aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds2022-01-17 05:49:30 +0200
committerLinus Torvalds2022-01-17 05:49:30 +0200
commit35ce8ae9ae2e471f92759f9d6880eab42cc1c3b6 (patch)
treed6299a6010d1d88c1ab93f406c0a392e3aaa919e /kernel
parent6661224e66f03706daea8e27714436851cf01731 (diff)
parenta403df29789ba38796edb97dad9bfb47836b68c0 (diff)
Merge branch 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull signal/exit/ptrace updates from Eric Biederman: "This set of changes deletes some dead code, makes a lot of cleanups which hopefully make the code easier to follow, and fixes bugs found along the way. The end-game which I have not yet reached yet is for fatal signals that generate coredumps to be short-circuit deliverable from complete_signal, for force_siginfo_to_task not to require changing userspace configured signal delivery state, and for the ptrace stops to always happen in locations where we can guarantee on all architectures that the all of the registers are saved and available on the stack. Removal of profile_task_ext, profile_munmap, and profile_handoff_task are the big successes for dead code removal this round. A bunch of small bug fixes are included, as most of the issues reported were small enough that they would not affect bisection so I simply added the fixes and did not fold the fixes into the changes they were fixing. There was a bug that broke coredumps piped to systemd-coredump. I dropped the change that caused that bug and replaced it entirely with something much more restrained. Unfortunately that required some rebasing. Some successes after this set of changes: There are few enough calls to do_exit to audit in a reasonable amount of time. The lifetime of struct kthread now matches the lifetime of struct task, and the pointer to struct kthread is no longer stored in set_child_tid. The flag SIGNAL_GROUP_COREDUMP is removed. The field group_exit_task is removed. Issues where task->exit_code was examined with signal->group_exit_code should been examined were fixed. There are several loosely related changes included because I am cleaning up and if I don't include them they will probably get lost. The original postings of these changes can be found at: https://lkml.kernel.org/r/87a6ha4zsd.fsf@email.froward.int.ebiederm.org https://lkml.kernel.org/r/87bl1kunjj.fsf@email.froward.int.ebiederm.org https://lkml.kernel.org/r/87r19opkx1.fsf_-_@email.froward.int.ebiederm.org I trimmed back the last set of changes to only the obviously correct once. Simply because there was less time for review than I had hoped" * 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (44 commits) ptrace/m68k: Stop open coding ptrace_report_syscall ptrace: Remove unused regs argument from ptrace_report_syscall ptrace: Remove second setting of PT_SEIZED in ptrace_attach taskstats: Cleanup the use of task->exit_code exit: Use the correct exit_code in /proc/<pid>/stat exit: Fix the exit_code for wait_task_zombie exit: Coredumps reach do_group_exit exit: Remove profile_handoff_task exit: Remove profile_task_exit & profile_munmap signal: clean up kernel-doc comments signal: Remove the helper signal_group_exit signal: Rename group_exit_task group_exec_task coredump: Stop setting signal->group_exit_task signal: Remove SIGNAL_GROUP_COREDUMP signal: During coredumps set SIGNAL_GROUP_EXIT in zap_process signal: Make coredump handling explicit in complete_signal signal: Have prepare_signal detect coredumps using signal->core_state signal: Have the oom killer detect coredumps using signal->core_state exit: Move force_uaccess back into do_exit exit: Guarantee make_task_dead leaks the tsk when calling do_task_exit ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c97
-rw-r--r--kernel/fork.c20
-rw-r--r--kernel/futex/core.c2
-rw-r--r--kernel/kexec_core.c2
-rw-r--r--kernel/kthread.c88
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/profile.c73
-rw-r--r--kernel/ptrace.c2
-rw-r--r--kernel/sched/core.c16
-rw-r--r--kernel/signal.c61
-rw-r--r--kernel/tsacct.c7
11 files changed, 172 insertions, 202 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index f702a6a63686..b00a25bb4ab9 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -116,7 +116,7 @@ static void __exit_signal(struct task_struct *tsk)
* then notify it:
*/
if (sig->notify_count > 0 && !--sig->notify_count)
- wake_up_process(sig->group_exit_task);
+ wake_up_process(sig->group_exec_task);
if (tsk == sig->curr_target)
sig->curr_target = next_thread(tsk);
@@ -697,7 +697,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
/* mt-exec, de_thread() is waiting for group leader */
if (unlikely(tsk->signal->notify_count < 0))
- wake_up_process(tsk->signal->group_exit_task);
+ wake_up_process(tsk->signal->group_exec_task);
write_unlock_irq(&tasklist_lock);
list_for_each_entry_safe(p, n, &dead, ptrace_entry) {
@@ -735,37 +735,22 @@ void __noreturn do_exit(long code)
struct task_struct *tsk = current;
int group_dead;
- /*
- * We can get here from a kernel oops, sometimes with preemption off.
