Merge branch 'for-4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Waiman's cgroup2 cpuset support has been finally merged closing one
   of the last remaining feature gaps.

 - cgroup.procs could show non-leader threads when cgroup2 threaded mode
   was used in certain ways. I forgot to push the fix during the last
   cycle.

 - A patch to fix mount option parsing when all mount options have been
   consumed by someone else (LSM).

 - cgroup_no_v1 boot param can now block named cgroup1 hierarchies too.

* 'for-4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Add named hierarchy disabling to cgroup_no_v1 boot param
  cgroup: fix parsing empty mount option string
  cpuset: Remove set but not used variable 'cs'
  cgroup: fix CSS_TASK_ITER_PROCS
  cgroup: Add .__DEBUG__. prefix to debug file names
  cpuset: Minor cgroup2 interface updates
  cpuset: Expose cpuset.cpus.subpartitions with cgroup_debug
  cpuset: Add documentation about the new "cpuset.sched.partition" flag
  cpuset: Use descriptive text when reading/writing cpuset.sched.partition
  cpuset: Expose cpus.effective and mems.effective on cgroup v2 root
  cpuset: Make generate_sched_domains() work with partition
  cpuset: Make CPU hotplug work with partition
  cpuset: Track cpusets that use parent's effective_cpus
  cpuset: Add an error state to cpuset.sched.partition
  cpuset: Add new v2 cpuset.sched.partition flag
  cpuset: Simply allocation and freeing of cpumasks
  cpuset: Define data structures to support scheduling partition
  cpuset: Enable cpuset controller in default hierarchy
  cgroup: remove unnecessary unlikely()

Documentation/admin-guide/cgroup-v2.rst

@@ -56,11 +56,13 @@ v1 is available under Documentation/cgroup-v1/.
          5-3-3-2. IO Latency Interface Files
      5-4. PID
        5-4-1. PID Interface Files
-     5-5. Device
-     5-6. RDMA
-       5-6-1. RDMA Interface Files
-     5-7. Misc
-       5-7-1. perf_event
+     5-5. Cpuset
+       5.5-1. Cpuset Interface Files
+     5-6. Device
+     5-7. RDMA
+       5-7-1. RDMA Interface Files
+     5-8. Misc
+       5-8-1. perf_event
      5-N. Non-normative information
        5-N-1. CPU controller root cgroup process behaviour
        5-N-2. IO controller root cgroup process behaviour
@@ -1610,6 +1612,176 @@ through fork() or clone(). These will return -EAGAIN if the creation
 of a new process would cause a cgroup policy to be violated.
 
 
+Cpuset
+------
+
+The "cpuset" controller provides a mechanism for constraining
+the CPU and memory node placement of tasks to only the resources
+specified in the cpuset interface files in a task's current cgroup.
+This is especially valuable on large NUMA systems where placing jobs
+on properly sized subsets of the systems with careful processor and
+memory placement to reduce cross-node memory access and contention
+can improve overall system performance.
+
+The "cpuset" controller is hierarchical.  That means the controller
+cannot use CPUs or memory nodes not allowed in its parent.
+
+
+Cpuset Interface Files
+~~~~~~~~~~~~~~~~~~~~~~
+
+  cpuset.cpus
+	A read-write multiple values file which exists on non-root
+	cpuset-enabled cgroups.
+
+	It lists the requested CPUs to be used by tasks within this
+	cgroup.  The actual list of CPUs to be granted, however, is
+	subjected to constraints imposed by its parent and can differ
+	from the requested CPUs.
+
+	The CPU numbers are comma-separated numbers or ranges.
+	For example:
+
+	  # cat cpuset.cpus
+	  0-4,6,8-10
+
+	An empty value indicates that the cgroup is using the same
+	setting as the nearest cgroup ancestor with a non-empty
+	"cpuset.cpus" or all the available CPUs if none is found.
+
+	The value of "cpuset.cpus" stays constant until the next update
+	and won't be affected by any CPU hotplug events.
+
+  cpuset.cpus.effective
+	A read-only multiple values file which exists on all
+	cpuset-enabled cgroups.
+
+	It lists the onlined CPUs that are actually granted to this
+	cgroup by its parent.  These CPUs are allowed to be used by
+	tasks within the current cgroup.
+
+	If "cpuset.cpus" is empty, the "cpuset.cpus.effective" file shows
+	all the CPUs from the parent cgroup that can be available to
+	be used by this cgroup.  Otherwise, it should be a subset of
+	"cpuset.cpus" unless none of the CPUs listed in "cpuset.cpus"
+	can be granted.  In this case, it will be treated just like an
+	empty "cpuset.cpus".
+
+	Its value will be affected by CPU hotplug events.
+
+  cpuset.mems
+	A read-write multiple values file which exists on non-root
+	cpuset-enabled cgroups.
+
+	It lists the requested memory nodes to be used by tasks within
+	this cgroup.  The actual list of memory nodes granted, however,
+	is subjected to constraints imposed by its parent and can differ
+	from the requested memory nodes.
+
+	The memory node numbers are comma-separated numbers or ranges.
+	For example:
+
+	  # cat cpuset.mems
+	  0-1,3
+
+	An empty value indicates that the cgroup is using the same
+	setting as the nearest cgroup ancestor with a non-empty
+	"cpuset.mems" or all the available memory nodes if none
+	is found.
+
+	The value of "cpuset.mems" stays constant until the next update
+	and won't be affected by any memory nodes hotplug events.
+
+  cpuset.mems.effective
+	A read-only multiple values file which exists on all
+	cpuset-enabled cgroups.
+
+	It lists the onlined memory nodes that are actually granted to
+	this cgroup by its parent. These memory nodes are allowed to
+	be used by tasks within the current cgroup.
+
+	If "cpuset.mems" is empty, it shows all the memory nodes from the
+	parent cgroup that will be available to be used by this cgroup.
+	Otherwise, it should be a subset of "cpuset.mems" unless none of
+	the memory nodes listed in "cpuset.mems" can be granted.  In this
+	case, it will be treated just like an empty "cpuset.mems".
+
+	Its value will be affected by memory nodes hotplug events.
+
+  cpuset.cpus.partition
+	A read-write single value file which exists on non-root
+	cpuset-enabled cgroups.  This flag is owned by the parent cgroup
+	and is not delegatable.
+
+        It accepts only the following input values when written to.
+
+        "root"   - a paritition 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.
+
+
 Device controller
 -----------------
 

Documentation/admin-guide/kernel-parameters.txt

@@ -486,10 +486,14 @@
 			cut the overhead, others just disable the usage. So
 			only cgroup_disable=memory is actually worthy}
 
-	cgroup_no_v1=	[KNL] Disable one, multiple, all cgroup controllers in v1
-			Format: { controller[,controller...] | "all" }
+	cgroup_no_v1=	[KNL] Disable cgroup controllers and named hierarchies in v1
+			Format: { { controller | "all" | "named" }
+			          [,{ controller | "all" | "named" }...] }
 			Like cgroup_disable, but only applies to cgroup v1;
 			the blacklisted controllers remain available in cgroup2.
+			"all" blacklists all controllers and "named" disables
+			named mounts. Specifying both "all" and "named" disables
+			all v1 hierarchies.
 
 	cgroup.memory=	[KNL] Pass options to the cgroup memory controller.
 			Format: <string>

include/linux/cgroup-defs.h

@@ -92,6 +92,7 @@ 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 */
 
 	/* internal flags, do not use outside cgroup core proper */
 	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */

kernel/cgroup/cgroup-internal.h

@@ -11,6 +11,8 @@
 #define TRACE_CGROUP_PATH_LEN 1024
 extern spinlock_t trace_cgroup_path_lock;
 extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+extern bool cgroup_debug;
+extern void __init enable_debug_cgroup(void);
 
 /*
  * cgroup_path() takes a spin lock. It is good practice not to take

kernel/cgroup/cgroup-v1.c

@@ -27,6 +27,9 @@
 /* Controllers blocked by the commandline in v1 */
 static u16 cgroup_no_v1_mask;
 
