mm: rmap: fix CONT-PTE/PMD size hugetlb issue when migration

On some architectures (like ARM64), it can support CONT-PTE/PMD size
hugetlb, which means it can support not only PMD/PUD size hugetlb: 2M and
1G, but also CONT-PTE/PMD size: 64K and 32M if a 4K page size specified.

When migrating a hugetlb page, we will get the relevant page table entry
by huge_pte_offset() only once to nuke it and remap it with a migration
pte entry.  This is correct for PMD or PUD size hugetlb, since they always
contain only one pmd entry or pud entry in the page table.

However this is incorrect for CONT-PTE and CONT-PMD size hugetlb, since
they can contain several continuous pte or pmd entry with same page table
attributes.  So we will nuke or remap only one pte or pmd entry for this
CONT-PTE/PMD size hugetlb page, which is not expected for hugetlb
migration.  The problem is we can still continue to modify the subpages'
data of a hugetlb page during migrating a hugetlb page, which can cause a
serious data consistent issue, since we did not nuke the page table entry
and set a migration pte for the subpages of a hugetlb page.

To fix this issue, we should change to use huge_ptep_clear_flush() to nuke
a hugetlb page table, and remap it with set_huge_pte_at() and
set_huge_swap_pte_at() when migrating a hugetlb page, which already
considered the CONT-PTE or CONT-PMD size hugetlb.

[akpm@linux-foundation.org: fix nommu build]
[baolin.wang@linux.alibaba.com: fix build errors for !CONFIG_MMU]
  Link: https://lkml.kernel.org/r/a4baca670aca637e7198d9ae4543b8873cb224dc.1652270205.git.baolin.wang@linux.alibaba.com
Link: https://lkml.kernel.org/r/ea5abf529f0997b5430961012bfda6166c1efc8c.1652147571.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.osdn.me>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 29 insertions, 6 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 04f0186b089b..0f2894d01333 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1093,6 +1093,17 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 					pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
+
+static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+					  unsigned long addr, pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/mm/rmap.c b/mm/rmap.c
index 94d6b24a1ac2..4e96daff9293 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1926,13 +1926,15 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 					break;
 				}
 			}
+
+			/* Nuke the hugetlb page table entry */
+			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
 		} else {
 			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+			/* Nuke the page table entry. */
+			pteval = ptep_clear_flush(vma, address, pvmw.pte);
 		}
 
-		/* Nuke the page table entry. */
-		pteval = ptep_clear_flush(vma, address, pvmw.pte);
-
 		/* Set the dirty flag on the folio now the pte is gone. */
 		if (pte_dirty(pteval))
 			folio_mark_dirty(folio);
@@ -2017,7 +2019,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			pte_t swp_pte;
 
 			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				if (folio_test_hugetlb(folio))
+					set_huge_pte_at(mm, address, pvmw.pte, pteval);
+				else
+					set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
@@ -2026,7 +2031,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				       !anon_exclusive, subpage);
 			if (anon_exclusive &&
 			    page_try_share_anon_rmap(subpage)) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				if (folio_test_hugetlb(folio))
+					set_huge_pte_at(mm, address, pvmw.pte, pteval);
+				else
+					set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
@@ -2052,7 +2060,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
 			if (pte_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
-			set_pte_at(mm, address, pvmw.pte, swp_pte);
+			if (folio_test_hugetlb(folio))
+				set_huge_swap_pte_at(mm, address, pvmw.pte,
+						     swp_pte, vma_mmu_pagesize(vma));
+			else
+				set_pte_at(mm, address, pvmw.pte, swp_pte);
 			trace_set_migration_pte(address, pte_val(swp_pte),
 						compound_order(&folio->page));
 			/*