From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752555AbZHRX64 (ORCPT ); Tue, 18 Aug 2009 19:58:56 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752463AbZHRX6q (ORCPT ); Tue, 18 Aug 2009 19:58:46 -0400 Received: from smtp-out.google.com ([216.239.33.17]:27977 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752432AbZHRX6p (ORCPT ); Tue, 18 Aug 2009 19:58:45 -0400 DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns; h=from:subject:to:cc:date:message-id:in-reply-to:references: user-agent:mime-version:content-type: content-transfer-encoding:x-system-of-record; b=yLpz/PmaHmkGUbbaaremzrexCZuYAuD5YVwTy5Bo9brvFDPhMuIIU6ztMMr/3PsYU H8+wd+hE7r2tS1NoLri1w== From: Paul Menage Subject: [PATCH 4/8] Use vmalloc for large cgroups pidlist allocations To: akpm@linux-foundation.org, bblum@andrew.cmu.edu, lizf@cn.fujitsu.com Cc: linux-kernel@vger.kernel.org, containers@lists.linux-foundation.org Date: Tue, 18 Aug 2009 16:58:27 -0700 Message-ID: <20090818235827.22531.60306.stgit@menage.mtv.corp.google.com> In-Reply-To: <20090818235059.22531.42618.stgit@menage.mtv.corp.google.com> References: <20090818235059.22531.42618.stgit@menage.mtv.corp.google.com> User-Agent: StGIT/0.14.3 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Ben Blum Use vmalloc for large cgroups pidlist allocations Separates all pidlist allocation requests to a separate function that judges based on the requested size whether or not the array needs to be vmalloced or can be gotten via kmalloc, and similar for kfree/vfree. Signed-off-by: Ben Blum Signed-off-by: Paul Menage --- kernel/cgroup.c | 47 ++++++++++++++++++++++++++++++++++++++++++----- 1 files changed, 42 insertions(+), 5 deletions(-) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d207871..7e2b285 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -50,6 +50,7 @@ #include #include #include +#include /* TODO: replace with more sophisticated array */ #include @@ -2351,6 +2352,42 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) */ /* + * The following two functions "fix" the issue where there are more pids + * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. + * TODO: replace with a kernel-wide solution to this problem + */ +#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2)) +static void *pidlist_allocate(int count) +{ + if (PIDLIST_TOO_LARGE(count)) + return vmalloc(count * sizeof(pid_t)); + else + return kmalloc(count * sizeof(pid_t), GFP_KERNEL); +} +static void pidlist_free(void *p) +{ + if (is_vmalloc_addr(p)) + vfree(p); + else + kfree(p); +} +static void *pidlist_resize(void *p, int newcount) +{ + void *newlist; + /* note: if new alloc fails, old p will still be valid either way */ + if (is_vmalloc_addr(p)) { + newlist = vmalloc(newcount * sizeof(pid_t)); + if (!newlist) + return NULL; + memcpy(newlist, p, newcount * sizeof(pid_t)); + vfree(p); + } else { + newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL); + } + return newlist; +} + +/* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * If the new stripped list is sufficiently smaller and there's enough memory * to allocate a new buffer, will let go of the unneeded memory. Returns the @@ -2389,7 +2426,7 @@ after: * we'll just stay with what we've got. */ if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) { - newlist = krealloc(list, dest * sizeof(pid_t), GFP_KERNEL); + newlist = pidlist_resize(list, dest); if (newlist) *p = newlist; } @@ -2470,7 +2507,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, * show up until sometime later on. */ length = cgroup_task_count(cgrp); - array = kmalloc(length * sizeof(pid_t), GFP_KERNEL); + array = pidlist_allocate(length); if (!array) return -ENOMEM; /* now, populate the array */ @@ -2494,11 +2531,11 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, length = pidlist_uniq(&array, length); l = cgroup_pidlist_find(cgrp, type); if (!l) { - kfree(array); + pidlist_free(array); return -ENOMEM; } /* store array, freeing old if necessary - lock already held */ - kfree(l->list); + pidlist_free(l->list); l->list = array; l->length = length; l->use_count++; @@ -2659,7 +2696,7 @@ static void cgroup_release_pid_array(struct cgroup_pidlist *l) /* we're the last user if refcount is 0; remove and free */ list_del(&l->links); mutex_unlock(&l->owner->pidlist_mutex); - kfree(l->list); + pidlist_free(l->list); put_pid_ns(l->key.ns); up_write(&l->mutex); kfree(l);