dax: remove VM_MIXEDMAP for fsdax and device dax

This patch is reworked from an earlier patch that Dan has posted:
https://patchwork.kernel.org/patch/10131727/

VM_MIXEDMAP is used by dax to direct mm paths like vm_normal_page() that
the memory page it is dealing with is not typical memory from the linear
map.  The get_user_pages_fast() path, since it does not resolve the vma,
is already using {pte,pmd}_devmap() as a stand-in for VM_MIXEDMAP, so we
use that as a VM_MIXEDMAP replacement in some locations.  In the cases
where there is no pte to consult we fallback to using vma_is_dax() to
detect the VM_MIXEDMAP special case.

Now that we have explicit driver pfn_t-flag opt-in/opt-out for
get_user_pages() support for DAX we can stop setting VM_MIXEDMAP.  This
also means we no longer need to worry about safely manipulating vm_flags
in a future where we support dynamically changing the dax mode of a
file.

DAX should also now be supported with madvise_behavior(), vma_merge(),
and copy_page_range().

This patch has been tested against ndctl unit test.  It has also been
tested against xfstests commit: 625515d using fake pmem created by
memmap and no additional issues have been observed.

Link: http://lkml.kernel.org/r/152847720311.55924.16999195879201817653.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/dax/device.c

@@ -474,7 +474,7 @@ static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
 		return rc;
 
 	vma->vm_ops = &dax_vm_ops;
-	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	vma->vm_flags |= VM_HUGEPAGE;
 	return 0;
 }
 

fs/ext2/file.c

@@ -126,7 +126,6 @@ static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &ext2_dax_vm_ops;
-	vma->vm_flags |= VM_MIXEDMAP;
 	return 0;
 }
 #else

fs/ext4/file.c

@@ -374,7 +374,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
-		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+		vma->vm_flags |= VM_HUGEPAGE;
 	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
 	}

fs/xfs/xfs_file.c

@@ -1169,7 +1169,7 @@ xfs_file_mmap(
 	file_accessed(filp);
 	vma->vm_ops = &xfs_file_vm_ops;
 	if (IS_DAX(file_inode(filp)))
-		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+		vma->vm_flags |= VM_HUGEPAGE;
 	return 0;
 }
 

mm/hmm.c

@@ -676,7 +676,8 @@ int hmm_vma_get_pfns(struct hmm_range *range)
 		return -EINVAL;
 
 	/* FIXME support hugetlb fs */
-	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
+	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
+			vma_is_dax(vma)) {
 		hmm_pfns_special(range);
 		return -EINVAL;
 	}
@@ -849,7 +850,8 @@ int hmm_vma_fault(struct hmm_range *range, bool block)
 		return -EINVAL;
 
 	/* FIXME support hugetlb fs */
-	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
+	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
+			vma_is_dax(vma)) {
 		hmm_pfns_special(range);
 		return -EINVAL;
 	}

mm/huge_memory.c

@@ -762,11 +762,11 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	 * but we need to be consistent with PTEs and architectures that
 	 * can't support a 'special' bit.
 	 */
-	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+			!pfn_t_devmap(pfn));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
 	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
-	BUG_ON(!pfn_t_devmap(pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;

mm/ksm.c

@@ -2430,6 +2430,9 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 				 VM_HUGETLB | VM_MIXEDMAP))
 			return 0;		/* just ignore the advice */
 
+		if (vma_is_dax(vma))
+			return 0;
+
 #ifdef VM_SAO
 		if (*vm_flags & VM_SAO)
 			return 0;

mm/memory.c

@@ -859,6 +859,10 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 				return NULL;
 			}
 		}
+
+		if (pte_devmap(pte))
+			return NULL;
+
 		print_bad_pte(vma, addr, pte, NULL);
 		return NULL;
 	}
@@ -923,6 +927,8 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 		}
 	}
 
+	if (pmd_devmap(pmd))
+		return NULL;
 	if (is_zero_pfn(pfn))
 		return NULL;
 	if (unlikely(pfn > highest_memmap_pfn))

mm/migrate.c

@@ -2951,7 +2951,8 @@ int migrate_vma(const struct migrate_vma_ops *ops,
 	/* Sanity check the arguments */
 	start &= PAGE_MASK;
 	end &= PAGE_MASK;
-	if (!vma || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL))
+	if (!vma || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL) ||
+			vma_is_dax(vma))
 		return -EINVAL;
 	if (start < vma->vm_start || start >= vma->vm_end)
 		return -EINVAL;

mm/mlock.c

@@ -527,7 +527,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	vm_flags_t old_flags = vma->vm_flags;
 
 	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
-	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
+	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
+	    vma_is_dax(vma))
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;
 

mm/mmap.c

@@ -1796,11 +1796,12 @@ out:
 
 	vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
-		if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
-					vma == get_gate_vma(current->mm)))
-			mm->locked_vm += (len >> PAGE_SHIFT);
-		else
+		if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) ||
+					is_vm_hugetlb_page(vma) ||
+					vma == get_gate_vma(current->mm))
 			vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
+		else
+			mm->locked_vm += (len >> PAGE_SHIFT);
 	}
 
 	if (file)