mm: thp: refactor NUMA fault handling

When the THP NUMA fault support was added THP migration was not supported
yet.  So the ad hoc THP migration was implemented in NUMA fault handling.
Since v4.14 THP migration has been supported so it doesn't make too much
sense to still keep another THP migration implementation rather than using
the generic migration code.

This patch reworks the NUMA fault handling to use generic migration
implementation to migrate misplaced page.  There is no functional change.

After the refactor the flow of NUMA fault handling looks just like its
PTE counterpart:
  Acquire ptl
  Prepare for migration (elevate page refcount)
  Release ptl
  Isolate page from lru and elevate page refcount
  Migrate the misplaced THP

If migration fails just restore the old normal PMD.

In the old code anon_vma lock was needed to serialize THP migration
against THP split, but since then the THP code has been reworked a lot, it
seems anon_vma lock is not required anymore to avoid the race.

The page refcount elevation when holding ptl should prevent from THP
split.

Use migrate_misplaced_page() for both base page and THP NUMA hinting fault
and remove all the dead and duplicate code.

[dan.carpenter@oracle.com: fix a double unlock bug]
  Link: https://lkml.kernel.org/r/YLX8uYN01JmfLnlK@mwanda

Link: https://lkml.kernel.org/r/20210518200801.7413-4-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 44 insertions, 101 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f3a3138d33e9..de7a8c2a0c80 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1423,92 +1423,20 @@ out:
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	pmd_t pmd = vmf->orig_pmd;
-	struct anon_vma *anon_vma = NULL;
+	pmd_t oldpmd = vmf->orig_pmd;
+	pmd_t pmd;
 	struct page *page;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
-	int page_nid = NUMA_NO_NODE, this_nid = numa_node_id();
+	int page_nid = NUMA_NO_NODE;
 	int target_nid, last_cpupid = -1;
-	bool page_locked;
 	bool migrated = false;
-	bool was_writable;
+	bool was_writable = pmd_savedwrite(oldpmd);
 	int flags = 0;
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
-	if (unlikely(!pmd_same(pmd, *vmf->pmd)))
-		goto out_unlock;
-
-	/*
-	 * If there are potential migrations, wait for completion and retry
-	 * without disrupting NUMA hinting information. Do not relock and
-	 * check_same as the page may no longer be mapped.
-	 */
-	if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
-		page = pmd_page(*vmf->pmd);
-		if (!get_page_unless_zero(page))
-			goto out_unlock;
-		spin_unlock(vmf->ptl);
-		put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
-		goto out;
-	}
-
-	page = pmd_page(pmd);
-	BUG_ON(is_huge_zero_page(page));
-	page_nid = page_to_nid(page);
-	last_cpupid = page_cpupid_last(page);
-	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (page_nid == this_nid) {
-		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
-		flags |= TNF_FAULT_LOCAL;
-	}
-
-	/* See similar comment in do_numa_page for explanation */
-	if (!pmd_savedwrite(pmd))
-		flags |= TNF_NO_GROUP;
-
-	/*
-	 * Acquire the page lock to serialise THP migrations but avoid dropping
-	 * page_table_lock if at all possible
-	 */
-	page_locked = trylock_page(page);
-	target_nid = mpol_misplaced(page, vma, haddr);
-	/* Migration could have started since the pmd_trans_migrating check */
-	if (!page_locked) {
-		page_nid = NUMA_NO_NODE;
-		if (!get_page_unless_zero(page))
-			goto out_unlock;
+	if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
 		spin_unlock(vmf->ptl);
-		put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
 		goto out;
-	} else if (target_nid == NUMA_NO_NODE) {
-		/* There are no parallel migrations and page is in the right
-		 * node. Clear the numa hinting info in this pmd.
-		 */
-		goto clear_pmdnuma;
-	}
-
-	/*
-	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
-	 * to serialises splits
-	 */
-	get_page(page);
-	spin_unlock(vmf->ptl);
-	anon_vma = page_lock_anon_vma_read(page);
-
-	/* Confirm the PMD did not change while page_table_lock was released */
-	spin_lock(vmf->ptl);
-	if (unlikely(!pmd_same(pmd, *vmf->pmd))) {
-		unlock_page(page);
-		put_page(page);
-		page_nid = NUMA_NO_NODE;
-		goto out_unlock;
-	}
-
-	/* Bail if we fail to protect against THP splits for any reason */
-	if (unlikely(!anon_vma)) {
-		put_page(page);
-		page_nid = NUMA_NO_NODE;
-		goto clear_pmdnuma;
 	}
 
 	/*
@@ -1537,43 +1465,58 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 					      haddr + HPAGE_PMD_SIZE);
 	}
 
-	/*
-	 * Migrate the THP to the requested node, returns with page unlocked
-	 * and access rights restored.
-	 */
+	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+	page = vm_normal_page_pmd(vma, haddr, pmd);
+	if (!page)
+		goto out_map;
+
+	/* See similar comment in do_numa_page for explanation */
+	if (!was_writable)
+		flags |= TNF_NO_GROUP;
+
+	page_nid = page_to_nid(page);
+	last_cpupid = page_cpupid_last(page);
+	target_nid = numa_migrate_prep(page, vma, haddr, page_nid,
+				       &flags);
+
+	if (target_nid == NUMA_NO_NODE) {
+		put_page(page);
+		goto out_map;
+	}
+
 	spin_unlock(vmf->ptl);
 
-	migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma,
-				vmf->pmd, pmd, vmf->address, page, target_nid);
+	migrated = migrate_misplaced_page(page, vma, target_nid);
 	if (migrated) {
 		flags |= TNF_MIGRATED;
 		page_nid = target_nid;
-	} else
+	} else {
 		flags |= TNF_MIGRATE_FAIL;
-
-	goto out;
-clear_pmdnuma:
-	BUG_ON(!PageLocked(page));
-	was_writable = pmd_savedwrite(pmd);
-	pmd = pmd_modify(pmd, vma->vm_page_prot);
-	pmd = pmd_mkyoung(pmd);
-	if (was_writable)
-		pmd = pmd_mkwrite(pmd);
-	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
-	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
-	unlock_page(page);
-out_unlock:
-	spin_unlock(vmf->ptl);
+		vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+		if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+			spin_unlock(vmf->ptl);
+			goto out;
+		}
+		goto out_map;
+	}
 
 out:
-	if (anon_vma)
-		page_unlock_anon_vma_read(anon_vma);
-
 	if (page_nid != NUMA_NO_NODE)
 		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
 				flags);
 
 	return 0;
+
+out_map:
+	/* Restore the PMD */
+	pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+	pmd = pmd_mkyoung(pmd);
+	if (was_writable)
+		pmd = pmd_mkwrite(pmd);
+	set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
+	update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
+	spin_unlock(vmf->ptl);
+	goto out;
 }
 
 /*