The patch titled
Subject: mm: memcontrol: do not account memory+swap on unified hierarchy
has been added to the -mm tree. Its filename is
mm-memcontrol-do-not-account-memoryswap-on-unified-hierarchy.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-memcontrol-do-not-account-memoryswap-on-unified-hierarchy.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-memcontrol-do-not-account-memoryswap-on-unified-hierarchy.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm: memcontrol: do not account memory+swap on unified hierarchy
The unified hierarchy memory controller doesn't expose the memory+swap
counter to userspace, but its accounting is hardcoded in all charge paths
right now, including the per-cpu charge cache ("the stock").
To avoid adding yet more pointless memory+swap accounting with the socket
memory support in unified hierarchy, disable the counter altogether when
in unified hierarchy mode.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Reviewed-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Acked-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 44 +++++++++++++++++++++++++-------------------
1 file changed, 25 insertions(+), 19 deletions(-)
diff -puN mm/memcontrol.c~mm-memcontrol-do-not-account-memoryswap-on-unified-hierarchy mm/memcontrol.c
--- a/mm/memcontrol.c~mm-memcontrol-do-not-account-memoryswap-on-unified-hierarchy
+++ a/mm/memcontrol.c
@@ -87,6 +87,12 @@ int do_swap_account __read_mostly;
#define do_swap_account 0
#endif
+/* Whether legacy memory+swap accounting is active */
+static bool do_memsw_account(void)
+{
+ return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account;
+}
+
static const char * const mem_cgroup_stat_names[] = {
"cache",
"rss",
@@ -1175,7 +1181,7 @@ static unsigned long mem_cgroup_margin(s
if (count < limit)
margin = limit - count;
- if (do_swap_account) {
+ if (do_memsw_account()) {
count = page_counter_read(&memcg->memsw);
limit = READ_ONCE(memcg->memsw.limit);
if (count <= limit)
@@ -1278,7 +1284,7 @@ void mem_cgroup_print_oom_info(struct me
pr_cont(":");
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
continue;
pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
K(mem_cgroup_read_stat(iter, i)));
@@ -1901,7 +1907,7 @@ static void drain_stock(struct memcg_sto
if (stock->nr_pages) {
page_counter_uncharge(&old->memory, stock->nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&old->memsw, stock->nr_pages);
css_put_many(&old->css, stock->nr_pages);
stock->nr_pages = 0;
@@ -2031,11 +2037,11 @@ retry:
if (consume_stock(memcg, nr_pages))
return 0;
- if (!do_swap_account ||
+ if (!do_memsw_account() ||
page_counter_try_charge(&memcg->memsw, batch, &counter)) {
if (page_counter_try_charge(&memcg->memory, batch, &counter))
goto done_restock;
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, batch);
mem_over_limit = mem_cgroup_from_counter(counter, memory);
} else {
@@ -2122,7 +2128,7 @@ force:
* temporarily by force charging it.
*/
page_counter_charge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_charge(&memcg->memsw, nr_pages);
css_get_many(&memcg->css, nr_pages);
@@ -2159,7 +2165,7 @@ static void cancel_charge(struct mem_cgr
return;
page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
css_put_many(&memcg->css, nr_pages);
@@ -2445,7 +2451,7 @@ void __memcg_kmem_uncharge(struct page *
page_counter_uncharge(&memcg->kmem, nr_pages);
page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
page->mem_cgroup = NULL;
@@ -3160,7 +3166,7 @@ static int memcg_stat_show(struct seq_fi
BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
continue;
seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
@@ -3182,14 +3188,14 @@ static int memcg_stat_show(struct seq_fi
}
seq_printf(m, "hierarchical_memory_limit %llu\n",
(u64)memory * PAGE_SIZE);
- if (do_swap_account)
+ if (do_memsw_account())
seq_printf(m, "hierarchical_memsw_limit %llu\n",
(u64)memsw * PAGE_SIZE);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
unsigned long long val = 0;
- if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
continue;
for_each_mem_cgroup_tree(mi, memcg)
val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
@@ -3320,7 +3326,7 @@ static void mem_cgroup_threshold(struct
{
while (memcg) {
__mem_cgroup_threshold(memcg, false);
- if (do_swap_account)
+ if (do_memsw_account())
__mem_cgroup_threshold(memcg, true);
memcg = parent_mem_cgroup(memcg);
@@ -4466,7 +4472,7 @@ static struct page *mc_handle_swap_pte(s
* we call find_get_page() with swapper_space directly.
