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
  ...

1 files changed, 100 insertions, 218 deletions

diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 9ee4520ce83c..36cf1a498227 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,261 +16,145 @@
 
 #include <asm/stacktrace.h>
 
+static char *exception_stack_names[N_EXCEPTION_STACKS] = {
+		[ DOUBLEFAULT_STACK-1	]	= "#DF",
+		[ NMI_STACK-1		]	= "NMI",
+		[ DEBUG_STACK-1		]	= "#DB",
+		[ MCE_STACK-1		]	= "#MC",
+};
 
-#define N_EXCEPTION_STACKS_END \
-		(N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
-
-static char x86_stack_ids[][8] = {
-		[ DEBUG_STACK-1			]	= "#DB",
-		[ NMI_STACK-1			]	= "NMI",
-		[ DOUBLEFAULT_STACK-1		]	= "#DF",
-		[ MCE_STACK-1			]	= "#MC",
-#if DEBUG_STKSZ > EXCEPTION_STKSZ
-		[ N_EXCEPTION_STACKS ...
-		  N_EXCEPTION_STACKS_END	]	= "#DB[?]"
-#endif
+static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	[0 ... N_EXCEPTION_STACKS - 1]		= EXCEPTION_STKSZ,
+	[DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
-static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
-					 unsigned *usedp, char **idp)
+void stack_type_str(enum stack_type type, const char **begin, const char **end)
 {
-	unsigned k;
-
-	/*
-	 * Iterate over all exception stacks, and figure out whether
-	 * 'stack' is in one of them:
-	 */
-	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
-		unsigned long end = per_cpu(orig_ist, cpu).ist[k];
-		/*
-		 * Is 'stack' above this exception frame's end?
-		 * If yes then skip to the next frame.
-		 */
-		if (stack >= end)
-			continue;
-		/*
-		 * Is 'stack' above this exception frame's start address?
-		 * If yes then we found the right frame.
-		 */
-		if (stack >= end - EXCEPTION_STKSZ) {
-			/*
-			 * Make sure we only iterate through an exception
-			 * stack once. If it comes up for the second time
-			 * then there's something wrong going on - just
-			 * break out and return NULL:
-			 */
-			if (*usedp & (1U << k))
-				break;
-			*usedp |= 1U << k;
-			*idp = x86_stack_ids[k];
-			return (unsigned long *)end;
-		}
-		/*
-		 * If this is a debug stack, and if it has a larger size than
-		 * the usual exception stacks, then 'stack' might still
-		 * be within the lower portion of the debug stack:
-		 */
-#if DEBUG_STKSZ > EXCEPTION_STKSZ
-		if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) {
-			unsigned j = N_EXCEPTION_STACKS - 1;
-
-			/*
-			 * Black magic. A large debug stack is composed of
-			 * multiple exception stack entries, which we
-			 * iterate through now. Dont look:
-			 */
-			do {
-				++j;
-				end -= EXCEPTION_STKSZ;
-				x86_stack_ids[j][4] = '1' +
-						(j - N_EXCEPTION_STACKS);
-			} while (stack < end - EXCEPTION_STKSZ);
-			if (*usedp & (1U << j))
-				break;
-			*usedp |= 1U << j;
-			*idp = x86_stack_ids[j];
-			return (unsigned long *)end;
-		}
-#endif
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+
+	switch (type) {
+	case STACK_TYPE_IRQ:
+		*begin = "IRQ";
+		*end   = "EOI";
+		break;
+	case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
+		*begin = exception_stack_names[type - STACK_TYPE_EXCEPTION];
+		*end   = "EOE";
+		break;
+	default:
+		*begin = NULL;
+		*end   = NULL;
 	}
-	return NULL;
 }
 
