thp, dax: add thp_get_unmapped_area for pmd mappings

When CONFIG_FS_DAX_PMD is set, DAX supports mmap() using pmd page size.
This feature relies on both mmap virtual address and FS block (i.e.
physical address) to be aligned by the pmd page size.  Users can use
mkfs options to specify FS to align block allocations.  However,
aligning mmap address requires code changes to existing applications for
providing a pmd-aligned address to mmap().

For instance, fio with "ioengine=mmap" performs I/Os with mmap() [1].
It calls mmap() with a NULL address, which needs to be changed to
provide a pmd-aligned address for testing with DAX pmd mappings.
Changing all applications that call mmap() with NULL is undesirable.

Add thp_get_unmapped_area(), which can be called by filesystem's
get_unmapped_area to align an mmap address by the pmd size for a DAX
file.  It calls the default handler, mm->get_unmapped_area(), to find a
range and then aligns it for a DAX file.

The patch is based on Matthew Wilcox's change that allows adding support
of the pud page size easily.

[1]: https://github.com/axboe/fio/blob/master/engines/mmap.c
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Toshi Kani <[email protected]>
Reviewed-by: Dan Williams <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Ross Zwisler <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Dave Chinner <[email protected]>
Cc: Jan Kara <[email protected]>
Cc: Theodore Ts'o <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Hugh Dickins <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

2 files changed, 50 insertions, 0 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 6f14de45b5ce..4fca5263fd42 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -87,6 +87,10 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 
 extern unsigned long transparent_hugepage_flags;
 
+extern unsigned long thp_get_unmapped_area(struct file *filp,
+		unsigned long addr, unsigned long len, unsigned long pgoff,
+		unsigned long flags);
+
 extern void prep_transhuge_page(struct page *page);
 extern void free_transhuge_page(struct page *page);
 
@@ -169,6 +173,9 @@ void put_huge_zero_page(void);
 static inline void prep_transhuge_page(struct page *page) {}
 
 #define transparent_hugepage_flags 0UL
+
+#define thp_get_unmapped_area	NULL
+
 static inline int
 split_huge_page_to_list(struct page *page, struct list_head *list)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 283583fcb1e7..a0b0e562407d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -469,6 +469,49 @@ void prep_transhuge_page(struct page *page)
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
+unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+		loff_t off, unsigned long flags, unsigned long size)
+{
+	unsigned long addr;
+	loff_t off_end = off + len;
+	loff_t off_align = round_up(off, size);
+	unsigned long len_pad;
+
+	if (off_end <= off_align || (off_end - off_align) < size)
+		return 0;
+
+	len_pad = len + size;
+	if (len_pad < len || (off + len_pad) < off)
+		return 0;
+
+	addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+					      off >> PAGE_SHIFT, flags);
+	if (IS_ERR_VALUE(addr))
+		return 0;
+
+	addr += (off - addr) & (size - 1);
+	return addr;
+}
+
+unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	loff_t off = (loff_t)pgoff << PAGE_SHIFT;
+
+	if (addr)
+		goto out;
+	if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
+		goto out;
+
+	addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
+	if (addr)
+		return addr;
+
+ out:
+	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+}
+EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
+
 static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
 		gfp_t gfp)
 {