FAILED: patch "[PATCH] mm/page_vma_mapped: use huge_ptep_get() for hugetlb" failed to apply to 6.6-stable tree

index bac2eb5de63d..d7670ba4147b 100644
@@ -107,7 +107,13 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, pmd_t *pmdvalp,
 static bool check_pte(struct page_vma_mapped_walk *pvmw, unsigned long pte_nr)
 {
 	unsigned long pfn;
-	pte_t ptent = ptep_get(pvmw->pte);
+	pte_t ptent;
+
+	if (is_vm_hugetlb_page(pvmw->vma))
+		ptent = huge_ptep_get(pvmw->vma->vm_mm, pvmw->address,
+				      pvmw->pte);
+	else
+		ptent = ptep_get(pvmw->pte);
 
 	if (pvmw->flags & PVMW_MIGRATION) {
 		const softleaf_t entry = softleaf_from_pte(ptent);

index edae641407b96..27322ffd140c3 100644
@@ -6085,17 +6085,27 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
 vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags)
 {
-	pte_t *ptep, entry;
-	spinlock_t *ptl;
 	vm_fault_t ret;
 	u32 hash;
-	pgoff_t idx;
 	struct folio *folio = NULL;
 	struct folio *pagecache_folio = NULL;
 	struct hstate *h = hstate_vma(vma);
 	struct address_space *mapping;
 	int need_wait_lock = 0;
-	unsigned long haddr = address & huge_page_mask(h);
+	struct vm_fault vmf = {
+		.vma = vma,
+		.address = address & huge_page_mask(h),
+		.real_address = address,
+		.flags = flags,
+		.pgoff = vma_hugecache_offset(h, vma,
+				address & huge_page_mask(h)),
+		/* TODO: Track hugetlb faults using vm_fault */
+
+		/*
+		 * Some fields may not be initialized, be careful as it may
+		 * be hard to debug if called functions make assumptions
+		 */
+	};
 
 	/* TODO: Handle faults under the VMA lock */
 	if (flags & FAULT_FLAG_VMA_LOCK) {

@@ -6109,28 +6119,27 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * the same page in the page cache.
 	 */
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, haddr);
-	hash = hugetlb_fault_mutex_hash(mapping, idx);
+	hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	/*
 	 * Acquire vma lock before calling huge_pte_alloc and hold
-	 * until finished with ptep.  This prevents huge_pmd_unshare from
-	 * being called elsewhere and making the ptep no longer valid.
+	 * until finished with vmf.pte.  This prevents huge_pmd_unshare from
+	 * being called elsewhere and making the vmf.pte no longer valid.
 	 */
 	hugetlb_vma_lock_read(vma);
-	ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h));
-	if (!ptep) {
+	vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h));
+	if (!vmf.pte) {
 		hugetlb_vma_unlock_read(vma);
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		return VM_FAULT_OOM;
 	}
 
-	entry = huge_ptep_get(ptep);
-	if (huge_pte_none_mostly(entry)) {
-		if (is_pte_marker(entry)) {
+	vmf.orig_pte = huge_ptep_get(vmf.pte);
+	if (huge_pte_none_mostly(vmf.orig_pte)) {
+		if (is_pte_marker(vmf.orig_pte)) {
 			pte_marker marker =
-				pte_marker_get(pte_to_swp_entry(entry));
+				pte_marker_get(pte_to_swp_entry(vmf.orig_pte));
 
 			if (marker & PTE_MARKER_POISONED) {
 				ret = VM_FAULT_HWPOISON_LARGE;

@@ -6144,21 +6153,21 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * hugetlb_no_page will drop vma lock and hugetlb fault
 		 * mutex internally, which make us return immediately.
 		 */
-		return hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
-				      entry, flags);
+		return hugetlb_no_page(mm, vma, mapping, vmf.pgoff, address,
+				       vmf.pte, vmf.orig_pte, flags);
 	}
 
 	ret = 0;
 