-static inline int
-in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
-	     unsigned long *irq_stack_end)
+static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 {
-	return (stack >= irq_stack && stack < irq_stack_end);
-}
-
-static const unsigned long irq_stack_size =
-	(IRQ_STACK_SIZE - 64) / sizeof(unsigned long);
-
-enum stack_type {
-	STACK_IS_UNKNOWN,
-	STACK_IS_NORMAL,
-	STACK_IS_EXCEPTION,
-	STACK_IS_IRQ,
-};
-
-static enum stack_type
-analyze_stack(int cpu, struct task_struct *task, unsigned long *stack,
-	      unsigned long **stack_end, unsigned long *irq_stack,
-	      unsigned *used, char **id)
-{
-	unsigned long addr;
+	unsigned long *begin, *end;
+	struct pt_regs *regs;
+	unsigned k;
 
-	addr = ((unsigned long)stack & (~(THREAD_SIZE - 1)));
-	if ((unsigned long)task_stack_page(task) == addr)
-		return STACK_IS_NORMAL;
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
 
-	*stack_end = in_exception_stack(cpu, (unsigned long)stack,
-					used, id);
-	if (*stack_end)
-		return STACK_IS_EXCEPTION;
+	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
+		end   = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
+		begin = end - (exception_stack_sizes[k] / sizeof(long));
+		regs  = (struct pt_regs *)end - 1;
 
-	if (!irq_stack)
-		return STACK_IS_NORMAL;
+		if (stack < begin || stack >= end)
+			continue;
 
-	*stack_end = irq_stack;
-	irq_stack = irq_stack - irq_stack_size;
+		info->type	= STACK_TYPE_EXCEPTION + k;
+		info->begin	= begin;
+		info->end	= end;
+		info->next_sp	= (unsigned long *)regs->sp;
 
-	if (in_irq_stack(stack, irq_stack, *stack_end))
-		return STACK_IS_IRQ;
+		return true;
+	}
 
-	return STACK_IS_UNKNOWN;
+	return false;
 }
 
-/*
- * x86-64 can have up to three kernel stacks:
- * process stack
- * interrupt stack
- * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
- */
-
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data)
+static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	const unsigned cpu = get_cpu();
-	unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
-	unsigned long dummy;
-	unsigned used = 0;
-	int graph = 0;
-	int done = 0;
-
-	if (!task)
-		task = current;
-
-	if (!stack) {
-		if (regs)
-			stack = (unsigned long *)regs->sp;
-		else if (task != current)
-			stack = (unsigned long *)task->thread.sp;
-		else
-			stack = &dummy;
-	}
+	unsigned long *end   = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
 
-	if (!bp)
-		bp = stack_frame(task, regs);
 	/*
-	 * Print function call entries in all stacks, starting at the
-	 * current stack address. If the stacks consist of nested
-	 * exceptions
+	 * This is a software stack, so 'end' can be a valid stack pointer.
+	 * It just means the stack is empty.
 	 */
-	while (!done) {
-		unsigned long *stack_end;
-		enum stack_type stype;
-		char *id;
+	if (stack < begin || stack > end)
+		return false;
 
-		stype = analyze_stack(cpu, task, stack, &stack_end,
-				      irq_stack, &used, &id);
+	info->type	= STACK_TYPE_IRQ;
+	info->begin	= begin;
+	info->end	= end;
 
-		/* Default finish unless specified to continue */
-		done = 1;
+	/*
+	 * The next stack pointer is the first thing pushed by the entry code
+	 * after switching to the irq stack.
+	 */
+	info->next_sp = (unsigned long *)*(end - 1);
 
-		switch (stype) {
+	return true;
+}
 
-		/* Break out early if we are on the thread stack */
-		case STACK_IS_NORMAL:
-			break;
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask)
+{
+	if (!stack)
+		goto unknown;
 
-		case STACK_IS_EXCEPTION:
+	task = task ? : current;
 
-			if (ops->stack(data, id) < 0)
-				break;
+	if (in_task_stack(stack, task, info))
+		goto recursion_check;
 
