summaryrefslogtreecommitdiffstats
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c55
1 files changed, 39 insertions, 16 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 4385f3d639f2..142b23645d82 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -94,8 +94,8 @@
#include <linux/thread_info.h>
#include <linux/stackleak.h>
#include <linux/kasan.h>
+#include <linux/scs.h>
-#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -456,6 +456,8 @@ void put_task_stack(struct task_struct *tsk)
void free_task(struct task_struct *tsk)
{
+ scs_release(tsk);
+
#ifndef CONFIG_THREAD_INFO_IN_TASK
/*
* The task is finally done with both the stack and thread_info,
@@ -490,7 +492,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
LIST_HEAD(uf);
uprobe_start_dup_mmap();
- if (down_write_killable(&oldmm->mmap_sem)) {
+ if (mmap_write_lock_killable(oldmm)) {
retval = -EINTR;
goto fail_uprobe_end;
}
@@ -499,7 +501,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
/*
* Not linked in yet - no deadlock potential:
*/
- down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
+ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
/* No ordering required: file already has been exposed. */
RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
@@ -615,9 +617,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
/* a new mm has just been created */
retval = arch_dup_mmap(oldmm, mm);
out:
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
flush_tlb_mm(oldmm);
- up_write(&oldmm->mmap_sem);
+ mmap_write_unlock(oldmm);
dup_userfaultfd_complete(&uf);
fail_uprobe_end:
uprobe_end_dup_mmap();
@@ -647,9 +649,9 @@ static inline void mm_free_pgd(struct mm_struct *mm)
#else
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
- down_write(&oldmm->mmap_sem);
+ mmap_write_lock(oldmm);
RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
- up_write(&oldmm->mmap_sem);
+ mmap_write_unlock(oldmm);
return 0;
}
#define mm_alloc_pgd(mm) (0)
@@ -840,6 +842,8 @@ void __init fork_init(void)
NULL, free_vm_stack_cache);
#endif
+ scs_init();
+
lockdep_init_task(&init_task);
uprobes_init();
}
@@ -899,6 +903,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
if (err)
goto free_stack;
+ err = scs_prepare(tsk, node);
+ if (err)
+ goto free_stack;
+
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
@@ -1014,7 +1022,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm->vmacache_seqnum = 0;
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
- init_rwsem(&mm->mmap_sem);
+ mmap_init_lock(mm);
INIT_LIST_HEAD(&mm->mmlist);
mm->core_state = NULL;
mm_pgtables_bytes_init(mm);
@@ -1683,6 +1691,11 @@ static inline void rcu_copy_process(struct task_struct *p)
INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
p->rcu_tasks_idle_cpu = -1;
#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+ p->trc_reader_nesting = 0;
+ p->trc_reader_special.s = 0;
+ INIT_LIST_HEAD(&p->trc_holdout_list);
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
}
struct pid *pidfd_pid(const struct file *file)
@@ -1745,7 +1758,7 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
pid_t nr = -1;
if (likely(pid_has_task(pid, PIDTYPE_PID))) {
- ns = proc_pid_ns(file_inode(m->file));
+ ns = proc_pid_ns(file_inode(m->file)->i_sb);
nr = pid_nr_ns(pid, ns);
}
@@ -2486,11 +2499,11 @@ long do_fork(unsigned long clone_flags,
int __user *child_tidptr)
{
struct kernel_clone_args args = {
- .flags = (clone_flags & ~CSIGNAL),
+ .flags = (lower_32_bits(clone_flags) & ~CSIGNAL),
.pidfd = parent_tidptr,
.child_tid = child_tidptr,
.parent_tid = parent_tidptr,
- .exit_signal = (clone_flags & CSIGNAL),
+ .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL),
.stack = stack_start,
.stack_size = stack_size,
};
@@ -2508,8 +2521,9 @@ long do_fork(unsigned long clone_flags,
pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
{
struct kernel_clone_args args = {
- .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL),
- .exit_signal = (flags & CSIGNAL),
+ .flags = ((lower_32_bits(flags) | CLONE_VM |
+ CLONE_UNTRACED) & ~CSIGNAL),
+ .exit_signal = (lower_32_bits(flags) & CSIGNAL),
.stack = (unsigned long)fn,
.stack_size = (unsigned long)arg,
};
@@ -2570,11 +2584,11 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
#endif
{
struct kernel_clone_args args = {
- .flags = (clone_flags & ~CSIGNAL),
+ .flags = (lower_32_bits(clone_flags) & ~CSIGNAL),
.pidfd = parent_tidptr,
.child_tid = child_tidptr,
.parent_tid = parent_tidptr,
- .exit_signal = (clone_flags & CSIGNAL),
+ .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL),
.stack = newsp,
.tls = tls,
};
@@ -2605,6 +2619,14 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
struct clone_args args;
pid_t *kset_tid = kargs->set_tid;
+ BUILD_BUG_ON(offsetofend(struct clone_args, tls) !=
+ CLONE_ARGS_SIZE_VER0);
+ BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) !=
+ CLONE_ARGS_SIZE_VER1);
+ BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) !=
+ CLONE_ARGS_SIZE_VER2);
+ BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2);
+
if (unlikely(usize > PAGE_SIZE))
return -E2BIG;
if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
@@ -2631,7 +2653,8 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
!valid_signal(args.exit_signal)))
return -EINVAL;
- if ((args.flags & CLONE_INTO_CGROUP) && args.cgroup < 0)
+ if ((args.flags & CLONE_INTO_CGROUP) &&
+ (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2))
return -EINVAL;
*kargs = (struct kernel_clone_args){
generated by cgit v1.2.3 (git 2.39.1) at 2025-05-24 06:21:33 +0000