 	/*
-	 * entry could be a migration/hwpoison entry at this point, so this
-	 * check prevents the kernel from going below assuming that we have
-	 * an active hugepage in pagecache. This goto expects the 2nd page
-	 * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will
-	 * properly handle it.
+	 * vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this
+	 * point, so this check prevents the kernel from going below assuming
+	 * that we have an active hugepage in pagecache. This goto expects
+	 * the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned)
+	 * check will properly handle it.
 	 */
-	if (!pte_present(entry)) {
-		if (unlikely(is_hugetlb_entry_migration(entry))) {
+	if (!pte_present(vmf.orig_pte)) {
+		if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) {
 			/*
 			 * Release the hugetlb fault lock now, but retain
 			 * the vma lock, because it is needed to guard the

@@ -6167,9 +6176,9 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			 * be released there.
 			 */
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-			migration_entry_wait_huge(vma, ptep);
+			migration_entry_wait_huge(vma, vmf.pte);
 			return 0;
-		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+		} else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte)))
 			ret = VM_FAULT_HWPOISON_LARGE |
 			    VM_FAULT_SET_HINDEX(hstate_index(h));
 		goto out_mutex;

@@ -6183,36 +6192,29 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * determine if a reservation has been consumed.
 	 */
 	if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) &&
-	    !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) {
-		if (vma_needs_reservation(h, vma, haddr) < 0) {
+	    !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) {
+		if (vma_needs_reservation(h, vma, vmf.address) < 0) {
 			ret = VM_FAULT_OOM;
 			goto out_mutex;
 		}
 		/* Just decrements count, does not deallocate */
-		vma_end_reservation(h, vma, haddr);
+		vma_end_reservation(h, vma, vmf.address);
 
-		pagecache_folio = filemap_lock_folio(mapping, idx);
+		pagecache_folio = filemap_lock_folio(mapping, vmf.pgoff);
 		if (IS_ERR(pagecache_folio))
 			pagecache_folio = NULL;
 	}
 
-	ptl = huge_pte_lock(h, mm, ptep);
+	vmf.ptl = huge_pte_lock(h, mm, vmf.pte);
 
 	/* Check for a racing update before calling hugetlb_wp() */
-	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
+	if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(vmf.pte))))
 		goto out_ptl;
 
 	/* Handle userfault-wp first, before trying to lock more pages */
-	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) &&
-	    (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
-		struct vm_fault vmf = {
-			.vma = vma,
-			.address = haddr,
-			.real_address = address,
-			.flags = flags,
-		};
-
-		spin_unlock(ptl);
+	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(vmf.pte)) &&
+	    (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) {
+		spin_unlock(vmf.ptl);
 		if (pagecache_folio) {
 			folio_unlock(pagecache_folio);
 			folio_put(pagecache_folio);

@@ -6223,11 +6225,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	/*
-	 * hugetlb_wp() requires page locks of pte_page(entry) and
+	 * hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and
 	 * pagecache_folio, so here we need take the former one
 	 * when folio != pagecache_folio or !pagecache_folio.
 	 */
-	folio = page_folio(pte_page(entry));
+	folio = page_folio(pte_page(vmf.orig_pte));
 	if (folio != pagecache_folio)
 		if (!folio_trylock(folio)) {
 			need_wait_lock = 1;

@@ -6237,24 +6239,24 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	folio_get(folio);
 
