[RFC PATCH v3 06/14] mm/vmscan, memcontrol: Add nodemask to try_to_free_mem_cgroup_pages

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.

Signed-off-by: Joshua Hahn <[email protected]>
---
 mm/internal.h      |  3 ++-
 mm/memcontrol-v1.c |  5 +++--
 mm/memcontrol.c    | 11 +++++++----
 mm/vmscan.c        | 10 +++++++---
 4 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index f47f06c555481..5f2f6a1757bd9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -84,7 +84,8 @@ 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,
+					   const nodemask_t *allowed);
 unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 				     gfp_t gfp_mask, bool noswap,
 				     pg_data_t *pgdat,
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 835fc8e511844..688896b59efe4 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -1815,7 +1815,8 @@ 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;
 		}
@@ -1851,7 +1852,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 			break;
 
 		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 defd04acfb3fd..6c67d9d2c9ac7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2397,7 +2397,7 @@ 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));
@@ -2710,7 +2710,8 @@ 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)
@@ -4946,7 +4947,8 @@ 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;
@@ -5007,7 +5009,8 @@ 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 17d2b793cbfc4..ffe7ea3c5aff6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6859,7 +6859,8 @@ 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,
+					   const nodemask_t *allowed)
 {
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
@@ -6875,6 +6876,7 @@ 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
@@ -6900,7 +6902,8 @@ 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,
+					   const nodemask_t *allowed)
 {
 	return 0;
 }
@@ -8033,7 +8036,8 @@ int user_proactive_reclaim(char *buf,
 			reclaimed = try_to_free_mem_cgroup_pages(memcg,
 						 batch_size, gfp_mask,
 						 reclaim_options,
-						 swappiness == -1 ? NULL : &swappiness);
+						 swappiness == -1 ? NULL : &swappiness,
+						 NULL);
 		} else {
 			struct scan_control sc = {
 				.gfp_mask = current_gfp_context(gfp_mask),
-- 
2.53.0-Meta