mm: vmpressure: don't count proactive reclaim in vmpressure

memory.reclaim is a cgroup v2 interface that allows users to proactively
reclaim memory from a memcg, without real memory pressure.  Reclaim
operations invoke vmpressure, which is used: (a) To notify userspace of
reclaim efficiency in cgroup v1, and (b) As a signal for a memcg being
under memory pressure for networking (see
mem_cgroup_under_socket_pressure()).

For (a), vmpressure notifications in v1 are not affected by this change
since memory.reclaim is a v2 feature.

For (b), the effects of the vmpressure signal (according to Shakeel [1])
are as follows:
1. Reducing send and receive buffers of the current socket.
2. May drop packets on the rx path.
3. May throttle current thread on the tx path.

Since proactive reclaim is invoked directly by userspace, not by memory
pressure, it makes sense not to throttle networking.  Hence, this change
makes sure that proactive reclaim caused by memory.reclaim does not
trigger vmpressure.

[1] https://lore.kernel.org/lkml/CALvZod68WdrXEmBpOkadhB5GPYmCXaDZzXH=yyGOCAjFRn4NDQ@mail.gmail.com/

[yosryahmed@google.com: update documentation]
  Link: https://lkml.kernel.org/r/20220721173015.2643248-1-yosryahmed@google.com
Link: https://lkml.kernel.org/r/20220714064918.2576464-1-yosryahmed@google.comSigned-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Documentation/admin-guide/cgroup-v2.rst

@@ -1229,6 +1229,13 @@ PAGE_SIZE multiple when read back.
 	the target cgroup. If less bytes are reclaimed than the
 	specified amount, -EAGAIN is returned.
 
+	Please note that the proactive reclaim (triggered by this
+	interface) is not meant to indicate memory pressure on the
+	memory cgroup. Therefore socket memory balancing triggered by
+	the memory reclaim normally is not exercised in this case.
+	This means that the networking layer will not adapt based on
+	reclaim induced by memory.reclaim.
+
   memory.peak
 	A read-only single value file which exists on non-root
 	cgroups.

include/linux/swap.h

@@ -411,10 +411,13 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
+
+#define MEMCG_RECLAIM_MAY_SWAP (1 << 1)
+#define MEMCG_RECLAIM_PROACTIVE (1 << 2)
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
-						  bool may_swap);
+						  unsigned int reclaim_options);
 extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,

mm/memcontrol.c

@@ -2330,7 +2330,8 @@ 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, true);
+							gfp_mask,
+							MEMCG_RECLAIM_MAY_SWAP);
 		psi_memstall_leave(&pflags);
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
 		 !mem_cgroup_is_root(memcg));
@@ -2575,7 +2576,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	struct page_counter *counter;
 	unsigned long nr_reclaimed;
 	bool passed_oom = false;
-	bool may_swap = true;
+	unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP;
 	bool drained = false;
 	bool raised_max_event = false;
 	unsigned long pflags;
@@ -2593,7 +2594,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		mem_over_limit = mem_cgroup_from_counter(counter, memory);
 	} else {
 		mem_over_limit = mem_cgroup_from_counter(counter, memsw);
-		may_swap = false;
+		reclaim_options &= ~MEMCG_RECLAIM_MAY_SWAP;
 	}
 
 	if (batch > nr_pages) {
@@ -2621,7 +2622,7 @@ 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, may_swap);
+						    gfp_mask, reclaim_options);
 	psi_memstall_leave(&pflags);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
@@ -3439,8 +3440,8 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
 			continue;
 		}
 
-		if (!try_to_free_mem_cgroup_pages(memcg, 1,
-					GFP_KERNEL, !memsw)) {
+		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
+					memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) {
 			ret = -EBUSY;
 			break;
 		}
@@ -3550,7 +3551,8 @@ 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, true))
+		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
+						  MEMCG_RECLAIM_MAY_SWAP))
 			nr_retries--;
 	}
 
@@ -6302,7 +6304,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 		}
 
 		reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
-							 GFP_KERNEL, true);
+					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP);
 
 		if (!reclaimed && !nr_retries--)
 			break;
@@ -6351,7 +6353,7 @@ 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, true))
+					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP))
 				nr_reclaims--;
 			continue;
 		}
@@ -6480,6 +6482,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
 	unsigned long nr_to_reclaim, nr_reclaimed = 0;
+	unsigned int reclaim_options;
 	int err;
 
 	buf = strstrip(buf);
@@ -6487,6 +6490,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
 	if (err)
 		return err;
 
+	reclaim_options	= MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
 	while (nr_reclaimed < nr_to_reclaim) {
 		unsigned long reclaimed;
 
@@ -6503,7 +6507,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
 
 		reclaimed = try_to_free_mem_cgroup_pages(memcg,
 						nr_to_reclaim - nr_reclaimed,
-						GFP_KERNEL, true);
+						GFP_KERNEL, reclaim_options);
 
 		if (!reclaimed && !nr_retries--)
 			return -EAGAIN;

mm/vmscan.c

@@ -101,6 +101,9 @@ struct scan_control {
 	/* Can pages be swapped as part of reclaim? */
 	unsigned int may_swap:1;
 
+	/* Proactive reclaim invoked by userspace through memory.reclaim */
+	unsigned int proactive:1;
+
 	/*
 	 * Cgroup memory below memory.low is protected as long as we
 	 * don't threaten to OOM. If any cgroup is reclaimed at
@@ -3180,9 +3183,10 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 			    sc->priority);
 
 		/* Record the group's reclaim efficiency */
-		vmpressure(sc->gfp_mask, memcg, false,
-			   sc->nr_scanned - scanned,
-			   sc->nr_reclaimed - reclaimed);
+		if (!sc->proactive)
+			vmpressure(sc->gfp_mask, memcg, false,
+				   sc->nr_scanned - scanned,
+				   sc->nr_reclaimed - reclaimed);
 
 	} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
 }
@@ -3305,9 +3309,10 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	}
 
 	/* Record the subtree's reclaim efficiency */
-	vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
-		   sc->nr_scanned - nr_scanned,
-		   sc->nr_reclaimed - nr_reclaimed);
+	if (!sc->proactive)
+		vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
+			   sc->nr_scanned - nr_scanned,
+			   sc->nr_reclaimed - nr_reclaimed);
 
 	if (sc->nr_reclaimed - nr_reclaimed)
 		reclaimable = true;
@@ -3589,8 +3594,9 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
 
 	do {
-		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
-				sc->priority);
+		if (!sc->proactive)
+			vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
+					sc->priority);
 		sc->nr_scanned = 0;
 		shrink_zones(zonelist, sc);
 
@@ -3880,7 +3886,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
-					   bool may_swap)
+					   unsigned int reclaim_options)
 {
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
@@ -3893,7 +3899,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.priority = DEF_PRIORITY,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
-		.may_swap = may_swap,
+		.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
+		.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
 	};
 	/*
 	 * Traverse the ZONELIST_FALLBACK zonelist of the current node to put