-			bp = ops->walk_stack(task, stack, bp, ops,
-					     data, stack_end, &graph);
-			ops->stack(data, "<EOE>");
-			/*
-			 * We link to the next stack via the
-			 * second-to-last pointer (index -2 to end) in the
-			 * exception stack:
-			 */
-			stack = (unsigned long *) stack_end[-2];
-			done = 0;
-			break;
+	if (task != current)
+		goto unknown;
 
-		case STACK_IS_IRQ:
+	if (in_exception_stack(stack, info))
+		goto recursion_check;
 
-			if (ops->stack(data, "IRQ") < 0)
-				break;
-			bp = ops->walk_stack(task, stack, bp,
-				     ops, data, stack_end, &graph);
-			/*
-			 * We link to the next stack (which would be
-			 * the process stack normally) the last
-			 * pointer (index -1 to end) in the IRQ stack:
-			 */
-			stack = (unsigned long *) (stack_end[-1]);
-			irq_stack = NULL;
-			ops->stack(data, "EOI");
-			done = 0;
-			break;
+	if (in_irq_stack(stack, info))
+		goto recursion_check;
 
-		case STACK_IS_UNKNOWN:
-			ops->stack(data, "UNK");
-			break;
-		}
-	}
+	goto unknown;
 
+recursion_check:
 	/*
-	 * This handles the process stack:
+	 * Make sure we don't iterate through any given stack more than once.
+	 * If it comes up a second time then there's something wrong going on:
+	 * just break out and report an unknown stack type.
 	 */
-	bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph);
-	put_cpu();
+	if (visit_mask) {
+		if (*visit_mask & (1UL << info->type))
+			goto unknown;
+		*visit_mask |= 1UL << info->type;
+	}
+
+	return 0;
+
+unknown:
+	info->type = STACK_TYPE_UNKNOWN;
+	return -EINVAL;
 }
-EXPORT_SYMBOL(dump_trace);
 
-void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *sp, unsigned long bp, char *log_lvl)
+void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+			unsigned long *sp, char *log_lvl)
 {
 	unsigned long *irq_stack_end;
 	unsigned long *irq_stack;
 	unsigned long *stack;
-	int cpu;
 	int i;
 
-	preempt_disable();
-	cpu = smp_processor_id();
+	if (!try_get_task_stack(task))
+		return;
 
-	irq_stack_end	= (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
-	irq_stack	= (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE);
+	irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	irq_stack     = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long));
 
-	/*
-	 * Debugging aid: "show_stack(NULL, NULL);" prints the
-	 * back trace for this cpu:
-	 */
-	if (sp == NULL) {
-		if (regs)
-			sp = (unsigned long *)regs->sp;
-		else if (task)
-			sp = (unsigned long *)task->thread.sp;
-		else
-			sp = (unsigned long *)&sp;
-	}
+	sp = sp ? : get_stack_pointer(task, regs);
 
 	stack = sp;
 	for (i = 0; i < kstack_depth_to_print; i++) {
@@ -299,18 +183,17 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		stack++;
 		touch_nmi_watchdog();
 	}
-	preempt_enable();
 
 	pr_cont("\n");
-	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+	show_trace_log_lvl(task, regs, sp, log_lvl);
+
+	put_task_stack(task);
 }
 
 void show_regs(struct pt_regs *regs)
 {
 	int i;
-	unsigned long sp;
 
-	sp = regs->sp;
 	show_regs_print_info(KERN_DEFAULT);
 	__show_regs(regs, 1);
 
@@ -325,8 +208,7 @@ void show_regs(struct pt_regs *regs)
 		u8 *ip;
 
 		printk(KERN_DEFAULT "Stack:\n");
-		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-				   0, KERN_DEFAULT);
+		show_stack_log_lvl(current, regs, NULL, KERN_DEFAULT);
 
 		printk(KERN_DEFAULT "Code: ");