aboutsummaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c994
1 files changed, 584 insertions, 410 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 3b159c5991b..6a13c46cd87 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,18 +28,21 @@
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
+#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
-#include <linux/tracehook.h>
#include <linux/futex.h>
#include <linux/compat.h>
+#include <linux/kthread.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/rcupdate.h>
#include <linux/ptrace.h>
@@ -47,6 +50,7 @@
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
+#include <linux/proc_fs.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
@@ -58,7 +62,6 @@
#include <linux/taskstats_kern.h>
#include <linux/random.h>
#include <linux/tty.h>
-#include <linux/proc_fs.h>
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
@@ -66,6 +69,11 @@
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
#include <linux/oom.h>
+#include <linux/khugepaged.h>
+#include <linux/signalfd.h>
+#include <linux/uprobes.h>
+#include <linux/aio.h>
+#include <linux/compiler.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -76,11 +84,14 @@
#include <trace/events/sched.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/task.h>
+
/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
unsigned long total_forks; /* Handle normal Linux uptimes. */
-int nr_threads; /* The idle threads do not count.. */
+int nr_threads; /* The idle threads do not count.. */
int max_threads; /* tunable limit on nr_threads */
@@ -107,27 +118,69 @@ int nr_processes(void)
return total;
}
-#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-# define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL)
-# define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk))
+void __weak arch_release_task_struct(struct task_struct *tsk)
+{
+}
+
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static struct kmem_cache *task_struct_cachep;
-#endif
-#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
+static inline struct task_struct *alloc_task_struct_node(int node)
{
-#ifdef CONFIG_DEBUG_STACK_USAGE
- gfp_t mask = GFP_KERNEL | __GFP_ZERO;
-#else
- gfp_t mask = GFP_KERNEL;
+ return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
+}
+
+static inline void free_task_struct(struct task_struct *tsk)
+{
+ kmem_cache_free(task_struct_cachep, tsk);
+}
#endif
- return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
+
+void __weak arch_release_thread_info(struct thread_info *ti)
+{
+}
+
+#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+
+/*
+ * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
+ * kmemcache based allocator.
+ */
+# if THREAD_SIZE >= PAGE_SIZE
+static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+ int node)
+{
+ struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
+ THREAD_SIZE_ORDER);
+
+ return page ? page_address(page) : NULL;
}
static inline void free_thread_info(struct thread_info *ti)
{
- free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+ free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+}
+# else
+static struct kmem_cache *thread_info_cache;
+
+static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+ int node)
+{
+ return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+}
+
+static void free_thread_info(struct thread_info *ti)
+{
+ kmem_cache_free(thread_info_cache, ti);
+}
+
+void thread_info_cache_init(void)
+{
+ thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ THREAD_SIZE, 0, NULL);
+ BUG_ON(thread_info_cache == NULL);
}
+# endif
#endif
/* SLAB cache for signal_struct structures (tsk->signal) */
@@ -157,11 +210,13 @@ static void account_kernel_stack(struct thread_info *ti, int account)
void free_task(struct task_struct *tsk)
{
- prop_local_destroy_single(&tsk->dirties);
account_kernel_stack(tsk->stack, -1);
+ arch_release_thread_info(tsk->stack);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
+ put_seccomp_filter(tsk);
+ arch_release_task_struct(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -169,6 +224,7 @@ EXPORT_SYMBOL(free_task);
static inline void free_signal_struct(struct signal_struct *sig)
{
taskstats_tgid_free(sig);
+ sched_autogroup_exit(sig);
kmem_cache_free(signal_cachep, sig);
}
@@ -184,6 +240,8 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
+ task_numa_free(tsk);
+ security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
@@ -191,18 +249,13 @@ void __put_task_struct(struct task_struct *tsk)
if (!profile_handoff_task(tsk))
free_task(tsk);
}
+EXPORT_SYMBOL_GPL(__put_task_struct);
-/*
- * macro override instead of weak attribute alias, to workaround
- * gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions.
- */
-#ifndef arch_task_cache_init
-#define arch_task_cache_init()
-#endif
+void __init __weak arch_task_cache_init(void) { }
void __init fork_init(unsigned long mempages)
{
-#ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN L1_CACHE_BYTES
#endif
@@ -225,7 +278,7 @@ void __init fork_init(unsigned long mempages)
/*
* we need to allow at least 20 threads to boot a system
*/
- if(max_threads < 20)
+ if (max_threads < 20)
max_threads = 20;
init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
@@ -234,7 +287,7 @@ void __init fork_init(unsigned long mempages)
init_task.signal->rlim[RLIMIT_NPROC];
}
-int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst,
+int __weak arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
@@ -246,33 +299,26 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
struct task_struct *tsk;
struct thread_info *ti;
unsigned long *stackend;
-
+ int node = tsk_fork_get_node(orig);
int err;
- prepare_to_copy(orig);
-
- tsk = alloc_task_struct();
+ tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
- ti = alloc_thread_info(tsk);
- if (!ti) {
- free_task_struct(tsk);
- return NULL;
- }
+ ti = alloc_thread_info_node(tsk, node);
+ if (!ti)
+ goto free_tsk;
- err = arch_dup_task_struct(tsk, orig);
+ err = arch_dup_task_struct(tsk, orig);
if (err)
- goto out;
+ goto free_ti;
tsk->stack = ti;
- err = prop_local_init_single(&tsk->dirties);
- if (err)
- goto out;
-
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
+ clear_tsk_need_resched(tsk);
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
@@ -280,20 +326,24 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
tsk->stack_canary = get_random_int();
#endif
- /* One for us, one for whoever does the "release_task()" (usually parent) */
- atomic_set(&tsk->usage,2);
- atomic_set(&tsk->fs_excl, 0);
+ /*
+ * One for us, one for whoever does the "release_task()" (usually
+ * parent)
+ */
+ atomic_set(&tsk->usage, 2);
#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
+ tsk->task_frag.page = NULL;
account_kernel_stack(ti, 1);
return tsk;
-out:
+free_ti:
free_thread_info(ti);
+free_tsk:
free_task_struct(tsk);
return NULL;
}
@@ -305,10 +355,11 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
- struct mempolicy *pol;
+ uprobe_start_dup_mmap();
down_write(&oldmm->mmap_sem);
flush_cache_dup_mm(oldmm);
+ uprobe_dup_mmap(oldmm, mm);
/*
* Not linked in yet - no deadlock potential:
*/
@@ -316,9 +367,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
mm->locked_vm = 0;
mm->mmap = NULL;
- mm->mmap_cache = NULL;
- mm->free_area_cache = oldmm->mmap_base;
- mm->cached_hole_size = ~0UL;
+ mm->vmacache_seqnum = 0;
mm->map_count = 0;
cpumask_clear(mm_cpumask(mm));
mm->mm_rb = RB_ROOT;
@@ -328,22 +377,24 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
retval = ksm_fork(mm, oldmm);
if (retval)
goto out;
+ retval = khugepaged_fork(mm, oldmm);
+ if (retval)
+ goto out;
prev = NULL;
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
- long pages = vma_pages(mpnt);
- mm->total_vm -= pages;
vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
- -pages);
+ -vma_pages(mpnt));
continue;
}
charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
- unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
- if (security_vm_enough_memory(len))
+ unsigned long len = vma_pages(mpnt);
+
+ if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
goto fail_nomem;
charge = len;
}
@@ -352,11 +403,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
goto fail_nomem;
*tmp = *mpnt;
INIT_LIST_HEAD(&tmp->anon_vma_chain);
- pol = mpol_dup(vma_policy(mpnt));
- retval = PTR_ERR(pol);
- if (IS_ERR(pol))
+ retval = vma_dup_policy(mpnt, tmp);
+ if (retval)
goto fail_nomem_policy;
- vma_set_policy(tmp, pol);
tmp->vm_mm = mm;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
@@ -364,21 +413,25 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
tmp->vm_next = tmp->vm_prev = NULL;
file = tmp->vm_file;
if (file) {
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct address_space *mapping = file->f_mapping;
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
if (tmp->vm_flags & VM_SHARED)
mapping->i_mmap_writable++;
- tmp->vm_truncate_count = mpnt->vm_truncate_count;
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
- vma_prio_tree_add(tmp, mpnt);
+ if (unlikely(tmp->vm_flags & VM_NONLINEAR))
+ vma_nonlinear_insert(tmp,
+ &mapping->i_mmap_nonlinear);
+ else
+ vma_interval_tree_insert_after(tmp, mpnt,
+ &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/*
@@ -417,9 +470,10 @@ out:
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
+ uprobe_end_dup_mmap();
return retval;
fail_nomem_anon_vma_fork:
- mpol_put(pol);
+ mpol_put(vma_policy(tmp));
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
@@ -428,7 +482,7 @@ fail_nomem:
goto out;
}
-static inline int mm_alloc_pgd(struct mm_struct * mm)
+static inline int mm_alloc_pgd(struct mm_struct *mm)
{
mm->pgd = pgd_alloc(mm);
if (unlikely(!mm->pgd))
@@ -436,7 +490,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm)
return 0;
}
-static inline void mm_free_pgd(struct mm_struct * mm)
+static inline void mm_free_pgd(struct mm_struct *mm)
{
pgd_free(mm, mm->pgd);
}
@@ -469,30 +523,33 @@ static void mm_init_aio(struct mm_struct *mm)
{
#ifdef CONFIG_AIO
spin_lock_init(&mm->ioctx_lock);
- INIT_HLIST_HEAD(&mm->ioctx_list);
+ mm->ioctx_table = NULL;
#endif
}
-static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
+static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
{
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
- mm->flags = (current->mm) ?
- (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
- mm->nr_ptes = 0;
+ atomic_long_set(&mm->nr_ptes, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
- mm->free_area_cache = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = ~0UL;
mm_init_aio(mm);
mm_init_owner(mm, p);
- atomic_set(&mm->oom_disable_count, 0);
+ clear_tlb_flush_pending(mm);
- if (likely(!mm_alloc_pgd(mm))) {
+ if (current->mm) {
+ mm->flags = current->mm->flags & MMF_INIT_MASK;
+ mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+ } else {
+ mm->flags = default_dump_filter;
mm->def_flags = 0;
+ }
+
+ if (likely(!mm_alloc_pgd(mm))) {
mmu_notifier_mm_init(mm);
return mm;
}
@@ -501,19 +558,37 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
return NULL;
}
+static void check_mm(struct mm_struct *mm)
+{
+ int i;
+
+ for (i = 0; i < NR_MM_COUNTERS; i++) {
+ long x = atomic_long_read(&mm->rss_stat.count[i]);
+
+ if (unlikely(x))
+ printk(KERN_ALERT "BUG: Bad rss-counter state "
+ "mm:%p idx:%d val:%ld\n", mm, i, x);
+ }
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+ VM_BUG_ON(mm->pmd_huge_pte);
+#endif
+}
+
/*
* Allocate and initialize an mm_struct.