 	if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
-		if (!huge_pte_write(entry)) {
-			ret = hugetlb_wp(mm, vma, address, ptep, flags,
-					 pagecache_folio, ptl);
+		if (!huge_pte_write(vmf.orig_pte)) {
+			ret = hugetlb_wp(mm, vma, address, vmf.pte, flags,
+					 pagecache_folio, vmf.ptl);
 			goto out_put_page;
 		} else if (likely(flags & FAULT_FLAG_WRITE)) {
-			entry = huge_pte_mkdirty(entry);
+			vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte);
 		}
 	}
-	entry = pte_mkyoung(entry);
-	if (huge_ptep_set_access_flags(vma, haddr, ptep, entry,
+	vmf.orig_pte = pte_mkyoung(vmf.orig_pte);
+	if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte,
 						flags & FAULT_FLAG_WRITE))
-		update_mmu_cache(vma, haddr, ptep);
+		update_mmu_cache(vma, vmf.address, vmf.pte);
 out_put_page:
 	if (folio != pagecache_folio)
 		folio_unlock(folio);
 	folio_put(folio);
 out_ptl:
-	spin_unlock(ptl);
+	spin_unlock(vmf.ptl);
 
 	if (pagecache_folio) {
 		folio_unlock(pagecache_folio);

index 27322ffd140c3..a9757b11b7c49 100644
@@ -5848,22 +5848,19 @@ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm,
 	return same;
 }
 
-static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
-			struct vm_area_struct *vma,
-			struct address_space *mapping, pgoff_t idx,
-			unsigned long address, pte_t *ptep,
-			pte_t old_pte, unsigned int flags)
+static vm_fault_t hugetlb_no_page(struct address_space *mapping,
+			struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
 	struct hstate *h = hstate_vma(vma);
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 	int anon_rmap = 0;
 	unsigned long size;
 	struct folio *folio;
 	pte_t new_pte;
-	spinlock_t *ptl;
-	unsigned long haddr = address & huge_page_mask(h);
 	bool new_folio, new_pagecache_folio = false;
-	u32 hash = hugetlb_fault_mutex_hash(mapping, idx);
+	u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff);
 
 	/*
 	 * Currently, we are forced to kill the process in the event the

@@ -5882,10 +5879,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	 * before we get page_table_lock.
 	 */
 	new_folio = false;
-	folio = filemap_lock_folio(mapping, idx);
+	folio = filemap_lock_folio(mapping, vmf->pgoff);
 	if (IS_ERR(folio)) {
 		size = i_size_read(mapping->host) >> huge_page_shift(h);
-		if (idx >= size)
+		if (vmf->pgoff >= size)
 			goto out;
 		/* Check for page in userfault range */
 		if (userfaultfd_missing(vma)) {

@@ -5906,17 +5903,18 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			 * never happen on the page after UFFDIO_COPY has
 			 * correctly installed the page and returned.
 			 */
-			if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) {
+			if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) {
 				ret = 0;
 				goto out;
 			}
 
-			return hugetlb_handle_userfault(vma, mapping, idx, flags,
-							haddr, address,
+			return hugetlb_handle_userfault(vma, mapping, vmf->pgoff,
+							vmf->flags, vmf->address,
+							vmf->real_address,
 							VM_UFFD_MISSING);
 		}
 
-		folio = alloc_hugetlb_folio(vma, haddr, 0);
+		folio = alloc_hugetlb_folio(vma, vmf->address, 0);
 		if (IS_ERR(folio)) {
 			/*
 			 * Returning error will result in faulting task being

@@ -5930,18 +5928,20 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			 * here.  Before returning error, get ptl and make
 			 * sure there really is no pte entry.
 			 */
-			if (hugetlb_pte_stable(h, mm, ptep, old_pte))
+			if (hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte))
 				ret = vmf_error(PTR_ERR(folio));
 			else
 				ret = 0;
 			goto out;
 		}
-		clear_huge_page(&folio->page, address, pages_per_huge_page(h));
+		clear_huge_page(&folio->page, vmf->real_address,
+				pages_per_huge_page(h));
 		__folio_mark_uptodate(folio);
 		new_folio = true;
 
 		if (vma->vm_flags & VM_MAYSHARE) {
-			int err = hugetlb_add_to_page_cache(folio, mapping, idx);
+			int err = hugetlb_add_to_page_cache(folio, mapping,
+							vmf->pgoff);
 			if (err) {
 				/*
 				 * err can't be -EEXIST which implies someone

