FAILED: patch "[PATCH] mm/rmap: use huge_ptep_get() in try_to_migrate_one()" failed to apply to 6.12-stable tree

From: Lorenzo Stoakes <[email protected]>

[ Upstream commit aa62204cb680d8ff32497181fc9e0dac4956f7e5 ]

PMD 'non-swap' swap entries are currently used for PMD-level migration entries and device private entries.

To add to the confusion in this terminology we use is_swap_pmd() in an inconsistent way similar to how is_swap_pte() was being used - sometimes adopting the convention that !pmd_none(), !pmd_present() implies PMD 'swap' entry, sometimes not.

This patch handles the low-hanging fruit of cases where we can simply substitute other predicates for is_swap_pmd().

No functional change intended.

Link https://lkml.kernel.org/r/8a1704b36a009c18032d5bea4cb68e71448fbbe5.1762812360.git.lorenzo.stoakes@oracle.com open here

Signed-off-by Lorenzo Stoakes <[email protected]>

Reviewed-by Vlastimil Babka <[email protected]>

Cc Alexander Gordeev <[email protected]>

Cc Alistair Popple <[email protected]>

Cc Al Viro <[email protected]>

Cc Arnd Bergmann <[email protected]>

Cc Axel Rasmussen <[email protected]>

Cc Baolin Wang <[email protected]>

Cc Baoquan He <[email protected]>

Cc Barry Song <[email protected]>

Cc Byungchul Park <[email protected]>

Cc Chengming Zhou <[email protected]>

Cc Chris Li <[email protected]>

Cc Christian Borntraeger <[email protected]>

Cc Christian Brauner <[email protected]>

Cc Claudio Imbrenda <[email protected]>

Cc David Hildenbrand <[email protected]>

Cc Dev Jain <[email protected]>

Cc Gerald Schaefer <[email protected]>

Cc Gregory Price <[email protected]>

Cc Heiko Carstens <[email protected]>

Cc "Huang, Ying" <[email protected]>

Cc Hugh Dickins <[email protected]>

Cc Jan Kara <[email protected]>

Cc Jann Horn <[email protected]>

Cc Janosch Frank <[email protected]>

Cc Jason Gunthorpe <[email protected]>

Cc Joshua Hahn <[email protected]>

Cc Kairui Song <[email protected]>

Cc Kemeng Shi <[email protected]>

Cc Lance Yang <[email protected]>

Cc Leon Romanovsky <[email protected]>

Cc Liam Howlett <[email protected]>

Cc Mathew Brost <[email protected]>

Cc Matthew Wilcox (Oracle) <[email protected]>

Cc Miaohe Lin <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Mike Rapoport <[email protected]>

Cc Muchun Song <[email protected]>

Cc Naoya Horiguchi <[email protected]>

Cc Nhat Pham <[email protected]>

Cc Nico Pache <[email protected]>

Cc Oscar Salvador <[email protected]>

Cc Pasha Tatashin <[email protected]>

Cc Peter Xu <[email protected]>

Cc Rakie Kim <[email protected]>

Cc Rik van Riel <[email protected]>

Cc Ryan Roberts <[email protected]>

Cc SeongJae Park <[email protected]>

Cc Suren Baghdasaryan <[email protected]>

Cc Sven Schnelle <[email protected]>

Cc Vasily Gorbik <[email protected]>

Cc Vlastimil Babka <[email protected]>

Cc Wei Xu <[email protected]>

Cc xu xin <[email protected]>

Cc Yuanchu Xie <[email protected]>

Cc Zi Yan <[email protected]>

Signed-off-by Andrew Morton <[email protected]>

Stable-dep-of: 9be12ffa78cd ("mm/rmap: use huge_ptep_get() in try_to_migrate_one()")

Signed-off-by Sasha Levin <[email protected]>

---
 fs/proc/task_mmu.c       |  15 ++++-
 include/linux/mm_types.h |   3 +
 include/linux/swapops.h  |  12 +++-
 mm/huge_memory.c         |   4 +-
 mm/memory.c              |  49 ++++++++-------
 mm/page_table_check.c    |  12 ++--
 mm/rmap.c                | 126 ++++++++++++++++-----------------------
 7 files changed, 117 insertions(+), 104 deletions(-)

fs/proc/task_mmu.c +12 -3

index 44dc442b4f0e7..cfcf0daa1e626 100644
@@ -860,10 +860,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	bool present = false;
 	struct folio *folio;
 
