From dd499f7a7e34270208350a849ef103c0b3ae477f Mon Sep 17 00:00:00 2001 From: Amanieu d'Antras Date: Thu, 2 Jan 2020 18:24:13 +0100 Subject: clone3: ensure copy_thread_tls is implemented copy_thread implementations handle CLONE_SETTLS by reading the TLS value from the registers containing the syscall arguments for clone. This doesn't work with clone3 since the TLS value is passed in clone_args instead. Signed-off-by: Amanieu d'Antras Cc: # 5.3.x Link: https://lore.kernel.org/r/20200102172413.654385-8-amanieu@gmail.com Signed-off-by: Christian Brauner --- kernel/fork.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 2508a4f238a3..080809560072 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2578,6 +2578,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif #ifdef __ARCH_WANT_SYS_CLONE3 + +/* + * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from + * the registers containing the syscall arguments for clone. This doesn't work + * with clone3 since the TLS value is passed in clone_args instead. + */ +#ifndef CONFIG_HAVE_COPY_THREAD_TLS +#error clone3 requires copy_thread_tls support in arch +#endif + noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) -- cgit v1.2.3 From 769071ac9f20b6a447410c7eaa55d1a5233ef40c Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Tue, 12 Nov 2019 01:26:52 +0000 Subject: ns: Introduce Time Namespace Time Namespace isolates clock values. The kernel provides access to several clocks CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME, etc. CLOCK_REALTIME System-wide clock that measures real (i.e., wall-clock) time. CLOCK_MONOTONIC Clock that cannot be set and represents monotonic time since some unspecified starting point. CLOCK_BOOTTIME Identical to CLOCK_MONOTONIC, except it also includes any time that the system is suspended. For many users, the time namespace means the ability to changes date and time in a container (CLOCK_REALTIME). Providing per namespace notions of CLOCK_REALTIME would be complex with a massive overhead, but has a dubious value. But in the context of checkpoint/restore functionality, monotonic and boottime clocks become interesting. Both clocks are monotonic with unspecified starting points. These clocks are widely used to measure time slices and set timers. After restoring or migrating processes, it has to be guaranteed that they never go backward. In an ideal case, the behavior of these clocks should be the same as for a case when a whole system is suspended. All this means that it is required to set CLOCK_MONOTONIC and CLOCK_BOOTTIME clocks, which can be achieved by adding per-namespace offsets for clocks. A time namespace is similar to a pid namespace in the way how it is created: unshare(CLONE_NEWTIME) system call creates a new time namespace, but doesn't set it to the current process. Then all children of the process will be born in the new time namespace, or a process can use the setns() system call to join a namespace. This scheme allows setting clock offsets for a namespace, before any processes appear in it. All available clone flags have been used, so CLONE_NEWTIME uses the highest bit of CSIGNAL. It means that it can be used only with the unshare() and the clone3() system calls. [ tglx: Adjusted paragraph about clone3() to reality and massaged the changelog a bit. ] Co-developed-by: Dmitry Safonov Signed-off-by: Andrei Vagin Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Link: https://criu.org/Time_namespace Link: https://lists.openvz.org/pipermail/criu/2018-June/041504.html Link: https://lore.kernel.org/r/20191112012724.250792-4-dima@arista.com --- kernel/fork.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 2508a4f238a3..363595815144 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1832,6 +1832,7 @@ static __latent_entropy struct task_struct *copy_process( struct multiprocess_signals delayed; struct file *pidfile = NULL; u64 clone_flags = args->flags; + struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different @@ -1874,8 +1875,16 @@ static __latent_entropy struct task_struct *copy_process( */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || - (task_active_pid_ns(current) != - current->nsproxy->pid_ns_for_children)) + (task_active_pid_ns(current) != nsp->pid_ns_for_children)) + return ERR_PTR(-EINVAL); + } + + /* + * If the new process will be in a different time namespace + * do not allow it to share VM or a thread group with the forking task. + */ + if (clone_flags & (CLONE_THREAD | CLONE_VM)) { + if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } @@ -2811,7 +2820,8 @@ static int check_unshare_flags(unsigned long