+/* disable named v1 mounts */
+static bool cgroup_no_v1_named;
+
 /*
  * pidlist destructions need to be flushed on cgroup destruction.  Use a
  * separate workqueue as flush domain.
@@ -963,6 +966,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 		}
 		if (!strncmp(token, "name=", 5)) {
 			const char *name = token + 5;
+
+			/* blocked by boot param? */
+			if (cgroup_no_v1_named)
+				return -ENOENT;
 			/* Can't specify an empty name */
 			if (!strlen(name))
 				return -EINVAL;
@@ -1292,7 +1299,12 @@ static int __init cgroup_no_v1(char *str)
 
 		if (!strcmp(token, "all")) {
 			cgroup_no_v1_mask = U16_MAX;
-			break;
+			continue;
+		}
+
+		if (!strcmp(token, "named")) {
+			cgroup_no_v1_named = true;
+			continue;
 		}
 
 		for_each_subsys(ss, i) {

kernel/cgroup/cgroup.c

@@ -86,6 +86,7 @@ EXPORT_SYMBOL_GPL(css_set_lock);
 
 DEFINE_SPINLOCK(trace_cgroup_path_lock);
 char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+bool cgroup_debug __read_mostly;
 
 /*
  * Protects cgroup_idr and css_idr so that IDs can be released without
@@ -1429,12 +1430,15 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 	struct cgroup_subsys *ss = cft->ss;
 
 	if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
-	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
-		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
-			 cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
+	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
+		const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : "";
+
+		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s",
+			 dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
 			 cft->name);
-	else
+	} else {
 		strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+	}
 	return buf;
 }
 
@@ -1774,7 +1778,7 @@ static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
 
 	*root_flags = 0;
 
-	if (!data)
+	if (!data || *data == '\0')
 		return 0;
 
 	while ((token = strsep(&data, ",")) != NULL) {
@@ -3669,7 +3673,8 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css,
 			continue;
 		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
 			continue;
-
+		if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug)
+			continue;
 		if (is_add) {
 			ret = cgroup_add_file(css, cgrp, cft);
 			if (ret) {
@@ -4232,10 +4237,11 @@ static void css_task_iter_advance(struct css_task_iter *it)
 
 	lockdep_assert_held(&css_set_lock);
 repeat:
+	if (it->task_pos) {
 		/*
-	 * Advance iterator to find next entry.  cset->tasks is consumed
-	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
-	 * next cset.
+		 * Advance iterator to find next entry.  cset->tasks is
+		 * consumed first and then ->mg_tasks.  After ->mg_tasks,
+		 * we move onto the next cset.
 		 */
 		next = it->task_pos->next;
 
@@ -4246,6 +4252,10 @@ static void css_task_iter_advance(struct css_task_iter *it)
 			css_task_iter_advance_css_set(it);
 		else
 			it->task_pos = next;
+	} else {
+		/* called from start, proceed to the first cset */
+		css_task_iter_advance_css_set(it);
+	}
 
 	/* if PROCS, skip over tasks which aren't group leaders */
 	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
@@ -4285,7 +4295,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 
 	it->cset_head = it->cset_pos;
 
-	css_task_iter_advance_css_set(it);
+	css_task_iter_advance(it);
 
 	spin_unlock_irq(&css_set_lock);
 }
@@ -5773,6 +5783,16 @@ static int __init cgroup_disable(char *str)
 }
 __setup("cgroup_disable=", cgroup_disable);
 
+void __init __weak enable_debug_cgroup(void) { }
+
+static int __init enable_cgroup_debug(char *str)
+{
+	cgroup_debug = true;
+	enable_debug_cgroup();
+	return 1;
+}
+__setup("cgroup_debug", enable_cgroup_debug);
+
 /**
  * css_tryget_online_from_dir - get corresponding css from a cgroup dentry
  * @dentry: directory dentry of interest
@@ -6008,11 +6028,9 @@ static ssize_t show_delegatable_files(struct cftype *files, char *buf,
 
 		ret += snprintf(buf + ret, size - ret, "%s\n", cft->name);
 
-		if (unlikely(ret >= size)) {
-			WARN_ON(1);
+		if (WARN_ON(ret >= size))
 			break;
 	}
-	}
 
 	return ret;
 }

kernel/cgroup/debug.c

@@ -373,11 +373,9 @@ struct cgroup_subsys debug_cgrp_subsys = {
  * On v2, debug is an implicit controller enabled by "cgroup_debug" boot
  * parameter.
  */
-static int __init enable_cgroup_debug(char *str)
+void __init enable_debug_cgroup(void)
 {
 	debug_cgrp_subsys.dfl_cftypes = debug_files;
 	debug_cgrp_subsys.implicit_on_dfl = true;
 	debug_cgrp_subsys.threaded = true;
-	return 1;
 }
-__setup("cgroup_debug", enable_cgroup_debug);