1 files changed, 105 insertions, 3 deletions
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index 2be6b9112808..8660908850dc 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -490,6 +490,19 @@ static void mem_cgroup_threshold(struct mem_cgroup *memcg)
 }
 
 /* Cgroup1: threshold notifications & softlimit tree updates */
+
+/*
+ * Per memcg event counter is incremented at every pagein/pageout. With THP,
+ * it will be incremented by the number of pages. This counter is used
+ * to trigger some periodic events. This is straightforward and better
+ * than using jiffies etc. to handle periodic memcg event.
+ */
+enum mem_cgroup_events_target {
+	MEM_CGROUP_TARGET_THRESH,
+	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_NTARGETS,
+};
+
 struct memcg1_events_percpu {
 	unsigned long nr_page_events;
 	unsigned long targets[MEM_CGROUP_NTARGETS];
@@ -568,8 +581,59 @@ void memcg1_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 	local_irq_restore(flags);
 }
 
-void memcg1_swapout(struct folio *folio, struct mem_cgroup *memcg)
+/**
+ * memcg1_swapout - transfer a memsw charge to swap
+ * @folio: folio whose memsw charge to transfer
+ * @entry: swap entry to move the charge to
+ *
+ * Transfer the memsw charge of @folio to @entry.
+ */
+void memcg1_swapout(struct folio *folio, swp_entry_t entry)
 {
+	struct mem_cgroup *memcg, *swap_memcg;
+	unsigned int nr_entries;
+
+	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
+	VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
+
+	if (mem_cgroup_disabled())
+		return;
+
+	if (!do_memsw_account())
+		return;
+
+	memcg = folio_memcg(folio);
+
+	VM_WARN_ON_ONCE_FOLIO(!memcg, folio);
+	if (!memcg)
+		return;
+
+	/*
+	 * In case the memcg owning these pages has been offlined and doesn't
+	 * have an ID allocated to it anymore, charge the closest online
+	 * ancestor for the swap instead and transfer the memory+swap charge.
+	 */
+	swap_memcg = mem_cgroup_id_get_online(memcg);
+	nr_entries = folio_nr_pages(folio);
+	/* Get references for the tail pages, too */
+	if (nr_entries > 1)
+		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
+	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
+
+	swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
+
+	folio_unqueue_deferred_split(folio);
+	folio->memcg_data = 0;
+
+	if (!mem_cgroup_is_root(memcg))
+		page_counter_uncharge(&memcg->memory, nr_entries);
+
+	if (memcg != swap_memcg) {
+		if (!mem_cgroup_is_root(swap_memcg))
+			page_counter_charge(&swap_memcg->memsw, nr_entries);
+		page_counter_uncharge(&memcg->memsw, nr_entries);
+	}
+
 	/*
 	 * Interrupts should be disabled here because the caller holds the
 	 * i_pages lock which is taken with interrupts-off. It is
@@ -581,6 +645,42 @@ void memcg1_swapout(struct folio *folio, struct mem_cgroup *memcg)
 	memcg1_charge_statistics(memcg, -folio_nr_pages(folio));
 	preempt_enable_nested();
 	memcg1_check_events(memcg, folio_nid(folio));
+
+	css_put(&memcg->css);
+}
+
+/*
+ * memcg1_swapin - uncharge swap slot
+ * @entry: the first swap entry for which the pages are charged
+ * @nr_pages: number of pages which will be uncharged
+ *
+ * Call this function after successfully adding the charged page to swapcache.
+ *
+ * Note: This function assumes the page for which swap slot is being uncharged
+ * is order 0 page.
+ */
+void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages)
+{
+	/*
+	 * Cgroup1's unified memory+swap counter has been charged with the
+	 * new swapcache page, finish the transfer by uncharging the swap
+	 * slot. The swap slot would also get uncharged when it dies, but
+	 * it can stick around indefinitely and we'd count the page twice
+	 * the entire time.
+	 *
+	 * Cgroup2 has separate resource counters for memory and swap,
+	 * so this is a non-issue here. Memory and swap charge lifetimes
+	 * correspond 1:1 to page and swap slot lifetimes: we charge the
+	 * page to memory here, and uncharge swap when the slot is freed.
+	 */
+	if (do_memsw_account()) {
+		/*
+		 * The swap entry might not get freed for a long time,
+		 * let's not wait for it.  The page already received a
+		 * memory+swap charge, drop the swap entry duplicate.
+		 */
+		mem_cgroup_uncharge_swap(entry, nr_pages);
+	}
 }
 
 void memcg1_uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
@@ -1855,9 +1955,11 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 	if (val > MAX_SWAPPINESS)
 		return -EINVAL;
 
-	if (!mem_cgroup_is_root(memcg))
+	if (!mem_cgroup_is_root(memcg)) {
+		pr_info_once("Per memcg swappiness does not exist in cgroup v2. "
+			     "See memory.reclaim or memory.swap.max there\n ");
 		WRITE_ONCE(memcg->swappiness, val);
-	else
+	} else
 		WRITE_ONCE(vm_swappiness, val);
 
 	return 0;