X-Git-Url: http://git.cascardo.info/?a=blobdiff_plain;f=kernel%2Ffork.c;h=6d42242485cb2863e940ae0d54983a2d34789096;hb=904763e1fb5eebf8249ec41a2019e5e32246df2f;hp=beb31725f7e2746fb17cdd305c4193ab2c70e551;hpb=72a9cdd083005900f15934e8568f1ac43a6bb755;p=cascardo%2Flinux.git

diff --git a/kernel/fork.c b/kernel/fork.c
index beb31725f7e2..6d42242485cb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -158,19 +158,83 @@ void __weak arch_release_thread_stack(unsigned long *stack)
  * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
  * kmemcache based allocator.
  */
-# if THREAD_SIZE >= PAGE_SIZE
-static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
-						  int node)
+# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
+
+#ifdef CONFIG_VMAP_STACK
+/*
+ * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
+ * flush.  Try to minimize the number of calls by caching stacks.
+ */
+#define NR_CACHED_STACKS 2
+static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+#endif
+
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 {
+#ifdef CONFIG_VMAP_STACK
+	void *stack;
+	int i;
+
+	local_irq_disable();
+	for (i = 0; i < NR_CACHED_STACKS; i++) {
+		struct vm_struct *s = this_cpu_read(cached_stacks[i]);
+
+		if (!s)
+			continue;
+		this_cpu_write(cached_stacks[i], NULL);
+
+		tsk->stack_vm_area = s;
+		local_irq_enable();
+		return s->addr;
+	}
+	local_irq_enable();
+
+	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
+				     VMALLOC_START, VMALLOC_END,
+				     THREADINFO_GFP | __GFP_HIGHMEM,
+				     PAGE_KERNEL,
+				     0, node, __builtin_return_address(0));
+
+	/*
+	 * We can't call find_vm_area() in interrupt context, and
+	 * free_thread_stack() can be called in interrupt context,
+	 * so cache the vm_struct.
+	 */
+	if (stack)
+		tsk->stack_vm_area = find_vm_area(stack);
+	return stack;
+#else
 	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
 					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
+#endif
 }
 
-static inline void free_thread_stack(unsigned long *stack)
+static inline void free_thread_stack(struct task_struct *tsk)
 {
-	__free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
+#ifdef CONFIG_VMAP_STACK
+	if (task_stack_vm_area(tsk)) {
+		unsigned long flags;
+		int i;
+
+		local_irq_save(flags);
+		for (i = 0; i < NR_CACHED_STACKS; i++) {
+			if (this_cpu_read(cached_stacks[i]))
+				continue;
+
+			this_cpu_write(cached_stacks[i], tsk->stack_vm_area);
+			local_irq_restore(flags);
+			return;
+		}
+		local_irq_restore(flags);
+
+		vfree(tsk->stack);
+		return;
+	}
+#endif
+
+	__free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
 }
 # else
 static struct kmem_cache *thread_stack_cache;
@@ -181,9 +245,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 	return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
 }
 
-static void free_thread_stack(unsigned long *stack)
+static void free_thread_stack(struct task_struct *tsk)
 {
-	kmem_cache_free(thread_stack_cache, stack);
+	kmem_cache_free(thread_stack_cache, tsk->stack);
 }
 
 void thread_stack_cache_init(void)
@@ -213,24 +277,76 @@ 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(unsigned long *stack, int account)
+static void account_kernel_stack(struct task_struct *tsk, int account)
 {
-	/* All stack pages are in the same zone and belong to the same memcg. */
-	struct page *first_page = virt_to_page(stack);
+	void *stack = task_stack_page(tsk);
+	struct vm_struct *vm = task_stack_vm_area(tsk);
+
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
+
+	if (vm) {
+		int i;
+
+		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
+			mod_zone_page_state(page_zone(vm->pages[i]),
+					    NR_KERNEL_STACK_KB,
+					    PAGE_SIZE / 1024 * account);
+		}
+
+		/* All stack pages belong to the same memcg. */
+		memcg_kmem_update_page_stat(vm->pages[0], MEMCG_KERNEL_STACK_KB,
+					    account * (THREAD_SIZE / 1024));
+	} else {
+		/*
+		 * 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(page_zone(first_page), NR_KERNEL_STACK_KB,
-			    THREAD_SIZE / 1024 * 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));
+		memcg_kmem_update_page_stat(first_page, MEMCG_KERNEL_STACK_KB,
+					    account * (THREAD_SIZE / 1024));
+	}
 }
 