@@ -5950,7 +5950,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 				 * to the page cache. So it's safe to call
 				 * restore_reserve_on_error() here.
 				 */
-				restore_reserve_on_error(h, vma, haddr, folio);
+				restore_reserve_on_error(h, vma, vmf->address,
+							folio);
 				folio_put(folio);
 				goto out;
 			}

@@ -5980,12 +5981,13 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			folio_unlock(folio);
 			folio_put(folio);
 			/* See comment in userfaultfd_missing() block above */
-			if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) {
+			if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) {
 				ret = 0;
 				goto out;
 			}
-			return hugetlb_handle_userfault(vma, mapping, idx, flags,
-							haddr, address,
+			return hugetlb_handle_userfault(vma, mapping, vmf->pgoff,
+							vmf->flags, vmf->address,
+							vmf->real_address,
 							VM_UFFD_MINOR);
 		}
 	}

@@ -5996,23 +5998,23 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	 * any allocations necessary to record that reservation occur outside
 	 * the spinlock.
 	 */
-	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
-		if (vma_needs_reservation(h, vma, haddr) < 0) {
+	if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
+		if (vma_needs_reservation(h, vma, vmf->address) < 0) {
 			ret = VM_FAULT_OOM;
 			goto backout_unlocked;
 		}
 		/* Just decrements count, does not deallocate */
-		vma_end_reservation(h, vma, haddr);
+		vma_end_reservation(h, vma, vmf->address);
 	}
 
-	ptl = huge_pte_lock(h, mm, ptep);
+	vmf->ptl = huge_pte_lock(h, mm, vmf->pte);
 	ret = 0;
 	/* If pte changed from under us, retry */
-	if (!pte_same(huge_ptep_get(ptep), old_pte))
+	if (!pte_same(huge_ptep_get(vmf->pte), vmf->orig_pte))
 		goto backout;
 
 	if (anon_rmap)
-		hugepage_add_new_anon_rmap(folio, vma, haddr);
+		hugepage_add_new_anon_rmap(folio, vma, vmf->address);
 	else
 		page_dup_file_rmap(&folio->page, true);
 	new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE)

@@ -6021,17 +6023,18 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	 * If this pte was previously wr-protected, keep it wr-protected even
 	 * if populated.
 	 */
-	if (unlikely(pte_marker_uffd_wp(old_pte)))
+	if (unlikely(pte_marker_uffd_wp(vmf->orig_pte)))
 		new_pte = huge_pte_mkuffd_wp(new_pte);
-	set_huge_pte_at(mm, haddr, ptep, new_pte, huge_page_size(h));
+	set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h));
 
 	hugetlb_count_add(pages_per_huge_page(h), mm);
-	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
+	if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_wp(mm, vma, address, ptep, flags, folio, ptl);
+		ret = hugetlb_wp(mm, vma, vmf->real_address, vmf->pte,
+				vmf->flags, folio, vmf->ptl);
 	}
 
-	spin_unlock(ptl);
+	spin_unlock(vmf->ptl);
 
 	/*
 	 * Only set hugetlb_migratable in newly allocated pages.  Existing pages

@@ -6048,10 +6051,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	return ret;
 
 backout:
-	spin_unlock(ptl);
+	spin_unlock(vmf->ptl);
 backout_unlocked:
 	if (new_folio && !new_pagecache_folio)
-		restore_reserve_on_error(h, vma, haddr, folio);
+		restore_reserve_on_error(h, vma, vmf->address, folio);
 
 	folio_unlock(folio);
 	folio_put(folio);

