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
  ...

lib/dma-debug.c

@@ -22,6 +22,7 @@
 #include <linux/stacktrace.h>
 #include <linux/dma-debug.h>
 #include <linux/spinlock.h>
+#include <linux/vmalloc.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/export.h>
@@ -1164,11 +1165,32 @@ static void check_unmap(struct dma_debug_entry *ref)
 	put_hash_bucket(bucket, &flags);
 }
 
-static void check_for_stack(struct device *dev, void *addr)
+static void check_for_stack(struct device *dev,
+			    struct page *page, size_t offset)
 {
-	if (object_is_on_stack(addr))
-		err_printk(dev, NULL, "DMA-API: device driver maps memory from "
-				"stack [addr=%p]\n", addr);
+	void *addr;
+	struct vm_struct *stack_vm_area = task_stack_vm_area(current);
+
+	if (!stack_vm_area) {
+		/* Stack is direct-mapped. */
+		if (PageHighMem(page))
+			return;
+		addr = page_address(page) + offset;
+		if (object_is_on_stack(addr))
+			err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr);
+	} else {
+		/* Stack is vmalloced. */
+		int i;
+
+		for (i = 0; i < stack_vm_area->nr_pages; i++) {
+			if (page != stack_vm_area->pages[i])
+				continue;
+
+			addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
+			err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr);
+			break;
+		}
+	}
 }
 
 static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
@@ -1291,10 +1313,11 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
 	if (map_single)
 		entry->type = dma_debug_single;
 
+	check_for_stack(dev, page, offset);
+
 	if (!PageHighMem(page)) {
 		void *addr = page_address(page) + offset;
 
-		check_for_stack(dev, addr);
 		check_for_illegal_area(dev, addr, size);
 	}
 
@@ -1386,8 +1409,9 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		entry->sg_call_ents   = nents;
 		entry->sg_mapped_ents = mapped_ents;
 
+		check_for_stack(dev, sg_page(s), s->offset);
+
 		if (!PageHighMem(sg_page(s))) {
-			check_for_stack(dev, sg_virt(s));
 			check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
 		}
 

lib/syscall.c

@@ -7,9 +7,19 @@ static int collect_syscall(struct task_struct *target, long *callno,
 			   unsigned long args[6], unsigned int maxargs,
 			   unsigned long *sp, unsigned long *pc)
 {
-	struct pt_regs *regs = task_pt_regs(target);
-	if (unlikely(!regs))
+	struct pt_regs *regs;
+
+	if (!try_get_task_stack(target)) {
+		/* Task has no stack, so the task isn't in a syscall. */
+		*callno = -1;
+		return 0;
+	}
+
+	regs = task_pt_regs(target);
+	if (unlikely(!regs)) {
+		put_task_stack(target);
 		return -EAGAIN;
+	}
 
 	*sp = user_stack_pointer(regs);
 	*pc = instruction_pointer(regs);
@@ -18,6 +28,7 @@ static int collect_syscall(struct task_struct *target, long *callno,
 	if (*callno != -1L && maxargs > 0)
 		syscall_get_arguments(target, regs, 0, maxargs, args);
 
+	put_task_stack(target);
 	return 0;
 }