From: Dave Airlie <[email protected]> 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 <[email protected]> Cc: Matthew Brost <[email protected]> Cc: Johannes Weiner <[email protected]> Cc: [email protected] Cc: Andrew Morton <[email protected]> Acked-by: Zi Yan <[email protected]> Acked-by: Shakeel Butt <[email protected]> Acked-by: Andrew Morton <[email protected]> Signed-off-by: Dave Airlie <[email protected]> --- v2: add more info to the documentation on this memory. I'd like to get acks to merge this via the drm tree, if possible, Dave. --- Documentation/filesystems/proc.rst | 8 ++++++++ drivers/base/node.c | 5 +++++ fs/proc/meminfo.c | 6 ++++++ include/linux/mmzone.h | 2 ++ mm/show_mem.c | 9 +++++++-- mm/vmstat.c | 2 ++ 6 files changed, 30 insertions(+), 2 deletions(-) diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 2971551b7235..ae0aad28fe7d 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -1095,6 +1095,8 @@ 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 @@ -1275,6 +1277,12 @@ 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 diff --git a/drivers/base/node.c b/drivers/base/node.c index 3399594136b2..b2fa9d55666d 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -485,6 +485,8 @@ 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)), @@ -518,6 +520,9 @@ 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; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index a458f1e112fd..65ba49ec3a63 100644 --- a/fs/proc/meminfo.c +++ b/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); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c5da9141983..12f1b872f40f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -245,6 +245,8 @@ enum node_stat_item { NR_HUGETLB, #endif NR_BALLOON_PAGES, + NR_GPU_ACTIVE, /* Pages assigned to GPU objects */ + NR_GPU_RECLAIM, /* Pages in shrinkable GPU pools */ NR_VM_NODE_STAT_ITEMS }; diff --git a/mm/show_mem.c b/mm/show_mem.c index 41999e94a56d..e63cc4e0f419 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -254,7 +254,9 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z " sec_pagetables:%lukB" " all_unreclaimable? %s" " Balloon:%lukB" - "\n", + " gpu_active:%lukB" + " gpu_reclaim:%lukB" + "\n", pgdat->node_id, K(node_page_state(pgdat, NR_ACTIVE_ANON)), K(node_page_state(pgdat, NR_INACTIVE_ANON)), @@ -279,7 +281,10 @@ 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(pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES), - 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) { diff --git a/mm/vmstat.c b/mm/vmstat.c index 71cd1ceba191..8c95b731e723 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1289,6 +1289,8 @@ const char * const vmstat_text[] = { [I(NR_HUGETLB)] = "nr_hugetlb", #endif [I(NR_BALLOON_PAGES)] = "nr_balloon_pages", + [I(NR_GPU_ACTIVE)] = "nr_gpu_active", + [I(NR_GPU_RECLAIM)] = "nr_gpu_reclaim", #undef I /* system-wide enum vm_stat_item counters */ -- 2.50.1