- * Start by checking for critical errors.
- * Then fix up important state like USER_DS and preemption.
- * Then do everything else.
- */
-
WARN_ON(blk_needs_flush_plug(tsk));
- if (unlikely(in_interrupt()))
- panic("Aiee, killing interrupt handler!");
- if (unlikely(!tsk->pid))
- panic("Attempted to kill the idle task!");
-
/*
- * If do_exit is called because this processes oopsed, it's possible
+ * If do_dead is called because this processes oopsed, it's possible
* that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
* continuing. Amongst other possible reasons, this is to prevent
* mm_release()->clear_child_tid() from writing to a user-controlled
* kernel address.
+ *
+ * On uptodate architectures force_uaccess_begin is a noop. On
+ * architectures that still have set_fs/get_fs in addition to handling
+ * oopses handles kernel threads that run as set_fs(KERNEL_DS) by
+ * default.
*/
force_uaccess_begin();
- if (unlikely(in_atomic())) {
- pr_info("note: %s[%d] exited with preempt_count %d\n",
- current->comm, task_pid_nr(current),
- preempt_count());
- preempt_count_set(PREEMPT_ENABLED);
- }
-
- profile_task_exit(tsk);
kcov_task_exit(tsk);
coredump_task_exit(tsk);
@@ -773,17 +758,6 @@ void __noreturn do_exit(long code)
validate_creds_for_do_exit(tsk);
- /*
- * We're taking recursive faults here in do_exit. Safest is to just
- * leave this task alone and wait for reboot.
- */
- if (unlikely(tsk->flags & PF_EXITING)) {
- pr_alert("Fixing recursive fault but reboot is needed!\n");
- futex_exit_recursive(tsk);
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule();
- }
-
io_uring_files_cancel();
exit_signals(tsk); /* sets PF_EXITING */
@@ -882,16 +856,46 @@ void __noreturn do_exit(long code)
lockdep_free_task(tsk);
do_task_dead();
}
-EXPORT_SYMBOL_GPL(do_exit);
-void complete_and_exit(struct completion *comp, long code)
+void __noreturn make_task_dead(int signr)
{
- if (comp)
- complete(comp);
+ /*
+ * Take the task off the cpu after something catastrophic has
+ * happened.
+ *
+ * We can get here from a kernel oops, sometimes with preemption off.
+ * Start by checking for critical errors.
+ * Then fix up important state like USER_DS and preemption.
+ * Then do everything else.
+ */
+ struct task_struct *tsk = current;
- do_exit(code);
+ if (unlikely(in_interrupt()))
+ panic("Aiee, killing interrupt handler!");
+ if (unlikely(!tsk->pid))
+ panic("Attempted to kill the idle task!");
+
+ if (unlikely(in_atomic())) {
+ pr_info("note: %s[%d] exited with preempt_count %d\n",
+ current->comm, task_pid_nr(current),
+ preempt_count());
+ preempt_count_set(PREEMPT_ENABLED);
+ }
+
+ /*
+ * We're taking recursive faults here in make_task_dead. Safest is to just
+ * leave this task alone and wait for reboot.