*/
-struct mm_struct * mm_alloc(void)
+struct mm_struct *mm_alloc(void)
{
- struct mm_struct * mm;
+ struct mm_struct *mm;
mm = allocate_mm();
- if (mm) {
- memset(mm, 0, sizeof(*mm));
- mm = mm_init(mm, current);
- }
- return mm;
+ if (!mm)
+ return NULL;
+
+ memset(mm, 0, sizeof(*mm));
+ mm_init_cpumask(mm);
+ return mm_init(mm, current);
}
/*
@@ -527,6 +602,7 @@ void __mmdrop(struct mm_struct *mm)
mm_free_pgd(mm);
destroy_context(mm);
mmu_notifier_mm_destroy(mm);
+ check_mm(mm);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
@@ -539,8 +615,10 @@ void mmput(struct mm_struct *mm)
might_sleep();
if (atomic_dec_and_test(&mm->mm_users)) {
+ uprobe_clear_state(mm);
exit_aio(mm);
ksm_exit(mm);
+ khugepaged_exit(mm); /* must run before exit_mmap */
exit_mmap(mm);
set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
@@ -548,7 +626,6 @@ void mmput(struct mm_struct *mm)
list_del(&mm->mmlist);
spin_unlock(&mmlist_lock);
}
- put_swap_token(mm);
if (mm->binfmt)
module_put(mm->binfmt->module);
mmdrop(mm);
@@ -556,6 +633,35 @@ void mmput(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mmput);
+void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+ if (new_exe_file)
+ get_file(new_exe_file);
+ if (mm->exe_file)
+ fput(mm->exe_file);
+ mm->exe_file = new_exe_file;
+}
+
+struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+ struct file *exe_file;
+
+ /* We need mmap_sem to protect against races with removal of exe_file */
+ down_read(&mm->mmap_sem);
+ exe_file = mm->exe_file;
+ if (exe_file)
+ get_file(exe_file);
+ up_read(&mm->mmap_sem);
+ return exe_file;
+}
+
+static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+ /* It's safe to write the exe_file pointer without exe_file_lock because
+ * this is called during fork when the task is not yet in /proc */
+ newmm->exe_file = get_mm_exe_file(oldmm);
+}
+
/**
* get_task_mm - acquire a reference to the task's mm
*
@@ -582,6 +688,58 @@ struct mm_struct *get_task_mm(struct task_struct *task)
}
EXPORT_SYMBOL_GPL(get_task_mm);
+struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
+{
+ struct mm_struct *mm;
+ int err;
+
+ err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (err)
+ return ERR_PTR(err);
+
+ mm = get_task_mm(task);
+ if (mm && mm != current->mm &&
+ !ptrace_may_access(task, mode)) {
+ mmput(mm);
+ mm = ERR_PTR(-EACCES);
+ }
+ mutex_unlock(&task->signal->cred_guard_mutex);
+
+ return mm;
+}
+
+static void complete_vfork_done(struct task_struct *tsk)
+{
+ struct completion *vfork;
+
+ task_lock(tsk);
+ vfork = tsk->vfork_done;
+ if (likely(vfork)) {
+ tsk->vfork_done = NULL;
+ complete(vfork);
+ }
+ task_unlock(tsk);
+}
+
+static int wait_for_vfork_done(struct task_struct *child,
+ struct completion *vfork)
+{
+ int killed;
+
+ freezer_do_not_count();
+ killed = wait_for_completion_killable(vfork);
+ freezer_count();
+
+ if (killed) {
+ task_lock(child);
+ child->vfork_done = NULL;
+ task_unlock(child);
+ }
+
+ put_task_struct(child);
+ return killed;
+}
+
/* Please note the differences between mmput and mm_release.
* mmput is called whenever we stop holding onto a mm_struct,
* error success whatever.
@@ -597,8 +755,6 @@ EXPORT_SYMBOL_GPL(get_task_mm);
*/
void mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
- struct completion *vfork_done = tsk->vfork_done;
-
/* Get rid of any futexes when releasing the mm */
#ifdef CONFIG_FUTEX
if (unlikely(tsk->robust_list)) {
@@ -615,20 +771,17 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
exit_pi_state_list(tsk);
#endif
+ uprobe_free_utask(tsk);
+
/* Get rid of any cached register state */
deactivate_mm(tsk, mm);
- /* notify parent sleeping on vfork() */
- if (vfork_done) {
- tsk->vfork_done = NULL;
- complete(vfork_done);
- }
-
/*
* If we're exiting normally, clear a user-space tid field if
* requested. We leave this alone when dying by signal, to leave
* the value intact in a core dump, and to save the unnecessary
- * trouble otherwise. Userland only wants this done for a sys_exit.
+ * trouble, say, a killed vfork parent shouldn't touch this mm.
+ * Userland only wants this done for a sys_exit.
*/
if (tsk->clear_child_tid) {
if (!(tsk->flags & PF_SIGNALED) &&
@@ -643,30 +796,34 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
}
tsk->clear_child_tid = NULL;
}
+
+ /*
+ * All done, finally we can wake up parent and return this mm to him.
+ * Also kthread_stop() uses this completion for synchronization.
+ */
+ if (tsk->vfork_done)
+ complete_vfork_done(tsk);
}
/*
* Allocate a new mm structure and copy contents from the
* mm structure of the passed in task structure.
