hugetlb: add hugetlb.*.numa_stat file

For hugetlb backed jobs/VMs it's critical to understand the numa
information for the memory backing these jobs to deliver optimal
performance.

Currently this technically can be queried from /proc/self/numa_maps, but
there are significant issues with that. Namely:

1. Memory can be mapped or unmapped.

2. numa_maps are per process and need to be aggregated across all
processes in the cgroup. For shared memory this is more involved as
the userspace needs to make sure it doesn't double count shared
mappings.

3. I believe querying numa_maps needs to hold the mmap_lock which adds
to the contention on this lock.

For these reasons I propose simply adding hugetlb.*.numa_stat file,
which shows the numa information of the cgroup similarly to
memory.numa_stat.

On cgroup-v2:
cat /sys/fs/cgroup/unified/test/hugetlb.2MB.numa_stat
total=2097152 N0=2097152 N1=0

On cgroup-v1:
cat /sys/fs/cgroup/hugetlb/test/hugetlb.2MB.numa_stat
total=2097152 N0=2097152 N1=0
hierarichal_total=2097152 N0=2097152 N1=0

This patch was tested manually by allocating hugetlb memory and querying
the hugetlb.*.numa_stat file of the cgroup and its parents.

[[e-mail]: fix spelling mistake "hierarichal" -> "hierarchical"]
Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: fix copy/paste array assignment]
Link: https://lkml.kernel.org/r/[e-mail]

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Mina Almasry <[e-mail]>
Signed-off-by: Colin Ian King <[e-mail]>
Signed-off-by: Kees Cook <[e-mail]>
Reviewed-by: Shakeel Butt <[e-mail]>
Reviewed-by: Muchun Song <[e-mail]>
Reviewed-by: Mike Kravetz <[e-mail]>
Cc: Shuah Khan <[e-mail]>
Cc: Miaohe Lin <[e-mail]>
Cc: Oscar Salvador <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: David Rientjes <[e-mail]>
Cc: Jue Wang <[e-mail]>
Cc: Yang Yao <[e-mail]>
Cc: Joanna Li <[e-mail]>
Cc: Cannon Matthews <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

Documentation/admin-guide/cgroup-v1/hugetlb.rst

···
  hugetlb.<hugepagesize>.max_usage_in_bytes             # show max "hugepagesize" hugetlb  usage recorded
  hugetlb.<hugepagesize>.usage_in_bytes                 # show current usage for "hugepagesize" hugetlb
  hugetlb.<hugepagesize>.failcnt                        # show the number of allocation failure due to HugeTLB usage limit
+ hugetlb.<hugepagesize>.numa_stat                      # show the numa information of the hugetlb memory charged to this cgroup
 
 For a system supporting three hugepage sizes (64k, 32M and 1G), the control
 files include::
 
   hugetlb.1GB.limit_in_bytes
   hugetlb.1GB.max_usage_in_bytes
+  hugetlb.1GB.numa_stat
   hugetlb.1GB.usage_in_bytes
   hugetlb.1GB.failcnt
   hugetlb.1GB.rsvd.limit_in_bytes
···
   hugetlb.1GB.rsvd.failcnt
   hugetlb.64KB.limit_in_bytes
   hugetlb.64KB.max_usage_in_bytes
+  hugetlb.64KB.numa_stat
   hugetlb.64KB.usage_in_bytes
   hugetlb.64KB.failcnt
   hugetlb.64KB.rsvd.limit_in_bytes
···
   hugetlb.64KB.rsvd.failcnt
   hugetlb.32MB.limit_in_bytes
   hugetlb.32MB.max_usage_in_bytes
+  hugetlb.32MB.numa_stat
   hugetlb.32MB.usage_in_bytes
   hugetlb.32MB.failcnt
   hugetlb.32MB.rsvd.limit_in_bytes

Documentation/admin-guide/cgroup-v2.rst

···
 	are local to the cgroup i.e. not hierarchical. The file modified event
 	generated on this file reflects only the local events.
 
+  hugetlb.<hugepagesize>.numa_stat
+	Similar to memory.numa_stat, it shows the numa information of the
+        hugetlb pages of <hugepagesize> in this cgroup.  Only active in
+        use hugetlb pages are included.  The per-node values are in bytes.
+
 Misc
 ----
 

include/linux/hugetlb.h

···
 #endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
-	struct cftype cgroup_files_dfl[7];
-	struct cftype cgroup_files_legacy[9];
+	struct cftype cgroup_files_dfl[8];
+	struct cftype cgroup_files_legacy[10];
 #endif
 	char name[HSTATE_NAME_LEN];
 };

include/linux/hugetlb_cgroup.h

···
 	HUGETLB_NR_MEMORY_EVENTS,
 };
 
+struct hugetlb_cgroup_per_node {
+	/* hugetlb usage in pages over all hstates. */
+	unsigned long usage[HUGE_MAX_HSTATE];
+};
+
 struct hugetlb_cgroup {
 	struct cgroup_subsys_state css;
 
···
 
 	/* Handle for "hugetlb.events.local" */
 	struct cgroup_file events_local_file[HUGE_MAX_HSTATE];
+
+	struct hugetlb_cgroup_per_node *nodeinfo[];
 };
 
 static inline struct hugetlb_cgroup *

mm/hugetlb_cgroup.c

···
 	}
 }
 
+static void hugetlb_cgroup_free(struct hugetlb_cgroup *h_cgroup)
+{
+	int node;
+
+	for_each_node(node)
+		kfree(h_cgroup->nodeinfo[node]);
+	kfree(h_cgroup);
+}
+
 static struct cgroup_subsys_state *
 hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css);
 	struct hugetlb_cgroup *h_cgroup;
+	int node;
 