+ */
+ if (unlikely(tsk->flags & PF_EXITING)) {
+ pr_alert("Fixing recursive fault but reboot is needed!\n");
+ futex_exit_recursive(tsk);
+ tsk->exit_state = EXIT_DEAD;
+ refcount_inc(&tsk->rcu_users);
+ do_task_dead();
+ }
+
+ do_exit(signr);
}
-EXPORT_SYMBOL(complete_and_exit);
SYSCALL_DEFINE1(exit, int, error_code)
{
@@ -907,17 +911,19 @@ do_group_exit(int exit_code)
{
struct signal_struct *sig = current->signal;
- BUG_ON(exit_code & 0x80); /* core dumps don't get here */
-
- if (signal_group_exit(sig))
+ if (sig->flags & SIGNAL_GROUP_EXIT)
exit_code = sig->group_exit_code;
+ else if (sig->group_exec_task)
+ exit_code = 0;
else if (!thread_group_empty(current)) {
struct sighand_struct *const sighand = current->sighand;
spin_lock_irq(&sighand->siglock);
- if (signal_group_exit(sig))
+ if (sig->flags & SIGNAL_GROUP_EXIT)
/* Another thread got here before we took the lock. */
exit_code = sig->group_exit_code;
+ else if (sig->group_exec_task)
+ exit_code = 0;
else {
sig->group_exit_code = exit_code;
sig->flags = SIGNAL_GROUP_EXIT;
@@ -1012,7 +1018,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
return 0;
if (unlikely(wo->wo_flags & WNOWAIT)) {
- status = p->exit_code;
+ status = (p->signal->flags & SIGNAL_GROUP_EXIT)
+ ? p->signal->group_exit_code : p->exit_code;
get_task_struct(p);
read_unlock(&tasklist_lock);
sched_annotate_sleep();
diff --git a/kernel/fork.c b/kernel/fork.c
index 1c989cc4208a..d75a528f7b21 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -757,9 +757,7 @@ void __put_task_struct(struct task_struct *tsk)
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
sched_core_free(tsk);
-
- if (!profile_handoff_task(tsk))
- free_task(tsk);
+ free_task(tsk);
}
EXPORT_SYMBOL_GPL(__put_task_struct);
@@ -953,7 +951,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
tsk->splice_pipe = NULL;
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- tsk->pf_io_worker = NULL;
+ tsk->worker_private = NULL;
account_kernel_stack(tsk, 1);
@@ -2009,12 +2007,6 @@ static __latent_entropy struct task_struct *copy_process(
siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
}
- /*
- * This _must_ happen before we call free_task(), i.e. before we jump
- * to any of the bad_fork_* labels. This is to avoid freeing
- * p->set_child_tid which is (ab)used as a kthread's data pointer for
- * kernel threads (PF_KTHREAD).
- */
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
/*
* Clear TID on mm_release()?
@@ -2095,12 +2087,16 @@ static __latent_entropy struct task_struct *copy_process(
p->io_context = NULL;
audit_set_context(p, NULL);
cgroup_fork(p);
+ if (p->flags & PF_KTHREAD) {
+ if (!set_kthread_struct(p))
+ goto bad_fork_cleanup_delayacct;
+ }
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
- goto bad_fork_cleanup_threadgroup_lock;
+ goto bad_fork_cleanup_delayacct;
}
#endif
#ifdef CONFIG_CPUSETS
@@ -2437,8 +2433,8 @@ bad_fork_cleanup_policy:
lockdep_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
-bad_fork_cleanup_threadgroup_lock:
#endif
+bad_fork_cleanup_delayacct:
delayacct_tsk_free(p);
bad_fork_cleanup_count:
dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 926c2bb752bc..51dd822a8060 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1031,7 +1031,7 @@ static void futex_cleanup(struct task_struct *tsk)
* actually finished the futex cleanup. The worst case for this is that the
* waiter runs through the wait loop until the state becomes visible.
*
- * This is called from the recursive fault handling path in do_exit().
+ * This is called from the recursive fault handling path in make_task_dead().
*
* This is best effort. Either the futex exit code has run already or
* not. If the OWNER_DIED bit has been set on the futex then the waiter can
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 5a5d192a89ac..68480f731192 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -81,7 +81,7 @@ int kexec_should_crash(struct task_struct *p)
if (crash_kexec_post_notifiers)
return 0;
/*
- * There are 4 panic() calls in do_exit() path, each of which
+ * There are 4 panic() calls in make_task_dead() path, each of which
* corresponds to each of these 4 conditions.