@@ -6153,8 +6156,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * hugetlb_no_page will drop vma lock and hugetlb fault
 		 * mutex internally, which make us return immediately.
 		 */
-		return hugetlb_no_page(mm, vma, mapping, vmf.pgoff, address,
-				       vmf.pte, vmf.orig_pte, flags);
+		return hugetlb_no_page(mapping, &vmf);
 	}
 
 	ret = 0;

index a9757b11b7c49..271f42eb53ac9 100644
@@ -5563,18 +5563,18 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
  * cannot race with other handlers or page migration.
  * Keep the pte_same checks anyway to make transition from the mutex easier.
  */
-static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
-		       unsigned long address, pte_t *ptep, unsigned int flags,
-		       struct folio *pagecache_folio, spinlock_t *ptl)
+static vm_fault_t hugetlb_wp(struct folio *pagecache_folio,
+		       struct vm_fault *vmf)
 {
-	const bool unshare = flags & FAULT_FLAG_UNSHARE;
-	pte_t pte = huge_ptep_get(ptep);
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
+	pte_t pte = huge_ptep_get(vmf->pte);
 	struct hstate *h = hstate_vma(vma);
 	struct folio *old_folio;
 	struct folio *new_folio;
 	int outside_reserve = 0;
 	vm_fault_t ret = 0;
-	unsigned long haddr = address & huge_page_mask(h);
 	struct mmu_notifier_range range;
 
 	/*

@@ -5597,7 +5597,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Let's take out MAP_SHARED mappings first. */
 	if (vma->vm_flags & VM_MAYSHARE) {
-		set_huge_ptep_writable(vma, haddr, ptep);
+		set_huge_ptep_writable(vma, vmf->address, vmf->pte);
 		return 0;
 	}
 

@@ -5614,7 +5614,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (!PageAnonExclusive(&old_folio->page))
 			page_move_anon_rmap(&old_folio->page, vma);
 		if (likely(!unshare))
-			set_huge_ptep_writable(vma, haddr, ptep);
+			set_huge_ptep_writable(vma, vmf->address, vmf->pte);
 
 		delayacct_wpcopy_end();
 		return 0;

@@ -5641,8 +5641,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * Drop page table lock as buddy allocator may be called. It will
 	 * be acquired again before returning to the caller, as expected.
 	 */
-	spin_unlock(ptl);
-	new_folio = alloc_hugetlb_folio(vma, haddr, outside_reserve);
+	spin_unlock(vmf->ptl);
+	new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve);
 
 	if (IS_ERR(new_folio)) {
 		/*

@@ -5667,19 +5667,21 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 			 *
 			 * Reacquire both after unmap operation.
 			 */
-			idx = vma_hugecache_offset(h, vma, haddr);
+			idx = vma_hugecache_offset(h, vma, vmf->address);
 			hash = hugetlb_fault_mutex_hash(mapping, idx);
 			hugetlb_vma_unlock_read(vma);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
-			unmap_ref_private(mm, vma, &old_folio->page, haddr);
+			unmap_ref_private(mm, vma, &old_folio->page,
+					vmf->address);
 
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			hugetlb_vma_lock_read(vma);
-			spin_lock(ptl);
-			ptep = hugetlb_walk(vma, haddr, huge_page_size(h));
-			if (likely(ptep &&
-				   pte_same(huge_ptep_get(ptep), pte)))
+			spin_lock(vmf->ptl);
+			vmf->pte = hugetlb_walk(vma, vmf->address,
+					huge_page_size(h));
+			if (likely(vmf->pte &&
+				   pte_same(huge_ptep_get(vmf->pte), pte)))
 				goto retry_avoidcopy;
 			/*
 			 * race occurs while re-acquiring page table

@@ -5702,37 +5704,38 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_release_all;
 	}
 
-	if (copy_user_large_folio(new_folio, old_folio, address, vma)) {
+	if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) {
 		ret = VM_FAULT_HWPOISON_LARGE;
 		goto out_release_all;
 	}
 	__folio_mark_uptodate(new_folio);
 
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr,
-				haddr + huge_page_size(h));
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address,
+				vmf->address + huge_page_size(h));
 	mmu_notifier_invalidate_range_start(&range);
 
