mm: memcg: add swapcache stat for memcg v2

This patch adds swapcache stat for the cgroup v2.  The swapcache
represents the memory that is accounted against both the memory and the
swap limit of the cgroup.  The main motivation behind exposing the
swapcache stat is for enabling users to gracefully migrate from cgroup
v1's memsw counter to cgroup v2's memory and swap counters.

Cgroup v1's memsw limit allows users to limit the memory+swap usage of a
workload but without control on the exact proportion of memory and swap.
Cgroup v2 provides separate limits for memory and swap which enables more
control on the exact usage of memory and swap individually for the
workload.

With some little subtleties, the v1's memsw limit can be switched with the
sum of the v2's memory and swap limits.  However the alternative for memsw
usage is not yet available in cgroup v2.  Exposing per-cgroup swapcache
stat enables that alternative.  Adding the memory usage and swap usage and
subtracting the swapcache will approximate the memsw usage.  This will
help in the transparent migration of the workloads depending on memsw
usage and limit to v2' memory and swap counters.

The reasons these applications are still interested in this approximate
memsw usage are: (1) these applications are not really interested in two
separate memory and swap usage metrics.  A single usage metric is more
simple to use and reason about for them.

(2) The memsw usage metric hides the underlying system's swap setup from
the applications.  Applications with multiple instances running in a
datacenter with heterogeneous systems (some have swap and some don't) will
keep seeing a consistent view of their usage.

[akpm@linux-foundation.org: fix CONFIG_SWAP=n build]

Link: https://lkml.kernel.org/r/20210108155813.2914586-3-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 32 insertions, 27 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index c513eafaddea..9acc57f68f31 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1299,6 +1299,10 @@ PAGE_SIZE multiple when read back.
 		Amount of cached filesystem data that was modified and
 		is currently being written back to disk
 
+	  swapcached
+		Amount of swap cached in memory. The swapcache is accounted
+		against both memory and swap usage.
+
 	  anon_thp
 		Amount of memory used in anonymous mappings backed by
 		transparent hugepages
diff --git a/drivers/base/node.c b/drivers/base/node.c
index d02d86aec19f..f449dbb2c746 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -372,14 +372,19 @@ static ssize_t node_read_meminfo(struct device *dev,
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct sysinfo i;
 	unsigned long sreclaimable, sunreclaimable;
+	unsigned long swapcached = 0;
 
 	si_meminfo_node(&i, nid);
 	sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B);
 	sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B);
+#ifdef CONFIG_SWAP
+	swapcached = node_page_state_pages(pgdat, NR_SWAPCACHE);
+#endif
 	len = sysfs_emit_at(buf, len,
 			    "Node %d MemTotal:       %8lu kB\n"
 			    "Node %d MemFree:        %8lu kB\n"
 			    "Node %d MemUsed:        %8lu kB\n"
+			    "Node %d SwapCached:     %8lu kB\n"
 			    "Node %d Active:         %8lu kB\n"
 			    "Node %d Inactive:       %8lu kB\n"
 			    "Node %d Active(anon):   %8lu kB\n"
@@ -391,6 +396,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 			    nid, K(i.totalram),
 			    nid, K(i.freeram),
 			    nid, K(i.totalram - i.freeram),
+			    nid, K(swapcached),
 			    nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) +
 				   node_page_state(pgdat, NR_ACTIVE_FILE)),
 			    nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) +
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 66d68e5d5a0f..fc99e9241846 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,6 +206,9 @@ enum node_stat_item {
 	NR_KERNEL_SCS_KB,	/* measured in KiB */
 #endif
 	NR_PAGETABLE,		/* used for pagetables */
+#ifdef CONFIG_SWAP
+	NR_SWAPCACHE,
+#endif
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3f1f7ae0fbe9..0d64a2bc7e00 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -408,7 +408,11 @@ extern struct address_space *swapper_spaces[];
 #define swap_address_space(entry)			    \
 	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
 		>> SWAP_ADDRESS_SPACE_SHIFT])
-extern unsigned long total_swapcache_pages(void);
+static inline unsigned long total_swapcache_pages(void)
+{
+	return global_node_page_state(NR_SWAPCACHE);
+}
+
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
 extern void *get_shadow_from_swap_cache(swp_entry_t entry);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5435b370c929..58edfb6614b8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1521,6 +1521,9 @@ static const struct memory_stat memory_stats[] = {
 	{ "file_mapped",		NR_FILE_MAPPED			},
 	{ "file_dirty",			NR_FILE_DIRTY			},
 	{ "file_writeback",		NR_WRITEBACK			},
+#ifdef CONFIG_SWAP
+	{ "swapcached",			NR_SWAPCACHE			},
+#endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	{ "anon_thp",			NR_ANON_THPS			},
 	{ "file_thp",			NR_FILE_THPS			},
diff --git a/mm/migrate.c b/mm/migrate.c
index 4ec727adfaa2..62b81d5257aa 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -500,6 +500,12 @@ int migrate_page_move_mapping(struct address_space *mapping,
 			__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
 			__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
 		}
+#ifdef CONFIG_SWAP
+		if (PageSwapCache(page)) {
+			__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
+			__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
+		}
+#endif
 		if (dirty && mapping_can_writeback(mapping)) {
 			__mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr);
 			__mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 807b00eae969..c1a648d9092b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -68,32 +68,6 @@ static struct {
 	unsigned long find_total;
 } swap_cache_info;
 
-unsigned long total_swapcache_pages(void)
-{
-	unsigned int i, j, nr;
-	unsigned long ret = 0;
-	struct address_space *spaces;
-	struct swap_info_struct *si;
-
-	for (i = 0; i < MAX_SWAPFILES; i++) {
-		swp_entry_t entry = swp_entry(i, 1);
-
-		/* Avoid get_swap_device() to warn for bad swap entry */
-		if (!swp_swap_info(entry))
-			continue;
-		/* Prevent swapoff to free swapper_spaces */
-		si = get_swap_device(entry);
-		if (!si)
-			continue;
-		nr = nr_swapper_spaces[i];
-		spaces = swapper_spaces[i];
-		for (j = 0; j < nr; j++)
-			ret += spaces[j].nrpages;
-		put_swap_device(si);
-	}
-	return ret;
-}
-
 static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
 
 void show_swap_cache_info(void)
@@ -163,6 +137,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry,
 		address_space->nrexceptional -= nr_shadows;
 		address_space->nrpages += nr;
 		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
+		__mod_lruvec_page_state(page, NR_SWAPCACHE, nr);
 		ADD_CACHE_INFO(add_total, nr);
 unlock:
 		xas_unlock_irq(&xas);
@@ -203,6 +178,7 @@ void __delete_from_swap_cache(struct page *page,
 		address_space->nrexceptional += nr;
 	address_space->nrpages -= nr;
 	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+	__mod_lruvec_page_state(page, NR_SWAPCACHE, -nr);
 	ADD_CACHE_INFO(del_total, nr);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 07dc0af50cf0..a0e949542204 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1215,6 +1215,9 @@ const char * const vmstat_text[] = {
 	"nr_shadow_call_stack",
 #endif
 	"nr_page_table_pages",
+#ifdef CONFIG_SWAP
+	"nr_swapcached",
+#endif
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",