*/
if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4ed9e7bce9e8..a2c156ee8275 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -52,6 +52,7 @@ struct kthread_create_info
struct kthread {
unsigned long flags;
unsigned int cpu;
+ int result;
int (*threadfn)(void *);
void *data;
mm_segment_t oldfs;
@@ -71,7 +72,7 @@ enum KTHREAD_BITS {
static inline struct kthread *to_kthread(struct task_struct *k)
{
WARN_ON(!(k->flags & PF_KTHREAD));
- return (__force void *)k->set_child_tid;
+ return k->worker_private;
}
/*
@@ -79,7 +80,7 @@ static inline struct kthread *to_kthread(struct task_struct *k)
*
* Per construction; when:
*
- * (p->flags & PF_KTHREAD) && p->set_child_tid
+ * (p->flags & PF_KTHREAD) && p->worker_private
*
* the task is both a kthread and struct kthread is persistent. However
* PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and
@@ -87,26 +88,29 @@ static inline struct kthread *to_kthread(struct task_struct *k)
*/
static inline struct kthread *__to_kthread(struct task_struct *p)
{
- void *kthread = (__force void *)p->set_child_tid;
+ void *kthread = p->worker_private;
if (kthread && !(p->flags & PF_KTHREAD))
kthread = NULL;
return kthread;
}
-void set_kthread_struct(struct task_struct *p)
+bool set_kthread_struct(struct task_struct *p)
{
struct kthread *kthread;
- if (__to_kthread(p))
- return;
+ if (WARN_ON_ONCE(to_kthread(p)))
+ return false;
kthread = kzalloc(sizeof(*kthread), GFP_KERNEL);
- /*
- * We abuse ->set_child_tid to avoid the new member and because it
- * can't be wrongly copied by copy_process(). We also rely on fact
- * that the caller can't exec, so PF_KTHREAD can't be cleared.
- */
- p->set_child_tid = (__force void __user *)kthread;
+ if (!kthread)
+ return false;
+
+ init_completion(&kthread->exited);
+ init_completion(&kthread->parked);
+ p->vfork_done = &kthread->exited;
+
+ p->worker_private = kthread;
+ return true;
}
void free_kthread_struct(struct task_struct *k)
@@ -114,13 +118,13 @@ void free_kthread_struct(struct task_struct *k)
struct kthread *kthread;
/*
- * Can be NULL if this kthread was created by kernel_thread()
- * or if kmalloc() in kthread() failed.
+ * Can be NULL if kmalloc() in set_kthread_struct() failed.
*/
kthread = to_kthread(k);
#ifdef CONFIG_BLK_CGROUP
WARN_ON_ONCE(kthread && kthread->blkcg_css);
#endif
+ k->worker_private = NULL;
kfree(kthread);
}
@@ -268,6 +272,44 @@ void kthread_parkme(void)
}
EXPORT_SYMBOL_GPL(kthread_parkme);
+/**
+ * kthread_exit - Cause the current kthread return @result to kthread_stop().
+ * @result: The integer value to return to kthread_stop().
+ *
+ * While kthread_exit can be called directly, it exists so that
+ * functions which do some additional work in non-modular code such as
+ * module_put_and_kthread_exit can be implemented.
+ *
+ * Does not return.
+ */
+void __noreturn kthread_exit(long result)
+{
+ struct kthread *kthread = to_kthread(current);
+ kthread->result = result;
+ do_exit(0);
+}
+
+/**
+ * kthread_complete_and_exit - Exit the current kthread.
+ * @comp: Completion to complete
+ * @code: The integer value to return to kthread_stop().
+ *
+ * If present complete @comp and the reuturn code to kthread_stop().
+ *
+ * A kernel thread whose module may be removed after the completion of
+ * @comp can use this function exit safely.
+ *
+ * Does not return.
+ */
+void __noreturn kthread_complete_and_exit(struct completion *comp, long code)
+{
+ if (comp)
+ complete(comp);
+
+ kthread_exit(code);
+}
+EXPORT_SYMBOL(kthread_complete_and_exit);
+
static int kthread(void *_create)
{
static const struct sched_param param = { .sched_priority = 0 };
@@ -279,27 +321,17 @@ static int kthread(void *_create)
struct kthread *self;
int ret;
- set_kthread_struct(current);
self = to_kthread(current);
/* If user was SIGKILLed, I release the structure. */
done = xchg(&create->done, NULL);
if (!done) {
kfree(create);
- do_exit(-EINTR);
- }
-
- if (!self) {
- create->result = ERR_PTR(-ENOMEM);
- complete(done);
- do_exit(-ENOMEM);
+ kthread_exit(-EINTR);
}
self->threadfn = threadfn;
self->data = data;
- init_completion(&self->exited);
- init_completion(&self->parked);
- current->vfork_done = &self->exited;
/*
* The new thread inherited kthreadd's priority and CPU mask. Reset
@@ -326,7 +358,7 @@ static int kthread(void *_create)
__kthread_parkme(self);
ret = threadfn(data);
}
- do_exit(ret);
+ kthread_exit(ret);
}
/* called from kernel_clone() to get node information for about to be created task */
@@ -628,7 +660,7 @@ EXPORT_SYMBOL_GPL(kthread_park);
* instead of calling wake_up_process(): the thread will exit without
* calling threadfn().