 	/*
 	 * Retake the page table lock to check for racing updates
 	 * before the page tables are altered
 	 */
-	spin_lock(ptl);
-	ptep = hugetlb_walk(vma, haddr, huge_page_size(h));
-	if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
+	spin_lock(vmf->ptl);
+	vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h));
+	if (likely(vmf->pte && pte_same(huge_ptep_get(vmf->pte), pte))) {
 		pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare);
 
 		/* Break COW or unshare */
-		huge_ptep_clear_flush(vma, haddr, ptep);
+		huge_ptep_clear_flush(vma, vmf->address, vmf->pte);
 		page_remove_rmap(&old_folio->page, vma, true);
-		hugepage_add_new_anon_rmap(new_folio, vma, haddr);
+		hugepage_add_new_anon_rmap(new_folio, vma, vmf->address);
 		if (huge_pte_uffd_wp(pte))
 			newpte = huge_pte_mkuffd_wp(newpte);
-		set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h));
+		set_huge_pte_at(mm, vmf->address, vmf->pte, newpte,
+				huge_page_size(h));
 		folio_set_hugetlb_migratable(new_folio);
 		/* Make the old page be freed below */
 		new_folio = old_folio;
 	}
-	spin_unlock(ptl);
+	spin_unlock(vmf->ptl);
 	mmu_notifier_invalidate_range_end(&range);
 out_release_all:
 	/*

@@ -5740,12 +5743,12 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * unshare)
 	 */
 	if (new_folio != old_folio)
-		restore_reserve_on_error(h, vma, haddr, new_folio);
+		restore_reserve_on_error(h, vma, vmf->address, new_folio);
 	folio_put(new_folio);
 out_release_old:
 	folio_put(old_folio);
 
-	spin_lock(ptl); /* Caller expects lock to be held */
+	spin_lock(vmf->ptl); /* Caller expects lock to be held */
 
 	delayacct_wpcopy_end();
 	return ret;

@@ -6030,8 +6033,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
 	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_wp(mm, vma, vmf->real_address, vmf->pte,
-				vmf->flags, folio, vmf->ptl);
+		ret = hugetlb_wp(folio, vmf);
 	}
 
 	spin_unlock(vmf->ptl);

@@ -6242,8 +6244,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
 		if (!huge_pte_write(vmf.orig_pte)) {
-			ret = hugetlb_wp(mm, vma, address, vmf.pte, flags,
-					 pagecache_folio, vmf.ptl);
+			ret = hugetlb_wp(pagecache_folio, &vmf);
 			goto out_put_page;
 		} else if (likely(flags & FAULT_FLAG_WRITE)) {
 			vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte);

index d0896bf8e12f0..1a9c1c9e53e4e 100644
@@ -723,19 +723,20 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 {
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = walk->vma;
-	struct page *page = NULL;
-	pte_t ptent = ptep_get(pte);
+	pte_t ptent = huge_ptep_get(pte);
+	struct folio *folio = NULL;
 
 	if (pte_present(ptent)) {
-		page = vm_normal_page(vma, addr, ptent);
+		folio = page_folio(pte_page(ptent));
 	} else if (is_swap_pte(ptent)) {
 		swp_entry_t swpent = pte_to_swp_entry(ptent);
 
 		if (is_pfn_swap_entry(swpent))
-			page = pfn_swap_entry_to_page(swpent);
+			folio = pfn_swap_entry_folio(swpent);
 	}
-	if (page) {
-		if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte))
+	if (folio) {
+		if (folio_likely_mapped_shared(folio) ||
+		    hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else
 			mss->private_hugetlb += huge_page_size(hstate_vma(vma));

index a30be55057939..87d48e2d90ad9 100644
@@ -13,12 +13,12 @@
 
 /*
  * If our huge pte is non-zero then mark the valid bit.
- * This allows pte_present(huge_ptep_get(ptep)) to return true for non-zero
+ * This allows pte_present(huge_ptep_get(mm,addr,ptep)) to return true for non-zero
  * ptes.
  * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
  */
 #define __HAVE_ARCH_HUGE_PTEP_GET
-static inline pte_t huge_ptep_get(pte_t *ptep)
+static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	pte_t retval = *ptep;
 	if (pte_val(retval))

