mm/vmpressure: move v1 userspace eventfd code into memcontrol-v1.c

Clean up mm/vmpressure.c by separating the cgroup v1 userspace eventfd
interface from the shared and v2 in-kernel code.

Currently, almost half of mm/vmpressure.c exists to serve tree=true:
struct vmpressure_event, the events list and its mutex, the work_struct
and vmpressure_work_fn that drains tree_scanned/tree_reclaimed, the parent
walk, vmpressure_event(), vmpressure_register_event(),
vmpressure_unregister_event(), and vmpressure_prio() (which always calls
vmpressure() with tree=true).

Move it all into mm/memcontrol-v1.c (built only when CONFIG_MEMCG_V1=y) as
a single contiguous block, following the per-component layout already used
by that file.  Keeping the v1 vmpressure code with the rest of the
deprecated cgroup v1 memory controller makes the full footprint of the
CONFIG_MEMCG_V1 option easy to see in one place, which matters more than
component-level file separation for code that has no active development.

vmpressure.c keeps the shared bits (constants, vmpressure_calc_level, the
runtime hierarchy check, the tree=false body, init/cleanup plumbing) and
calls into three small v1 hooks for the tree=true accumulator and the v1
portions of init/cleanup.  The hooks have static-inline no-op stubs in
include/linux/vmpressure.h for the !MEMCG_V1 case, so callers don't need
ifdefs.  vmpressure_prio() gets the same treatment, which means vmscan.c's
call site disappears at compile time on v2-only kernels.

The only #ifdef CONFIG_MEMCG_V1 in source remains around the v1-only
fields inside struct vmpressure itself.

Memory savings on CONFIG_MEMCG_V1=n (measured with pahole):

  struct vmpressure :  112B ->   24B
  struct mem_cgroup : 1664B -> 1536B

This split is the first step toward eventually making vmpressure
CONFIG_MEMCG_V1 only.  The v2 in-kernel socket pressure path (tree=false)
cannot be removed today immediately: PSI is not an exact replacement for
vmpressure, and switching networking socket-buffer back-off to PSI may
regress networking performance or increase memory pressure in workloads
that today rely on vmpressure's hysteresis.  The medium-term plan is to
introduce a PSI-based socket-pressure path, keep vmpressure available for
v2 behind a defconfig as an opt-out for several releases, and only then
drop the tree=false path entirely, at which point everything that remains
of the vmpressure block in mm/memcontrol-v1.c is the whole subsystem.

Link: https://lore.kernel.org/20260630112617.1198623-3-usama.arif@linux.dev
Signed-off-by: Usama Arif <usama.arif@linux.dev>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: David Hildenbrand <david@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 41 insertions, 5 deletions

diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h
index faecd5522401..b4d13457bc2a 100644
--- a/include/linux/vmpressure.h
+++ b/include/linux/vmpressure.h
@@ -13,18 +13,31 @@
 struct vmpressure {
 	unsigned long scanned;
 	unsigned long reclaimed;
+	/* The lock is used to keep the scanned/reclaimed in sync. */
+	spinlock_t sr_lock;
 
+#ifdef CONFIG_MEMCG_V1
+	/*
+	 * tree=true accumulators feed the v1 userspace eventfd interface
+	 * (memory.pressure_level). Drained by @work. v2 has no equivalent
+	 * interface, so this state is omitted on CONFIG_MEMCG_V1=n builds.
+	 */
 	unsigned long tree_scanned;
 	unsigned long tree_reclaimed;
-	/* The lock is used to keep the scanned/reclaimed above in sync. */
-	spinlock_t sr_lock;
-
 	/* The list of vmpressure_event structs. */
 	struct list_head events;
 	/* Have to grab the lock on events traversal or modifications. */
 	struct mutex events_lock;
 
 	struct work_struct work;
+#endif
+};
+
+enum vmpressure_levels {
+	VMPRESSURE_LOW = 0,
+	VMPRESSURE_MEDIUM,
+	VMPRESSURE_CRITICAL,
+	VMPRESSURE_NUM_LEVELS,
 };
 
 struct mem_cgroup;
@@ -32,18 +45,41 @@ struct mem_cgroup;
 #ifdef CONFIG_MEMCG
 void vmpressure(gfp_t gfp, int order, struct mem_cgroup *memcg, bool tree,
 		unsigned long scanned, unsigned long reclaimed);
-extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio);
-
 extern void vmpressure_init(struct vmpressure *vmpr);
 extern void vmpressure_cleanup(struct vmpressure *vmpr);
 extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg);
 extern struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr);
+
+/* Shared with the v1 vmpressure block in mm/memcontrol-v1.c. */
+extern const unsigned long vmpressure_win;
+extern enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
+						    unsigned long reclaimed);
+
+#ifdef CONFIG_MEMCG_V1
+extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio);
 extern int vmpressure_register_event(struct mem_cgroup *memcg,
 				     struct eventfd_ctx *eventfd,
 				     const char *args);
 extern void vmpressure_unregister_event(struct mem_cgroup *memcg,
 					struct eventfd_ctx *eventfd);
+
+/* v1 hooks called from mm/vmpressure.c; no-ops below when !MEMCG_V1. */
+extern void vmpressure_v1_init(struct vmpressure *vmpr);
+extern void vmpressure_v1_cleanup(struct vmpressure *vmpr);
+extern void vmpressure_v1_account_tree(struct vmpressure *vmpr,
+				       unsigned long scanned,
+				       unsigned long reclaimed);
 #else
+static inline void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg,
+				   int prio) {}
+static inline void vmpressure_v1_init(struct vmpressure *vmpr) {}
+static inline void vmpressure_v1_cleanup(struct vmpressure *vmpr) {}
+static inline void vmpressure_v1_account_tree(struct vmpressure *vmpr,
+					      unsigned long scanned,
+					      unsigned long reclaimed) {}
+#endif /* CONFIG_MEMCG_V1 */
+
+#else /* !CONFIG_MEMCG */
 static inline void vmpressure(gfp_t gfp, int order, struct mem_cgroup *memcg,
 			      bool tree, unsigned long scanned,
 			      unsigned long reclaimed) {}