Re: [PATCH v2 06/13] fork: Add generic vmalloced stack support

[Michal Hocko <mhocko@kernel.org>]

On Fri 17-06-16 13:00:42, Andy Lutomirski wrote:
> If CONFIG_VMAP_STACK is selected, kernel stacks are allocated with
> vmalloc_node.

I like this! It also reduces demand for higher order (order-2) pages
considerably which is a great plus on its own. I would be little bit
worried about the performance because vmalloc wasn't the fastest one
AFAIR. Have you tried to measure that?

>From a quick glance the patch looks OK, I will have to look closer
though.

> Signed-off-by: Andy Lutomirski <luto@kernel.org>
> ---
>  arch/Kconfig                        | 29 +++++++++++++
>  arch/ia64/include/asm/thread_info.h |  2 +-
>  include/linux/sched.h               | 15 +++++++
>  kernel/fork.c                       | 81 +++++++++++++++++++++++++++++--------
>  4 files changed, 109 insertions(+), 18 deletions(-)
> 
> diff --git a/arch/Kconfig b/arch/Kconfig
> index d794384a0404..a71e6e7195e6 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -658,4 +658,33 @@ config ARCH_NO_COHERENT_DMA_MMAP
>  config CPU_NO_EFFICIENT_FFS
>  	def_bool n
>  
> +config HAVE_ARCH_VMAP_STACK
> +	def_bool n
> +	help
> +	  An arch should select this symbol if it can support kernel stacks
> +	  in vmalloc space.  This means:
> +
> +	  - vmalloc space must be large enough to hold many kernel stacks.
> +	    This may rule out many 32-bit architectures.
> +
> +	  - Stacks in vmalloc space need to work reliably.  For example, if
> +	    vmap page tables are created on demand, either this mechanism
> +	    needs to work while the stack points to a virtual address with
> +	    unpopulated page tables or arch code (switch_to and switch_mm,
> +	    most likely) needs to ensure that the stack's page table entries
> +	    are populated before running on a possibly unpopulated stack.
> +
> +	  - If the stack overflows into a guard page, something reasonable
> +	    should happen.  The definition of "reasonable" is flexible, but
> +	    instantly rebooting without logging anything would be unfriendly.
> +
> +config VMAP_STACK
> +	bool "Use a virtually-mapped stack"
> +	depends on HAVE_ARCH_VMAP_STACK
> +	---help---
> +	  Enable this if you want the use virtually-mapped kernel stacks
> +	  with guard pages.  This causes kernel stack overflows to be
> +	  caught immediately rather than causing difficult-to-diagnose
> +	  corruption.
> +
>  source "kernel/gcov/Kconfig"
> diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
> index aa995b67c3f5..d13edda6e09c 100644
> --- a/arch/ia64/include/asm/thread_info.h
> +++ b/arch/ia64/include/asm/thread_info.h
> @@ -56,7 +56,7 @@ struct thread_info {
>  #define alloc_thread_info_node(tsk, node)	((struct thread_info *) 0)
>  #define task_thread_info(tsk)	((struct thread_info *) 0)
>  #endif
> -#define free_thread_info(ti)	/* nothing */
> +#define free_thread_info(tsk)	/* nothing */
>  #define task_stack_page(tsk)	((void *)(tsk))
>  
>  #define __HAVE_THREAD_FUNCTIONS
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 6e42ada26345..a37c3b790309 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1918,6 +1918,9 @@ struct task_struct {
>  #ifdef CONFIG_MMU
>  	struct task_struct *oom_reaper_list;
>  #endif
> +#ifdef CONFIG_VMAP_STACK
> +	struct vm_struct *stack_vm_area;
> +#endif
>  /* CPU-specific state of this task */
>  	struct thread_struct thread;
>  /*
> @@ -1934,6 +1937,18 @@ extern int arch_task_struct_size __read_mostly;
>  # define arch_task_struct_size (sizeof(struct task_struct))
>  #endif
>  
> +#ifdef CONFIG_VMAP_STACK
> +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
> +{
> +	return t->stack_vm_area;
> +}
> +#else
> +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
> +{
> +	return NULL;
> +}
> +#endif
> +
>  /* Future-safe accessor for struct task_struct's cpus_allowed. */
>  #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
>  
> diff --git a/kernel/fork.c b/kernel/fork.c
> index cd2abe6e4e41..ad77a6b07708 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -158,19 +158,38 @@ void __weak arch_release_thread_info(struct thread_info *ti)
