mm/khugepaged: record SCAN_PMD_MAPPED when scan_pmd() finds hugepage

When scanning an anon pmd to see if it's eligible for collapse, return
SCAN_PMD_MAPPED if the pmd already maps a hugepage.  Note that
SCAN_PMD_MAPPED is different from SCAN_PAGE_COMPOUND used in the
file-collapse path, since the latter might identify pte-mapped compound
pages.  This is required by MADV_COLLAPSE which necessarily needs to know
what hugepage-aligned/sized regions are already pmd-mapped.

In order to determine if a pmd already maps a hugepage, refactor
mm_find_pmd():

Return mm_find_pmd() to it's pre-commit f72e7dcdd252 ("mm: let mm_find_pmd
fix buggy race with THP fault") behavior.  ksm was the only caller that
explicitly wanted a pte-mapping pmd, so open code the pte-mapping logic
there (pmd_present() and pmd_trans_huge() checks).

Undo revert change in commit f72e7dcdd252 ("mm: let mm_find_pmd fix buggy
race with THP fault") that open-coded split_huge_pmd_address() pmd lookup
and use mm_find_pmd() instead.

Link: https://lkml.kernel.org/r/20220706235936.2197195-9-zokeefe@google.com
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rongwei Wang <rongwei.wang@linux.alibaba.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: "Souptick Joarder (HPE)" <jrdr.linux@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 67 insertions, 39 deletions

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index d651f3437367..55392bf30a03 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -11,6 +11,7 @@
 	EM( SCAN_FAIL,			"failed")			\
 	EM( SCAN_SUCCEED,		"succeeded")			\
 	EM( SCAN_PMD_NULL,		"pmd_null")			\
+	EM( SCAN_PMD_MAPPED,		"page_pmd_mapped")		\
 	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
 	EM( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")		\
 	EM( SCAN_EXCEED_SHARED_PTE,	"exceed_shared_pte")		\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 917d92e77a1b..3222b40a0f6d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2286,25 +2286,11 @@ out:
 void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 		bool freeze, struct folio *folio)
 {
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
+	pmd_t *pmd = mm_find_pmd(vma->vm_mm, address);
 
-	pgd = pgd_offset(vma->vm_mm, address);
-	if (!pgd_present(*pgd))
+	if (!pmd)
 		return;
 
-	p4d = p4d_offset(pgd, address);
-	if (!p4d_present(*p4d))
-		return;
-
-	pud = pud_offset(p4d, address);
-	if (!pud_present(*pud))
-		return;
-
-	pmd = pmd_offset(pud, address);
-
 	__split_huge_pmd(vma, pmd, address, freeze, folio);
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 785409805ed7..55ce10e4d0c0 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -187,7 +187,7 @@ extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason
 /*
  * in mm/rmap.c:
  */
-extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
+pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
 
 /*
  * in mm/page_alloc.c
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index af25206705aa..a6eb81722871 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -28,6 +28,7 @@ enum scan_result {
 	SCAN_FAIL,
 	SCAN_SUCCEED,
 	SCAN_PMD_NULL,
+	SCAN_PMD_MAPPED,
 	SCAN_EXCEED_NONE_PTE,
 	SCAN_EXCEED_SWAP_PTE,
 	SCAN_EXCEED_SHARED_PTE,
@@ -877,6 +878,45 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	return SCAN_SUCCEED;
 }
 
