[PATCH] mm: introduce remap_vmalloc_range()
Add remap_vmalloc_range, vmalloc_user, and vmalloc_32_user so that drivers
can have a nice interface for remapping vmalloc memory.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c0504f1..35f8553 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -257,6 +257,19 @@
}
/* Caller must hold vmlist_lock */
+static struct vm_struct *__find_vm_area(void *addr)
+{
+ struct vm_struct *tmp;
+
+ for (tmp = vmlist; tmp != NULL; tmp = tmp->next) {
+ if (tmp->addr == addr)
+ break;
+ }
+
+ return tmp;
+}
+
+/* Caller must hold vmlist_lock */
struct vm_struct *__remove_vm_area(void *addr)
{
struct vm_struct **p, *tmp;
@@ -498,11 +511,33 @@
*/
void *vmalloc(unsigned long size)
{
- return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
}
EXPORT_SYMBOL(vmalloc);
/**
+ * vmalloc_user - allocate virtually contiguous memory which has
+ * been zeroed so it can be mapped to userspace without
+ * leaking data.
+ *
+ * @size: allocation size
+ */
+void *vmalloc_user(unsigned long size)
+{
+ struct vm_struct *area;
+ void *ret;
+
+ ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
+ write_lock(&vmlist_lock);
+ area = __find_vm_area(ret);
+ area->flags |= VM_USERMAP;
+ write_unlock(&vmlist_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(vmalloc_user);
+
+/**
* vmalloc_node - allocate memory on a specific node
*
* @size: allocation size
@@ -516,7 +551,7 @@
*/
void *vmalloc_node(unsigned long size, int node)
{
- return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node);
+ return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node);
}
EXPORT_SYMBOL(vmalloc_node);
@@ -556,6 +591,28 @@
}
EXPORT_SYMBOL(vmalloc_32);
+/**
+ * vmalloc_32_user - allocate virtually contiguous memory (32bit
+ * addressable) which is zeroed so it can be
+ * mapped to userspace without leaking data.
+ *
+ * @size: allocation size
+ */
+void *vmalloc_32_user(unsigned long size)
+{
+ struct vm_struct *area;
+ void *ret;
+
+ ret = __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
+ write_lock(&vmlist_lock);
+ area = __find_vm_area(ret);
+ area->flags |= VM_USERMAP;
+ write_unlock(&vmlist_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(vmalloc_32_user);
+
long vread(char *buf, char *addr, unsigned long count)
{
struct vm_struct *tmp;
@@ -630,3 +687,64 @@
read_unlock(&vmlist_lock);
return buf - buf_start;
}
+
+/**
+ * remap_vmalloc_range - map vmalloc pages to userspace
+ *
+ * @vma: vma to cover (map full range of vma)
+ * @addr: vmalloc memory
+ * @pgoff: number of pages into addr before first page to map
+ * @returns: 0 for success, -Exxx on failure
+ *
+ * This function checks that addr is a valid vmalloc'ed area, and
+ * that it is big enough to cover the vma. Will return failure if
+ * that criteria isn't met.
+ *
+ * Similar to remap_pfn_range (see mm/memory.c)
+ */
+int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
+ unsigned long pgoff)
+{
+ struct vm_struct *area;
+ unsigned long uaddr = vma->vm_start;
+ unsigned long usize = vma->vm_end - vma->vm_start;
+ int ret;
+
+ if ((PAGE_SIZE-1) & (unsigned long)addr)
+ return -EINVAL;
+
+ read_lock(&vmlist_lock);
+ area = __find_vm_area(addr);
+ if (!area)
+ goto out_einval_locked;
+
+ if (!(area->flags & VM_USERMAP))
+ goto out_einval_locked;
+
+ if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE)
+ goto out_einval_locked;
+ read_unlock(&vmlist_lock);
+
+ addr += pgoff << PAGE_SHIFT;
+ do {
+ struct page *page = vmalloc_to_page(addr);
+ ret = vm_insert_page(vma, uaddr, page);
+ if (ret)
+ return ret;
+
+ uaddr += PAGE_SIZE;
+ addr += PAGE_SIZE;
+ usize -= PAGE_SIZE;
+ } while (usize > 0);
+
+ /* Prevent "things" like memory migration? VM_flags need a cleanup... */
+ vma->vm_flags |= VM_RESERVED;
+
+ return ret;
+
+out_einval_locked:
+ read_unlock(&vmlist_lock);
+ return -EINVAL;
+}
+EXPORT_SYMBOL(remap_vmalloc_range);
+