VM: add "vm_insert_page()" function

This is what a lot of drivers will actually want to use to insert
individual pages into a user VMA.  It doesn't have the old PageReserved
restrictions of remap_pfn_range(), and it doesn't complain about partial
remappings.

The page you insert needs to be a nice clean kernel allocation, so you
can't insert arbitrary page mappings with this, but that's not what
people want.

Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 35 insertions, 2 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0e73f1539d0..29f02d8513f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -956,6 +956,7 @@ struct page *vmalloc_to_page(void *addr);
 unsigned long vmalloc_to_pfn(void *addr);
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
+int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 
 struct page *follow_page(struct vm_area_struct *, unsigned long address,
 			unsigned int foll_flags);
diff --git a/mm/memory.c b/mm/memory.c
index 8d10b5540c7..4b4fc3a7ea4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1172,7 +1172,7 @@ static int insert_page(struct mm_struct *mm, unsigned long addr, struct page *pa
 	spinlock_t *ptl;  
 
 	retval = -EINVAL;
-	if (PageAnon(page) || !PageReserved(page))
+	if (PageAnon(page))
 		goto out;
 	retval = -ENOMEM;
 	flush_dcache_page(page);
@@ -1197,6 +1197,35 @@ out:
 }
 
 /*
+ * This allows drivers to insert individual pages they've allocated
+ * into a user vma.
+ *
+ * The page has to be a nice clean _individual_ kernel allocation.
+ * If you allocate a compound page, you need to have marked it as
+ * such (__GFP_COMP), or manually just split the page up yourself
+ * (which is mainly an issue of doing "set_page_count(page, 1)" for
+ * each sub-page, and then freeing them one by one when you free
+ * them rather than freeing it as a compound page).
+ *
+ * NOTE! Traditionally this was done with "remap_pfn_range()" which
+ * took an arbitrary page protection parameter. This doesn't allow
+ * that. Your vma protection will have to be set up correctly, which
+ * means that if you want a shared writable mapping, you'd better
+ * ask for a shared writable mapping!
+ *
+ * The page does not need to be reserved.
+ */
+int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page)
+{
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return -EFAULT;
+	if (!page_count(page))
+		return -EINVAL;
+	return insert_page(vma->vm_mm, addr, page, vma->vm_page_prot);
+}
+EXPORT_SYMBOL_GPL(vm_insert_page);
+
+/*
  * Somebody does a pfn remapping that doesn't actually work as a vma.
  *
  * Do it as individual pages instead, and warn about it. It's bad form,
@@ -1225,8 +1254,11 @@ static int incomplete_pfn_remap(struct vm_area_struct *vma,
 	if (!pfn_valid(pfn))
 		return -EINVAL;
 
-	retval = 0;
 	page = pfn_to_page(pfn);
+	if (!PageReserved(page))
+		return -EINVAL;
+
+	retval = 0;
 	while (start < end) {
 		retval = insert_page(vma->vm_mm, start, page, prot);
 		if (retval < 0)