mm: always enable thp for dax mappings

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.

Link: http://lkml.kernel.org/r/149739531127.20686.15813586620597484283.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8f39db7439c3c88ad0a375b83fb67d12552067c3..79481187573288505a8136e8dffbf810cf9088a2 100644 (file)
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -154,11 +154,6 @@ 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 0cfa47125d52472809c2ede29c3fcfae21a2b18c..78e1dbbe4cfd66eadb3c5165579b60c205f381e7 100644 (file)
--- 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/fcntl.h>
@@ -3127,6 +3128,11 @@ 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 f4239d3c9c73064f48beed43a86600c1e618db33..ee696347f928ffc7b0aac51e3c6e1180c11265c9 100644 (file)
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -3,6 +3,8 @@
 
 #include <linux/sched/coredump.h>
 
+#include <linux/fs.h> /* only for vma_is_dax() */
+
 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,
@@ -103,6 +105,9 @@ 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))
                return !!(vma->vm_flags & VM_HUGEPAGE);