroup cgrp;
 
-	/* for cgrp->ancestor_ids[0] */
-	u64 cgrp_ancestor_id_storage;
+	/* must follow cgrp for cgrp->ancestors[0], see above */
+	struct cgroup *cgrp_ancestor_storage;
 
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;

include/linux/cgroup.h

@@ -575,7 +575,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 {
 	if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
 		return false;
-	return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor);
+	return cgrp->ancestors[ancestor->level] == ancestor;
 }
 
 /**
@@ -592,11 +592,9 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
 					     int ancestor_level)
 {
-	if (cgrp->level < ancestor_level)
+	if (ancestor_level < 0 || ancestor_level > cgrp->level)
 		return NULL;
-	while (cgrp && cgrp->level > ancestor_level)
-		cgrp = cgroup_parent(cgrp);
-	return cgrp;
+	return cgrp->ancestors[ancestor_level];
 }
 
 /**
@@ -748,11 +746,6 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 
 static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
 {}
-
-static inline struct cgroup *cgroup_get_from_id(u64 id)
-{
-	return NULL;
-}
 #endif /* !CONFIG_CGROUPS */
 
 #ifdef CONFIG_CGROUPS

kernel/cgroup/cgroup-internal.h

@@ -250,6 +250,8 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup,
 
 int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 		       bool threadgroup);
+void cgroup_attach_lock(bool lock_threadgroup);
+void cgroup_attach_unlock(bool lock_threadgroup);
 struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 					     bool *locked)
 	__acquires(&cgroup_threadgroup_rwsem);

kernel/cgroup/cgroup-v1.c

@@ -59,8 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 	int retval = 0;
 
 	mutex_lock(&cgroup_mutex);
-	cpus_read_lock();
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(true);
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
 
@@ -72,8 +71,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 		if (retval)
 			break;
 	}
-	percpu_up_write(&cgroup_threadgroup_rwsem);
-	cpus_read_unlock();
+	cgroup_attach_unlock(true);
 	mutex_unlock(&cgroup_mutex);
 
 	return retval;

kernel/cgroup/pids.c

@@ -47,6 +47,7 @@ struct pids_cgroup {
 	 */
 	atomic64_t			counter;
 	atomic64_t			limit;
+	int64_t				watermark;
 
 	/* Handle for "pids.events" */
 	struct cgroup_file		events_file;
@@ -85,6 +86,16 @@ static void pids_css_free(struct cgroup_subsys_state *css)
 	kfree(css_pids(css));
 }
 
+static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids)
+{
+	/*
+	 * This is racy, but we don't need perfectly accurate tallying of
+	 * the watermark, and this lets us avoid extra atomic overhead.
+	 */
+	if (nr_pids > READ_ONCE(p->watermark))
+		WRITE_ONCE(p->watermark, nr_pids);
+}
+
 /**
  * pids_cancel - uncharge the local pid count
  * @pids: the pid cgroup state
@@ -128,8 +139,11 @@ static void pids_charge(struct pids_cgroup *pids, int num)
 {
 	struct pids_cgroup *p;
 
-	for (p = pids; parent_pids(p); p = parent_pids(p))
-		atomic64_add(num, &p->counter);
+	for (p = pids; parent_pids(p); p = parent_pids(p)) {
+		int64_t new = atomic64_add_return(num, &p->counter);
+
+		pids_update_watermark(p, new);
+	}
 }
 
 /**
@@ -156,6 +170,12 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
 		 */
 		if (new > limit)
 			goto revert;
+
+		/*
+		 * Not technically accurate if we go over limit somewhere up
+		 * the hierarchy, but that's tolerable for the watermark.
+		 */
+		pids_update_watermark(p, new);
 	}
 
 	return 0;
@@ -311,6 +331,14 @@ static s64 pids_current_read(struct cgroup_subsys_state *css,
 	return atomic64_read(&pids->counter);
 }
 
+static s64 pids_peak_read(struct cgroup_subsys_state *css,
+			  struct cftype *cft)
+{
+	struct pids_cgroup *pids = css_pids(css);
+
+	return READ_ONCE(pids->watermark);
+}
+
 static int pids_events_show(struct seq_file *sf, void *v)
 {
 	struct pids_cgroup *pids = css_pids(seq_css(sf));
@@ -331,6 +359,11 @@ static struct cftype pids_files[] = {
 		.read_s64 = pids_current_read,
 		.flags = CFTYPE_NOT_ON_ROOT,
 	},
+	{
+		.name = "peak",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = pids_peak_read,
+	},
 	{
 		.name = "events",
 		.seq_show = pids_events_show,

mm/memcontrol.c

@@ -5104,8 +5104,8 @@ struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino)
 	struct mem_cgroup *memcg;
 
 	cgrp = cgroup_get_from_id(ino);
-	if (!cgrp)
-		return ERR_PTR(-ENOENT);
+	if (IS_ERR(cgrp))
+		return ERR_CAST(cgrp);
 
 	css = cgroup_get_e_css(cgrp, &memory_cgrp_subsys);
 	if (css)

net/netfilter/nft_socket.c

@@ -40,16 +40,17 @@ static noinline bool
 nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level)
 {
 	struct cgroup *cgrp;
+	u64 cgid;
 
 	if (!sk_fullsock(sk))
 		return false;
 
