The madvise policy for transparent huge pages is meant to avoid unwanted
allocations of transparent huge pages. It allows a policy of disabling
the extra memory pressure and effort to arrange for a huge page when it
is not needed.
DAX by definition never incurs this overhead since it is statically
allocated. The policy choice makes even less sense for device-dax which
tries to guarantee a given tlb-fault size. Specifically, the following
setting:
echo never > /sys/kernel/mm/transparent_hugepage/enabled
...violates that guarantee and silently disables all device-dax
instances with a 2M or 1G alignment. So, let's avoid that non-obvious
side effect by force enabling thp for dax mappings in all cases.
It is worth noting that the reason this uses vma_is_dax(), and the
resulting header include changes, is that previous attempts to add a
VM_DAX flag were NAKd.
Cc: Jan Kara <jack@xxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
include/linux/dax.h | 5 -----
include/linux/fs.h | 6 ++++++
include/linux/huge_mm.h | 5 +++++
3 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 1f6b6072af64..cbaf3d53d66b 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -151,11 +151,6 @@ static inline unsigned int dax_radix_order(void *entry)
#endif
int dax_pfn_mkwrite(struct vm_fault *vmf);
-static inline bool vma_is_dax(struct vm_area_struct *vma)
-{
- return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
-}
-
static inline bool dax_mapping(struct address_space *mapping)
{
return mapping->host && IS_DAX(mapping->host);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 803e5a9b2654..5916ab3a12d5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
+#include <linux/mm_types.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fiemap.h>
@@ -3042,6 +3043,11 @@ static inline bool io_is_direct(struct file *filp)
return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host);
}
+static inline bool vma_is_dax(struct vm_area_struct *vma)
+{
+ return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+}
+
static inline int iocb_flags(struct file *file)
{
int res = 0;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c4706e2c3358..901ed3767d1b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -1,6 +1,8 @@
#ifndef _LINUX_HUGE_MM_H
#define _LINUX_HUGE_MM_H
+#include <linux/fs.h>
+
extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf);
extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
@@ -92,6 +94,9 @@ static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
return true;
+ if (vma_is_dax(vma))
+ return true;
+
if (transparent_hugepage_flags
& (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
/* check vma flags */;
