From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-13.7 required=3.0 tests=BAYES_00, DKIM_ADSP_CUSTOM_MED,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 280D4C433ED for ; Wed, 7 Apr 2021 17:09:49 +0000 (UTC) Received: from mother.openwall.net (mother.openwall.net [195.42.179.200]) by mail.kernel.org (Postfix) with SMTP id 4BA4761242 for ; Wed, 7 Apr 2021 17:09:48 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 4BA4761242 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=gmail.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kernel-hardening-return-21167-kernel-hardening=archiver.kernel.org@lists.openwall.com Received: (qmail 24119 invoked by uid 550); 7 Apr 2021 17:08:55 -0000 Mailing-List: contact kernel-hardening-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-ID: Received: (qmail 24030 invoked from network); 7 Apr 2021 17:08:54 -0000 From: Alexey Gladkov To: LKML , Kernel Hardening , Linux Containers , linux-mm@kvack.org Cc: Alexey Gladkov , Andrew Morton , Christian Brauner , "Eric W . Biederman" , Jann Horn , Jens Axboe , Kees Cook , Linus Torvalds , Oleg Nesterov Subject: [PATCH v10 5/9] Reimplement RLIMIT_MSGQUEUE on top of ucounts Date: Wed, 7 Apr 2021 19:08:10 +0200 Message-Id: <0c3254aaa23b0f03c10b5de6c75e93000be4e30f.1617814298.git.gladkov.alexey@gmail.com> X-Mailer: git-send-email 2.29.3 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.6.4 (raptor.unsafe.ru [5.9.43.93]); Wed, 07 Apr 2021 17:08:35 +0000 (UTC) The rlimit counter is tied to uid in the user_namespace. This allows rlimit values to be specified in userns even if they are already globally exceeded by the user. However, the value of the previous user_namespaces cannot be exceeded. Signed-off-by: Alexey Gladkov --- include/linux/sched/user.h | 4 ---- include/linux/user_namespace.h | 1 + ipc/mqueue.c | 41 ++++++++++++++++++---------------- kernel/fork.c | 1 + kernel/ucount.c | 1 + kernel/user_namespace.c | 1 + 6 files changed, 26 insertions(+), 23 deletions(-) diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index d33d867ad6c1..8a34446681aa 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -18,10 +18,6 @@ struct user_struct { #endif #ifdef CONFIG_EPOLL atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ -#endif -#ifdef CONFIG_POSIX_MQUEUE - /* protected by mq_lock */ - unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ #endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ unsigned long unix_inflight; /* How many files in flight in unix sockets */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 9d1ca370c201..d0fea0306394 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -51,6 +51,7 @@ enum ucount_type { UCOUNT_INOTIFY_WATCHES, #endif UCOUNT_RLIMIT_NPROC, + UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_COUNTS, }; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 8031464ed4ae..f0f8f013dae2 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -144,7 +144,7 @@ struct mqueue_inode_info { struct pid *notify_owner; u32 notify_self_exec_id; struct user_namespace *notify_user_ns; - struct user_struct *user; /* user who created, for accounting */ + struct ucounts *ucounts; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; @@ -292,7 +292,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb, struct ipc_namespace *ipc_ns, umode_t mode, struct mq_attr *attr) { - struct user_struct *u = current_user(); struct inode *inode; int ret = -ENOMEM; @@ -321,7 +320,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, info->notify_owner = NULL; info->notify_user_ns = NULL; info->qsize = 0; - info->user = NULL; /* set when all is ok */ + info->ucounts = NULL; /* set when all is ok */ info->msg_tree = RB_ROOT; info->msg_tree_rightmost = NULL; info->node_cache = NULL; @@ -371,19 +370,24 @@ static struct inode *mqueue_get_inode(struct super_block *sb, if (mq_bytes + mq_treesize < mq_bytes) goto out_inode; mq_bytes += mq_treesize; - spin_lock(&mq_lock); - if (u->mq_bytes + mq_bytes < u->mq_bytes || - u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) { + info->ucounts = get_ucounts(current_ucounts()); + if (info->ucounts) { + bool overlimit; + + spin_lock(&mq_lock); + overlimit = inc_rlimit_ucounts_and_test(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, + mq_bytes, rlimit(RLIMIT_MSGQUEUE)); + if (overlimit) { + dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); + spin_unlock(&mq_lock); + put_ucounts(info->ucounts); + info->ucounts = NULL; + /* mqueue_evict_inode() releases info->messages */ + ret = -EMFILE; + goto out_inode; + } spin_unlock(&mq_lock); - /* mqueue_evict_inode() releases info->messages */ - ret = -EMFILE; - goto out_inode; } - u->mq_bytes += mq_bytes; - spin_unlock(&mq_lock); - - /* all is ok */ - info->user = get_uid(u); } else if (S_ISDIR(mode)) { inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ @@ -497,7 +501,6 @@ static void mqueue_free_inode(struct inode *inode) static void mqueue_evict_inode(struct inode *inode) { struct mqueue_inode_info *info; - struct user_struct *user; struct ipc_namespace *ipc_ns; struct msg_msg *msg, *nmsg; LIST_HEAD(tmp_msg); @@ -520,8 +523,7 @@ static void mqueue_evict_inode(struct inode *inode) free_msg(msg); } - user = info->user; - if (user) { + if (info->ucounts) { unsigned long mq_bytes, mq_treesize; /* Total amount of bytes accounted for the mqueue */ @@ -533,7 +535,7 @@ static void mqueue_evict_inode(struct inode *inode) info->attr.mq_msgsize); spin_lock(&mq_lock); - user->mq_bytes -= mq_bytes; + dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); /* * get_ns_from_inode() ensures that the * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns @@ -543,7 +545,8 @@ static void mqueue_evict_inode(struct inode *inode) if (ipc_ns) ipc_ns->mq_queues_count--; spin_unlock(&mq_lock); - free_uid(user); + put_ucounts(info->ucounts); + info->ucounts = NULL; } if (ipc_ns) put_ipc_ns(ipc_ns); diff --git a/kernel/fork.c b/kernel/fork.c index d8a4956463ae..85c6094f5a48 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -823,6 +823,7 @@ void __init fork_init(void) init_user_ns.ucount_max[i] = max_threads/2; init_user_ns.ucount_max[UCOUNT_RLIMIT_NPROC] = task_rlimit(&init_task, RLIMIT_NPROC); + init_user_ns.ucount_max[UCOUNT_RLIMIT_MSGQUEUE] = task_rlimit(&init_task, RLIMIT_MSGQUEUE); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", diff --git a/kernel/ucount.c b/kernel/ucount.c index d2c2f991ab3e..3f1682b690e6 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -80,6 +80,7 @@ static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_inotify_instances"), UCOUNT_ENTRY("max_inotify_watches"), #endif + { }, { }, { } }; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 2434b13b02e5..cc90d5203acf 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -122,6 +122,7 @@ int create_user_ns(struct cred *new) ns->ucount_max[i] = INT_MAX; } ns->ucount_max[UCOUNT_RLIMIT_NPROC] = rlimit(RLIMIT_NPROC); + ns->ucount_max[UCOUNT_RLIMIT_MSGQUEUE] = rlimit(RLIMIT_MSGQUEUE); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ -- 2.29.3