>   * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
>   * kmemcache based allocator.
>   */
> -# if THREAD_SIZE >= PAGE_SIZE
> +# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
>  static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
>  						  int node)
>  {
> +#ifdef CONFIG_VMAP_STACK
> +	struct thread_info *ti = __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_info can be called in interrupt context, so cache
> +	 * the vm_struct.
> +	 */
> +	if (ti)
> +		tsk->stack_vm_area = find_vm_area(ti);
> +	return ti;
> +#else
>  	struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
>  						  THREAD_SIZE_ORDER);
>  
>  	return page ? page_address(page) : NULL;
> +#endif
>  }
>  
> -static inline void free_thread_info(struct thread_info *ti)
> +static inline void free_thread_info(struct task_struct *tsk)
>  {
> -	free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
> +	if (task_stack_vm_area(tsk))
> +		vfree(tsk->stack);
> +	else
> +		free_kmem_pages((unsigned long)tsk->stack, THREAD_SIZE_ORDER);
>  }
>  # else
>  static struct kmem_cache *thread_info_cache;
> @@ -181,9 +200,9 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
>  	return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
>  }
>  
> -static void free_thread_info(struct thread_info *ti)
> +static void free_thread_info(struct task_struct *tsk)
>  {
> -	kmem_cache_free(thread_info_cache, ti);
> +	kmem_cache_free(thread_info_cache, tsk->stack);
>  }
>  
>  void thread_info_cache_init(void)
> @@ -213,24 +232,46 @@ 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(struct task_struct *tsk, int account)
>  {
> -	struct zone *zone = page_zone(virt_to_page(ti));
> +	struct zone *zone;
> +	struct thread_info *ti = task_thread_info(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;
>  
> -	mod_zone_page_state(zone, NR_KERNEL_STACK_KB,
> -			    THREAD_SIZE / 1024 * account);
> +		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
>  
> -	/* All stack pages belong to the same memcg. */
> -	memcg_kmem_update_page_stat(
> -		virt_to_page(ti), MEMCG_KERNEL_STACK,
> -		account * (THREAD_SIZE / PAGE_SIZE));
> +		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
> +			mod_zone_page_state(page_zone(vm->pages[i]),
> +					    1, PAGE_SIZE / 1024 * account);
> +		}
> +
> +		/* All stack pages belong to the same memcg. */
> +		memcg_kmem_update_page_stat(
> +			vm->pages[0], MEMCG_KERNEL_STACK,
> +			account * (THREAD_SIZE / PAGE_SIZE));
> +	} else {
> +		zone = page_zone(virt_to_page(ti));
> +
> +		mod_zone_page_state(zone, NR_KERNEL_STACK_KB,
> +				    THREAD_SIZE / 1024 * account);
> +
> +		/* All stack pages belong to the same memcg. */
> +		memcg_kmem_update_page_stat(
> +			virt_to_page(ti), MEMCG_KERNEL_STACK,
> +			account * (THREAD_SIZE / PAGE_SIZE));
> +	}
>  }
>  
>  void free_task(struct task_struct *tsk)
>  {
> -	account_kernel_stack(tsk->stack, -1);
> +	account_kernel_stack(tsk, -1);
>  	arch_release_thread_info(tsk->stack);
> -	free_thread_info(tsk->stack);
> +	free_thread_info(tsk);
>  	rt_mutex_debug_task_free(tsk);
>  	ftrace_graph_exit_task(tsk);
>  	put_seccomp_filter(tsk);
> @@ -342,6 +383,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
>  {
>  	struct task_struct *tsk;
>  	struct thread_info *ti;
> +	struct vm_struct *stack_vm_area;
>  	int err;
>  
>  	if (node == NUMA_NO_NODE)
> @@ -354,11 +396,16 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
>  	if (!ti)
>  		goto free_tsk;
>  
> +	stack_vm_area = task_stack_vm_area(tsk);
> +
>  	err = arch_dup_task_struct(tsk, orig);
>  	if (err)
>  		goto free_ti;
>  
>  	tsk->stack = ti;
> +#ifdef CONFIG_VMAP_STACK
> +	tsk->stack_vm_area = stack_vm_area;
> +#endif
>  #ifdef CONFIG_SECCOMP
>  	/*
>  	 * We must handle setting up seccomp filters once we're under
> @@ -390,14 +437,14 @@ 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(ti, 1);
> +	account_kernel_stack(tsk, 1);
>  
>  	kcov_task_init(tsk);
>  
>  	return tsk;
>  
>  free_ti:
> -	free_thread_info(ti);
> +	free_thread_info(tsk);
>  free_tsk:
>  	free_task_struct(tsk);
>  	return NULL;
> -- 
> 2.5.5

-- 
Michal Hocko
SUSE Labs