*/
-struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm = current->mm;
int err;
- if (!oldmm)
- return NULL;
-
mm = allocate_mm();
if (!mm)
goto fail_nomem;
memcpy(mm, oldmm, sizeof(*mm));
+ mm_init_cpumask(mm);
- /* Initializing for Swap token stuff */
- mm->token_priority = 0;
- mm->last_interval = 0;
-
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+ mm->pmd_huge_pte = NULL;
+#endif
if (!mm_init(mm, tsk))
goto fail_nomem;
@@ -705,9 +862,9 @@ fail_nocontext:
return NULL;
}
-static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
{
- struct mm_struct * mm, *oldmm;
+ struct mm_struct *mm, *oldmm;
int retval;
tsk->min_flt = tsk->maj_flt = 0;
@@ -728,6 +885,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
if (!oldmm)
return 0;
+ /* initialize the new vmacache entries */
+ vmacache_flush(tsk);
+
if (clone_flags & CLONE_VM) {
atomic_inc(&oldmm->mm_users);
mm = oldmm;
@@ -740,12 +900,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
goto fail_nomem;
good_mm:
- /* Initializing for Swap token stuff */
- mm->token_priority = 0;
- mm->last_interval = 0;
- if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
- atomic_inc(&mm->oom_disable_count);
-
tsk->mm = mm;
tsk->active_mm = mm;
return 0;
@@ -774,7 +928,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
return 0;
}
-static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
{
struct files_struct *oldf, *newf;
int error = 0;
@@ -805,6 +959,7 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
{
#ifdef CONFIG_BLOCK
struct io_context *ioc = current->io_context;
+ struct io_context *new_ioc;
if (!ioc)
return 0;
@@ -812,15 +967,15 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
* Share io context with parent, if CLONE_IO is set
*/
if (clone_flags & CLONE_IO) {
- tsk->io_context = ioc_task_link(ioc);
- if (unlikely(!tsk->io_context))
- return -ENOMEM;
+ ioc_task_link(ioc);
+ tsk->io_context = ioc;
} else if (ioprio_valid(ioc->ioprio)) {
- tsk->io_context = alloc_io_context(GFP_KERNEL, -1);
- if (unlikely(!tsk->io_context))
+ new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
+ if (unlikely(!new_ioc))
return -ENOMEM;
- tsk->io_context->ioprio = ioc->ioprio;
+ new_ioc->ioprio = ioc->ioprio;
+ put_io_context(new_ioc);
}
#endif
return 0;
@@ -845,8 +1000,10 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
void __cleanup_sighand(struct sighand_struct *sighand)
{
- if (atomic_dec_and_test(&sighand->count))
+ if (atomic_dec_and_test(&sighand->count)) {
+ signalfd_cleanup(sighand);
kmem_cache_free(sighand_cachep, sighand);
+ }
}
@@ -887,9 +1044,12 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
atomic_set(&sig->sigcnt, 1);
+
+ /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+ tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
init_waitqueue_head(&sig->wait_chldexit);
- if (clone_flags & CLONE_NEWPID)
- sig->flags |= SIGNAL_UNKILLABLE;
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
INIT_LIST_HEAD(&sig->posix_timers);
@@ -904,26 +1064,23 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
posix_cpu_timers_init_group(sig);
tty_audit_fork(sig);
+ sched_autogroup_fork(sig);
+
+#ifdef CONFIG_CGROUPS
+ init_rwsem(&sig->group_rwsem);
+#endif
- sig->oom_adj = current->signal->oom_adj;
sig->oom_score_adj = current->signal->oom_score_adj;
+ sig->oom_score_adj_min = current->signal->oom_score_adj_min;
+
+ sig->has_child_subreaper = current->signal->has_child_subreaper ||
+ current->signal->is_child_subreaper;
mutex_init(&sig->cred_guard_mutex);
return 0;
}
-static void copy_flags(unsigned long clone_flags, struct task_struct *p)
-{
- unsigned long new_flags = p->flags;
-
- new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
- new_flags |= PF_FORKNOEXEC;
- new_flags |= PF_STARTING;
- p->flags = new_flags;
- clear_freeze_flag(p);
-}
-
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
@@ -935,31 +1092,39 @@ static void rt_mutex_init_task(struct task_struct *p)
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init_raw(&p->pi_waiters, &p->pi_lock);
+ p->pi_waiters = RB_ROOT;
+ p->pi_waiters_leftmost = NULL;
p->pi_blocked_on = NULL;
+ p->pi_top_task = NULL;
#endif
}
-#ifdef CONFIG_MM_OWNER
+#ifdef CONFIG_MEMCG
void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
mm->owner = p;
}
-#endif /* CONFIG_MM_OWNER */
+#endif /* CONFIG_MEMCG */
/*
* Initialize POSIX timer handling for a single task.
*/
static void posix_cpu_timers_init(struct task_struct *tsk)
{
- tsk->cputime_expires.prof_exp = cputime_zero;
- tsk->cputime_expires.virt_exp = cputime_zero;
+ tsk->cputime_expires.prof_exp = 0;
+ tsk->cputime_expires.virt_exp = 0;
tsk->cputime_expires.sched_exp = 0;
INIT_LIST_HEAD(&tsk->cpu_timers[0]);
INIT_LIST_HEAD(&tsk->cpu_timers[1]);
INIT_LIST_HEAD(&tsk->cpu_timers[2]);
}
+static inline void
+init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
+{
+ task->pids[type].pid = pid;
+}
+
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
@@ -970,7 +1135,6 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
*/
static struct task_struct *copy_process(unsigned long clone_flags,
unsigned long stack_start,
- struct pt_regs *regs,
unsigned long stack_size,
int __user *child_tidptr,
struct pid *pid,
@@ -978,11 +1142,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
{
int retval;
struct task_struct *p;
- int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
+ if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
+ return ERR_PTR(-EINVAL);
+
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
@@ -1008,6 +1174,18 @@ static struct task_struct *copy_process(unsigned long clone_flags,
current->signal->flags & SIGNAL_UNKILLABLE)
return ERR_PTR(-EINVAL);
+ /*
+ * If the new process will be in a different pid or user namespace
+ * do not allow it to share a thread group or signal handlers or
+ * parent with the forking task.
