mm: memcontrol: charge swap to cgroup2
This patchset introduces swap accounting to cgroup2.
This patch (of 7):
In the legacy hierarchy we charge memsw, which is dubious, because:
- memsw.limit must be >= memory.limit, so it is impossible to limit
swap usage less than memory usage. Taking into account the fact that
the primary limiting mechanism in the unified hierarchy is
memory.high while memory.limit is either left unset or set to a very
large value, moving memsw.limit knob to the unified hierarchy would
effectively make it impossible to limit swap usage according to the
user preference.
- memsw.usage != memory.usage + swap.usage, because a page occupying
both swap entry and a swap cache page is charged only once to memsw
counter. As a result, it is possible to effectively eat up to
memory.limit of memory pages *and* memsw.limit of swap entries, which
looks unexpected.
That said, we should provide a different swap limiting mechanism for
cgroup2.
This patch adds mem_cgroup->swap counter, which charges the actual number
of swap entries used by a cgroup. It is only charged in the unified
hierarchy, while the legacy hierarchy memsw logic is left intact.
The swap usage can be monitored using new memory.swap.current file and
limited using memory.swap.max.
Note, to charge swap resource properly in the unified hierarchy, we have
to make swap_entry_free uncharge swap only when ->usage reaches zero, not
just ->count, i.e. when all references to a swap entry, including the one
taken by swap cache, are gone. This is necessary, because otherwise
swap-in could result in uncharging swap even if the page is still in swap
cache and hence still occupies a swap entry. At the same time, this
shouldn't break memsw counter logic, where a page is never charged twice
for using both memory and swap, because in case of legacy hierarchy we
uncharge swap on commit (see mem_cgroup_commit_charge).
Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f6bc78f..1ff552e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1220,7 +1220,7 @@
pr_cont(":");
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
+ if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
K(mem_cgroup_read_stat(iter, i)));
@@ -1259,9 +1259,12 @@
limit = memcg->memory.limit;
if (mem_cgroup_swappiness(memcg)) {
unsigned long memsw_limit;
+ unsigned long swap_limit;
memsw_limit = memcg->memsw.limit;
- limit = min(limit + total_swap_pages, memsw_limit);
+ swap_limit = memcg->swap.limit;
+ swap_limit = min(swap_limit, (unsigned long)total_swap_pages);
+ limit = min(limit + swap_limit, memsw_limit);
}
return limit;
}
@@ -4201,11 +4204,13 @@
if (parent && parent->use_hierarchy) {
memcg->use_hierarchy = true;
page_counter_init(&memcg->memory, &parent->memory);
+ page_counter_init(&memcg->swap, &parent->swap);
page_counter_init(&memcg->memsw, &parent->memsw);
page_counter_init(&memcg->kmem, &parent->kmem);
page_counter_init(&memcg->tcpmem, &parent->tcpmem);
} else {
page_counter_init(&memcg->memory, NULL);
+ page_counter_init(&memcg->swap, NULL);
page_counter_init(&memcg->memsw, NULL);
page_counter_init(&memcg->kmem, NULL);
page_counter_init(&memcg->tcpmem, NULL);
@@ -5224,7 +5229,7 @@
if (page->mem_cgroup)
goto out;
- if (do_memsw_account()) {
+ if (do_swap_account) {
swp_entry_t ent = { .val = page_private(page), };
unsigned short id = lookup_swap_cgroup_id(ent);
@@ -5677,26 +5682,66 @@
memcg_check_events(memcg, page);
}
+/*
+ * mem_cgroup_try_charge_swap - try charging a swap entry
+ * @page: page being added to swap
+ * @entry: swap entry to charge
+ *
+ * Try to charge @entry to the memcg that @page belongs to.
+ *
+ * Returns 0 on success, -ENOMEM on failure.
+ */
+int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+{
+ struct mem_cgroup *memcg;
+ struct page_counter *counter;
+ unsigned short oldid;
+
+ if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account)
+ return 0;
+
+ memcg = page->mem_cgroup;
+
+ /* Readahead page, never charged */
+ if (!memcg)
+ return 0;
+
+ if (!mem_cgroup_is_root(memcg) &&
+ !page_counter_try_charge(&memcg->swap, 1, &counter))
+ return -ENOMEM;
+
+ oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+ VM_BUG_ON_PAGE(oldid, page);
+ mem_cgroup_swap_statistics(memcg, true);
+
+ css_get(&memcg->css);
+ return 0;
+}
+
/**
* mem_cgroup_uncharge_swap - uncharge a swap entry
* @entry: swap entry to uncharge
*
- * Drop the memsw charge associated with @entry.
+ * Drop the swap charge associated with @entry.
*/
void mem_cgroup_uncharge_swap(swp_entry_t entry)
{
struct mem_cgroup *memcg;
unsigned short id;
- if (!do_memsw_account())
+ if (!do_swap_account)
return;
id = swap_cgroup_record(entry, 0);
rcu_read_lock();
memcg = mem_cgroup_from_id(id);
if (memcg) {
- if (!mem_cgroup_is_root(memcg))
- page_counter_uncharge(&memcg->memsw, 1);
+ if (!mem_cgroup_is_root(memcg)) {
+ if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+ page_counter_uncharge(&memcg->swap, 1);
+ else
+ page_counter_uncharge(&memcg->memsw, 1);
+ }
mem_cgroup_swap_statistics(memcg, false);
css_put(&memcg->css);
}
@@ -5720,6 +5765,63 @@
}
__setup("swapaccount=", enable_swap_account);
+static u64 swap_current_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+ return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE;
+}
+
+static int swap_max_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ unsigned long max = READ_ONCE(memcg->swap.limit);
+
+ if (max == PAGE_COUNTER_MAX)
+ seq_puts(m, "max\n");
+ else
+ seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
+
+ return 0;
+}
+
+static ssize_t swap_max_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+ unsigned long max;
+ int err;
+
+ buf = strstrip(buf);
+ err = page_counter_memparse(buf, "max", &max);
+ if (err)
+ return err;
+
+ mutex_lock(&memcg_limit_mutex);
+ err = page_counter_limit(&memcg->swap, max);
+ mutex_unlock(&memcg_limit_mutex);
+ if (err)
+ return err;
+
+ return nbytes;
+}
+
+static struct cftype swap_files[] = {
+ {
+ .name = "swap.current",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .read_u64 = swap_current_read,
+ },
+ {
+ .name = "swap.max",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = swap_max_show,
+ .write = swap_max_write,
+ },
+ { } /* terminate */
+};
+
static struct cftype memsw_cgroup_files[] = {
{
.name = "memsw.usage_in_bytes",
@@ -5751,6 +5853,8 @@
{
if (!mem_cgroup_disabled() && really_do_swap_account) {
do_swap_account = 1;
+ WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys,
+ swap_files));
WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys,
memsw_cgroup_files));
}