+	if (pmd_none(*pmd))
+		return;
 	if (pmd_present(*pmd)) {
 		page = vm_normal_page_pmd(vma, addr, *pmd);
 		present = true;
-	} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
+	} else if (unlikely(thp_migration_supported())) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 
 		if (is_pfn_swap_entry(entry))

@@ -1786,6 +1788,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		if (vma->vm_flags & VM_SOFTDIRTY)
 			flags |= PM_SOFT_DIRTY;
 
+		if (pmd_none(pmd))
+			goto populate_pagemap;
+
 		if (pmd_present(pmd)) {
 			page = pmd_page(pmd);
 

@@ -1798,7 +1803,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 				frame = pmd_pfn(pmd) + idx;
 		}
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-		else if (is_swap_pmd(pmd)) {
+		else {
 			swp_entry_t entry = pmd_to_swp_entry(pmd);
 			unsigned long offset;
 

@@ -1826,6 +1831,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 				flags |= PM_FILE;
 		}
 
+populate_pagemap:
 		for (; addr != end; addr += PAGE_SIZE, idx++) {
 			u64 cur_flags = flags;
 			pagemap_entry_t pme;

@@ -2172,6 +2178,9 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 {
 	unsigned long categories = PAGE_IS_HUGE;
 
+	if (pmd_none(pmd))
+		return categories;
+
 	if (pmd_present(pmd)) {
 		struct page *page;
 

@@ -2189,7 +2198,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 			categories |= PAGE_IS_PFNZERO;
 		if (pmd_soft_dirty(pmd))
 			categories |= PAGE_IS_SOFT_DIRTY;
-	} else if (is_swap_pmd(pmd)) {
+	} else {
 		swp_entry_t swp;
 
 		categories |= PAGE_IS_SWAPPED;

include/linux/mm_types.h +3 -0

index 2113f7da182c6..ca4e4a1c2d0b9 100644
@@ -283,6 +283,9 @@ typedef struct {
 	unsigned long val;
 } swp_entry_t;
 
+/* Transitional name used by newer MM fixes. */
+typedef swp_entry_t softleaf_t;
+
 /**
  * struct folio - Represents a contiguous set of bytes.
  * @flags: Identical to the page flags.

include/linux/swapops.h +11 -1

index d988ce9516510..d06bda5be5768 100644
@@ -139,6 +139,10 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
 	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
 }
 
+/* Transitional softleaf spellings for the equivalent swap entry helpers. */
+#define softleaf_from_pte(pte) pte_to_swp_entry(pte)
+#define softleaf_to_pfn(entry) swp_offset_pfn(entry)
+
 /*
  * Convert the arch-independent representation of a swp_entry_t into the
  * arch-dependent pte representation.

@@ -569,7 +573,13 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
 
 static inline int is_pmd_migration_entry(pmd_t pmd)
 {
-	return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
+	swp_entry_t entry;
+
+	if (pmd_present(pmd))
+		return 0;
+
+	entry = pmd_to_swp_entry(pmd);
+	return is_migration_entry(entry);
 }
 #else  /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
 static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,

mm/huge_memory.c +3 -1

index 29cbe43b60a4f..6fc4e1fb88ae6 100644
@@ -2149,9 +2149,11 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
 
 static pmd_t clear_uffd_wp_pmd(pmd_t pmd)
 {
+	if (pmd_none(pmd))
+		return pmd;
 	if (pmd_present(pmd))
 		pmd = pmd_clear_uffd_wp(pmd);
-	else if (is_swap_pmd(pmd))
+	else
 		pmd = pmd_swp_clear_uffd_wp(pmd);
 
 	return pmd;

mm/memory.c +27 -22

index 359de59c39b1a..c493f18cfb3ab 100644
@@ -5901,34 +5901,39 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	    thp_vma_allowable_order(vma, vm_flags,
 				TVA_IN_PF | TVA_ENFORCE_SYSFS, PMD_ORDER)) {
 		ret = create_huge_pmd(&vmf);
-		if (!(ret & VM_FAULT_FALLBACK))
+		if (ret & VM_FAULT_FALLBACK)
+			goto fallback;
+		else
 			return ret;
-	} else {
-		vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
+	}
 
-		if (unlikely(is_swap_pmd(vmf.orig_pmd))) {
-			VM_BUG_ON(thp_migration_supported() &&
-					  !is_pmd_migration_entry(vmf.orig_pmd));
-			if (is_pmd_migration_entry(vmf.orig_pmd))
-				pmd_migration_entry_wait(mm, vmf.pmd);
-			return 0;
-		}
-		if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
-			if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
-				return do_huge_pmd_numa_page(&vmf);
+	vmf.orig_pmd = pmdp_get_lockless(vmf.pmd);
+	if (pmd_none(vmf.orig_pmd))
+		goto fallback;
 
