mm/migrate: move common code to numa_migrate_check (was numa_migrate_prep)

do_numa_page() and do_huge_pmd_numa_page() share a lot of common code.  To
reduce redundancy, move common code to numa_migrate_prep() and rename the
function to numa_migrate_check() to reflect its functionality.

Now do_huge_pmd_numa_page() also checks shared folios to set TNF_SHARED
flag.

Link: https://lkml.kernel.org/r/20240809145906.1513458-4-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 11 insertions, 18 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 666fa675e5b6..f2fd3aabb67b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1669,22 +1669,23 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	pmd_t oldpmd = vmf->orig_pmd;
-	pmd_t pmd;
 	struct folio *folio;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	int nid = NUMA_NO_NODE;
-	int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK);
+	int target_nid, last_cpupid;
+	pmd_t pmd, old_pmd;
 	bool writable = false;
 	int flags = 0;
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
-	if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+	old_pmd = pmdp_get(vmf->pmd);
+
+	if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) {
 		spin_unlock(vmf->ptl);
 		return 0;
 	}
 
-	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+	pmd = pmd_modify(old_pmd, vma->vm_page_prot);
 
 	/*
 	 * Detect now whether the PMD could be writable; this information
@@ -1699,18 +1700,10 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	if (!folio)
 		goto out_map;
 
-	/* See similar comment in do_numa_page for explanation */
-	if (!writable)
-		flags |= TNF_NO_GROUP;
-
 	nid = folio_nid(folio);
-	/*
-	 * For memory tiering mode, cpupid of slow memory page is used
-	 * to record page access time.  So use default value.
-	 */
-	if (!folio_use_access_time(folio))
-		last_cpupid = folio_last_cpupid(folio);
-	target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
+
+	target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable,
+					&last_cpupid);
 	if (target_nid == NUMA_NO_NODE)
 		goto out_map;
 	if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
@@ -1730,13 +1723,13 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 
 	flags |= TNF_MIGRATE_FAIL;
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
-	if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+	if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) {
 		spin_unlock(vmf->ptl);
 		return 0;
 	}
 out_map:
 	/* Restore the PMD */
-	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+	pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot);
 	pmd = pmd_mkyoung(pmd);
 	if (writable)
 		pmd = pmd_mkwrite(pmd, vma);