1 files changed, 43 insertions, 17 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b669aa6f6caf..21fdf46ad5aa 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1118,6 +1118,32 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro
 EXPORT_SYMBOL(vm_map_ram);
 
 /**
+ * vm_area_add_early - add vmap area early during boot
+ * @vm: vm_struct to add
+ *
+ * This function is used to add fixed kernel vm area to vmlist before
+ * vmalloc_init() is called.  @vm->addr, @vm->size, and @vm->flags
+ * should contain proper values and the other fields should be zero.
+ *
+ * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
+ */
+void __init vm_area_add_early(struct vm_struct *vm)
+{
+	struct vm_struct *tmp, **p;
+
+	BUG_ON(vmap_initialized);
+	for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
+		if (tmp->addr >= vm->addr) {
+			BUG_ON(tmp->addr < vm->addr + vm->size);
+			break;
+		} else
+			BUG_ON(tmp->addr + tmp->size > vm->addr);
+	}
+	vm->next = *p;
+	*p = vm;
+}
+
+/**
  * vm_area_register_early - register vmap area early during boot
  * @vm: vm_struct to register
  * @align: requested alignment
@@ -1139,8 +1165,7 @@ void __init vm_area_register_early(struct vm_struct *vm, size_t align)
 
 	vm->addr = (void *)addr;
 
-	vm->next = vmlist;
-	vmlist = vm;
+	vm_area_add_early(vm);
 }
 
 void __init vmalloc_init(void)
@@ -1290,7 +1315,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 		unsigned long align, unsigned long flags, unsigned long start,
 		unsigned long end, int node, gfp_t gfp_mask, void *caller)
 {
-	static struct vmap_area *va;
+	struct vmap_area *va;
 	struct vm_struct *area;
 
 	BUG_ON(in_interrupt());
@@ -1633,6 +1658,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 		goto fail;
 
 	addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+	if (!addr)
+		return NULL;
 
 	/*
 	 * In this function, newly allocated vm_struct is not added
@@ -2141,23 +2168,30 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
 
 static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
 {
-	/* apply_to_page_range() does all the hard work. */
+	pte_t ***p = data;
+
+	if (p) {
+		*(*p) = pte;
+		(*p)++;
+	}
 	return 0;
 }
 
 /**
  *	alloc_vm_area - allocate a range of kernel address space
  *	@size:		size of the area
+ *	@ptes:		returns the PTEs for the address space
  *
  *	Returns:	NULL on failure, vm_struct on success
  *
  *	This function reserves a range of kernel address space, and
  *	allocates pagetables to map that range.  No actual mappings
- *	are created.  If the kernel address space is not shared
- *	between processes, it syncs the pagetable across all
- *	processes.
+ *	are created.
+ *
+ *	If @ptes is non-NULL, pointers to the PTEs (in init_mm)
+ *	allocated for the VM area are returned.
  */
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
 {
 	struct vm_struct *area;
 
@@ -2171,19 +2205,11 @@ struct vm_struct *alloc_vm_area(size_t size)
 	 * of kernel virtual address space and mapped into init_mm.
 	 */
 	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
-				area->size, f, NULL)) {
+				size, f, ptes ? &ptes : NULL)) {
 		free_vm_area(area);
 		return NULL;
 	}
 
-	/*
-	 * If the allocated address space is passed to a hypercall
-	 * before being used then we cannot rely on a page fault to
-	 * trigger an update of the page tables.  So sync all the page
-	 * tables here.
-	 */
-	vmalloc_sync_all();
-
 	return area;
 }
 EXPORT_SYMBOL_GPL(alloc_vm_area);