[RFC PATCH 6/9 v2] mm/vmscan, memcontrol: Add nodemask to try_to_free_mem_cgroup_pages

[Joshua Hahn]

Add a new nodemask parameter to try_to_free_mem_cgroup_pages to allow
selective reclaim on certain nodes. This new function signature can be
used in future patches to selectively perform reclaim on toptier and
place downward pressure when toptier limits are breached but memcg-wide
limits are not yet breached.

All callers pass NULL to the new nodemask, so there are no functional
changes with this patch.

Signed-off-by: Joshua Hahn <joshua.hahnjy@xxxxxxxxx>
---
 include/linux/swap.h |  3 ++-
 mm/memcontrol-v1.c   |  6 ++++--
 mm/memcontrol.c      | 11 +++++++----
 mm/vmscan.c          | 11 ++++++-----
 4 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 1930f81e6be4d..493dd99f3165a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -367,7 +367,8 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
 						  unsigned int reclaim_options,
-						  int *swappiness);
+						  int *swappiness,
+						  nodemask_t *allowed);
 extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 433bba9dfe715..03df1cc71842c 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -1500,7 +1500,8 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
 		}
 
 		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
-				memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, NULL)) {
+				memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP,
+				NULL, NULL)) {
 			ret = -EBUSY;
 			break;
 		}
@@ -1532,7 +1533,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 			return -EINTR;
 
 		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
-						  MEMCG_RECLAIM_MAY_SWAP, NULL))
+						  MEMCG_RECLAIM_MAY_SWAP,
+						  NULL, NULL))
 			nr_retries--;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3acb06388405c..3fb1ee1d18603 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2123,7 +2123,7 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg,
 		nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
 							gfp_mask,
 							MEMCG_RECLAIM_MAY_SWAP,
-							NULL);
+							NULL, NULL);
 		psi_memstall_leave(&pflags);
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
 		 !mem_cgroup_is_root(memcg));
@@ -2432,7 +2432,8 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	psi_memstall_enter(&pflags);
 	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
-						    gfp_mask, reclaim_options, NULL);
+						    gfp_mask, reclaim_options,
+						    NULL, NULL);
 	psi_memstall_leave(&pflags);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
@@ -4591,7 +4592,8 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 		}
 
 		reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
-					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL);
+					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
+					NULL, NULL);
 
 		if (!reclaimed && !nr_retries--)
 			break;
@@ -4651,7 +4653,8 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 
 		if (nr_reclaims) {
 			if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
-					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL))
+					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
+					NULL, NULL))
 				nr_reclaims--;
 			continue;
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5a8c8fcccbfc9..615aa0c899dad 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6807,7 +6807,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
 					   unsigned int reclaim_options,
-					   int *swappiness)
+					   int *swappiness, nodemask_t *allowed)
 {
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
@@ -6823,6 +6823,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.may_unmap = 1,
 		.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
 		.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
+		.nodemask = allowed,
 	};
 	/*
 	 * Traverse the ZONELIST_FALLBACK zonelist of the current node to put
@@ -6848,7 +6849,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
 					   unsigned int reclaim_options,
-					   int *swappiness)
+					   int *swappiness, nodemask_t *allowed)
 {
 	return 0;
 }
@@ -7964,9 +7965,9 @@ int user_proactive_reclaim(char *buf,
 			reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
 					  MEMCG_RECLAIM_PROACTIVE;
 			reclaimed = try_to_free_mem_cgroup_pages(memcg,
-						 batch_size, gfp_mask,
-						 reclaim_options,
-						 swappiness == -1 ? NULL : &swappiness);
+					batch_size, gfp_mask, reclaim_options,
+					swappiness == -1 ? NULL : &swappiness,
+					NULL);
 		} else {
 			struct scan_control sc = {
 				.gfp_mask = current_gfp_context(gfp_mask),
-- 
2.52.0