+static int find_pmd_or_thp_or_none(struct mm_struct *mm,
+				   unsigned long address,
+				   pmd_t **pmd)
+{
+	pmd_t pmde;
+
+	*pmd = mm_find_pmd(mm, address);
+	if (!*pmd)
+		return SCAN_PMD_NULL;
+
+	pmde = pmd_read_atomic(*pmd);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/* See comments in pmd_none_or_trans_huge_or_clear_bad() */
+	barrier();
+#endif
+	if (!pmd_present(pmde))
+		return SCAN_PMD_NULL;
+	if (pmd_trans_huge(pmde))
+		return SCAN_PMD_MAPPED;
+	if (pmd_bad(pmde))
+		return SCAN_PMD_NULL;
+	return SCAN_SUCCEED;
+}
+
+static int check_pmd_still_valid(struct mm_struct *mm,
+				 unsigned long address,
+				 pmd_t *pmd)
+{
+	pmd_t *new_pmd;
+	int result = find_pmd_or_thp_or_none(mm, address, &new_pmd);
+
+	if (result != SCAN_SUCCEED)
+		return result;
+	if (new_pmd != pmd)
+		return SCAN_FAIL;
+	return SCAN_SUCCEED;
+}
+
 /*
  * Bring missing pages in from swap, to complete THP collapse.
  * Only done if khugepaged_scan_pmd believes it is worthwhile.
@@ -988,9 +1028,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 		goto out_nolock;
 	}
 
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd) {
-		result = SCAN_PMD_NULL;
+	result = find_pmd_or_thp_or_none(mm, address, &pmd);
+	if (result != SCAN_SUCCEED) {
 		mmap_read_unlock(mm);
 		goto out_nolock;
 	}
@@ -1018,7 +1057,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 	/* check if the pmd is still valid */
-	if (mm_find_pmd(mm, address) != pmd)
+	result = check_pmd_still_valid(mm, address, pmd);
+	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 
 	anon_vma_lock_write(vma->anon_vma);
@@ -1121,11 +1161,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd) {
-		result = SCAN_PMD_NULL;
+	result = find_pmd_or_thp_or_none(mm, address, &pmd);
+	if (result != SCAN_SUCCEED)
 		goto out;
-	}
 
 	memset(cc->node_load, 0, sizeof(cc->node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
@@ -1383,8 +1421,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	if (!PageHead(hpage))
 		goto drop_hpage;
 
-	pmd = mm_find_pmd(mm, haddr);
-	if (!pmd)
+	if (find_pmd_or_thp_or_none(mm, haddr, &pmd) != SCAN_SUCCEED)
 		goto drop_hpage;
 
 	start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
@@ -1502,8 +1539,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		if (vma->vm_end < addr + HPAGE_PMD_SIZE)
 			continue;
 		mm = vma->vm_mm;
-		pmd = mm_find_pmd(mm, addr);
-		if (!pmd)
+		if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED)
 			continue;
 		/*
 		 * We need exclusive mmap_lock to retract page table.
diff --git a/mm/ksm.c b/mm/ksm.c
index 42ab153335a2..2f315c69fa2c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1134,6 +1134,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t *pmd;
+	pmd_t pmde;
 	pte_t *ptep;
 	pte_t newpte;
 	spinlock_t *ptl;
@@ -1148,6 +1149,15 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	pmd = mm_find_pmd(mm, addr);
 	if (!pmd)
 		goto out;
+	/*
+	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
+	 * without holding anon_vma lock for write.  So when looking for a
+	 * genuine pmde (in which to find pte), test present and !THP together.
+	 */
+	pmde = *pmd;
+	barrier();
+	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
+		goto out;
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr,
 				addr + PAGE_SIZE);
diff --git a/mm/rmap.c b/mm/rmap.c
index edc06c52bc82..af775855e58f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -767,13 +767,17 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 	return vma_address(page, vma);
 }
 
+/*
+ * Returns the actual pmd_t* where we expect 'address' to be mapped from, or
+ * NULL if it doesn't exist.  No guarantees / checks on what the pmd_t*
+ * represents.
+ */
 pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd = NULL;
-	pmd_t pmde;
 
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
@@ -788,15 +792,6 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 		goto out;
 
 	pmd = pmd_offset(pud, address);
-	/*
-	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
-	 * without holding anon_vma lock for write.  So when looking for a
-	 * genuine pmde (in which to find pte), test present and !THP together.
-	 */
-	pmde = *pmd;
-	barrier();
-	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
-		pmd = NULL;
 out:
 	return pmd;
 }