From ba14a194a434ccc8f733e263ad2ce941e35e5787 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 11 Aug 2016 02:35:21 -0700 Subject: fork: Add generic vmalloced stack support If CONFIG_VMAP_STACK=y is selected, kernel stacks are allocated with __vmalloc_node_range(). Grsecurity has had a similar feature (called GRKERNSEC_KSTACKOVERFLOW=y) for a long time. Signed-off-by: Andy Lutomirski Acked-by: Michal Hocko Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Dmitry Vyukov Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/14c07d4fd173a5b117f51e8b939f9f4323e39899.1470907718.git.luto@kernel.org [ Minor edits. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 62c68e513e39..20f9f47bcfd0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1923,6 +1923,9 @@ 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; /* @@ -1939,6 +1942,18 @@ 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) -- cgit v1.2.3 From c65eacbe290b8141554c71b2c94489e73ade8c8d Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 13 Sep 2016 14:29:24 -0700 Subject: sched/core: Allow putting thread_info into task_struct If an arch opts in by setting CONFIG_THREAD_INFO_IN_TASK_STRUCT, then thread_info is defined as a single 'u32 flags' and is the first entry of task_struct. thread_info::task is removed (it serves no purpose if thread_info is embedded in task_struct), and thread_info::cpu gets its own slot in task_struct. This is heavily based on a patch written by Linus. Originally-from: Linus Torvalds Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jann Horn Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/a0898196f0476195ca02713691a5037a14f2aac5.1473801993.git.luto@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 20f9f47bcfd0..a287e8b13549 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1458,6 +1458,13 @@ struct tlbflush_unmap_batch { }; struct task_struct { +#ifdef CONFIG_THREAD_INFO_IN_TASK + /* + * For reasons of header soup (see current_thread_info()), this + * must be the first element of task_struct. + */ + struct thread_info thread_info; +#endif volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; atomic_t usage; @@ -1467,6 +1474,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; +#ifdef CONFIG_THREAD_INFO_IN_TASK + unsigned int cpu; /* current CPU */ +#endif unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -2588,7 +2598,9 @@ extern void set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { +#ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; +#endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; @@ -3076,10 +3088,26 @@ static inline void threadgroup_change_end(struct task_struct *tsk) cgroup_threadgroup_change_end(tsk); } -#ifndef __HAVE_THREAD_FUNCTIONS +#ifdef CONFIG_THREAD_INFO_IN_TASK + +static inline struct thread_info *task_thread_info(struct task_struct *task) +{ + return &task->thread_info; +} +static inline void *task_stack_page(const struct task_struct *task) +{ + return task->stack; +} +#define setup_thread_stack(new,old) do { } while(0) +static inline unsigned long *end_of_stack(const struct task_struct *task) +{ + return task->stack; +} + +#elif !defined(__HAVE_THREAD_FUNCTIONS) #define task_thread_info(task) ((struct thread_info *)(task)->stack) -#define task_stack_page(task) ((task)->stack) +#define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { @@ -3379,7 +3407,11 @@ static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) static inline unsigned int task_cpu(const struct task_struct *p) { +#ifdef CONFIG_THREAD_INFO_IN_TASK + return p->cpu; +#else return task_thread_info(p)->cpu; +#endif } static inline int task_node(const struct task_struct *p) -- cgit v1.2.3 From c6c314a613cd7d03fb97713e0d642b493de42e69 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 15 Sep 2016 22:45:43 -0700 Subject: sched/core: Add try_get_task_stack() and put_task_stack() There are a few places in the kernel that access stack memory belonging to a different task. Before we can start freeing task stacks before the task_struct is freed, we need a way for those code paths to pin the stack. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jann Horn Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/17a434f50ad3d77000104f21666575e10a9c1fbd.1474003868.git.luto@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index a287e8b13549..a95867267e9f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3094,11 +3094,19 @@ static inline struct thread_info *task_thread_info(struct task_struct *task) { return &task->thread_info; } + +/* + * When accessing the stack of a non-current task that might exit, use + * try_get_task_stack() instead. task_stack_page will return a pointer + * that could get freed out from under you. + */ static inline void *task_stack_page(const struct task_struct *task) { return task->stack; } + #define setup_thread_stack(new,old) do { } while(0) + static inline unsigned long *end_of_stack(const struct task_struct *task) { return task->stack; @@ -3134,6 +3142,14 @@ static inline unsigned long *end_of_stack(struct task_struct *p) } #endif + +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return task_stack_page(tsk); +} + +static inline void put_task_stack(struct task_struct *tsk) {} + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) -- cgit v1.2.3 From 68f24b08ee892d47bdef925d676e1ae1ccc316f8 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 15 Sep 2016 22:45:48 -0700 Subject: sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK We currently keep every task's stack around until the task_struct itself is freed. This means that we keep the stack allocation alive for longer than necessary and that, under load, we free stacks in big batches whenever RCU drops the last task reference. Neither of these is good for reuse of cache-hot memory, and freeing in batches prevents us from usefully caching small numbers of vmalloced stacks. On architectures that have thread_info on the stack, we can't easily change this, but on architectures that set THREAD_INFO_IN_TASK, we can free it as soon as the task is dead. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jann Horn Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/08ca06cde00ebed0046c5d26cbbf3fbb7ef5b812.1474003868.git.luto@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index a95867267e9f..abb795afc823 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1936,6 +1936,10 @@ struct task_struct { #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif +#ifdef CONFIG_THREAD_INFO_IN_TASK + /* A live task holds one reference. */ + atomic_t stack_refcount; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* @@ -3143,12 +3147,22 @@ static inline unsigned long *end_of_stack(struct task_struct *p) #endif +#ifdef CONFIG_THREAD_INFO_IN_TASK +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return atomic_inc_not_zero(&tsk->stack_refcount) ? + task_stack_page(tsk) : NULL; +} + +extern void put_task_stack(struct task_struct *tsk); +#else static inline void *try_get_task_stack(struct task_struct *tsk) { return task_stack_page(tsk); } static inline void put_task_stack(struct task_struct *tsk) {} +#endif #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) -- cgit v1.2.3