+ */
+ if (clone_flags & CLONE_SIGHAND) {
+ if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
+ (task_active_pid_ns(current) !=
+ current->nsproxy->pid_ns_for_children))
+ return ERR_PTR(-EINVAL);
+ }
+
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
@@ -1018,6 +1196,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
ftrace_graph_init_task(p);
+ get_seccomp_filter(p);
rt_mutex_init_task(p);
@@ -1028,10 +1207,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
task_rlimit(p, RLIMIT_NPROC)) {
- if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
- p->real_cred->user != INIT_USER)
+ if (p->real_cred->user != INIT_USER &&
+ !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
goto bad_fork_free;
}
+ current->flags &= ~PF_NPROC_EXCEEDED;
retval = copy_creds(p, clone_flags);
if (retval < 0)
@@ -1049,9 +1229,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
- p->did_exec = 0;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
- copy_flags(clone_flags, p);
+ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
+ p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
rcu_copy_process(p);
@@ -1060,15 +1240,17 @@ static struct task_struct *copy_process(unsigned long clone_flags,
init_sigpending(&p->pending);
- p->utime = cputime_zero;
- p->stime = cputime_zero;
- p->gtime = cputime_zero;
- p->utimescaled = cputime_zero;
- p->stimescaled = cputime_zero;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
- p->prev_utime = cputime_zero;
- p->prev_stime = cputime_zero;
+ p->utime = p->stime = p->gtime = 0;
+ p->utimescaled = p->stimescaled = 0;
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ p->prev_cputime.utime = p->prev_cputime.stime = 0;
+#endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+ seqlock_init(&p->vtime_seqlock);
+ p->vtime_snap = 0;
+ p->vtime_snap_whence = VTIME_SLEEPING;
#endif
+
#if defined(SPLIT_RSS_COUNTING)
memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif
@@ -1080,29 +1262,30 @@ static struct task_struct *copy_process(unsigned long clone_flags,
posix_cpu_timers_init(p);
- p->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
p->io_context = NULL;
p->audit_context = NULL;
+ if (clone_flags & CLONE_THREAD)
+ threadgroup_change_begin(current);
cgroup_fork(p);
#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_cgroup;
- }
- mpol_fix_fork_child_flag(p);
+ if (IS_ERR(p->mempolicy)) {
+ retval = PTR_ERR(p->mempolicy);
+ p->mempolicy = NULL;
+ goto bad_fork_cleanup_threadgroup_lock;
+ }
+#endif
+#ifdef CONFIG_CPUSETS
+ p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
+ p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
+ seqcount_init(&p->mems_allowed_seq);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
- p->hardirqs_enabled = 1;
-#else
p->hardirqs_enabled = 0;
-#endif
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
@@ -1124,70 +1307,70 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
p->memcg_batch.do_batch = 0;
p->memcg_batch.memcg = NULL;
#endif
+#ifdef CONFIG_BCACHE
+ p->sequential_io = 0;
+ p->sequential_io_avg = 0;
+#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
- sched_fork(p, clone_flags);
+ retval = sched_fork(clone_flags, p);
+ if (retval)
+ goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
-
- if ((retval = audit_alloc(p)))
+ retval = audit_alloc(p);
+ if (retval)
goto bad_fork_cleanup_policy;
/* copy all the process information */
- if ((retval = copy_semundo(clone_flags, p)))
+ retval = copy_semundo(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_audit;
- if ((retval = copy_files(clone_flags, p)))
+ retval = copy_files(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_semundo;
- if ((retval = copy_fs(clone_flags, p)))
+ retval = copy_fs(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_files;
- if ((retval = copy_sighand(clone_flags, p)))
+ retval = copy_sighand(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_fs;
- if ((retval = copy_signal(clone_flags, p)))
+ retval = copy_signal(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_sighand;
- if ((retval = copy_mm(clone_flags, p)))
+ retval = copy_mm(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_signal;
- if ((retval = copy_namespaces(clone_flags, p)))
+ retval = copy_namespaces(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_mm;
- if ((retval = copy_io(clone_flags, p)))
+ retval = copy_io(clone_flags, p);
+ if (retval)
goto bad_fork_cleanup_namespaces;
- retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
+ retval = copy_thread(clone_flags, stack_start, stack_size, p);
if (retval)
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
retval = -ENOMEM;
- pid = alloc_pid(p->nsproxy->pid_ns);
+ pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (!pid)
goto bad_fork_cleanup_io;
-
- if (clone_flags & CLONE_NEWPID) {
- retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
- if (retval < 0)
- goto bad_fork_free_pid;
- }
- }
-
- p->pid = pid_nr(pid);
- p->tgid = p->pid;
- if (clone_flags & CLONE_THREAD)
- p->tgid = current->tgid;
-
- if (current->nsproxy != p->nsproxy) {
- retval = ns_cgroup_clone(p, pid);
- if (retval)
- goto bad_fork_free_pid;
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
/*
* Clear TID on mm_release()?
*/
- p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
+ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
+#ifdef CONFIG_BLOCK
+ p->plug = NULL;
+#endif
#ifdef CONFIG_FUTEX
p->robust_list = NULL;
#ifdef CONFIG_COMPAT
@@ -1214,24 +1397,32 @@ static struct task_struct *copy_process(unsigned long clone_flags,
clear_all_latency_tracing(p);
/* ok, now we should be set up.. */
- p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
+ p->pid = pid_nr(pid);
+ if (clone_flags & CLONE_THREAD) {
+ p->exit_signal = -1;
+ p->group_leader = current->group_leader;
+ p->tgid = current->tgid;
+ } else {
+ if (clone_flags & CLONE_PARENT)
+ p->exit_signal = current->group_leader->exit_signal;
+ else
+ p->exit_signal = (clone_flags & CSIGNAL);
+ p->group_leader = p;
+ p->tgid = p->pid;
+ }
+
+ p->nr_dirtied = 0;
+ p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
+ p->dirty_paused_when = 0;
+
p->pdeath_signal = 0;
- p->exit_state = 0;
+ INIT_LIST_HEAD(&p->thread_group);
+ p->task_works = NULL;
/*
- * Ok, make it visible to the rest of the system.
