X-Git-Url: http://git.cascardo.info/?a=blobdiff_plain;f=kernel%2Ffork.c;h=beb31725f7e2746fb17cdd305c4193ab2c70e551;hb=33e09f0ee76e9e4108c5aed67e027ef5e3fe0634;hp=42451aeb245f9aed29539ff75f648a2386d795b3;hpb=cd81a9170e69e018bbaba547c1fd85a585f5697a;p=cascardo%2Flinux.git

diff --git a/kernel/fork.c b/kernel/fork.c
index 42451aeb245f..beb31725f7e2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -148,57 +148,49 @@ static inline void free_task_struct(struct task_struct *tsk)
 }
 #endif
 
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
 {
 }
 
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_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,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
-	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
-						  THREAD_SIZE_ORDER);
-
-	if (page)
-		memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-					    1 << THREAD_SIZE_ORDER);
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
 }
 
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
 {
-	struct page *page = virt_to_page(ti);
-
-	memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-				    -(1 << THREAD_SIZE_ORDER));
-	__free_kmem_pages(page, THREAD_SIZE_ORDER);
+	__free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
 }
 # else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
 
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 						  int node)
 {
-	return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+	return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
 }
 
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
 {
-	kmem_cache_free(thread_info_cache, ti);
+	kmem_cache_free(thread_stack_cache, stack);
 }
 
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
 {
-	thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+	thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
 					      THREAD_SIZE, 0, NULL);
-	BUG_ON(thread_info_cache == NULL);
+	BUG_ON(thread_stack_cache == NULL);
 }
 # endif
 #endif
@@ -221,18 +213,24 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
 {
-	struct zone *zone = page_zone(virt_to_page(ti));
+	/* All stack pages are in the same zone and belong to the same memcg. */
+	struct page *first_page = virt_to_page(stack);
 
-	mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+	mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
+			    THREAD_SIZE / 1024 * account);
+
+	memcg_kmem_update_page_stat(
+		first_page, MEMCG_KERNEL_STACK_KB,
+		account * (THREAD_SIZE / 1024));
 }
 
 void free_task(struct task_struct *tsk)
 {
 	account_kernel_stack(tsk->stack, -1);
-	arch_release_thread_info(tsk->stack);
-	free_thread_info(tsk->stack);
+	arch_release_thread_stack(tsk->stack);
+	free_thread_stack(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
 	put_seccomp_filter(tsk);
@@ -340,26 +338,27 @@ void set_task_stack_end_magic(struct task_struct *tsk)
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 }
 
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
-	struct thread_info *ti;
-	int node = tsk_fork_get_node(orig);
+	unsigned long *stack;
 	int err;
 
+	if (node == NUMA_NO_NODE)
+		node = tsk_fork_get_node(orig);
 	tsk = alloc_task_struct_node(node);
 	if (!tsk)
 		return NULL;
 
-	ti = alloc_thread_info_node(tsk, node);
-	if (!ti)
+	stack = alloc_thread_stack_node(tsk, node);
+	if (!stack)
 		goto free_tsk;
 
 	err = arch_dup_task_struct(tsk, orig);
 	if (err)
-		goto free_ti;
+		goto free_stack;
 
-	tsk->stack = ti;
+	tsk->stack = stack;
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -391,14 +390,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
 
-	account_kernel_stack(ti, 1);
+	account_kernel_stack(stack, 1);
 
 	kcov_task_init(tsk);
 
 	return tsk;
 
-free_ti:
-	free_thread_info(ti);
+free_stack:
+	free_thread_stack(stack);
 free_tsk:
 	free_task_struct(tsk);
 	return NULL;
@@ -413,7 +412,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	unsigned long charge;
 
 	uprobe_start_dup_mmap();
-	down_write(&oldmm->mmap_sem);
+	if (down_write_killable(&oldmm->mmap_sem)) {
+		retval = -EINTR;
+		goto fail_uprobe_end;
+	}
 	flush_cache_dup_mm(oldmm);
 	uprobe_dup_mmap(oldmm, mm);
 	/*
@@ -525,6 +527,7 @@ out:
 	up_write(&mm->mmap_sem);
 	flush_tlb_mm(oldmm);
 	up_write(&oldmm->mmap_sem);
+fail_uprobe_end:
 	uprobe_end_dup_mmap();
 	return retval;
 fail_nomem_anon_vma_fork:
@@ -699,6 +702,26 @@ void __mmdrop(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
 