-void free_task(struct task_struct *tsk)
+static void release_task_stack(struct task_struct *tsk)
 {
-	account_kernel_stack(tsk->stack, -1);
+	account_kernel_stack(tsk, -1);
 	arch_release_thread_stack(tsk->stack);
-	free_thread_stack(tsk->stack);
+	free_thread_stack(tsk);
+	tsk->stack = NULL;
+#ifdef CONFIG_VMAP_STACK
+	tsk->stack_vm_area = NULL;
+#endif
+}
+
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+void put_task_stack(struct task_struct *tsk)
+{
+	if (atomic_dec_and_test(&tsk->stack_refcount))
+		release_task_stack(tsk);
+}
+#endif
+
+void free_task(struct task_struct *tsk)
+{
+#ifndef CONFIG_THREAD_INFO_IN_TASK
+	/*
+	 * The task is finally done with both the stack and thread_info,
+	 * so free both.
+	 */
+	release_task_stack(tsk);
+#else
+	/*
+	 * If the task had a separate stack allocation, it should be gone
+	 * by now.
+	 */
+	WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0);
+#endif
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
 	put_seccomp_filter(tsk);
@@ -243,6 +359,12 @@ static inline void free_signal_struct(struct signal_struct *sig)
 {
 	taskstats_tgid_free(sig);
 	sched_autogroup_exit(sig);
+	/*
+	 * __mmdrop is not safe to call from softirq context on x86 due to
+	 * pgd_dtor so postpone it to the async context
+	 */
+	if (sig->oom_mm)
+		mmdrop_async(sig->oom_mm);
 	kmem_cache_free(signal_cachep, sig);
 }
 
@@ -302,6 +424,7 @@ int arch_task_struct_size __read_mostly;
 
 void __init fork_init(void)
 {
+	int i;
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
 #define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
@@ -321,6 +444,10 @@ void __init fork_init(void)
 	init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
 	init_task.signal->rlim[RLIMIT_SIGPENDING] =
 		init_task.signal->rlim[RLIMIT_NPROC];
+
+	for (i = 0; i < UCOUNT_COUNTS; i++) {
+		init_user_ns.ucount_max[i] = max_threads/2;
+	}
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -342,6 +469,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 {
 	struct task_struct *tsk;
 	unsigned long *stack;
+	struct vm_struct *stack_vm_area;
 	int err;
 
 	if (node == NUMA_NO_NODE)
@@ -354,11 +482,26 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	if (!stack)
 		goto free_tsk;
 
+	stack_vm_area = task_stack_vm_area(tsk);
+
 	err = arch_dup_task_struct(tsk, orig);
+
+	/*
+	 * arch_dup_task_struct() clobbers the stack-related fields.  Make
+	 * sure they're properly initialized before using any stack-related
+	 * functions again.
+	 */
+	tsk->stack = stack;
+#ifdef CONFIG_VMAP_STACK
+	tsk->stack_vm_area = stack_vm_area;
+#endif
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	atomic_set(&tsk->stack_refcount, 1);
+#endif
+
 	if (err)
 		goto free_stack;
 
-	tsk->stack = stack;
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -390,14 +533,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
 
-	account_kernel_stack(stack, 1);
+	account_kernel_stack(tsk, 1);
 
 	kcov_task_init(tsk);
 
 	return tsk;
 
 free_stack:
-	free_thread_stack(stack);
+	free_thread_stack(tsk);
 free_tsk:
 	free_task_struct(tsk);
 	return NULL;
@@ -711,6 +854,7 @@ static inline void __mmput(struct mm_struct *mm)
 	ksm_exit(mm);
 	khugepaged_exit(mm); /* must run before exit_mmap */
 	exit_mmap(mm);
+	mm_put_huge_zero_page(mm);
 	set_mm_exe_file(mm, NULL);
 	if (!list_empty(&mm->mmlist)) {
 		spin_lock(&mmlist_lock);
@@ -719,6 +863,7 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
+	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmdrop(mm);
 }
 
@@ -1715,6 +1860,7 @@ bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
 	exit_creds(p);
 bad_fork_free:
+	put_task_stack(p);
 	free_task(p);
 fork_out:
 	return ERR_PTR(retval);