[PATCH v1] mm/pagewalk: fix usage of pmd_leaf()/pud_leaf() without present check

[David Hildenbrand]

pmd_leaf()/pud_leaf() only implies a pmd_present()/pud_present() check on
some architectures. We really should check for
pmd_present()/pud_present() first.

This should explain the report we got on ppc64 (which has
CONFIG_PGTABLE_HAS_HUGE_LEAVES set in the config) that triggered:
	VM_WARN_ON_ONCE(pmd_leaf(pmdp_get_lockless(pmdp)));

Likely we had a PMD migration entry for which pmd_leaf() did not
trigger. We raced with restoring the PMD migration entry, and suddenly
saw a pmd_leaf(). In this case, pte_offset_map_lock() saved us from more
trouble, because it rechecks the PMD value, but we would not have processed
the migration entry -- which is not too bad because the only user of
FW_MIGRATION is KSM for unsharing, and KSM only applies to small folios.

Further, we shouldn't re-read the PMD/PUD value for our warning, the
primary purpose of the VM_WARN_ON_ONCE() is to find spurious use of
pmd_leaf()/pud_leaf() without CONFIG_PGTABLE_HAS_HUGE_LEAVES.

As a side note, we are currently not implementing FW_MIGRATION support
for PUD migration entries, which likely should exist due to hugetlb. Add
a TODO so this won't fall through the cracks if more FW_MIGRATION users
get added.

Fixes: aa39ca6940f1 ("mm/pagewalk: introduce folio_walk_start() + folio_walk_end()")
Reported-by: syzbot+7d917f67c05066cec295@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://lkml.kernel.org/r/670d3248.050a0220.3e960.0064.GAE@xxxxxxxxxx
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Jann Horn <jannh@xxxxxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
 mm/pagewalk.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 461ea3bbd8d9..5f9f01532e67 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -744,7 +744,8 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 	pud = pudp_get(pudp);
 	if (pud_none(pud))
 		goto not_found;
-	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pud_leaf(pud)) {
+	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) &&
+	    (!pud_present(pud) || pud_leaf(pud))) {
 		ptl = pud_lock(vma->vm_mm, pudp);
 		pud = pudp_get(pudp);
 
@@ -753,6 +754,10 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 		fw->pudp = pudp;
 		fw->pud = pud;
 
+		/*
+		 * TODO: FW_MIGRATION support for PUD migration entries
+		 * once there are relevant users.
+		 */
 		if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) {
 			spin_unlock(ptl);
 			goto not_found;
@@ -769,12 +774,13 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 	}
 
 pmd_table:
-	VM_WARN_ON_ONCE(pud_leaf(*pudp));
+	VM_WARN_ON_ONCE(!pud_present(pud) || pud_leaf(pud));
 	pmdp = pmd_offset(pudp, addr);
 	pmd = pmdp_get_lockless(pmdp);
 	if (pmd_none(pmd))
 		goto not_found;
-	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pmd_leaf(pmd)) {
+	if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) &&
+	    (!pmd_present(pmd) || pmd_leaf(pmd))) {
 		ptl = pmd_lock(vma->vm_mm, pmdp);
 		pmd = pmdp_get(pmdp);
 
@@ -786,7 +792,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 		if (pmd_none(pmd)) {
 			spin_unlock(ptl);
 			goto not_found;
-		} else if (!pmd_leaf(pmd)) {
+		} else if (pmd_present(pmd) && !pmd_leaf(pmd)) {
 			spin_unlock(ptl);
 			goto pte_table;
 		} else if (pmd_present(pmd)) {
@@ -812,7 +818,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 	}
 
 pte_table:
-	VM_WARN_ON_ONCE(pmd_leaf(pmdp_get_lockless(pmdp)));
+	VM_WARN_ON_ONCE(!pmd_present(pmd) || pmd_leaf(pmd));
 	ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl);
 	if (!ptep)
 		goto not_found;
-- 
2.46.1