From 42815808f1791eb53c3a05fb78c0a8642ecf8467 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 6 Jul 2020 17:49:09 +0200 Subject: timens: make vdso_join_timens() always succeed As discussed on-list (cf. [1]), in order to make setns() support time namespaces when attaching to multiple namespaces at once properly we need to tweak vdso_join_timens() to always succeed. So switch vdso_join_timens() to using a read lock and replacing mmap_write_lock_killable() to mmap_read_lock() as we discussed. Last cycle setns() was changed to support attaching to multiple namespaces atomically. This requires all namespaces to have a point of no return where they can't fail anymore. Specifically, _install() is allowed to perform permission checks and install the namespace into the new struct nsset that it has been given but it is not allowed to make visible changes to the affected task. Once _install() returns anything that the given namespace type requires to be setup in addition needs to ideally be done in a function that can't fail or if it fails the failure is not fatal. For time namespaces the relevant functions that fall into this category are timens_set_vvar_page() and vdso_join_timens(). Currently the latter can fail but doesn't need to. With this we can go on to implement a timens_commit() helper in a follow up patch to be used by setns(). [1]: https://lore.kernel.org/lkml/20200611110221.pgd3r5qkjrjmfqa2@wittgenstein Signed-off-by: Christian Brauner Reviewed-by: Andrei Vagin Cc: Will Deacon Cc: Vincenzo Frascino Cc: Thomas Gleixner Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Mark Rutland Cc: Dmitry Safonov Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20200706154912.3248030-2-christian.brauner@ubuntu.com --- arch/x86/entry/vdso/vma.c | 5 ++--- kernel/time/namespace.c | 10 ++-------- 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index ea7c1f0b79df..9185cb1d13b9 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -144,8 +144,7 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) struct mm_struct *mm = task->mm; struct vm_area_struct *vma; - if (mmap_write_lock_killable(mm)) - return -EINTR; + mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { unsigned long size = vma->vm_end - vma->vm_start; @@ -154,7 +153,7 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) zap_page_range(vma, vma->vm_start, size); } - mmap_write_unlock(mm); + mmap_read_unlock(mm); return 0; } #else diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c index 5d9fc22d836a..e5af6fe87af8 100644 --- a/kernel/time/namespace.c +++ b/kernel/time/namespace.c @@ -284,7 +284,6 @@ static int timens_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct time_namespace *ns = to_time_ns(new); - int err; if (!current_is_single_threaded()) return -EUSERS; @@ -295,9 +294,7 @@ static int timens_install(struct nsset *nsset, struct ns_common *new) timens_set_vvar_page(current, ns); - err = vdso_join_timens(current, ns); - if (err) - return err; + vdso_join_timens(current, ns); get_time_ns(ns); put_time_ns(nsproxy->time_ns); @@ -313,7 +310,6 @@ int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { struct ns_common *nsc = &nsproxy->time_ns_for_children->ns; struct time_namespace *ns = to_time_ns(nsc); - int err; /* create_new_namespaces() already incremented the ref counter */ if (nsproxy->time_ns == nsproxy->time_ns_for_children) @@ -321,9 +317,7 @@ int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) timens_set_vvar_page(tsk, ns); - err = vdso_join_timens(tsk, ns); - if (err) - return err; + vdso_join_timens(tsk, ns); get_time_ns(ns); put_time_ns(nsproxy->time_ns); -- cgit v1.2.3