*
- * If threadfn() may call do_exit() itself, the caller must ensure
+ * If threadfn() may call kthread_exit() itself, the caller must ensure
* task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
@@ -647,7 +679,7 @@ int kthread_stop(struct task_struct *k)
kthread_unpark(k);
wake_up_process(k);
wait_for_completion(&kthread->exited);
- ret = k->exit_code;
+ ret = kthread->result;
put_task_struct(k);
trace_sched_kthread_stop_ret(ret);
diff --git a/kernel/module.c b/kernel/module.c
index 24fc305afe95..1038c013d8b2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -337,12 +337,12 @@ static inline void add_taint_module(struct module *mod, unsigned flag,
* A thread that wants to hold a reference to a module only while it
* is running can call this to safely exit. nfsd and lockd use this.
*/
-void __noreturn __module_put_and_exit(struct module *mod, long code)
+void __noreturn __module_put_and_kthread_exit(struct module *mod, long code)
{
module_put(mod);
- do_exit(code);
+ kthread_exit(code);
}
-EXPORT_SYMBOL(__module_put_and_exit);
+EXPORT_SYMBOL(__module_put_and_kthread_exit);
/* Find a module section: 0 means not found. */
static unsigned int find_sec(const struct load_info *info, const char *name)
diff --git a/kernel/profile.c b/kernel/profile.c
index eb9c7f0f5ac5..37640a0bd8a3 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -133,79 +133,6 @@ int __ref profile_init(void)
return -ENOMEM;
}
-/* Profile event notifications */
-
-static BLOCKING_NOTIFIER_HEAD(task_exit_notifier);
-static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
-static BLOCKING_NOTIFIER_HEAD(munmap_notifier);
-
-void profile_task_exit(struct task_struct *task)
-{
- blocking_notifier_call_chain(&task_exit_notifier, 0, task);
-}
-
-int profile_handoff_task(struct task_struct *task)
-{
- int ret;
- ret = atomic_notifier_call_chain(&task_free_notifier, 0, task);
- return (ret == NOTIFY_OK) ? 1 : 0;
-}
-
-void profile_munmap(unsigned long addr)
-{
- blocking_notifier_call_chain(&munmap_notifier, 0, (void *)addr);
-}
-
-int task_handoff_register(struct notifier_block *n)
-{
- return atomic_notifier_chain_register(&task_free_notifier, n);
-}
-EXPORT_SYMBOL_GPL(task_handoff_register);
-
-int task_handoff_unregister(struct notifier_block *n)
-{
- return atomic_notifier_chain_unregister(&task_free_notifier, n);
-}
-EXPORT_SYMBOL_GPL(task_handoff_unregister);
-
-int profile_event_register(enum profile_type type, struct notifier_block *n)
-{
- int err = -EINVAL;
-
- switch (type) {
- case PROFILE_TASK_EXIT:
- err = blocking_notifier_chain_register(
- &task_exit_notifier, n);
- break;
- case PROFILE_MUNMAP:
- err = blocking_notifier_chain_register(
- &munmap_notifier, n);
- break;
- }
-
- return err;
-}
-EXPORT_SYMBOL_GPL(profile_event_register);
-
-int profile_event_unregister(enum profile_type type, struct notifier_block *n)
-{
- int err = -EINVAL;
-
- switch (type) {
- case PROFILE_TASK_EXIT:
- err = blocking_notifier_chain_unregister(
- &task_exit_notifier, n);
- break;
- case PROFILE_MUNMAP:
- err = blocking_notifier_chain_unregister(
- &munmap_notifier, n);
- break;
- }
-
- return err;
-}
-EXPORT_SYMBOL_GPL(profile_event_unregister);
-
#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
/*
* Each cpu has a pair of open-addressed hashtables for pending
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index f8589bf8d7dc..eea265082e97 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -419,8 +419,6 @@ static int ptrace_attach(struct task_struct *task, long request,
if (task->ptrace)
goto unlock_tasklist;
- if (seize)
- flags |= PT_SEIZED;
task->ptrace = flags;
ptrace_link(task, current);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 83872f95a1ea..2e4ae00e52d1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8642,14 +8642,6 @@ void __init init_idle(struct task_struct *idle, int cpu)
__sched_fork(0, idle);
- /*
- * The idle task doesn't need the kthread struct to function, but it
- * is dressed up as a per-CPU kthread and thus needs to play the part
- * if we want to avoid special-casing it in code that deals with per-CPU
- * kthreads.
- */
- set_kthread_struct(idle);
-
raw_spin_lock_irqsave(&idle->pi_lock, flags);
raw_spin_rq_lock(rq);
@@ -9469,6 +9461,14 @@ void __init sched_init(void)
enter_lazy_tlb(&init_mm, current);
/*
+ * The idle task doesn't need the kthread struct to function, but it
+ * is dressed up as a per-CPU kthread and thus needs to play the part
+ * if we want to avoid special-casing it in code that deals with per-CPU
+ * kthreads.
+ */
+ WARN_ON(!set_kthread_struct(current));
+
+ /*
* Make us the idle thread. Technically, schedule() should not be
* called from this thread, however somewhere below it might be,
* but because we are the idle thread, we just pick up running again
diff --git a/kernel/signal.c b/kernel/signal.c
index dfcee3888b00..38602738866e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -626,7 +626,8 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
*
* All callers have to hold the siglock.
*/
-int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info)
+int dequeue_signal(struct task_struct *tsk, sigset_t *mask,
+ kernel_siginfo_t *info, enum pid_type *type)
{
bool resched_timer = false;
int signr;
@@ -634,8 +635,10 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in
/* We only dequeue private signals from ourselves, we don't let
* signalfd steal them
*/
+ *type = PIDTYPE_PID;
signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer);
if (!signr) {
+ *type = PIDTYPE_TGID;
signr = __dequeue_signal(&tsk->signal->shared_pending,
mask, info, &resched_timer);
#ifdef CONFIG_POSIX_TIMERS
@@ -903,8 +906,8 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
struct task_struct *t;
sigset_t flush;
- if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) {
- if (!(signal->flags & SIGNAL_GROUP_EXIT))
+ if (signal->flags & SIGNAL_GROUP_EXIT) {
+ if (signal->core_state)
return sig == SIGKILL;
/*
* The process is in the middle of dying, nothing to do.
@@ -1029,7 +1032,7 @@ static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
* then start taking the whole group down immediately.
*/
if (sig_fatal(p, sig) &&
- !(signal->flags & SIGNAL_GROUP_EXIT) &&
+ (signal->core_state || !(signal->flags & SIGNAL_GROUP_EXIT)) &&
!sigismember(&t->real_blocked, sig) &&
(sig == SIGKILL || !p->ptrace)) {
/*
@@ -1820,6 +1823,7 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data)
* force_sig_seccomp - signals the task to allow in-process syscall emulation
* @syscall: syscall number to send to userland
* @reason: filter-supplied reason code to send to userland (via si_errno)
+ * @force_coredump: true to trigger a coredump
*
* Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
*/
@@ -2383,7 +2387,8 @@ static bool do_signal_stop(int signr)
WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK);
if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) ||
- unlikely(signal_group_exit(sig)))
+ unlikely(sig->flags & SIGNAL_GROUP_EXIT) ||
+ unlikely(sig->group_exec_task))
return false;
/*
* There is no group stop already in progress. We must
@@ -2544,7 +2549,7 @@ static void do_freezer_trap(void)
freezable_schedule();
}
-static int ptrace_signal(int signr, kernel_siginfo_t *info)
+static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
{
/*
* We do not check sig_kernel_stop(signr) but set this marker
@@ -2584,8 +2589,9 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info)
}
/* If the (new) signal is now blocked, requeue it. */
- if (sigismember(&current->blocked, signr)) {
- send_signal(signr, info, current, PIDTYPE_PID);
+ if (sigismember(&current->blocked, signr) ||
+ fatal_signal_pending(current)) {
+ send_signal(signr, info, current, type);
signr = 0;
}
@@ -2684,18 +2690,20 @@ relock:
goto relock;
}
- /* Has this task already been marked for death? */
- if (signal_group_exit(signal)) {
- ksig->info.si_signo = signr = SIGKILL;
- sigdelset(&current->pending.signal, SIGKILL);
- trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO,
- &sighand->action[SIGKILL - 1]);
- recalc_sigpending();
- goto fatal;
- }
-
for (;;) {
struct k_sigaction *ka;
+ enum pid_type type;
+
+ /* Has this task already been marked for death? */
+ if ((signal->flags & SIGNAL_GROUP_EXIT) ||
+ signal->group_exec_task) {
+ ksig->info.si_signo = signr = SIGKILL;
+ sigdelset(&current->pending.signal, SIGKILL);
+ trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO,
+ &sighand->action[SIGKILL - 1]);
+ recalc_sigpending();
+ goto fatal;
+ }
if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) &&
do_signal_stop(0))
@@ -2728,16 +2736,18 @@ relock:
* so that the instruction pointer in the signal stack
* frame points to the faulting instruction.
