Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758730AbXHXPXs (ORCPT ); Fri, 24 Aug 2007 11:23:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756514AbXHXPV0 (ORCPT ); Fri, 24 Aug 2007 11:21:26 -0400 Received: from E23SMTP05.au.ibm.com ([202.81.18.174]:40590 "EHLO e23smtp05.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756406AbXHXPVY (ORCPT ); Fri, 24 Aug 2007 11:21:24 -0400 From: Balbir Singh To: Andrew Morton Cc: KAMEZAWA Hiroyuki , Peter Zijlstra , Linux Containers , YAMAMOTO Takashi , Paul Menage , Dave Hansen , Linux MM Mailing List , Nick Piggin , Vaidyanathan Srinivasan , Pavel Emelianov , Dhaval Giani , Balbir Singh , Linux Kernel Mailing List , Eric W Biederman Date: Fri, 24 Aug 2007 20:51:15 +0530 Message-Id: <20070824152115.16582.50301.sendpatchset@balbir-laptop> In-Reply-To: <20070824151948.16582.34424.sendpatchset@balbir-laptop> References: <20070824151948.16582.34424.sendpatchset@balbir-laptop> Subject: [-mm PATCH 8/10] Memory controller add switch to control what type of pages to limit (v7) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6794 Lines: 241 Choose if we want cached pages to be accounted or not. By default both are accounted for. A new set of tunables are added. echo -n 1 > mem_control_type switches the accounting to account for only mapped pages echo -n 3 > mem_control_type switches the behaviour back Signed-off-by: Balbir Singh --- include/linux/memcontrol.h | 9 ++++ mm/filemap.c | 2 mm/memcontrol.c | 92 +++++++++++++++++++++++++++++++++++++++++++++ mm/swap_state.c | 2 4 files changed, 103 insertions(+), 2 deletions(-) diff -puN include/linux/memcontrol.h~mem-control-choose-rss-vs-rss-and-pagecache include/linux/memcontrol.h --- linux-2.6.23-rc2-mm2/include/linux/memcontrol.h~mem-control-choose-rss-vs-rss-and-pagecache 2007-08-24 20:46:08.000000000 +0530 +++ linux-2.6.23-rc2-mm2-balbir/include/linux/memcontrol.h 2007-08-24 20:46:08.000000000 +0530 @@ -20,6 +20,8 @@ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H +#include + struct mem_container; struct page_container; @@ -40,6 +42,7 @@ extern unsigned long mem_container_isola struct mem_container *mem_cont, int active); extern void mem_container_out_of_memory(struct mem_container *mem); +extern int mem_container_cache_charge(struct page *page, struct mm_struct *mm); static inline void mem_container_uncharge_page(struct page *page) { @@ -84,6 +87,12 @@ static inline void mem_container_move_li { } +static inline int mem_container_cache_charge(struct page *page, + struct mm_struct *mm) +{ + return 0; +} + #endif /* CONFIG_CONTAINER_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff -puN mm/filemap.c~mem-control-choose-rss-vs-rss-and-pagecache mm/filemap.c --- linux-2.6.23-rc2-mm2/mm/filemap.c~mem-control-choose-rss-vs-rss-and-pagecache 2007-08-24 20:46:08.000000000 +0530 +++ linux-2.6.23-rc2-mm2-balbir/mm/filemap.c 2007-08-24 20:46:08.000000000 +0530 @@ -445,7 +445,7 @@ int add_to_page_cache(struct page *page, if (error == 0) { - error = mem_container_charge(page, current->mm); + error = mem_container_cache_charge(page, current->mm); if (error) goto out; diff -puN mm/memcontrol.c~mem-control-choose-rss-vs-rss-and-pagecache mm/memcontrol.c --- linux-2.6.23-rc2-mm2/mm/memcontrol.c~mem-control-choose-rss-vs-rss-and-pagecache 2007-08-24 20:46:08.000000000 +0530 +++ linux-2.6.23-rc2-mm2-balbir/mm/memcontrol.c 2007-08-24 20:46:08.000000000 +0530 @@ -28,6 +28,8 @@ #include #include +#include + struct container_subsys mem_container_subsys; static const int MEM_CONTAINER_RECLAIM_RETRIES = 5; @@ -59,6 +61,7 @@ struct mem_container { * spin_lock to protect the per container LRU */ spinlock_t lru_lock; + unsigned long