Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull low-level x86 updates from Ingo Molnar:
 "In this cycle this topic tree has become one of those 'super topics'
  that accumulated a lot of changes:

   - Add CONFIG_VMAP_STACK=y support to the core kernel and enable it on
     x86 - preceded by an array of changes. v4.8 saw preparatory changes
     in this area already - this is the rest of the work. Includes the
     thread stack caching performance optimization. (Andy Lutomirski)

   - switch_to() cleanups and all around enhancements. (Brian Gerst)

   - A large number of dumpstack infrastructure enhancements and an
     unwinder abstraction. The secret long term plan is safe(r) live
     patching plus maybe another attempt at debuginfo based unwinding -
     but all these current bits are standalone enhancements in a frame
     pointer based debug environment as well. (Josh Poimboeuf)

   - More __ro_after_init and const annotations. (Kees Cook)

   - Enable KASLR for the vmemmap memory region. (Thomas Garnier)"

[ The virtually mapped stack changes are pretty fundamental, and not
  x86-specific per se, even if they are only used on x86 right now. ]

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  x86/asm: Get rid of __read_cr4_safe()
  thread_info: Use unsigned long for flags
  x86/alternatives: Add stack frame dependency to alternative_call_2()
  x86/dumpstack: Fix show_stack() task pointer regression
  x86/dumpstack: Remove dump_trace() and related callbacks
  x86/dumpstack: Convert show_trace_log_lvl() to use the new unwinder
  oprofile/x86: Convert x86_backtrace() to use the new unwinder
  x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder
  perf/x86: Convert perf_callchain_kernel() to use the new unwinder
  x86/unwind: Add new unwind interface and implementations
  x86/dumpstack: Remove NULL task pointer convention
  fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y
  sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK
  lib/syscall: Pin the task stack in collect_syscall()
  x86/process: Pin the target stack in get_wchan()
  x86/dumpstack: Pin the target stack when dumping it
  kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function
  sched/core: Add try_get_task_stack() and put_task_stack()
  x86/entry/64: Fix a minor comment rebase error
  iommu/amd: Don't put completion-wait semaphore on stack
  ...

4 files changed, 121 insertions, 3 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 7d565afe35d2..6f93ac46e7f0 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -795,7 +795,12 @@ struct ftrace_ret_stack {
         unsigned long func;
         unsigned long long calltime;
         unsigned long long subtime;
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
         unsigned long fp;
+#endif
+#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+        unsigned long *retp;
+#endif
 };
 
 /*
@@ -807,7 +812,10 @@ extern void return_to_handler(void);
 
 extern int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
-                         unsigned long frame_pointer);
+                         unsigned long frame_pointer, unsigned long *retp);
+
+unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
+                                    unsigned long ret, unsigned long *retp);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -870,6 +878,13 @@ static inline int task_curr_ret_stack(struct task_struct *tsk)
         return -1;
 }
 
+static inline unsigned long
+ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret,
+                      unsigned long *retp)
+{
+        return ret;
+}
+
 static inline void pause_graph_tracing(void) { }
 static inline void unpause_graph_tracing(void) { }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f8834f820ec2..325f649d77ff 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -15,6 +15,8 @@
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
 
+#include <asm/thread_info.h>
+
 #ifdef CONFIG_SMP
 # define INIT_PUSHABLE_TASKS(tsk)                                       \
         .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO),
@@ -183,12 +185,21 @@ extern struct task_group root_task_group;
 # define INIT_KASAN(tsk)
 #endif
 
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+# define INIT_TASK_TI(tsk)                      \
+        .thread_info = INIT_THREAD_INFO(tsk),   \
+        .stack_refcount = ATOMIC_INIT(1),
+#else
+# define INIT_TASK_TI(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
  */
 #define INIT_TASK(tsk)  \
 {                                                                       \
+        INIT_TASK_TI(tsk)                                               \
         .state          = 0,                                            \
         .stack          = init_stack,                                   \
         .usage          = ATOMIC_INIT(2),                               \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f76d75fc9eaf..7543a476178b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1471,6 +1471,13 @@ 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;
@@ -1480,6 +1487,9 @@ 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;
@@ -1936,6 +1946,13 @@ struct task_struct {
 #ifdef CONFIG_MMU
         struct task_struct *oom_reaper_list;
 #endif
+#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;
 /*
@@ -1952,6 +1969,18 @@ 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)
 
@@ -2586,7 +2615,9 @@ extern void ia64_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)];
 };
 
@@ -3074,10 +3105,34 @@ 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;
+}
+
+/*
+ * 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;
+}
+
+#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)
 {
@@ -3104,6 +3159,24 @@ 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)
 
@@ -3390,7 +3463,11 @@ 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)
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 2b5b10eed74f..45f004e9cc59 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -13,6 +13,21 @@
 struct timespec;
 struct compat_timespec;
 
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+struct thread_info {
+        unsigned long           flags;          /* low level flags */
+};
+
+#define INIT_THREAD_INFO(tsk)                   \
+{                                               \
+        .flags          = 0,                    \
+}
+#endif
+
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+#define current_thread_info() ((struct thread_info *)current)
+#endif
+
 /*
  * System call restart block.
  */