*/
page = find_get_page(swap_address_space(ent), ent.val);
- if (do_swap_account)
+ if (do_memsw_account())
entry->val = ent.val;
return page;
@@ -4501,7 +4507,7 @@ static struct page *mc_handle_file_pte(s
page = find_get_entry(mapping, pgoff);
if (radix_tree_exceptional_entry(page)) {
swp_entry_t swp = radix_to_swp_entry(page);
- if (do_swap_account)
+ if (do_memsw_account())
*entry = swp;
page = find_get_page(swap_address_space(swp), swp.val);
}
@@ -5292,7 +5298,7 @@ int mem_cgroup_try_charge(struct page *p
if (page->mem_cgroup)
goto out;
- if (do_swap_account) {
+ if (do_memsw_account()) {
swp_entry_t ent = { .val = page_private(page), };
unsigned short id = lookup_swap_cgroup_id(ent);
@@ -5366,7 +5372,7 @@ void mem_cgroup_commit_charge(struct pag
memcg_check_events(memcg, page);
local_irq_enable();
- if (do_swap_account && PageSwapCache(page)) {
+ if (do_memsw_account() && PageSwapCache(page)) {
swp_entry_t entry = { .val = page_private(page) };
/*
* The swap entry might not get freed for a long time,
@@ -5415,7 +5421,7 @@ static void uncharge_batch(struct mem_cg
if (!mem_cgroup_is_root(memcg)) {
page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
memcg_oom_recover(memcg);
}
@@ -5623,7 +5629,7 @@ void mem_cgroup_swapout(struct page *pag
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(page_count(page), page);
- if (!do_swap_account)
+ if (!do_memsw_account())
return;
memcg = page->mem_cgroup;
@@ -5663,7 +5669,7 @@ void mem_cgroup_uncharge_swap(swp_entry_
struct mem_cgroup *memcg;
unsigned short id;
- if (!do_swap_account)
+ if (!do_memsw_account())
return;
id = swap_cgroup_record(entry, 0);
_
Patches currently in -mm which might be from hannes@xxxxxxxxxxx are
maintainers-make-vladimir-co-maintainer-of-the-memory-controller.patch
mm-page_alloc-generalize-the-dirty-balance-reserve.patch
proc-meminfo-estimate-available-memory-more-conservatively.patch
mm-memcontrol-export-root_mem_cgroup.patch
net-tcp_memcontrol-properly-detect-ancestor-socket-pressure.patch
net-tcp_memcontrol-remove-bogus-hierarchy-pressure-propagation.patch
net-tcp_memcontrol-protect-all-tcp_memcontrol-calls-by-jump-label.patch
net-tcp_memcontrol-remove-dead-per-memcg-count-of-allocated-sockets.patch
net-tcp_memcontrol-simplify-the-per-memcg-limit-access.patch
net-tcp_memcontrol-sanitize-tcp-memory-accounting-callbacks.patch
net-tcp_memcontrol-simplify-linkage-between-socket-and-page-counter.patch
mm-memcontrol-generalize-the-socket-accounting-jump-label.patch
mm-memcontrol-do-not-account-memoryswap-on-unified-hierarchy.patch
mm-memcontrol-move-socket-code-for-unified-hierarchy-accounting.patch
mm-memcontrol-account-socket-memory-in-unified-hierarchy-memory-controller.patch
mm-memcontrol-hook-up-vmpressure-to-socket-pressure.patch
mm-memcontrol-switch-to-the-updated-jump-label-api.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