unshare_flags) if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| - CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP)) + CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| + CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing -- cgit v1.2.3 From 984cfe4e252681d516df056b982e3c47b66fba92 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 18 Dec 2019 13:40:35 -0400 Subject: mm/mmu_notifier: Rename struct mmu_notifier_mm to mmu_notifier_subscriptions The name mmu_notifier_mm implies that the thing is a mm_struct pointer, and is difficult to abbreviate. The struct is actually holding the interval tree and hlist containing the notifiers subscribed to a mm. Use 'subscriptions' as the variable name for this struct instead of the really terrible and misleading 'mmn_mm'. Signed-off-by: Jason Gunthorpe --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 2508a4f238a3..047865086cdf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -692,7 +692,7 @@ void __mmdrop(struct mm_struct *mm) WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); - mmu_notifier_mm_destroy(mm); + mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); free_mm(mm); @@ -1025,7 +1025,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_aio(mm); mm_init_owner(mm, p); RCU_INIT_POINTER(mm->exe_file, NULL); - mmu_notifier_mm_init(mm); + mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; -- cgit v1.2.3 From 0c282b068eb26db0e85e2ab4ec6d1e932acda841 Mon Sep 17 00:00:00 2001 From: Madhuparna Bhowmik Date: Mon, 27 Jan 2020 23:28:21 +0530 Subject: fork: Use RCU_INIT_POINTER() instead of rcu_access_pointer() Use RCU_INIT_POINTER() instead of rcu_access_pointer() in copy_sighand(). Suggested-by: Oleg Nesterov Signed-off-by: Madhuparna Bhowmik Acked-by: Oleg Nesterov Acked-by: Christian Brauner [christian.brauner@ubuntu.com: edit commit message] Link: https://lore.kernel.org/r/20200127175821.10833-1-madhuparnabhowmik10@gmail.com Signed-off-by: Christian Brauner --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 60a1295f4384..86425305cd4a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1508,7 +1508,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); - rcu_assign_pointer(tsk->sighand, sig); + RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; -- cgit v1.2.3 From 8380ce479010f2f779587b462a9b4681934297c3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 28 Mar 2020 19:17:25 -0700 Subject: mm: fork: fix kernel_stack memcg stats for various stack implementations Depending on CONFIG_VMAP_STACK and the THREAD_SIZE / PAGE_SIZE ratio the space for task stacks can be allocated using __vmalloc_node_range(), alloc_pages_node() and kmem_cache_alloc_node(). In the first and the second cases page->mem_cgroup pointer is set, but in the third it's not: memcg membership of a slab page should be determined using the memcg_from_slab_page() function, which looks at page->slab_cache->memcg_params.memcg . In this case, using mod_memcg_page_state() (as in account_kernel_stack()) is incorrect: page->mem_cgroup pointer is NULL even for pages charged to a non-root memory cgroup. It can lead to kernel_stack per-memcg counters permanently showing 0 on some architectures (depending on the configuration). In order to fix it, let's introduce a mod_memcg_obj_state() helper, which takes a pointer to a kernel object as a first argument, uses mem_cgroup_from_obj() to get a RCU-protected memcg pointer and calls mod_memcg_state(). It allows to handle all possible configurations (CONFIG_VMAP_STACK and various THREAD_SIZE/PAGE_SIZE values) without spilling any memcg/kmem specifics into fork.c . Note: This is a special version of the patch created for stable backports. It contains code from the following two patches: - mm: memcg/slab: introduce mem_cgroup_from_obj() - mm: fork: fix kernel_stack memcg stats for various stack implementations [guro@fb.com: introduce mem_cgroup_from_obj()] Link: http://lkml.kernel.org/r/20200324004221.GA36662@carbon.dhcp.thefacebook.com Fixes: 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages") Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Bharata B Rao Cc: Shakeel Butt Cc: Link: http://lkml.kernel.org/r/20200303233550.251375-1-guro@fb.com Signed-off-by: Linus Torvalds --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 86425305cd4a..d90af13431c7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -397,8 +397,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account) mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, THREAD_SIZE / 1024 * account); - mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB, - account * (THREAD_SIZE / 1024)); + mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); } } -- cgit v1.2.3