From c233bb6234e13a50184626bf00cd8cbe58b8bc8d Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 19 Nov 2021 16:43:21 -0800 Subject: shm: extend forced shm destroy to support objects from several IPC nses commit 85b6d24646e4125c591639841169baa98a2da503 upstream. Currently, the exit_shm() function not designed to work properly when task->sysvshm.shm_clist holds shm objects from different IPC namespaces. This is a real pain when sysctl kernel.shm_rmid_forced = 1, because it leads to use-after-free (reproducer exists). This is an attempt to fix the problem by extending exit_shm mechanism to handle shm's destroy from several IPC ns'es. To achieve that we do several things: 1. add a namespace (non-refcounted) pointer to the struct shmid_kernel 2. during new shm object creation (newseg()/shmget syscall) we initialize this pointer by current task IPC ns 3. exit_shm() fully reworked such that it traverses over all shp's in task->sysvshm.shm_clist and gets IPC namespace not from current task as it was before but from shp's object itself, then call shm_destroy(shp, ns). Note: We need to be really careful here, because as it was said before (1), our pointer to IPC ns non-refcnt'ed. To be on the safe side we using special helper get_ipc_ns_not_zero() which allows to get IPC ns refcounter only if IPC ns not in the "state of destruction". Q/A Q: Why can we access shp->ns memory using non-refcounted pointer? A: Because shp object lifetime is always shorther than IPC namespace lifetime, so, if we get shp object from the task->sysvshm.shm_clist while holding task_lock(task) nobody can steal our namespace. Q: Does this patch change semantics of unshare/setns/clone syscalls? A: No. It's just fixes non-covered case when process may leave IPC namespace without getting task->sysvshm.shm_clist list cleaned up. Link: https://lkml.kernel.org/r/67bb03e5-f79c-1815-e2bf-949c67047418@colorfullife.com Link: https://lkml.kernel.org/r/20211109151501.4921-1-manfred@colorfullife.com Fixes: ab602f79915 ("shm: make exit_shm work proportional to task activity") Co-developed-by: Manfred Spraul Signed-off-by: Manfred Spraul Signed-off-by: Alexander Mikhalitsyn Cc: "Eric W. Biederman" Cc: Davidlohr Bueso Cc: Greg KH Cc: Andrei Vagin Cc: Pavel Tikhomirov Cc: Vasily Averin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/ipc_namespace.h | 15 +++++++++++++++ include/linux/sched.h | 2 +- include/linux/shm.h | 13 +++++++++++-- 3 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 1eee6bcfcf76..cf1a1c126e89 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -123,6 +123,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + if (ns) { + if (atomic_inc_not_zero(&ns->count)) + return ns; + } + + return NULL; +} + extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, @@ -139,6 +149,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + return ns; +} + static inline void put_ipc_ns(struct ipc_namespace *ns) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 8c10e97f94fe..eea75f519421 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2792,7 +2792,7 @@ static inline int thread_group_empty(struct task_struct *p) * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. And ->vfork_done. + * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), diff --git a/include/linux/shm.h b/include/linux/shm.h index 6fb801686ad6..fbb74824f0df 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -19,9 +19,18 @@ struct shmid_kernel /* private to the kernel */ pid_t shm_lprid; struct user_struct *mlock_user; - /* The task created the shm object. NULL if the task is dead. */ + /* + * The task created the shm object, for + * task_lock(shp->shm_creator) + */ struct task_struct *shm_creator; - struct list_head shm_clist; /* list by creator */ + + /* + * List by creator. task_lock(->shm_creator) required for read/write. + * If list_empty(), then the creator is dead already. + */ + struct list_head shm_clist; + struct ipc_namespace *ns; }; /* shm_mode upper byte flags */ -- cgit v1.2.3