-			if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
-			    !pmd_write(vmf.orig_pmd)) {
-				ret = wp_huge_pmd(&vmf);
-				if (!(ret & VM_FAULT_FALLBACK))
-					return ret;
-			} else {
-				huge_pmd_set_accessed(&vmf);
-				return 0;
-			}
+	if (unlikely(!pmd_present(vmf.orig_pmd))) {
+		VM_BUG_ON(thp_migration_supported() &&
+				  !is_pmd_migration_entry(vmf.orig_pmd));
+		if (is_pmd_migration_entry(vmf.orig_pmd))
+			pmd_migration_entry_wait(mm, vmf.pmd);
+		return 0;
+	}
+	if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
+		if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
+			return do_huge_pmd_numa_page(&vmf);
+
+		if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
+		    !pmd_write(vmf.orig_pmd)) {
+			ret = wp_huge_pmd(&vmf);
+			if (!(ret & VM_FAULT_FALLBACK))
+				return ret;
+		} else {
+			huge_pmd_set_accessed(&vmf);
+			return 0;
 		}
 	}
 
+fallback:
 	return handle_pte_fault(&vmf);
 }
 

mm/page_table_check.c +8 -4

index 509c6ef8de400..ee52927e9e66b 100644
@@ -228,10 +228,14 @@ EXPORT_SYMBOL(__page_table_check_ptes_set);
 
 static inline void page_table_check_pmd_flags(pmd_t pmd)
 {
-	if (pmd_present(pmd) && pmd_uffd_wp(pmd))
-		WARN_ON_ONCE(pmd_write(pmd));
-	else if (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd))
-		WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd)));
+	if (pmd_present(pmd)) {
+		if (pmd_uffd_wp(pmd))
+			WARN_ON_ONCE(pmd_write(pmd));
+	} else if (pmd_swp_uffd_wp(pmd)) {
+		swp_entry_t entry = pmd_to_swp_entry(pmd);
+
+		WARN_ON_ONCE(swap_cached_writable(entry));
+	}
 }
 
 void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd)

mm/rmap.c +53 -73

index ea9c6d540d498..36a2e0eb8be48 100644
@@ -2001,9 +2001,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
+	bool anon_exclusive, writable, ret = true;
 	pte_t pteval;
 	struct page *subpage;
-	bool anon_exclusive, ret = true;
 	struct mmu_notifier_range range;
 	enum ttu_flags flags = (enum ttu_flags)(long)arg;
 	unsigned long pfn;

@@ -2070,24 +2070,21 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 		/* Unexpected PMD-mapped THP? */
 		VM_BUG_ON_FOLIO(!pvmw.pte, folio);
 
-		pfn = pte_pfn(ptep_get(pvmw.pte));
-
-		if (folio_is_zone_device(folio)) {
-			/*
-			 * Our PTE is a non-present device exclusive entry and
-			 * calculating the subpage as for the common case would
-			 * result in an invalid pointer.
-			 *
-			 * Since only PAGE_SIZE pages can currently be
-			 * migrated, just set it to page. This will need to be
-			 * changed when hugepage migrations to device private
-			 * memory are supported.
-			 */
-			VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio);
-			subpage = &folio->page;
+		/*
+		 * Handle PFN swap PTEs, such as device-exclusive ones, that
+		 * actually map pages.
+		 */
+		pteval = ptep_get(pvmw.pte);
+		if (likely(pte_present(pteval))) {
+			pfn = pte_pfn(pteval);
 		} else {
-			subpage = folio_page(folio, pfn - folio_pfn(folio));
+			const softleaf_t entry = softleaf_from_pte(pteval);
+
+			pfn = softleaf_to_pfn(entry);
+			VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
 		}
+
+		subpage = folio_page(folio, pfn - folio_pfn(folio));
 		address = pvmw.address;
 		anon_exclusive = folio_test_anon(folio) &&
 				 PageAnonExclusive(subpage);

@@ -2141,7 +2138,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			}
 			/* Nuke the hugetlb page table entry */
 			pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
-		} else {
+			if (pte_dirty(pteval))
+				folio_mark_dirty(folio);
+			writable = pte_write(pteval);
+		} else if (likely(pte_present(pteval))) {
 			flush_cache_page(vma, address, pfn);
 			/* Nuke the page table entry. */
 			if (should_defer_flush(mm, flags)) {

