mm: add gpu active/reclaim per-node stat counters (v2)

While discussing memcg intergration with gpu memory allocations,
it was pointed out that there was no numa/system counters for
GPU memory allocations.

With more integrated memory GPU server systems turning up, and
more requirements for memory tracking it seems we should start
closing the gap.

Add two counters to track GPU per-node system memory allocations.

The first is currently allocated to GPU objects, and the second
is for memory that is stored in GPU page pools that can be reclaimed,
by the shrinker.

Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

Author: airlied

Documentation/filesystems/proc.rst

@@ -1089,6 +1089,8 @@ Example output. You may not have all of these fields.
     CmaFree:               0 kB
     Unaccepted:            0 kB
     Balloon:               0 kB
+    GPUActive:             0 kB
+    GPUReclaim:            0 kB
     HugePages_Total:       0
     HugePages_Free:        0
     HugePages_Rsvd:        0
@@ -1269,6 +1271,12 @@ Unaccepted
               Memory that has not been accepted by the guest
 Balloon
               Memory returned to Host by VM Balloon Drivers
+GPUActive
+              System memory allocated to active GPU objects
+GPUReclaim
+              System memory stored in GPU pools for reuse. This memory is not
+              counted in GPUActive. It is shrinker reclaimable memory kept in a reuse
+              pool because it has non-standard page table attributes, like WC or UC.
 HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb
               See Documentation/admin-guide/mm/hugetlbpage.rst.
 DirectMap4k, DirectMap2M, DirectMap1G

drivers/base/node.c

@@ -523,6 +523,8 @@ static ssize_t node_read_meminfo(struct device *dev,
 #ifdef CONFIG_UNACCEPTED_MEMORY
 			     "Node %d Unaccepted:     %8lu kB\n"
 #endif
+			     "Node %d GPUActive:      %8lu kB\n"
+			     "Node %d GPUReclaim:     %8lu kB\n"
 			     ,
 			     nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
 			     nid, K(node_page_state(pgdat, NR_WRITEBACK)),
@@ -556,6 +558,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 			     ,
 			     nid, K(sum_zone_node_page_state(nid, NR_UNACCEPTED))
 #endif
+			     ,
+			     nid, K(node_page_state(pgdat, NR_GPU_ACTIVE)),
+			     nid, K(node_page_state(pgdat, NR_GPU_RECLAIM))
 			    );
 	len += hugetlb_report_node_meminfo(buf, len, nid);
 	return len;

fs/proc/meminfo.c

@@ -163,6 +163,12 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "Balloon:        ",
 		    global_node_page_state(NR_BALLOON_PAGES));
 
+	show_val_kb(m, "GPUActive:      ",
+		    global_node_page_state(NR_GPU_ACTIVE));
+
+	show_val_kb(m, "GPUReclaim:     ",
+		    global_node_page_state(NR_GPU_RECLAIM));
+
 	hugetlb_report_meminfo(m);
 
 	arch_report_meminfo(m);

include/linux/mmzone.h

@@ -260,6 +260,8 @@ enum node_stat_item {
 #endif
 	NR_BALLOON_PAGES,
 	NR_KERNEL_FILE_PAGES,
+	NR_GPU_ACTIVE,	/* Pages assigned to GPU objects */
+	NR_GPU_RECLAIM,	/* Pages in shrinkable GPU pools */
 	NR_VM_NODE_STAT_ITEMS
 };
 

mm/show_mem.c

@@ -254,6 +254,8 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 			" sec_pagetables:%lukB"
 			" all_unreclaimable? %s"
 			" Balloon:%lukB"
+			" gpu_active:%lukB"
+			" gpu_reclaim:%lukB"
 			"\n",
 			pgdat->node_id,
 			K(node_page_state(pgdat, NR_ACTIVE_ANON)),
@@ -279,7 +281,9 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 			K(node_page_state(pgdat, NR_PAGETABLE)),
 			K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
 			str_yes_no(kswapd_test_hopeless(pgdat)),
-			K(node_page_state(pgdat, NR_BALLOON_PAGES)));
+			K(node_page_state(pgdat, NR_BALLOON_PAGES)),
+			K(node_page_state(pgdat, NR_GPU_ACTIVE)),
+			K(node_page_state(pgdat, NR_GPU_RECLAIM)));
 	}
 
 	for_each_populated_zone(zone) {

mm/vmstat.c

@@ -1281,6 +1281,8 @@ const char * const vmstat_text[] = {
 #endif
 	[I(NR_BALLOON_PAGES)]			= "nr_balloon_pages",
 	[I(NR_KERNEL_FILE_PAGES)]		= "nr_kernel_file_pages",
+	[I(NR_GPU_ACTIVE)]			= "nr_gpu_active",
+	[I(NR_GPU_RECLAIM)]			= "nr_gpu_reclaim",
 #undef I
 
 	/* system-wide enum vm_stat_item counters */