+static inline void __mmput(struct mm_struct *mm)
+{
+	VM_BUG_ON(atomic_read(&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)) {
+		spin_lock(&mmlist_lock);
+		list_del(&mm->mmlist);
+		spin_unlock(&mmlist_lock);
+	}
+	if (mm->binfmt)
+		module_put(mm->binfmt->module);
+	mmdrop(mm);
+}
+
 /*
  * Decrement the use count and release all resources for an mm.
  */
@@ -706,24 +729,26 @@ void mmput(struct mm_struct *mm)
 {
 	might_sleep();
 
+	if (atomic_dec_and_test(&mm->mm_users))
+		__mmput(mm);
+}
+EXPORT_SYMBOL_GPL(mmput);
+
+#ifdef CONFIG_MMU
+static void mmput_async_fn(struct work_struct *work)
+{
+	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+	__mmput(mm);
+}
+
+void mmput_async(struct mm_struct *mm)
+{
 	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)) {
-			spin_lock(&mmlist_lock);
-			list_del(&mm->mmlist);
-			spin_unlock(&mmlist_lock);
-		}
-		if (mm->binfmt)
-			module_put(mm->binfmt->module);
-		mmdrop(mm);
+		INIT_WORK(&mm->async_put_work, mmput_async_fn);
+		schedule_work(&mm->async_put_work);
 	}
 }
-EXPORT_SYMBOL_GPL(mmput);
+#endif
 
 /**
  * set_mm_exe_file - change a reference to the mm's executable file
@@ -911,14 +936,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	deactivate_mm(tsk, mm);
 
 	/*
-	 * 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, say, a killed vfork parent shouldn't touch this mm.
-	 * Userland only wants this done for a sys_exit.
+	 * Signal userspace if we're not exiting with a core dump
+	 * because we want to leave the value intact for debugging
+	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->flags & PF_SIGNALED) &&
+		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
 		    atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has
@@ -1279,7 +1302,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					int __user *child_tidptr,
 					struct pid *pid,
 					int trace,
-					unsigned long tls)
+					unsigned long tls,
+					int node)
 {
 	int retval;
 	struct task_struct *p;
@@ -1331,7 +1355,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto fork_out;
 
 	retval = -ENOMEM;
-	p = dup_task_struct(current);
+	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
 
@@ -1401,7 +1425,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1493,7 +1516,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
 		if (IS_ERR(pid)) {
 			retval = PTR_ERR(pid);
-			goto bad_fork_cleanup_io;
+			goto bad_fork_cleanup_thread;
 		}
 	}
 
@@ -1517,7 +1540,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * sigaltstack should be cleared when sharing the same VM
 	 */
 	if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
-		p->sas_ss_sp = p->sas_ss_size = 0;
+		sas_ss_reset(p);
 
 	/*
 	 * Syscall tracing and stepping should be turned off in the
@@ -1553,6 +1576,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1653,8 +1677,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p);
 bad_fork_free_pid:
+	threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
+bad_fork_cleanup_thread:
+	exit_thread(p);
 bad_fork_cleanup_io:
 	if (p->io_context)
 		exit_io_context(p);
@@ -1683,7 +1710,6 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
@@ -1707,7 +1733,8 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
 		init_idle_pids(task->pids);
 		init_idle(task, cpu);
@@ -1752,7 +1779,7 @@ long _do_fork(unsigned long clone_flags,
 	}
 
 	p = copy_process(clone_flags, stack_start, stack_size,
-			 child_tidptr, NULL, trace, tls);
+			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.