@@ -2159,54 +2159,23 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			} else {
 				pteval = ptep_clear_flush(vma, address, pvmw.pte);
 			}
+			if (pte_dirty(pteval))
+				folio_mark_dirty(folio);
+			writable = pte_write(pteval);
+		} else {
+			pte_clear(mm, address, pvmw.pte);
+			writable = is_writable_device_private_entry(pte_to_swp_entry(pteval));
 		}
 
-		/* Set the dirty flag on the folio now the pte is gone. */
-		if (pte_dirty(pteval))
-			folio_mark_dirty(folio);
+		VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) &&
+				!anon_exclusive, folio);
 
 		/* Update high watermark before we lower rss */
 		update_hiwater_rss(mm);
 
-		if (folio_is_device_private(folio)) {
-			unsigned long pfn = folio_pfn(folio);
-			swp_entry_t entry;
-			pte_t swp_pte;
-
-			if (anon_exclusive)
-				WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio,
-									   subpage));
-
-			/*
-			 * Store the pfn of the page in a special migration
-			 * pte. do_swap_page() will wait until the migration
-			 * pte is removed and then restart fault handling.
-			 */
-			entry = pte_to_swp_entry(pteval);
-			if (is_writable_device_private_entry(entry))
-				entry = make_writable_migration_entry(pfn);
-			else if (anon_exclusive)
-				entry = make_readable_exclusive_migration_entry(pfn);
-			else
-				entry = make_readable_migration_entry(pfn);
-			swp_pte = swp_entry_to_pte(entry);
+		if (PageHWPoison(subpage)) {
+			VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio);
 
-			/*
-			 * pteval maps a zone device page and is therefore
-			 * a swap pte.
-			 */
-			if (pte_swp_soft_dirty(pteval))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_swp_uffd_wp(pteval))
-				swp_pte = pte_swp_mkuffd_wp(swp_pte);
-			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
-			trace_set_migration_pte(pvmw.address, pte_val(swp_pte),
-						folio_order(folio));
-			/*
-			 * No need to invalidate here it will synchronize on
-			 * against the special swap migration pte.
-			 */
-		} else if (PageHWPoison(subpage)) {
 			pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
 			if (folio_test_hugetlb(folio)) {
 				hugetlb_count_sub(folio_nr_pages(folio), mm);

@@ -2216,8 +2185,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				dec_mm_counter(mm, mm_counter(folio));
 				set_pte_at(mm, address, pvmw.pte, pteval);
 			}
-
-		} else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
+		} else if (likely(pte_present(pteval)) && pte_unused(pteval) &&
+			   !userfaultfd_armed(vma)) {
 			/*
 			 * The guest indicated that the page content is of no
 			 * interest anymore. Simply discard the pte, vmscan

@@ -2233,6 +2202,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			swp_entry_t entry;
 			pte_t swp_pte;
 
+			/*
+			 * arch_unmap_one() is expected to be a NOP on
+			 * architectures where we could have PFN swap PTEs,
+			 * so we'll not check/care.
+			 */
 			if (arch_unmap_one(mm, vma, address, pteval) < 0) {
 				if (folio_test_hugetlb(folio))
 					set_huge_pte_at(mm, address, pvmw.pte,

@@ -2243,8 +2217,6 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
-			VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) &&
-				       !anon_exclusive, subpage);
 
 			/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
 			if (folio_test_hugetlb(folio)) {

@@ -2269,7 +2241,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			if (pte_write(pteval))
+			if (writable)
 				entry = make_writable_migration_entry(
 							page_to_pfn(subpage));
 			else if (anon_exclusive)

@@ -2278,15 +2250,23 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			else
 				entry = make_readable_migration_entry(
 							page_to_pfn(subpage));
-			if (pte_young(pteval))
-				entry = make_migration_entry_young(entry);
-			if (pte_dirty(pteval))
-				entry = make_migration_entry_dirty(entry);
-			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pteval))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pteval))
-				swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			if (likely(pte_present(pteval))) {
+				if (pte_young(pteval))
+					entry = make_migration_entry_young(entry);
+				if (pte_dirty(pteval))
+					entry = make_migration_entry_dirty(entry);
+				swp_pte = swp_entry_to_pte(entry);
+				if (pte_soft_dirty(pteval))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_uffd_wp(pteval))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			} else {
+				swp_pte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(pteval))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_swp_uffd_wp(pteval))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			}
 			if (folio_test_hugetlb(folio))
 				set_huge_pte_at(mm, address, pvmw.pte, swp_pte,
 						hsz);

Signature · 1 line

2.53.0