index 92a5e0879b111..5d278bf511fa4 100644
@@ -46,7 +46,7 @@ extern pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_GET
-extern pte_t huge_ptep_get(pte_t *ptep);
+extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
 void __init arm64_hugetlb_cma_reserve(void);
 

index 688d11b1cabdb..b2ca8fa5af44c 100644
@@ -141,7 +141,7 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 	return contig_ptes;
 }
 
-pte_t huge_ptep_get(pte_t *ptep)
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	int ncontig, i;
 	size_t pgsize;

index 0e809026b6e39..7107d1eaeb24b 100644
@@ -45,7 +45,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       pte_t pte, int dirty);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET
-pte_t huge_ptep_get(pte_t *ptep);
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
 pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
 #define arch_make_huge_pte arch_make_huge_pte

index 57afbc3270a3c..8a059b15d760a 100644
@@ -3,7 +3,7 @@
 #include <linux/err.h>
 
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
-pte_t huge_ptep_get(pte_t *ptep)
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	unsigned long pte_num;
 	int i;

index 097b388d4e690..87ead138973d8 100644
@@ -19,7 +19,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte, unsigned long sz);
 void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
-pte_t huge_ptep_get(pte_t *ptep);
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep);
 

@@ -71,7 +71,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
 {
-	int changed = !pte_same(huge_ptep_get(ptep), pte);
+	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 	if (changed) {
 		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);

index 5ebd730f1ffbb..eef46fd9eaaff 100644
@@ -169,7 +169,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	__set_huge_pte_at(mm, addr, ptep, pte);
 }
 
-pte_t huge_ptep_get(pte_t *ptep)
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	return __rste_to_pte(pte_val(*ptep));
 }

@@ -177,7 +177,7 @@ pte_t huge_ptep_get(pte_t *ptep)
 pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get(ptep);
+	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
 	pud_t *pudp = (pud_t *) ptep;
 

index 914e850b9cbb7..7fd8dccca8189 100644
@@ -448,7 +448,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
 	if (!ptep)
 		return false;
 
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, addr, ptep);
 	if (huge_pte_none(pte) || !pte_present(pte))
 		return false;
 

index 1a9c1c9e53e4e..a245ee038ed55 100644
@@ -723,7 +723,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 {
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = walk->vma;
-	pte_t ptent = huge_ptep_get(pte);
+	pte_t ptent = huge_ptep_get(walk->mm, addr, pte);
 	struct folio *folio = NULL;
 
 	if (pte_present(ptent)) {

@@ -732,10 +732,10 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 		swp_entry_t swpent = pte_to_swp_entry(ptent);
 
 		if (is_pfn_swap_entry(swpent))
-			folio = pfn_swap_entry_folio(swpent);
+			folio = page_folio(pfn_swap_entry_to_page(swpent));
 	}
 	if (folio) {
-		if (folio_likely_mapped_shared(folio) ||
+		if (folio_mapcount(folio) >= 2 ||
 		    hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else

@@ -1579,7 +1579,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
 	if (vma->vm_flags & VM_SOFTDIRTY)
 		flags |= PM_SOFT_DIRTY;
 
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(walk->mm, addr, ptep);
 	if (pte_present(pte)) {
 		struct page *page = pte_page(pte);
 

@@ -1911,7 +1911,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
-	pte_t huge_pte = huge_ptep_get(pte);
+	pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte);
 	struct numa_maps *md;
 	struct page *page;
 

index 0ebdf3c2c9ee6..4349afd3c742c 100644
@@ -291,7 +291,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	ret = false;
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep);
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it

index 2d7ae9b51d1e3..215bf9f317cbf 100644
@@ -144,7 +144,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 #endif
 