-	h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
+	h_cgroup = kzalloc(struct_size(h_cgroup, nodeinfo, nr_node_ids),
+			   GFP_KERNEL);
+
 	if (!h_cgroup)
 		return ERR_PTR(-ENOMEM);
 
 	if (!parent_h_cgroup)
 		root_h_cgroup = h_cgroup;
 
+	/*
+	 * TODO: this routine can waste much memory for nodes which will
+	 * never be onlined. It's better to use memory hotplug callback
+	 * function.
+	 */
+	for_each_node(node) {
+		/* Set node_to_alloc to -1 for offline nodes. */
+		int node_to_alloc =
+			node_state(node, N_NORMAL_MEMORY) ? node : -1;
+		h_cgroup->nodeinfo[node] =
+			kzalloc_node(sizeof(struct hugetlb_cgroup_per_node),
+				     GFP_KERNEL, node_to_alloc);
+		if (!h_cgroup->nodeinfo[node])
+			goto fail_alloc_nodeinfo;
+	}
+
 	hugetlb_cgroup_init(h_cgroup, parent_h_cgroup);
 	return &h_cgroup->css;
+
+fail_alloc_nodeinfo:
+	hugetlb_cgroup_free(h_cgroup);
+	return ERR_PTR(-ENOMEM);
 }
 
 static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
 {
-	struct hugetlb_cgroup *h_cgroup;
-
-	h_cgroup = hugetlb_cgroup_from_css(css);
-	kfree(h_cgroup);
+	hugetlb_cgroup_free(hugetlb_cgroup_from_css(css));
 }
 
 /*
···
 		return;
 
 	__set_hugetlb_cgroup(page, h_cg, rsvd);
-	return;
+	if (!rsvd) {
+		unsigned long usage =
+			h_cg->nodeinfo[page_to_nid(page)]->usage[idx];
+		/*
+		 * This write is not atomic due to fetching usage and writing
+		 * to it, but that's fine because we call this with
+		 * hugetlb_lock held anyway.
+		 */
+		WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx],
+			   usage + nr_pages);
+	}
 }
 
 void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
···
 
 	if (rsvd)
 		css_put(&h_cg->css);
-
-	return;
+	else {
+		unsigned long usage =
+			h_cg->nodeinfo[page_to_nid(page)]->usage[idx];
+		/*
+		 * This write is not atomic due to fetching usage and writing
+		 * to it, but that's fine because we call this with
+		 * hugetlb_lock held anyway.
+		 */
+		WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx],
+			   usage - nr_pages);
+	}
 }
 
 void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
···
 	RES_FAILCNT,
 	RES_RSVD_FAILCNT,
 };
+
+static int hugetlb_cgroup_read_numa_stat(struct seq_file *seq, void *dummy)
+{
+	int nid;
+	struct cftype *cft = seq_cft(seq);
+	int idx = MEMFILE_IDX(cft->private);
+	bool legacy = MEMFILE_ATTR(cft->private);
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq));
+	struct cgroup_subsys_state *css;
+	unsigned long usage;
+
+	if (legacy) {
+		/* Add up usage across all nodes for the non-hierarchical total. */
+		usage = 0;
+		for_each_node_state(nid, N_MEMORY)
+			usage += READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]);
+		seq_printf(seq, "total=%lu", usage * PAGE_SIZE);
+
+		/* Simply print the per-node usage for the non-hierarchical total. */
+		for_each_node_state(nid, N_MEMORY)
+			seq_printf(seq, " N%d=%lu", nid,
+				   READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]) *
+					   PAGE_SIZE);
+		seq_putc(seq, '\n');
+	}
+
+	/*
+	 * The hierarchical total is pretty much the value recorded by the
+	 * counter, so use that.
+	 */
+	seq_printf(seq, "%stotal=%lu", legacy ? "hierarchical_" : "",
+		   page_counter_read(&h_cg->hugepage[idx]) * PAGE_SIZE);
+
+	/*
+	 * For each node, transverse the css tree to obtain the hierarchical
+	 * node usage.
+	 */
+	for_each_node_state(nid, N_MEMORY) {
+		usage = 0;
+		rcu_read_lock();
+		css_for_each_descendant_pre(css, &h_cg->css) {
+			usage += READ_ONCE(hugetlb_cgroup_from_css(css)
+						   ->nodeinfo[nid]
+						   ->usage[idx]);
+		}
+		rcu_read_unlock();
+		seq_printf(seq, " N%d=%lu", nid, usage * PAGE_SIZE);
+	}
+
+	seq_putc(seq, '\n');
+
+	return 0;
+}
 
 static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 				   struct cftype *cft)
···
 				    events_local_file[idx]);
 	cft->flags = CFTYPE_NOT_ON_ROOT;
 
-	/* NULL terminate the last cft */
+	/* Add the numa stat file */
 	cft = &h->cgroup_files_dfl[6];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf);
+	cft->seq_show = hugetlb_cgroup_read_numa_stat;
+	cft->flags = CFTYPE_NOT_ON_ROOT;
+
+	/* NULL terminate the last cft */
+	cft = &h->cgroup_files_dfl[7];
 	memset(cft, 0, sizeof(*cft));
 
 	WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys,
···
 	cft->write = hugetlb_cgroup_reset;
 	cft->read_u64 = hugetlb_cgroup_read_u64;
 
-	/* NULL terminate the last cft */
+	/* Add the numa stat file */
 	cft = &h->cgroup_files_legacy[8];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf);
+	cft->private = MEMFILE_PRIVATE(idx, 1);
+	cft->seq_show = hugetlb_cgroup_read_numa_stat;
+
+	/* NULL terminate the last cft */
+	cft = &h->cgroup_files_legacy[9];
 	memset(cft, 0, sizeof(*cft));
 
 	WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys,