#include <linux/kasan.h>
#include <linux/scs.h>
#include <linux/io_uring.h>
+#include <linux/bpf.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
void *stack = task_stack_page(tsk);
struct vm_struct *vm = task_stack_vm_area(tsk);
+ if (vm) {
+ int i;
- /* All stack pages are in the same node. */
- if (vm)
- mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
- account * (THREAD_SIZE / 1024));
- else
+ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
+ mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
+ account * (PAGE_SIZE / 1024));
+ } else {
+ /* All stack pages are in the same node. */
mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
account * (THREAD_SIZE / 1024));
+ }
}
static int memcg_charge_kernel_stack(struct task_struct *tsk)
cgroup_free(tsk);
task_numa_free(tsk, true);
security_task_free(tsk);
+ bpf_task_storage_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
tsk->splice_pipe = NULL;
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
+ tsk->pf_io_worker = NULL;
account_kernel_stack(tsk, 1);
#endif
}
+static void mm_init_pasid(struct mm_struct *mm)
+{
+#ifdef CONFIG_IOMMU_SUPPORT
+ mm->pasid = INIT_PASID;
+#endif
+}
+
static void mm_init_uprobes_state(struct mm_struct *mm)
{
#ifdef CONFIG_UPROBES
mm_init_cpumask(mm);
mm_init_aio(mm);
mm_init_owner(mm, p);
+ mm_init_pasid(mm);
RCU_INIT_POINTER(mm->exe_file, NULL);
mmu_notifier_subscriptions_init(mm);
init_tlb_flush_pending(mm);
* invocations: in mmput() nobody alive left, in execve task is single
* threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
* mm->exe_file, but does so without using set_mm_exe_file() in order
- * to do avoid the need for any locks.
+ * to avoid the need for any locks.
*/
void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm;
- int retval;
tsk->min_flt = tsk->maj_flt = 0;
tsk->nvcsw = tsk->nivcsw = 0;
if (clone_flags & CLONE_VM) {
mmget(oldmm);
mm = oldmm;
- goto good_mm;
+ } else {
+ mm = dup_mm(tsk, current->mm);
+ if (!mm)
+ return -ENOMEM;
}
- retval = -ENOMEM;
- mm = dup_mm(tsk, current->mm);
- if (!mm)
- goto fail_nomem;
-
-good_mm:
tsk->mm = mm;
tsk->active_mm = mm;
return 0;
-
-fail_nomem:
- return retval;
}
static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
* /proc/<pid>/status where Pid and NSpid are always shown relative to
* the pid namespace of the procfs instance. The difference becomes
* obvious when sending around a pidfd between pid namespaces from a
- * different branch of the tree, i.e. where no ancestoral relation is
+ * different branch of the tree, i.e. where no ancestral relation is
* present between the pid namespaces:
* - create two new pid namespaces ns1 and ns2 in the initial pid
* namespace (also take care to create new mount namespaces in the
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
retval = -ERESTARTNOINTR;
- if (signal_pending(current))
+ if (task_sigpending(current))
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current, node);
if (!p)
goto fork_out;
- if (args->io_thread)
+ if (args->io_thread) {
+ /*
+ * Mark us an IO worker, and block any signal that isn't
+ * fatal or STOP
+ */
p->flags |= PF_IO_WORKER;
+ siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+ }
/*
* This _must_ happen before we call free_task(), i.e. before we jump
spin_lock_init(&p->alloc_lock);
init_sigpending(&p->pending);
+ p->sigqueue_cache = NULL;
p->utime = p->stime = p->gtime = 0;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
p->sequential_io = 0;
p->sequential_io_avg = 0;
#endif
+#ifdef CONFIG_BPF_SYSCALL
+ RCU_INIT_POINTER(p->bpf_storage, NULL);
+#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
retval = sched_fork(clone_flags, p);
if (retval)
goto bad_fork_cleanup_policy;
- retval = perf_event_init_task(p);
+ retval = perf_event_init_task(p, clone_flags);
if (retval)
goto bad_fork_cleanup_policy;
retval = audit_alloc(p);
.stack_size = (unsigned long)arg,
.io_thread = 1,
};
- struct task_struct *tsk;
- tsk = copy_process(NULL, 0, node, &args);
- if (!IS_ERR(tsk)) {
- sigfillset(&tsk->blocked);
- sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
- }
- return tsk;
+ return copy_process(NULL, 0, node, &args);
}
/*
return false;
/*
- * - make the CLONE_DETACHED bit reuseable for clone3
- * - make the CSIGNAL bits reuseable for clone3
+ * - make the CLONE_DETACHED bit reusable for clone3
+ * - make the CSIGNAL bits reusable for clone3
*/
if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
return false;