mm: Tag VMA with VM_CDM flag explicitly during mbind(MPOL_BIND) and page fault

euler inclusion
category: feature
bugzilla: 11082
CVE: NA
-------------------

Mark all the applicable VMAs with VM_CDM explicitly during mbind(MPOL_BIND)
call if the user provided nodemask has a CDM node.

Mark the corresponding VMA with VM_CDM flag if the allocated page happens
to be from a CDM node. This can be expensive from performance stand point.
There are multiple checks to avoid an expensive page_to_nid lookup but it
can be optimized further.
Signed-off-by: NAnshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Nzhong jiang <zhongjiang@huawei.com>
Signed-off-by: NLijun Fang <fanglijun3@huawei.com>
Reviewed-by: Nzhong jiang <zhongjiang@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

include/linux/mm.h

@@ -203,6 +203,11 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
+
+#ifdef CONFIG_COHERENT_DEVICE
+#define VM_CDM		0x00800000	/* Contains coherent device memory */
+#endif
+
 #define VM_SYNC		0x00800000	/* Synchronous page faults */
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
 #define VM_WIPEONFORK	0x02000000	/* Wipe VMA contents in child. */

mm/mempolicy.c

@@ -164,6 +164,42 @@ static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
 	nodes_onto(*ret, tmp, *rel);
 }
 
+#ifdef CONFIG_COHERENT_DEVICE
+static inline void set_vm_cdm(struct vm_area_struct *vma)
+{
+	vma->vm_flags |= VM_CDM;
+}
+
+static inline void clr_vm_cdm(struct vm_area_struct *vma)
+{
+	vma->vm_flags &= ~VM_CDM;
+}
+
+static void mark_vma_cdm(nodemask_t *nmask,
+		struct page *page, struct vm_area_struct *vma)
+{
+	if (!page)
+		return;
+
+	if (vma->vm_flags & VM_CDM)
+		return;
+
+	if (nmask && !nodemask_has_cdm(*nmask))
+		return;
+
+	if (is_cdm_node(page_to_nid(page)))
+		vma->vm_flags |= VM_CDM;
+}
+#else
+static inline void set_vm_cdm(struct vm_area_struct *vma) { }
+static inline void clr_vm_cdm(struct vm_area_struct *vma) { }
+
+static void mark_vma_cdm(nodemask_t *nmask,
+		struct page *page, struct vm_area_struct *vma)
+{
+}
+#endif
+
 static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
 {
 	if (nodes_empty(*nodes))
@@ -724,6 +760,10 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 		vmstart = max(start, vma->vm_start);
 		vmend   = min(end, vma->vm_end);
 
+		if ((new_pol->mode == MPOL_BIND)
+			&& nodemask_has_cdm(new_pol->v.nodes))
+			set_vm_cdm(vma);
+
 		if (mpol_equal(vma_policy(vma), new_pol))
 			continue;
 
@@ -2109,6 +2149,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
 	page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
+	mark_vma_cdm(nmask, page, vma);
 	mpol_cond_put(pol);
 out:
 	return page;