The patch titled Subject: memcg: do not create memsw files if swap accounting is disabled has been added to the -mm tree. Its filename is memcg-do-not-create-memsw-files-if-swap-accounting-is-disabled.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: Michal Hocko <mhocko@xxxxxxx> Subject: memcg: do not create memsw files if swap accounting is disabled Zhouping Liu has reported that memsw files are exported even though swap accounting is runtime disabled if CONFIG_MEMCG_SWAP is enabled. This behavior has been introduced by af36f906 (memcg: always create memsw files if CONFIG_CGROUP_MEM_RES_CTLR_SWAP) and it causes any attempt to open the file to return EOPNOTSUPP. Although EOPNOTSUPP should say be clear that memsw operations are not supported in the given configuration it is fair to say that this behavior could be quite confusing. Let's tear memsw files out of default cgroup files and add them only if the swap accounting is really enabled (either by CONFIG_MEMCG_SWAP_ENABLED or swapaccount=1 boot parameter). We can hook into mem_cgroup_init which is called when the memcg subsystem is initialized and which happens after boot command line is processed. Signed-off-by: Michal Hocko <mhocko@xxxxxxx> Reported-by: Zhouping Liu <zliu@xxxxxxxxxx> Tested-by: Zhouping Liu <zliu@xxxxxxxxxx> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Li Zefan <lizefan@xxxxxxxxxx> Cc: CAI Qian <caiqian@xxxxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/memcontrol.c | 94 ++++++++++++++++++++++++++-------------------- 1 file changed, 54 insertions(+), 40 deletions(-) diff -puN mm/memcontrol.c~memcg-do-not-create-memsw-files-if-swap-accounting-is-disabled mm/memcontrol.c --- a/mm/memcontrol.c~memcg-do-not-create-memsw-files-if-swap-accounting-is-disabled +++ a/mm/memcontrol.c @@ -5821,33 +5821,6 @@ static struct cftype mem_cgroup_files[] .read_seq_string = memcg_numa_stat_show, }, #endif -#ifdef CONFIG_MEMCG_SWAP - { - .name = "memsw.usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), - .read = mem_cgroup_read, - .register_event = mem_cgroup_usage_register_event, - .unregister_event = mem_cgroup_usage_unregister_event, - }, - { - .name = "memsw.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, - }, - { - .name = "memsw.limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write_string = mem_cgroup_write, - .read = mem_cgroup_read, - }, - { - .name = "memsw.failcnt", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .trigger = mem_cgroup_reset, - .read = mem_cgroup_read, - }, -#endif #ifdef CONFIG_MEMCG_KMEM { .name = "kmem.limit_in_bytes", @@ -5882,6 +5855,36 @@ static struct cftype mem_cgroup_files[] { }, /* terminate */ }; +#ifdef CONFIG_MEMCG_SWAP +static struct cftype memsw_cgroup_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read = mem_cgroup_read, + .register_event = mem_cgroup_usage_register_event, + .unregister_event = mem_cgroup_usage_unregister_event, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .trigger = mem_cgroup_reset, + .read = mem_cgroup_read, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write_string = mem_cgroup_write, + .read = mem_cgroup_read, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .trigger = mem_cgroup_reset, + .read = mem_cgroup_read, + }, + { }, /* terminate */ +}; +#endif static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -6781,19 +6784,6 @@ struct cgroup_subsys mem_cgroup_subsys = .use_id = 1, }; -/* - * The rest of init is performed during ->css_alloc() for root css which - * happens before initcalls. hotcpu_notifier() can't be done together as - * it would introduce circular locking by adding cgroup_lock -> cpu hotplug - * dependency. Do it from a subsys_initcall(). - */ -static int __init mem_cgroup_init(void) -{ - hotcpu_notifier(memcg_cpu_hotplug_callback, 0); - return 0; -} -subsys_initcall(mem_cgroup_init); - #ifdef CONFIG_MEMCG_SWAP static int __init enable_swap_account(char *s) { @@ -6806,4 +6796,28 @@ static int __init enable_swap_account(ch } __setup("swapaccount=", enable_swap_account); +static void __init memsw_file_init(void) +{ + if (really_do_swap_account) + WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, + memsw_cgroup_files)); +} +#else +static void __init memsw_file_init(void) +{ +} #endif + +/* + * The rest of init is performed during ->css_alloc() for root css which + * happens before initcalls. hotcpu_notifier() can't be done together as + * it would introduce circular locking by adding cgroup_lock -> cpu hotplug + * dependency. Do it from a subsys_initcall(). + */ +static int __init mem_cgroup_init(void) +{ + hotcpu_notifier(memcg_cpu_hotplug_callback, 0); + memsw_file_init(); + return 0; +} +subsys_initcall(mem_cgroup_init); _ Patches currently in -mm which might be from mhocko@xxxxxxx are linux-next.patch memcg-oom-provide-more-precise-dump-info-while-memcg-oom-happening.patch mm-memcontrolc-convert-printkkern_foo-to-pr_foo.patch mm-hugetlbc-convert-to-pr_foo.patch mm-memcg-only-evict-file-pages-when-we-have-plenty.patch mm-vmscan-save-work-scanning-almost-empty-lru-lists.patch mm-vmscan-clarify-how-swappiness-highest-priority-memcg-interact.patch mm-vmscan-improve-comment-on-low-page-cache-handling.patch mm-vmscan-clean-up-get_scan_count.patch mm-vmscan-clean-up-get_scan_count-fix.patch mm-vmscan-compaction-works-against-zones-not-lruvecs.patch mm-vmscan-compaction-works-against-zones-not-lruvecs-fix.patch mm-reduce-rmap-overhead-for-ex-ksm-page-copies-created-on-swap-faults.patch mm-page_allocc-__setup_per_zone_wmarks-make-min_pages-unsigned-long.patch mm-vmscanc-__zone_reclaim-replace-max_t-with-max.patch mmksm-use-new-hashtable-implementation.patch memcgvmscan-do-not-break-out-targeted-reclaim-without-reclaimed-pages.patch memory-hotplug-implement-register_page_bootmem_info_section-of-sparse-vmemmap-fix.patch memory-hotplug-implement-register_page_bootmem_info_section-of-sparse-vmemmap-fix-fix.patch memory-hotplug-implement-register_page_bootmem_info_section-of-sparse-vmemmap-fix-fix-fix.patch memory-hotplug-implement-register_page_bootmem_info_section-of-sparse-vmemmap-fix-fix-fix-fix.patch memory-hotplug-remove-memmap-of-sparse-vmemmap-fix.patch mm-use-zone-present_pages-instead-of-zone-managed_pages-where-appropriate.patch mm-set-zone-present_pages-to-number-of-existing-pages-in-the-zone.patch mm-increase-totalram_pages-when-free-pages-allocated-by-bootmem-allocator.patch mm-teach-mm-by-current-context-info-to-not-do-i-o-during-memory-allocation.patch pm-runtime-introduce-pm_runtime_set_memalloc_noio.patch block-genhdc-apply-pm_runtime_set_memalloc_noio-on-block-devices.patch net-core-apply-pm_runtime_set_memalloc_noio-on-network-devices.patch pm-runtime-force-memory-allocation-with-no-i-o-during-runtime-pm-callbcack.patch usb-forbid-memory-allocation-with-i-o-during-bus-reset.patch memcg-do-not-create-memsw-files-if-swap-accounting-is-disabled.patch drop_caches-add-some-documentation-and-info-messsge.patch memcg-debugging-facility-to-access-dangling-memcgs.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