- * We dont wake it up yet.
+ * Make it visible to the rest of the system, but dont wake it up yet.
+ * Need tasklist lock for parent etc handling!
*/
- p->group_leader = p;
- INIT_LIST_HEAD(&p->thread_group);
-
- /* Now that the task is set up, run cgroup callbacks if
- * necessary. We need to run them before the task is visible
- * on the tasklist. */
- cgroup_fork_callbacks(p);
- cgroup_callbacks_done = 1;
-
- /* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
/* CLONE_PARENT re-uses the old parent */
@@ -1252,7 +1443,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
* it's process group.
* A fatal signal pending means that current will exit, so the new
* thread can't slip out of an OOM kill (or normal SIGKILL).
- */
+ */
recalc_sigpending();
if (signal_pending(current)) {
spin_unlock(&current->sighand->siglock);
@@ -1261,39 +1452,53 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_free_pid;
}
- if (clone_flags & CLONE_THREAD) {
- current->signal->nr_threads++;
- atomic_inc(&current->signal->live);
- atomic_inc(&current->signal->sigcnt);
- p->group_leader = current->group_leader;
- list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
- }
-
if (likely(p->pid)) {
- tracehook_finish_clone(p, clone_flags, trace);
+ ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
+ init_task_pid(p, PIDTYPE_PID, pid);
if (thread_group_leader(p)) {
- if (clone_flags & CLONE_NEWPID)
- p->nsproxy->pid_ns->child_reaper = p;
+ init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
+ init_task_pid(p, PIDTYPE_SID, task_session(current));
+
+ if (is_child_reaper(pid)) {
+ ns_of_pid(pid)->child_reaper = p;
+ p->signal->flags |= SIGNAL_UNKILLABLE;
+ }
p->signal->leader_pid = pid;
p->signal->tty = tty_kref_get(current->signal->tty);
- attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
- attach_pid(p, PIDTYPE_SID, task_session(current));
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
- __get_cpu_var(process_counts)++;
+ attach_pid(p, PIDTYPE_PGID);
+ attach_pid(p, PIDTYPE_SID);
+ __this_cpu_inc(process_counts);
+ } else {
+ current->signal->nr_threads++;
+ atomic_inc(&current->signal->live);
+ atomic_inc(&current->signal->sigcnt);
+ list_add_tail_rcu(&p->thread_group,
+ &p->group_leader->thread_group);
+ list_add_tail_rcu(&p->thread_node,
+ &p->signal->thread_head);
}
- attach_pid(p, PIDTYPE_PID, pid);
+ attach_pid(p, PIDTYPE_PID);
nr_threads++;
}
total_forks++;
spin_unlock(&current->sighand->siglock);
+ syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
+
proc_fork_connector(p);
cgroup_post_fork(p);
+ if (clone_flags & CLONE_THREAD)
+ threadgroup_change_end(current);
perf_event_fork(p);
+
+ trace_task_newtask(p, clone_flags);
+ uprobe_copy_process(p, clone_flags);
+
return p;
bad_fork_free_pid:
@@ -1305,13 +1510,8 @@ bad_fork_cleanup_io:
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
- if (p->mm) {
- task_lock(p);
- if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
- atomic_dec(&p->mm->oom_disable_count);
- task_unlock(p);
+ if (p->mm)
mmput(p->mm);
- }
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
free_signal_struct(p->signal);
@@ -1329,9 +1529,10 @@ bad_fork_cleanup_policy:
perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
-bad_fork_cleanup_cgroup:
+bad_fork_cleanup_threadgroup_lock:
#endif
- cgroup_exit(p, cgroup_callbacks_done);
+ if (clone_flags & CLONE_THREAD)
+ threadgroup_change_end(current);
delayacct_tsk_free(p);
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
@@ -1343,12 +1544,6 @@ fork_out:
return ERR_PTR(retval);
}
-noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
-{
- memset(regs, 0, sizeof(struct pt_regs));
- return regs;
-}
-
static inline void init_idle_pids(struct pid_link *links)
{
enum pid_type type;
@@ -1359,13 +1554,10 @@ static inline void init_idle_pids(struct pid_link *links)
}
}
-struct task_struct * __cpuinit fork_idle(int cpu)
+struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- struct pt_regs regs;
-
- task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
- &init_struct_pid, 0);
+ task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
if (!IS_ERR(task)) {
init_idle_pids(task->pids);
init_idle(task, cpu);
@@ -1382,7 +1574,6 @@ struct task_struct * __cpuinit fork_idle(int cpu)
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
- struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
@@ -1392,44 +1583,24 @@ long do_fork(unsigned long clone_flags,
long nr;
/*
- * Do some preliminary argument and permissions checking before we
- * actually start allocating stuff
- */
- if (clone_flags & CLONE_NEWUSER) {
- if (clone_flags & CLONE_THREAD)
- return -EINVAL;
- /* hopefully this check will go away when userns support is
- * complete
- */
- if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
- !capable(CAP_SETGID))
- return -EPERM;
- }
-
- /*
- * We hope to recycle these flags after 2.6.26
+ * Determine whether and which event to report to ptracer. When
+ * called from kernel_thread or CLONE_UNTRACED is explicitly
+ * requested, no event is reported; otherwise, report if the event
+ * for the type of forking is enabled.