-	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	if (level > cgrp->level)
+	cgrp = cgroup_ancestor(sock_cgroup_ptr(&sk->sk_cgrp_data), level);
+	if (!cgrp)
 		return false;
 
-	memcpy(dest, &cgrp->ancestor_ids[level], sizeof(u64));
-
+	cgid = cgroup_id(cgrp);
+	memcpy(dest, &cgid, sizeof(u64));
 	return true;
 }
 #endif

tools/cgroup/iocost_monitor.py

@@ -61,6 +61,11 @@ autop_names = {
 }
 
 class BlkgIterator:
+    def __init__(self, root_blkcg, q_id, include_dying=False):
+        self.include_dying = include_dying
+        self.blkgs = []
+        self.walk(root_blkcg, q_id, '')
+
     def blkcg_name(blkcg):
         return blkcg.css.cgroup.kn.name.string_().decode('utf-8')
 
@@ -82,11 +87,6 @@ class BlkgIterator:
                                      blkcg.css.children.address_of_(), 'css.sibling'):
             self.walk(c, q_id, path)
 
-    def __init__(self, root_blkcg, q_id, include_dying=False):
-        self.include_dying = include_dying
-        self.blkgs = []
-        self.walk(root_blkcg, q_id, '')
-
     def __iter__(self):
         return iter(self.blkgs)
 

tools/perf/util/bpf_skel/bperf_cgroup.bpf.c

@@ -77,7 +77,7 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size)
 			break;
 
 		// convert cgroup-id to a map index
-		cgrp_id = BPF_CORE_READ(cgrp, ancestor_ids[i]);
+		cgrp_id = BPF_CORE_READ(cgrp, ancestors[i], kn, id);
 		elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id);
 		if (!elem)
 			continue;

tools/testing/selftests/cgroup/.gitignore

@@ -5,3 +5,4 @@ test_freezer
 test_kmem
 test_kill
 test_cpu
+wait_inotify

tools/testing/selftests/cgroup/Makefile

 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -Wall -pthread
 
-all:
+all: ${HELPER_PROGS}
 
 TEST_FILES     := with_stress.sh
-TEST_PROGS     := test_stress.sh
+TEST_PROGS     := test_stress.sh test_cpuset_prs.sh
+TEST_GEN_FILES := wait_inotify
 TEST_GEN_PROGS = test_memcontrol
 TEST_GEN_PROGS += test_kmem
 TEST_GEN_PROGS += test_core

tools/testing/selftests/cgroup/wait_inotify.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wait until an inotify event on the given cgroup file.
+ */
+#include <linux/limits.h>
+#include <sys/inotify.h>
+#include <sys/mman.h>
+#include <sys/ptrace.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static const char usage[] = "Usage: %s [-v] <cgroup_file>\n";
+static char *file;
+static int verbose;
+
+static inline void fail_message(char *msg)
+{
+	fprintf(stderr, msg, file);
+	exit(1);
+}
+
+int main(int argc, char *argv[])
+{
+	char *cmd = argv[0];
+	int c, fd;
+	struct pollfd fds = { .events = POLLIN, };
+
+	while ((c = getopt(argc, argv, "v")) != -1) {
+		switch (c) {
+		case 'v':
+			verbose++;
+			break;
+		}
+		argv++, argc--;
+	}
+
+	if (argc != 2) {
+		fprintf(stderr, usage, cmd);
+		return -1;
+	}
+	file = argv[1];
+	fd = open(file, O_RDONLY);
+	if (fd < 0)
+		fail_message("Cgroup file %s not found!\n");
+	close(fd);
+
+	fd = inotify_init();
+	if (fd < 0)
+		fail_message("inotify_init() fails on %s!\n");
+	if (inotify_add_watch(fd, file, IN_MODIFY) < 0)
+		fail_message("inotify_add_watch() fails on %s!\n");
+	fds.fd = fd;
+
+	/*
+	 * poll waiting loop
+	 */
+	for (;;) {
+		int ret = poll(&fds, 1, 10000);
+
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			perror("poll");
+			exit(1);
+		}
+		if ((ret > 0) && (fds.revents & POLLIN))
+			break;
+	}
+	if (verbose) {
+		struct inotify_event events[10];
+		long len;
+
+		usleep(1000);
+		len = read(fd, events, sizeof(events));
+		printf("Number of events read = %ld\n",
+			len/sizeof(struct inotify_event));
+	}
+	close(fd);
+	return 0;
+}