From eedeb787ebb53de5c5dcf7b7b39d01bf1b0f037d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 3 Feb 2023 15:31:11 +0100 Subject: freezer,umh: Fix call_usermode_helper_exec() vs SIGKILL Tetsuo-San noted that commit f5d39b020809 ("freezer,sched: Rewrite core freezer logic") broke call_usermodehelper_exec() for the KILLABLE case. Specifically it was missed that the second, unconditional, wait_for_completion() was not optional and ensures the on-stack completion is unused before going out-of-scope. Fixes: f5d39b020809 ("freezer,sched: Rewrite core freezer logic") Reported-by: syzbot+6cd18e123583550cf469@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Debugged-by: Tetsuo Handa Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/Y90ar35uKQoUrLEK@hirez.programming.kicks-ass.net --- kernel/umh.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/kernel/umh.c b/kernel/umh.c index 850631518665..fbf872c624cb 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -438,21 +438,27 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; - if (wait & UMH_KILLABLE) - state |= TASK_KILLABLE; - if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; - retval = wait_for_completion_state(&done, state); - if (!retval) - goto wait_done; - if (wait & UMH_KILLABLE) { + retval = wait_for_completion_state(&done, state | TASK_KILLABLE); + if (!retval) + goto wait_done; + /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; + + /* + * fallthrough; in case of -ERESTARTSYS now do uninterruptible + * wait_for_completion_state(). Since umh_complete() shall call + * complete() in a moment if xchg() above returned NULL, this + * uninterruptible wait_for_completion_state() will not block + * SIGKILL'ed processes for long. + */ } + wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; -- cgit v1.2.3 From df14b7f9efcda35e59bb6f50351aac25c50f6e24 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 3 Feb 2023 13:18:49 -0500 Subject: sched/core: Fix a missed update of user_cpus_ptr Since commit 8f9ea86fdf99 ("sched: Always preserve the user requested cpumask"), a successful call to sched_setaffinity() should always save the user requested cpu affinity mask in a task's user_cpus_ptr. However, when the given cpu mask is the same as the current one, user_cpus_ptr is not updated. Fix this by saving the user mask in this case too. Fixes: 8f9ea86fdf99 ("sched: Always preserve the user requested cpumask") Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230203181849.221943-1-longman@redhat.com --- kernel/sched/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e838feb6adc5..2a4918a1faa9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2951,8 +2951,11 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, } if (!(ctx->flags & SCA_MIGRATE_ENABLE)) { - if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) + if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) { + if (ctx->flags & SCA_USER) + swap(p->user_cpus_ptr, ctx->user_mask); goto out; + } if (WARN_ON_ONCE(p == current && is_migration_disabled(p) && -- cgit v1.2.3 From c2dbe32d5db5c4ead121cf86dabd5ab691fb47fe Mon Sep 17 00:00:00 2001 From: Munehisa Kamata Date: Tue, 14 Feb 2023 13:27:05 -0800 Subject: sched/psi: Fix use-after-free in ep_remove_wait_queue() If a non-root cgroup gets removed when there is a thread that registered trigger and is polling on a pressure file within the cgroup, the polling waitqueue gets freed in the following path: do_rmdir cgroup_rmdir kernfs_drain_open_files cgroup_file_release cgroup_pressure_release psi_trigger_destroy However, the polling thread still has a reference to the pressure file and will access the freed waitqueue when the file is closed or upon exit: fput ep_eventpoll_release ep_free ep_remove_wait_queue remove_wait_queue This results in use-after-free as pasted below. The fundamental problem here is that cgroup_file_release() (and consequently waitqueue's lifetime) is not tied to the file's real lifetime. Using wake_up_pollfree() here might be less than ideal, but it is in line with the comment at commit 42288cb44c4b ("wait: add wake_up_pollfree()") since the waitqueue's lifetime is not tied to file's one and can be considered as another special case. While this would be fixable by somehow making cgroup_file_release() be tied to the fput(), it would require sizable refactoring at cgroups or higher layer which might be more justifiable if we identify more cases like this. BUG: KASAN: use-after-free in _raw_spin_lock_irqsave+0x60/0xc0 Write of size 4 at addr ffff88810e625328 by task a.out/4404 CPU: 19 PID: 4404 Comm: a.out Not tainted 6.2.0-rc6 #38 Hardware name: Amazon EC2 c5a.8xlarge/, BIOS 1.0 10/16/2017 Call Trace: dump_stack_lvl+0x73/0xa0 print_report+0x16c/0x4e0 kasan_report+0xc3/0xf0 kasan_check_range+0x2d2/0x310 _raw_spin_lock_irqsave+0x60/0xc0 remove_wait_queue+0x1a/0xa0 ep_free+0x12c/0x170 ep_eventpoll_release+0x26/0x30 __fput+0x202/0x400 task_work_run+0x11d/0x170 do_exit+0x495/0x1130 do_group_exit+0x100/0x100 get_signal+0xd67/0xde0 arch_do_signal_or_restart+0x2a/0x2b0 exit_to_user_mode_prepare+0x94/0x100 syscall_exit_to_user_mode+0x20/0x40 do_syscall_64+0x52/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Allocated by task 4404: kasan_set_track+0x3d/0x60 __kasan_kmalloc+0x85/0x90 psi_trigger_create+0x113/0x3e0 pressure_write+0x146/0x2e0 cgroup_file_write+0x11c/0x250 kernfs_fop_write_iter+0x186/0x220 vfs_write+0x3d8/0x5c0 ksys_write+0x90/0x110 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 4407: kasan_set_track+0x3d/0x60 kasan_save_free_info+0x27/0x40 ____kasan_slab_free+0x11d/0x170 slab_free_freelist_hook+0x87/0x150 __kmem_cache_free+0xcb/0x180 psi_trigger_destroy+0x2e8/0x310 cgroup_file_release+0x4f/0xb0 kernfs_drain_open_files+0x165/0x1f0 kernfs_drain+0x162/0x1a0 __kernfs_remove+0x1fb/0x310 kernfs_remove_by_name_ns+0x95/0xe0 cgroup_addrm_files+0x67f/0x700 cgroup_destroy_locked+0x283/0x3c0 cgroup_rmdir+0x29/0x100 kernfs_iop_rmdir+0xd1/0x140 vfs_rmdir+0xfe/0x240 do_rmdir+0x13d/0x280 __x64_sys_rmdir+0x2c/0x30 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 0e94682b73bf ("psi: introduce psi monitor") Signed-off-by: Munehisa Kamata Signed-off-by: Mengchi Cheng Signed-off-by: Ingo Molnar Acked-by: Suren Baghdasaryan Acked-by: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/20230106224859.4123476-1-kamatam@amazon.com/ Link: https://lore.kernel.org/r/20230214212705.4058045-1-kamatam@amazon.com --- kernel/sched/psi.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 8ac8b81bfee6..02e011cabe91 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1343,10 +1343,11 @@ void psi_trigger_destroy(struct psi_trigger *t) group = t->group; /* - * Wakeup waiters to stop polling. Can happen if cgroup is deleted - * from under a polling process. + * Wakeup waiters to stop polling and clear the queue to prevent it from + * being accessed later. Can happen if cgroup is deleted from under a + * polling process. */ - wake_up_interruptible(&t->event_wait); + wake_up_pollfree(&t->event_wait); mutex_lock(&group->trigger_lock); -- cgit v1.2.3