diff mbox series

[RFC,v2,3/5] memory: allow non-fault migration in numa_migrate_check path

Message ID 20241210213744.2968-4-gourry@gourry.net (mailing list archive)
State New
Headers show
Series Promotion of Unmapped Page Cache Folios. | expand

Commit Message

Gregory Price Dec. 10, 2024, 9:37 p.m. UTC
numa_migrate_check and mpol_misplaced presume callers are in the
fault path with access to a VMA.  To enable migrations from page
cache, re-using the same logic to handle migration prep is preferable.

Mildly refactor numa_migrate_check and mpol_misplaced so that they may
be called with (vmf = NULL) from non-faulting paths.

Signed-off-by: Gregory Price <gourry@gourry.net>
---
 mm/memory.c    | 24 ++++++++++++++----------
 mm/mempolicy.c | 25 +++++++++++++++++--------
 2 files changed, 31 insertions(+), 18 deletions(-)
diff mbox series

Patch

diff --git a/mm/memory.c b/mm/memory.c
index 6ad7616918c4..af7ba56a4e1e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5542,7 +5542,20 @@  int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
 		      unsigned long addr, int *flags,
 		      bool writable, int *last_cpupid)
 {
-	struct vm_area_struct *vma = vmf->vma;
+	if (vmf) {
+		struct vm_area_struct *vma = vmf->vma;
+		const vm_flags_t vmflags = vma->vm_flags;
+
+		/*
+		 * Flag if the folio is shared between multiple address spaces.
+		 * This used later when determining whether to group tasks.
+		 */
+		if (folio_likely_mapped_shared(folio))
+			*flags |= vmflags & VM_SHARED ? TNF_SHARED : 0;
+
+		/* Record the current PID acceesing VMA */
+		vma_set_access_pid_bit(vma);
+	}
 
 	/*
 	 * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
@@ -5555,12 +5568,6 @@  int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
 	if (!writable)
 		*flags |= TNF_NO_GROUP;
 
-	/*
-	 * Flag if the folio is shared between multiple address spaces. This
-	 * is later used when determining whether to group tasks together
-	 */
-	if (folio_likely_mapped_shared(folio) && (vma->vm_flags & VM_SHARED))
-		*flags |= TNF_SHARED;
 	/*
 	 * For memory tiering mode, cpupid of slow memory page is used
 	 * to record page access time.  So use default value.
@@ -5570,9 +5577,6 @@  int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
 	else
 		*last_cpupid = folio_last_cpupid(folio);
 
-	/* Record the current PID acceesing VMA */
-	vma_set_access_pid_bit(vma);
-
 #ifdef CONFIG_NUMA_BALANCING
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 88eef9776bb0..77a123fa71b0 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2746,12 +2746,16 @@  static void sp_free(struct sp_node *n)
  * mpol_misplaced - check whether current folio node is valid in policy
  *
  * @folio: folio to be checked
- * @vmf: structure describing the fault
+ * @vmf: structure describing the fault (NULL if called outside fault path)
  * @addr: virtual address in @vma for shared policy lookup and interleave policy
+ *	  Ignored if vmf is NULL.
  *
  * Lookup current policy node id for vma,addr and "compare to" folio's
- * node id.  Policy determination "mimics" alloc_page_vma().
- * Called from fault path where we know the vma and faulting address.
+ * node id - or task's policy node id if vmf is NULL.  Policy determination
+ * "mimics" alloc_page_vma().
+ *
+ * vmf must be non-NULL if called from fault path where we know the vma and
+ * faulting address. The PTL must be held by caller if vmf is not NULL.
  *
  * Return: NUMA_NO_NODE if the page is in a node that is valid for this
  * policy, or a suitable node ID to allocate a replacement folio from.
@@ -2763,7 +2767,6 @@  int mpol_misplaced(struct folio *folio, struct vm_fault *vmf,
 	pgoff_t ilx;
 	struct zoneref *z;
 	int curnid = folio_nid(folio);
-	struct vm_area_struct *vma = vmf->vma;
 	int thiscpu = raw_smp_processor_id();
 	int thisnid = numa_node_id();
 	int polnid = NUMA_NO_NODE;
@@ -2773,18 +2776,24 @@  int mpol_misplaced(struct folio *folio, struct vm_fault *vmf,
 	 * Make sure ptl is held so that we don't preempt and we
 	 * have a stable smp processor id
 	 */
-	lockdep_assert_held(vmf->ptl);
-	pol = get_vma_policy(vma, addr, folio_order(folio), &ilx);
+	if (vmf) {
+		lockdep_assert_held(vmf->ptl);
+		pol = get_vma_policy(vmf->vma, addr, folio_order(folio), &ilx);
+	} else {
+		pol = get_task_policy(current);
+	}
 	if (!(pol->flags & MPOL_F_MOF))
 		goto out;
 
 	switch (pol->mode) {
 	case MPOL_INTERLEAVE:
-		polnid = interleave_nid(pol, ilx);
+		polnid = vmf ? interleave_nid(pol, ilx) :
+			       interleave_nodes(pol);
 		break;
 
 	case MPOL_WEIGHTED_INTERLEAVE:
-		polnid = weighted_interleave_nid(pol, ilx);
+		polnid = vmf ? weighted_interleave_nid(pol, ilx) :
+			       weighted_interleave_nodes(pol);
 		break;
 
 	case MPOL_PREFERRED: