---

yaml
---
r: 258963
b: refs/heads/master
c: 2efaca9
h: refs/heads/master
i:
  258961: 215219b
  258959: 0f14f8d
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 72c4783210f77fd743f0a316858d33f27db51e7c
+refs/heads/master: 2efaca927f5cd7ecd0f1554b8f9b6a9a2c329c03

trunk/include/linux/mm.h

@@ -988,6 +988,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 struct page *get_dump_page(unsigned long addr);
+extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+			    unsigned long address, unsigned int fault_flags);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
 extern void do_invalidatepage(struct page *page, unsigned long offset);

trunk/kernel/futex.c

@@ -355,8 +355,8 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 	int ret;
 
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages(current, mm, (unsigned long)uaddr,
-			     1, 1, 0, NULL, NULL);
+	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
+			       FAULT_FLAG_WRITE);
 	up_read(&mm->mmap_sem);
 
 	return ret < 0 ? ret : 0;

trunk/mm/memory.c

@@ -1805,7 +1805,63 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 }
 EXPORT_SYMBOL(__get_user_pages);
 
-/**
+/*
+ * fixup_user_fault() - manually resolve a user page fault
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @address:	user address
+ * @fault_flags:flags to pass down to handle_mm_fault()
+ *
+ * This is meant to be called in the specific scenario where for locking reasons
+ * we try to access user memory in atomic context (within a pagefault_disable()
+ * section), this returns -EFAULT, and we want to resolve the user fault before
+ * trying again.
+ *
+ * Typically this is meant to be used by the futex code.
+ *
+ * The main difference with get_user_pages() is that this function will
+ * unconditionally call handle_mm_fault() which will in turn perform all the
+ * necessary SW fixup of the dirty and young bits in the PTE, while
+ * handle_mm_fault() only guarantees to update these in the struct page.
+ *
+ * This is important for some architectures where those bits also gate the
+ * access permission to the page because they are maintained in software.  On
+ * such architectures, gup() will not be enough to make a subsequent access
+ * succeed.
+ *
+ * This should be called with the mm_sem held for read.
+ */
+int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long address, unsigned int fault_flags)
+{
+	struct vm_area_struct *vma;
+	int ret;
+
+	vma = find_extend_vma(mm, address);
+	if (!vma || address < vma->vm_start)
+		return -EFAULT;
+
+	ret = handle_mm_fault(mm, vma, address, fault_flags);
+	if (ret & VM_FAULT_ERROR) {
+		if (ret & VM_FAULT_OOM)
+			return -ENOMEM;
+		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
+			return -EHWPOISON;
+		if (ret & VM_FAULT_SIGBUS)
+			return -EFAULT;
+		BUG();
+	}
+	if (tsk) {
+		if (ret & VM_FAULT_MAJOR)
+			tsk->maj_flt++;
+		else
+			tsk->min_flt++;
+	}
+	return 0;
+}
+
+/*
  * get_user_pages() - pin user pages in memory
  * @tsk:	the task_struct to use for page fault accounting, or
  *		NULL if faults are not to be recorded.