If CONFIG_VMAP_STACK is selected, kernel stacks are allocated with vmalloc_node.
Signed-off-by: Andy Lutomirski <[email protected]> --- arch/Kconfig | 12 ++++++++++++ kernel/fork.c | 45 +++++++++++++++++++++++++++++++++++++-------- 2 files changed, 49 insertions(+), 8 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index d794384a0404..1acd262036b0 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -658,4 +658,16 @@ config ARCH_NO_COHERENT_DMA_MMAP config CPU_NO_EFFICIENT_FFS def_bool n +config HAVE_ARCH_VMAP_STACK + def_bool n + +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/kernel/fork.c b/kernel/fork.c index 59e52f2120a3..37234fa0ba9b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -158,19 +158,30 @@ 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 + return __vmalloc_node_range( + THREAD_SIZE, THREAD_SIZE, VMALLOC_START, VMALLOC_END, + GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, + 0, node, __builtin_return_address(0)); +#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) { +#ifdef CONFIG_VMAP_STACK + vfree(ti); +#else free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); +#endif } # else static struct kmem_cache *thread_info_cache; @@ -215,15 +226,33 @@ static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct thread_info *ti, int account) { - struct zone *zone = page_zone(virt_to_page(ti)); + struct zone *zone; + + if (IS_ENABLED(CONFIG_VMAP_STACK) && !virt_addr_valid(ti)) { + int i; + struct vm_struct *vm = find_vm_area(ti); - mod_zone_page_state(zone, NR_KERNEL_STACK, - THREAD_SIZE / PAGE_SIZE * account); + WARN_ON_ONCE(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, 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, + THREAD_SIZE / PAGE_SIZE * 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) -- 2.7.4
