hugetlb_cgroup: add accounting for shared mappings

For shared mappings, the pointer to the hugetlb_cgroup to uncharge lives
in the resv_map entries, in file_region->reservation_counter.

After a call to region_chg, we charge the approprate hugetlb_cgroup, and
if successful, we pass on the hugetlb_cgroup info to a follow up
region_add call.  When a file_region entry is added to the resv_map via
region_add, we put the pointer to that cgroup in
file_region->reservation_counter.  If charging doesn't succeed, we report
the error to the caller, so that the kernel fails the reservation.

On region_del, which is when the hugetlb memory is unreserved, we also
uncharge the file_region->reservation_counter.

[akpm@linux-foundation.org: forward declare struct file_region]
Signed-off-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Link: http://lkml.kernel.org/r/20200211213128.73302-5-almasrymina@google.comSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/hugetlb.h

@@ -57,6 +57,41 @@ struct resv_map {
 	struct cgroup_subsys_state *css;
 #endif
 };
+
+/*
+ * Region tracking -- allows tracking of reservations and instantiated pages
+ *                    across the pages in a mapping.
+ *
+ * The region data structures are embedded into a resv_map and protected
+ * by a resv_map's lock.  The set of regions within the resv_map represent
+ * reservations for huge pages, or huge pages that have already been
+ * instantiated within the map.  The from and to elements are huge page
+ * indicies into the associated mapping.  from indicates the starting index
+ * of the region.  to represents the first index past the end of  the region.
+ *
+ * For example, a file region structure with from == 0 and to == 4 represents
+ * four huge pages in a mapping.  It is important to note that the to element
+ * represents the first element past the end of the region. This is used in
+ * arithmetic as 4(to) - 0(from) = 4 huge pages in the region.
+ *
+ * Interval notation of the form [from, to) will be used to indicate that
+ * the endpoint from is inclusive and to is exclusive.
+ */
+struct file_region {
+	struct list_head link;
+	long from;
+	long to;
+#ifdef CONFIG_CGROUP_HUGETLB
+	/*
+	 * On shared mappings, each reserved region appears as a struct
+	 * file_region in resv_map. These fields hold the info needed to
+	 * uncharge each reservation.
+	 */
+	struct page_counter *reservation_counter;
+	struct cgroup_subsys_state *css;
+#endif
+};
+
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
 

include/linux/hugetlb_cgroup.h

@@ -19,6 +19,7 @@
 
 struct hugetlb_cgroup;
 struct resv_map;
+struct file_region;
 
 /*
  * Minimum page order trackable by hugetlb cgroup.
@@ -135,11 +136,21 @@ extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv,
 					    unsigned long start,
 					    unsigned long end);
 
+extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
+						struct file_region *rg,
+						unsigned long nr_pages);
+
 extern void hugetlb_cgroup_file_init(void) __init;
 extern void hugetlb_cgroup_migrate(struct page *oldhpage,
 				   struct page *newhpage);
 
 #else
+static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
+						       struct file_region *rg,
+						       unsigned long nr_pages)
+{
+}
+
 static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
 {
 	return NULL;

mm/hugetlb_cgroup.c

@@ -391,6 +391,21 @@ void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start,
 	css_put(resv->css);
 }
 
+void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
+					 struct file_region *rg,
+					 unsigned long nr_pages)
+{
+	if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages)
+		return;
+
+	if (rg->reservation_counter && resv->pages_per_hpage && nr_pages > 0 &&
+	    !resv->reservation_counter) {
+		page_counter_uncharge(rg->reservation_counter,
+				      nr_pages * resv->pages_per_hpage);
+		css_put(rg->css);
+	}
+}
+
 enum {
 	RES_USAGE,
 	RES_RSVD_USAGE,