[PATCH 07/16] memcg: add support for GPU page counters. (v4)

[Dave Airlie <airlied@gmail.com>]

From: Dave Airlie <airlied@redhat.com>

This introduces 2 new statistics and 3 new memcontrol APIs for dealing
with GPU system memory allocations.

The stats corresponds to the same stats in the global vmstat,
for number of active GPU pages, and number of pages in pools that
can be reclaimed.

The first API charges a order of pages to a objcg, and sets
the objcg on the pages like kmem does, and updates the active/reclaim
statistic.

The second API uncharges a page from the obj cgroup it is currently charged
to.

The third API allows moving a page to/from reclaim and between obj cgroups.
When pages are added to the pool lru, this just updates accounting.
When pages are being removed from a pool lru, they can be taken from
the parent objcg so this allows them to be uncharged from there and transferred
to a new child objcg.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
v2: use memcg_node_stat_items
v3: fix null ptr dereference in uncharge
v4: AI review: fix parameter names, fix problem with reclaim moving doing wrong thing
---
 Documentation/admin-guide/cgroup-v2.rst |   6 ++
 include/linux/memcontrol.h              |  11 +++
 mm/memcontrol.c                         | 104 ++++++++++++++++++++++++
 3 files changed, 121 insertions(+)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 91beaa6798ce..3ea7f1a399e8 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1573,6 +1573,12 @@ The following nested keys are defined.
 	  vmalloc (npn)
 		Amount of memory used for vmap backed memory.
 
+	  gpu_active (npn)
+		Amount of system memory used for GPU devices.
+
+	  gpu_reclaim (npn)
+		Amount of system memory cached for GPU devices.
+
 	  shmem
 		Amount of cached filesystem data that is swap-backed,
 		such as tmpfs, shm segments, shared anonymous mmap()s
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 70b685a85bf4..4f75d64f5fca 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1583,6 +1583,17 @@ static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 struct sock;
+bool mem_cgroup_charge_gpu_page(struct obj_cgroup *objcg, struct page *page,
+			   unsigned int order,
+			   gfp_t gfp_mask, bool reclaim);
+void mem_cgroup_uncharge_gpu_page(struct page *page,
+				  unsigned int order,
+				  bool reclaim);
+bool mem_cgroup_move_gpu_page_reclaim(struct obj_cgroup *objcg,
+				      struct page *page,
+				      unsigned int order,
+				      bool to_reclaim);
+
 #ifdef CONFIG_MEMCG
 extern struct static_key_false memcg_sockets_enabled_key;
 #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a52da3a5e4fd..90bb3e00c258 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -333,6 +333,8 @@ static const unsigned int memcg_node_stat_items[] = {
 #ifdef CONFIG_HUGETLB_PAGE
 	NR_HUGETLB,
 #endif
+	NR_GPU_ACTIVE,
+	NR_GPU_RECLAIM,
 };
 
 static const unsigned int memcg_stat_items[] = {
@@ -1360,6 +1362,8 @@ static const struct memory_stat memory_stats[] = {
 	{ "percpu",			MEMCG_PERCPU_B			},
 	{ "sock",			MEMCG_SOCK			},
 	{ "vmalloc",			MEMCG_VMALLOC			},
+	{ "gpu_active",			NR_GPU_ACTIVE			},
+	{ "gpu_reclaim",		NR_GPU_RECLAIM	                },
 	{ "shmem",			NR_SHMEM			},
 #ifdef CONFIG_ZSWAP
 	{ "zswap",			MEMCG_ZSWAP_B			},
@@ -5133,6 +5137,106 @@ void mem_cgroup_flush_workqueue(void)
 	flush_workqueue(memcg_wq);
 }
 
+/**
+ * mem_cgroup_charge_gpu_page - charge a page to GPU memory tracking
+ * @objcg: objcg to charge, NULL charges root memcg
+ * @page: page to charge
+ * @order: page allocation order
+ * @gfp_mask: gfp mode
+ * @reclaim: charge the reclaim counter instead of the active one.
+ *
+ * Charge the order sized @page to the objcg. Returns %true if the charge fit within
+ * @objcg's configured limit, %false if it doesn't.
+ */
+bool mem_cgroup_charge_gpu_page(struct obj_cgroup *objcg, struct page *page,
+				unsigned int order, gfp_t gfp_mask, bool reclaim)
+{
+	unsigned int nr_pages = 1 << order;
+	struct mem_cgroup *memcg = NULL;
+	struct lruvec *lruvec;
+	int ret;
+
+	if (objcg) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+
+		ret = try_charge_memcg(memcg, gfp_mask, nr_pages);
+		if (ret) {
+			mem_cgroup_put(memcg);
+			return false;
+		}
+
+		obj_cgroup_get(objcg);
+		page_set_objcg(page, objcg);
+	}
+
+	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
+	mod_lruvec_state(lruvec, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, nr_pages);
+
+	mem_cgroup_put(memcg);
+	return true;
+}
+EXPORT_SYMBOL_GPL(mem_cgroup_charge_gpu_page);
+
+/**
+ * mem_cgroup_uncharge_gpu_page - uncharge a page from GPU memory tracking
+ * @page: page to uncharge
+ * @order: order of the page allocation
+ * @reclaim: uncharge the reclaim counter instead of the active.
+ */
+void mem_cgroup_uncharge_gpu_page(struct page *page,
+				  unsigned int order, bool reclaim)
+{
+	struct obj_cgroup *objcg = page_objcg(page);
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+	int nr_pages = 1 << order;
+
+	memcg = objcg ? get_mem_cgroup_from_objcg(objcg) : NULL;
+
+	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
+	mod_lruvec_state(lruvec, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, -nr_pages);
+
+	if (memcg && !mem_cgroup_is_root(memcg))
+		refill_stock(memcg, nr_pages);
+	page->memcg_data = 0;
+	obj_cgroup_put(objcg);
+	mem_cgroup_put(memcg);
+}
+EXPORT_SYMBOL_GPL(mem_cgroup_uncharge_gpu_page);
+
+/**
+ * mem_cgroup_move_gpu_reclaim - move pages from gpu to gpu reclaim and back
+ * @new_objcg: objcg to move page to, NULL if just stats update.
+ * @nr_pages: number of pages to move
+ * @to_reclaim: true moves pages into reclaim, false moves them back
+ */
+bool mem_cgroup_move_gpu_page_reclaim(struct obj_cgroup *new_objcg,
+				      struct page *page,
+				      unsigned int order,
+				      bool to_reclaim)
+{
+	struct obj_cgroup *objcg = page_objcg(page);
+
+	if (!objcg || !new_objcg || objcg == new_objcg) {
+		struct mem_cgroup *memcg = objcg ? get_mem_cgroup_from_objcg(objcg) : NULL;
+		struct lruvec *lruvec;
+		unsigned long flags;
+		int nr_pages = 1 << order;
+
+		lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
+		local_irq_save(flags);
+		mod_lruvec_state(lruvec, to_reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE, nr_pages);
+		mod_lruvec_state(lruvec, to_reclaim ? NR_GPU_ACTIVE : NR_GPU_RECLAIM, -nr_pages);
+		local_irq_restore(flags);
+		mem_cgroup_put(memcg);
+		return true;
+	} else {
+		mem_cgroup_uncharge_gpu_page(page, order, true);
+		return mem_cgroup_charge_gpu_page(new_objcg, page, order, 0, false);
+	}
+}
+EXPORT_SYMBOL_GPL(mem_cgroup_move_gpu_page_reclaim);
+
 static int __init cgroup_memory(char *s)
 {
 	char *token;
-- 
2.52.0