*/
+ type = PIDTYPE_PID;
signr = dequeue_synchronous_signal(&ksig->info);
if (!signr)
- signr = dequeue_signal(current, &current->blocked, &ksig->info);
+ signr = dequeue_signal(current, &current->blocked,
+ &ksig->info, &type);
if (!signr)
break; /* will return 0 */
if (unlikely(current->ptrace) && (signr != SIGKILL) &&
!(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) {
- signr = ptrace_signal(signr, &ksig->info);
+ signr = ptrace_signal(signr, &ksig->info, type);
if (!signr)
continue;
}
@@ -2863,13 +2873,13 @@ out:
}
/**
- * signal_delivered -
+ * signal_delivered - called after signal delivery to update blocked signals
* @ksig: kernel signal struct
* @stepping: nonzero if debugger single-step or block-step in use
*
* This function should be called when a signal has successfully been
* delivered. It updates the blocked signals accordingly (@ksig->ka.sa.sa_mask
- * is always blocked, and the signal itself is blocked unless %SA_NODEFER
+ * is always blocked), and the signal itself is blocked unless %SA_NODEFER
* is set in @ksig->ka.sa.sa_flags. Tracing is notified.
*/
static void signal_delivered(struct ksignal *ksig, int stepping)
@@ -2942,7 +2952,7 @@ void exit_signals(struct task_struct *tsk)
*/
cgroup_threadgroup_change_begin(tsk);
- if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) {
+ if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) {
tsk->flags |= PF_EXITING;
cgroup_threadgroup_change_end(tsk);
return;
@@ -3562,6 +3572,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
ktime_t *to = NULL, timeout = KTIME_MAX;
struct task_struct *tsk = current;
sigset_t mask = *which;
+ enum pid_type type;
int sig, ret = 0;
if (ts) {
@@ -3578,7 +3589,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
signotset(&mask);
spin_lock_irq(&tsk->sighand->siglock);
- sig = dequeue_signal(tsk, &mask, info);
+ sig = dequeue_signal(tsk, &mask, info, &type);
if (!sig && timeout) {
/*
* None ready, temporarily unblock those we're interested
@@ -3597,7 +3608,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info,
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, &tsk->real_blocked);
sigemptyset(&tsk->real_blocked);
- sig = dequeue_signal(tsk, &mask, info);
+ sig = dequeue_signal(tsk, &mask, info, &type);
}
spin_unlock_irq(&tsk->sighand->siglock);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index f00de83d0246..1d261fbe367b 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -38,11 +38,10 @@ void bacct_add_tsk(struct user_namespace *user_ns,
stats->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX);
stats->ac_btime64 = btime;
- if (thread_group_leader(tsk)) {
+ if (tsk->flags & PF_EXITING)
stats->ac_exitcode = tsk->exit_code;
- if (tsk->flags & PF_FORKNOEXEC)
- stats->ac_flag |= AFORK;
- }
+ if (thread_group_leader(tsk) && (tsk->flags & PF_FORKNOEXEC))
+ stats->ac_flag |= AFORK;
if (tsk->flags & PF_SUPERPRIV)
stats->ac_flag |= ASU;
if (tsk->flags & PF_DUMPCORE)