*/
- if (unlikely(clone_flags & CLONE_STOPPED)) {
- static int __read_mostly count = 100;
-
- if (count > 0 && printk_ratelimit()) {
- char comm[TASK_COMM_LEN];
+ if (!(clone_flags & CLONE_UNTRACED)) {
+ if (clone_flags & CLONE_VFORK)
+ trace = PTRACE_EVENT_VFORK;
+ else if ((clone_flags & CSIGNAL) != SIGCHLD)
+ trace = PTRACE_EVENT_CLONE;
+ else
+ trace = PTRACE_EVENT_FORK;
- count--;
- printk(KERN_INFO "fork(): process `%s' used deprecated "
- "clone flags 0x%lx\n",
- get_task_comm(comm, current),
- clone_flags & CLONE_STOPPED);
- }
+ if (likely(!ptrace_event_enabled(current, trace)))
+ trace = 0;
}
- /*
- * When called from kernel_thread, don't do user tracing stuff.
- */
- if (likely(user_mode(regs)))
- trace = tracehook_prepare_clone(clone_flags);
-
- p = copy_process(clone_flags, stack_start, regs, stack_size,
+ p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
@@ -1437,10 +1608,12 @@ long do_fork(unsigned long clone_flags,
*/
if (!IS_ERR(p)) {
struct completion vfork;
+ struct pid *pid;
trace_sched_process_fork(current, p);
- nr = task_pid_vnr(p);
+ pid = get_task_pid(p, PIDTYPE_PID);
+ nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
@@ -1448,45 +1621,84 @@ long do_fork(unsigned long clone_flags,
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
+ get_task_struct(p);
}
- audit_finish_fork(p);
- tracehook_report_clone(regs, clone_flags, nr, p);
+ wake_up_new_task(p);
- /*
- * We set PF_STARTING at creation in case tracing wants to
- * use this to distinguish a fully live task from one that
- * hasn't gotten to tracehook_report_clone() yet. Now we
- * clear it and set the child going.
- */
- p->flags &= ~PF_STARTING;
-
- if (unlikely(clone_flags & CLONE_STOPPED)) {
- /*
- * We'll start up with an immediate SIGSTOP.
- */
- sigaddset(&p->pending.signal, SIGSTOP);
- set_tsk_thread_flag(p, TIF_SIGPENDING);
- __set_task_state(p, TASK_STOPPED);
- } else {
- wake_up_new_task(p, clone_flags);
- }
-
- tracehook_report_clone_complete(trace, regs,
- clone_flags, nr, p);
+ /* forking complete and child started to run, tell ptracer */
+ if (unlikely(trace))
+ ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
- freezer_do_not_count();
- wait_for_completion(&vfork);
- freezer_count();
- tracehook_report_vfork_done(p, nr);
+ if (!wait_for_vfork_done(p, &vfork))
+ ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
+
+ put_pid(pid);
} else {
nr = PTR_ERR(p);
}
return nr;
}
+/*
+ * Create a kernel thread.
+ */
+pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
+{
+ return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
+ (unsigned long)arg, NULL, NULL);
+}
+
+#ifdef __ARCH_WANT_SYS_FORK
+SYSCALL_DEFINE0(fork)
+{
+#ifdef CONFIG_MMU
+ return do_fork(SIGCHLD, 0, 0, NULL, NULL);
+#else
+ /* can not support in nommu mode */
+ return -EINVAL;
+#endif
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_VFORK
+SYSCALL_DEFINE0(vfork)
+{
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
+ 0, NULL, NULL);
+}
+#endif
+
+#ifdef __ARCH_WANT_SYS_CLONE
+#ifdef CONFIG_CLONE_BACKWARDS
+SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
+ int __user *, parent_tidptr,
+ int, tls_val,
+ int __user *, child_tidptr)
+#elif defined(CONFIG_CLONE_BACKWARDS2)
+SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
+ int __user *, parent_tidptr,
+ int __user *, child_tidptr,
+ int, tls_val)
+#elif defined(CONFIG_CLONE_BACKWARDS3)
+SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
+ int, stack_size,
+ int __user *, parent_tidptr,
+ int __user *, child_tidptr,
+ int, tls_val)
+#else
+SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
+ int __user *, parent_tidptr,
+ int __user *, child_tidptr,
+ int, tls_val)
+#endif
+{
+ return do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr);
+}
+#endif
+
#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
@@ -1514,46 +1726,41 @@ void __init proc_caches_init(void)
fs_cachep = kmem_cache_create("fs_cache",
sizeof(struct fs_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+ /*
+ * FIXME! The "sizeof(struct mm_struct)" currently includes the
+ * whole struct cpumask for the OFFSTACK case. We could change
+ * this to *only* allocate as much of it as required by the
+ * maximum number of CPU's we can ever have. The cpumask_allocation
+ * is at the end of the structure, exactly for that reason.
+ */
mm_cachep = kmem_cache_create("mm_struct",
sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
mmap_init();
+ nsproxy_cache_init();
}
/*
- * Check constraints on flags passed to the unshare system call and
- * force unsharing of additional process context as appropriate.
+ * Check constraints on flags passed to the unshare system call.
*/
-static void check_unshare_flags(unsigned long *flags_ptr)
+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))
+ return -EINVAL;
/*
- * If unsharing a thread from a thread group, must also
- * unshare vm.
- */
- if (*flags_ptr & CLONE_THREAD)
- *flags_ptr |= CLONE_VM;
-
- /*
- * If unsharing vm, must also unshare signal handlers.
+ * Not implemented, but pretend it works if there is nothing to
+ * unshare. Note that unsharing CLONE_THREAD or CLONE_SIGHAND
+ * needs to unshare vm.
*/
- if (*flags_ptr & CLONE_VM)
- *flags_ptr |= CLONE_SIGHAND;
-
- /*
- * If unsharing namespace, must also unshare filesystem information.
