Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755824Ab2FIJBy (ORCPT ); Sat, 9 Jun 2012 05:01:54 -0400 Received: from e28smtp09.in.ibm.com ([122.248.162.9]:50766 "EHLO e28smtp09.in.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755216Ab2FIJAv (ORCPT ); Sat, 9 Jun 2012 05:00:51 -0400 From: "Aneesh Kumar K.V" To: linux-mm@kvack.org, kamezawa.hiroyu@jp.fujitsu.com, dhillf@gmail.com, rientjes@google.com, mhocko@suse.cz, akpm@linux-foundation.org, hannes@cmpxchg.org Cc: linux-kernel@vger.kernel.org, cgroups@vger.kernel.org, "Aneesh Kumar K.V" Subject: [PATCH -V8 13/16] hugetlb/cgroup: add hugetlb cgroup control files Date: Sat, 9 Jun 2012 14:29:58 +0530 Message-Id: <1339232401-14392-14-git-send-email-aneesh.kumar@linux.vnet.ibm.com> X-Mailer: git-send-email 1.7.10 In-Reply-To: <1339232401-14392-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com> References: <1339232401-14392-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com> x-cbid: 12060909-2674-0000-0000-000004D70E9B Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7065 Lines: 240 From: "Aneesh Kumar K.V" Add the control files for hugetlb controller Signed-off-by: Aneesh Kumar K.V --- include/linux/hugetlb.h | 5 ++ include/linux/hugetlb_cgroup.h | 6 ++ mm/hugetlb.c | 8 +++ mm/hugetlb_cgroup.c | 130 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 149 insertions(+) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 4aca057..9650bb1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -4,6 +4,7 @@ #include #include #include +#include struct ctl_table; struct user_struct; @@ -221,6 +222,10 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +#ifdef CONFIG_CGROUP_HUGETLB_RES_CTLR + /* cgroup control files */ + struct cftype cgroup_files[5]; +#endif char name[HSTATE_NAME_LEN]; }; diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index ceff1d5..ba4836f 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -62,6 +62,7 @@ extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); +extern int hugetlb_cgroup_file_init(int idx) __init; #else static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) { @@ -106,5 +107,10 @@ hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, { return; } + +static inline int __init hugetlb_cgroup_file_init(int idx) +{ + return 0; +} #endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1ca2d8f..bf79131 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; @@ -1916,6 +1917,13 @@ void __init hugetlb_add_hstate(unsigned order) h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]); snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); + /* + * Add cgroup control files only if the huge page consists + * of more than two normal pages. This is because we use + * page[2].lru.next for storing cgoup details. + */ + if (order >= 2) + hugetlb_cgroup_file_init(hugetlb_max_hstate - 1); parsed_hstate = h; } diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 9458fe3..2a4881d 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -18,6 +18,11 @@ #include #include +/* lifted from mem control */ +#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) +#define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) +#define MEMFILE_ATTR(val) ((val) & 0xffff) + struct cgroup_subsys hugetlb_subsys __read_mostly; struct hugetlb_cgroup *root_h_cgroup __read_mostly; @@ -269,6 +274,131 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, return; } +static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft, + struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + u64 val; + char str[64]; + int idx, name, len; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(cft->private); + name = MEMFILE_ATTR(cft->private); + + val = res_counter_read_u64(&h_cg->hugepage[idx], name); + len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val); + return simple_read_from_buffer(buf, nbytes, ppos, str, len); +} + +static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft, + const char *buffer) +{ + int idx, name, ret; + unsigned long long val; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(cft->private); + name = MEMFILE_ATTR(cft->private); + + switch (name) { + case RES_LIMIT: + if (hugetlb_cgroup_is_root(h_cg)) { + /* Can't set limit on root */ + ret = -EINVAL; + break; + } + /* This function does all necessary parse...reuse it */ + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + ret = res_counter_set_limit(&h_cg->hugepage[idx], val); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event) +{ + int idx, name, ret = 0; + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup); + + idx = MEMFILE_IDX(event); + name = MEMFILE_ATTR(event); + + switch (name) { + case RES_MAX_USAGE: + res_counter_reset_max(&h_cg->hugepage[idx]); + break; + case RES_FAILCNT: + res_counter_reset_failcnt(&h_cg->hugepage[idx]); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static char *mem_fmt(char *buf, int size, unsigned long hsize) +{ + if (hsize >= (1UL << 30)) + snprintf(buf, size, "%luGB", hsize >> 30); + else if (hsize >= (1UL << 20)) + snprintf(buf, size, "%luMB", hsize >> 20); + else + snprintf(buf, size, "%luKB", hsize >> 10); + return buf; +} + +int __init hugetlb_cgroup_file_init(int idx) +{ + char buf[32]; + struct cftype *cft; + struct hstate *h = &hstates[idx]; + + /* format the size */ + mem_fmt(buf, 32, huge_page_size(h)); + + /* Add the limit file */ + cft = &h->cgroup_files[0]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT); + cft->read = hugetlb_cgroup_read; + cft->write_string = hugetlb_cgroup_write; + + /* Add the usage file */ + cft = &h->cgroup_files[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); + cft->read = hugetlb_cgroup_read; + + /* Add the MAX usage file */ + cft = &h->cgroup_files[2]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); + cft->trigger = hugetlb_cgroup_reset; + cft->read = hugetlb_cgroup_read; + + /* Add the failcntfile */ + cft = &h->cgroup_files[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->trigger = hugetlb_cgroup_reset; + cft->read = hugetlb_cgroup_read; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files[4]; + memset(cft, 0, sizeof(*cft)); + + WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files)); + + return 0; +} + struct cgroup_subsys hugetlb_subsys = { .name = "hugetlb", .create = hugetlb_cgroup_create, -- 1.7.10 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/