mm: memcg supports freeing the specified zone's memory

Commit Message

Zhiguo Jiang Jan. 16, 2025, 2:22 p.m. UTC

Currently, the try_to_free_mem_cgroup_pages interface releases the
memory occupied by the memcg, which defaults to all zones in the system.
However, for multi zone systems, such as when there are both movable zone
and normal zone, it is not possible to release memory that is only in
the normal zone.

This patch is used to implement the try_to_free_mem_cgroup_pages interface
to support for releasing the specified zone's memory occupied by the
memcg in a multi zone systems, in order to optimize the memory usage of
multiple zones.

Signed-off-by: Zhiguo Jiang <[e-mail]>
---
 mm/memcontrol-v1.c |  4 ++--
 mm/memcontrol.c    | 11 ++++++-----
 mm/vmscan.c        |  4 ++--
 3 files changed, 10 insertions(+), 9 deletions(-)

Comments

Michal Hocko Jan. 16, 2025, 2:36 p.m. UTC | #1

On Thu 16-01-25 22:22:42, Zhiguo Jiang wrote:
> Currently, the try_to_free_mem_cgroup_pages interface releases the
> memory occupied by the memcg, which defaults to all zones in the system.
> However, for multi zone systems, such as when there are both movable zone
> and normal zone, it is not possible to release memory that is only in
> the normal zone.
> 
> This patch is used to implement the try_to_free_mem_cgroup_pages interface
> to support for releasing the specified zone's memory occupied by the
> memcg in a multi zone systems, in order to optimize the memory usage of
> multiple zones.

Could you elaborate more on the actual usecase please? Who is going to
control which zone to reclaim from, how and why?

Patch

diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 2be6b9112808..9dc398e9d5f9
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -1377,7 +1377,7 @@  static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
 			continue;
 		}
 
-		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
+		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_HIGHUSER_MOVABLE,
 				memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, NULL)) {
 			ret = -EBUSY;
 			break;
@@ -1409,7 +1409,7 @@  static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 		if (signal_pending(current))
 			return -EINTR;
 
-		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
+		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_HIGHUSER_MOVABLE,
 						  MEMCG_RECLAIM_MAY_SWAP, NULL))
 			nr_retries--;
 	}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 46f8b372d212..e0b92edb2f3e
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1945,7 +1945,7 @@  static unsigned long reclaim_high(struct mem_cgroup *memcg,
 
 		psi_memstall_enter(&pflags);
 		nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
-							gfp_mask,
+							gfp_mask | __GFP_MOVABLE | __GFP_HIGHMEM,
 							MEMCG_RECLAIM_MAY_SWAP,
 							NULL);
 		psi_memstall_leave(&pflags);
@@ -2253,7 +2253,8 @@  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 | __GFP_MOVABLE | __GFP_HIGHMEM,
+						    reclaim_options, NULL);
 	psi_memstall_leave(&pflags);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
@@ -4109,7 +4110,7 @@  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_HIGHUSER_MOVABLE, MEMCG_RECLAIM_MAY_SWAP, NULL);
 
 		if (!reclaimed && !nr_retries--)
 			break;
@@ -4158,7 +4159,7 @@  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_HIGHUSER_MOVABLE, MEMCG_RECLAIM_MAY_SWAP, NULL))
 				nr_reclaims--;
 			continue;
 		}
@@ -4351,7 +4352,7 @@  static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
 			lru_add_drain_all();
 
 		reclaimed = try_to_free_mem_cgroup_pages(memcg,
-					batch_size, GFP_KERNEL,
+					batch_size, GFP_HIGHUSER_MOVABLE,
 					reclaim_options,
 					swappiness == -1 ? NULL : &swappiness);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5b626b4f38af..9d198bc4e543
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6610,8 +6610,8 @@  unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.proactive_swappiness = swappiness,
 		.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
-				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
-		.reclaim_idx = MAX_NR_ZONES - 1,
+				(gfp_mask & (__GFP_MOVABLE | __GFP_HIGHMEM)),
+		.reclaim_idx = gfp_zone(gfp_mask),
 		.target_mem_cgroup = memcg,
 		.priority = DEF_PRIORITY,
 		.may_writepage = !laptop_mode,