- */
- if (*flags_ptr & CLONE_NEWNS)
- *flags_ptr |= CLONE_FS;
-}
-
-/*
- * Unsharing of tasks created with CLONE_THREAD is not supported yet
- */
-static int unshare_thread(unsigned long unshare_flags)
-{
- if (unshare_flags & CLONE_THREAD)
- return -EINVAL;
+ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
+ /* FIXME: get_task_mm() increments ->mm_users */
+ if (atomic_read(&current->mm->mm_users) > 1)
+ return -EINVAL;
+ }
return 0;
}
@@ -1580,34 +1787,6 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
}
/*
- * Unsharing of sighand is not supported yet
- */
-static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
-{
- struct sighand_struct *sigh = current->sighand;
-
- if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1)
- return -EINVAL;
- else
- return 0;
-}
-
-/*
- * Unshare vm if it is being shared
- */
-static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
-{
- struct mm_struct *mm = current->mm;
-
- if ((unshare_flags & CLONE_VM) &&
- (mm && atomic_read(&mm->mm_users) > 1)) {
- return -EINVAL;
- }
-
- return 0;
-}
-
-/*
* Unshare file descriptor table if it is being shared
*/
static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
@@ -1635,23 +1814,37 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
*/
SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
{
- int err = 0;
struct fs_struct *fs, *new_fs = NULL;
- struct sighand_struct *new_sigh = NULL;
- struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
struct files_struct *fd, *new_fd = NULL;
+ struct cred *new_cred = NULL;
struct nsproxy *new_nsproxy = NULL;
int do_sysvsem = 0;
+ int err;
- check_unshare_flags(&unshare_flags);
+ /*
+ * If unsharing a user namespace must also unshare the thread.
+ */
+ if (unshare_flags & CLONE_NEWUSER)
+ unshare_flags |= CLONE_THREAD | CLONE_FS;
+ /*
+ * If unsharing a thread from a thread group, must also unshare vm.
+ */
+ if (unshare_flags & CLONE_THREAD)
+ unshare_flags |= CLONE_VM;
+ /*
+ * If unsharing vm, must also unshare signal handlers.
+ */
+ if (unshare_flags & CLONE_VM)
+ unshare_flags |= CLONE_SIGHAND;
+ /*
+ * If unsharing namespace, must also unshare filesystem information.
+ */
+ if (unshare_flags & CLONE_NEWNS)
+ unshare_flags |= CLONE_FS;
- /* Return -EINVAL for all unsupported flags */
- err = -EINVAL;
- if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
- CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
- CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
+ err = check_unshare_flags(unshare_flags);
+ if (err)
goto bad_unshare_out;
-
/*
* CLONE_NEWIPC must also detach from the undolist: after switching
* to a new ipc namespace, the semaphore arrays from the old
@@ -1659,21 +1852,21 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
*/
if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
do_sysvsem = 1;
- if ((err = unshare_thread(unshare_flags)))
+ err = unshare_fs(unshare_flags, &new_fs);
+ if (err)
goto bad_unshare_out;
- if ((err = unshare_fs(unshare_flags, &new_fs)))
- goto bad_unshare_cleanup_thread;
- if ((err = unshare_sighand(unshare_flags, &new_sigh)))
+ err = unshare_fd(unshare_flags, &new_fd);
+ if (err)
goto bad_unshare_cleanup_fs;
- if ((err = unshare_vm(unshare_flags, &new_mm)))
- goto bad_unshare_cleanup_sigh;
- if ((err = unshare_fd(unshare_flags, &new_fd)))
- goto bad_unshare_cleanup_vm;
- if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
- new_fs)))
+ err = unshare_userns(unshare_flags, &new_cred);
+ if (err)
goto bad_unshare_cleanup_fd;
+ err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
+ new_cred, new_fs);
+ if (err)
+ goto bad_unshare_cleanup_cred;
- if (new_fs || new_mm || new_fd || do_sysvsem || new_nsproxy) {
+ if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
if (do_sysvsem) {
/*
* CLONE_SYSVSEM is equivalent to sys_exit().
@@ -1681,10 +1874,8 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
exit_sem(current);
}
- if (new_nsproxy) {
+ if (new_nsproxy)
switch_task_namespaces(current, new_nsproxy);
- new_nsproxy = NULL;
- }
task_lock(current);
@@ -1699,19 +1890,6 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
spin_unlock(&fs->lock);
}
- if (new_mm) {
- mm = current->mm;
- active_mm = current->active_mm;
- current->mm = new_mm;
- current->active_mm = new_mm;
- if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
- atomic_dec(&mm->oom_disable_count);
- atomic_inc(&new_mm->oom_disable_count);
- }
- activate_mm(active_mm, new_mm);
- new_mm = mm;
- }
-
if (new_fd) {
fd = current->files;
current->files = new_fd;
@@ -1719,29 +1897,25 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
}
task_unlock(current);
- }
- if (new_nsproxy)
- put_nsproxy(new_nsproxy);
+ if (new_cred) {
+ /* Install the new user namespace */
+ commit_creds(new_cred);
+ new_cred = NULL;
+ }
+ }
+bad_unshare_cleanup_cred:
+ if (new_cred)
+ put_cred(new_cred);
bad_unshare_cleanup_fd:
if (new_fd)
put_files_struct(new_fd);
-bad_unshare_cleanup_vm:
- if (new_mm)
- mmput(new_mm);
-
-bad_unshare_cleanup_sigh:
- if (new_sigh)
- if (atomic_dec_and_test(&new_sigh->count))
- kmem_cache_free(sighand_cachep, new_sigh);
-
bad_unshare_cleanup_fs:
if (new_fs)
free_fs_struct(new_fs);
-bad_unshare_cleanup_thread:
bad_unshare_out:
return err;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-05 00:11:10 +0000