control_type; /* control RSS or RSS+Pagecache */ }; /* @@ -81,6 +84,15 @@ struct page_container { /* mapped and cached states */ }; +enum { + MEM_CONTAINER_TYPE_UNSPEC = 0, + MEM_CONTAINER_TYPE_MAPPED, + MEM_CONTAINER_TYPE_CACHED, + MEM_CONTAINER_TYPE_ALL, + MEM_CONTAINER_TYPE_MAX, +} mem_control_type; + +static struct mem_container init_mem_container; static inline struct mem_container *mem_container_from_cont(struct container *cont) @@ -361,6 +373,22 @@ err: } /* + * See if the cached pages should be charged at all? + */ +int mem_container_cache_charge(struct page *page, struct mm_struct *mm) +{ + struct mem_container *mem; + if (!mm) + mm = &init_mm; + + mem = rcu_dereference(mm->mem_container); + if (mem->control_type == MEM_CONTAINER_TYPE_ALL) + return mem_container_charge(page, mm); + else + return 0; +} + +/* * Uncharging is always a welcome operation, we never complain, simply * uncharge. */ @@ -370,6 +398,10 @@ void mem_container_uncharge(struct page_ struct page *page; unsigned long flags; + /* + * This can handle cases when a page is not charged at all and we + * are switching between handling the control_type. + */ if (!pc) return; @@ -405,6 +437,60 @@ static ssize_t mem_container_write(struc cft->private, userbuf, nbytes, ppos); } +static ssize_t mem_control_type_write(struct container *cont, + struct cftype *cft, struct file *file, + const char __user *userbuf, + size_t nbytes, loff_t *pos) +{ + int ret; + char *buf, *end; + unsigned long tmp; + struct mem_container *mem; + + mem = mem_container_from_cont(cont); + buf = kmalloc(nbytes + 1, GFP_KERNEL); + ret = -ENOMEM; + if (buf == NULL) + goto out; + + buf[nbytes] = 0; + ret = -EFAULT; + if (copy_from_user(buf, userbuf, nbytes)) + goto out_free; + + ret = -EINVAL; + tmp = simple_strtoul(buf, &end, 10); + if (*end != '\0') + goto out_free; + + if (tmp <= MEM_CONTAINER_TYPE_UNSPEC || tmp >= MEM_CONTAINER_TYPE_MAX) + goto out_free; + + mem->control_type = tmp; + ret = nbytes; +out_free: + kfree(buf); +out: + return ret; +} + +static ssize_t mem_control_type_read(struct container *cont, + struct cftype *cft, + struct file *file, char __user *userbuf, + size_t nbytes, loff_t *ppos) +{ + unsigned long val; + char buf[64], *s; + struct mem_container *mem; + + mem = mem_container_from_cont(cont); + s = buf; + val = mem->control_type; + s += sprintf(s, "%lu\n", val); + return simple_read_from_buffer((void __user *)userbuf, nbytes, + ppos, buf, s - buf); +} + static struct cftype mem_container_files[] = { { .name = "usage", @@ -422,6 +508,11 @@ static struct cftype mem_container_files .private = RES_FAILCNT, .read = mem_container_read, }, + { + .name = "control_type", + .write = mem_control_type_write, + .read = mem_control_type_read, + }, }; static struct mem_container init_mem_container; @@ -444,6 +535,7 @@ mem_container_create(struct container_su INIT_LIST_HEAD(&mem->active_list); INIT_LIST_HEAD(&mem->inactive_list); spin_lock_init(&mem->lru_lock); + mem->control_type = MEM_CONTAINER_TYPE_ALL; return &mem->css; } diff -puN mm/swap_state.c~mem-control-choose-rss-vs-rss-and-pagecache mm/swap_state.c --- linux-2.6.23-rc2-mm2/mm/swap_state.c~mem-control-choose-rss-vs-rss-and-pagecache 2007-08-24 20:46:08.000000000 +0530 +++ linux-2.6.23-rc2-mm2-balbir/mm/swap_state.c 2007-08-24 20:46:08.000000000 +0530 @@ -82,7 +82,7 @@ static int __add_to_swap_cache(struct pa error = radix_tree_preload(gfp_mask); if (!error) { - error = mem_container_charge(page, current->mm); + error = mem_container_cache_charge(page, current->mm); if (error) goto out; _ -- Warm Regards, Balbir Singh Linux Technology Center IBM, ISTL - 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/