From 85b6d24646e4125c591639841169baa98a2da503 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 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 --- include/linux/ipc_namespace.h | 15 +++++++++++++++ include/linux/sched/task.h | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 05e22770af51..b75395ec8d52 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -131,6 +131,16 @@ 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 (refcount_inc_not_zero(&ns->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, @@ -147,6 +157,11 @@ 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/task.h b/include/linux/sched/task.h index ba88a6987400..058d7f371e25 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -158,7 +158,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) * 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), -- cgit v1.2.3 From afe041c2d0febd83698b8b0164e6b3b1dfae0b66 Mon Sep 17 00:00:00 2001 From: Bui Quang Minh Date: Fri, 19 Nov 2021 16:43:40 -0800 Subject: hugetlb: fix hugetlb cgroup refcounting during mremap When hugetlb_vm_op_open() is called during copy_vma(), we may take the reference to resv_map->css. Later, when clearing the reservation pointer of old_vma after transferring it to new_vma, we forget to drop the reference to resv_map->css. This leads to a reference leak of css. Fixes this by adding a check to drop reservation css reference in clear_vma_resv_huge_pages() Link: https://lkml.kernel.org/r/20211113154412.91134-1-minhquangbui99@gmail.com Fixes: 550a7d60bd5e35 ("mm, hugepages: add mremap() support for hugepage backed vma") Signed-off-by: Bui Quang Minh Reviewed-by: Mike Kravetz Reviewed-by: Mina Almasry Cc: Miaohe Lin Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb_cgroup.h | 12 ++++++++++++ mm/hugetlb.c | 4 +++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index c137396129db..ba025ae27882 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -128,6 +128,13 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( css_get(resv_map->css); } +static inline void resv_map_put_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ + if (resv_map->css) + css_put(resv_map->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -211,6 +218,11 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( { } +static inline void resv_map_put_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e09159c957e3..3a2479003ddf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1037,8 +1037,10 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) */ struct resv_map *reservations = vma_resv_map(vma); - if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); + } reset_vma_resv_huge_pages(vma); } -- cgit v1.2.3