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET
-static inline pte_t huge_ptep_get(pte_t *ptep)
+static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	return ptep_get(ptep);
 }

index 7555a4a3d3d49..229e409ac2f69 100644
@@ -334,7 +334,7 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry)
 
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
-extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte);
+extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte);
 #else  /* CONFIG_MIGRATION */
 static inline swp_entry_t make_readable_migration_entry(pgoff_t offset)
 {

@@ -359,7 +359,7 @@ static inline int is_migration_entry(swp_entry_t swp)
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address) { }
 static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
-					pte_t *pte) { }
+					     unsigned long addr, pte_t *pte) { }
 static inline int is_writable_migration_entry(swp_entry_t entry)
 {
 	return 0;

index 4d7dc9f65f682..01319e28f2054 100644
@@ -339,7 +339,7 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm,
 				struct vm_area_struct *vma, unsigned long addr)
 {
 	bool referenced = false;
-	pte_t entry = huge_ptep_get(pte);
+	pte_t entry = huge_ptep_get(mm, addr, pte);
 	struct folio *folio = pfn_folio(pte_pfn(entry));
 	unsigned long psize = huge_page_size(hstate_vma(vma));
 

@@ -373,7 +373,7 @@ static int damon_mkold_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	pte_t entry;
 
 	ptl = huge_pte_lock(h, walk->mm, pte);
-	entry = huge_ptep_get(pte);
+	entry = huge_ptep_get(walk->mm, addr, pte);
 	if (!pte_present(entry))
 		goto out;
 

@@ -507,7 +507,7 @@ static int damon_young_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	pte_t entry;
 
 	ptl = huge_pte_lock(h, walk->mm, pte);
-	entry = huge_ptep_get(pte);
+	entry = huge_ptep_get(walk->mm, addr, pte);
 	if (!pte_present(entry))
 		goto out;
 

index 60006de1219ee..dbb051eac6021 100644
@@ -2812,7 +2812,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	if (pte_end < end)
 		end = pte_end;
 
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(current->mm, addr, ptep);
 
 	if (!pte_access_permitted(pte, flags & FOLL_WRITE))
 		return 0;

index a36e1b4046dbd..575fb7b6db7f0 100644
@@ -485,7 +485,7 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	pte_t entry;
 
 	ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
-	entry = huge_ptep_get(pte);
+	entry = huge_ptep_get(walk->mm, addr, pte);
 
 	i = (start - range->start) >> PAGE_SHIFT;
 	pfn_req_flags = range->hmm_pfns[i];

181 lines not on this page · raw message

index 86cdf36ee3bb9..2dca9b862ca39 100644
@@ -825,7 +825,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
 			    struct mm_walk *walk)
 {
 	struct hwpoison_walk *hwp = walk->private;
-	pte_t pte = huge_ptep_get(ptep);
+	pte_t pte = huge_ptep_get(walk->mm, addr, ptep);
 	struct hstate *h = hstate_vma(walk->vma);
 
 	return check_hwpoisoned_entry(pte, addr, huge_page_shift(h),

index 5bbeb6df9c007..1be46783d9d4b 100644
@@ -584,7 +584,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
 	pte_t entry;
 
 	ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
-	entry = huge_ptep_get(pte);
+	entry = huge_ptep_get(walk->mm, addr, pte);
 	if (!pte_present(entry)) {
 		if (unlikely(is_hugetlb_entry_migration(entry)))
 			qp->nr_failed++;

index 620871d193c7c..5fbec4834a138 100644
@@ -335,14 +335,14 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
  *
  * This function will release the vma lock before returning.
  */
-void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *ptep)
+void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, ptep);
 	pte_t pte;
 
 	hugetlb_vma_assert_locked(vma);
 	spin_lock(ptl);
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, addr, ptep);
 
 	if (unlikely(!is_hugetlb_entry_migration(pte))) {
 		spin_unlock(ptl);

index 2a55eed792b64..03b42e8dfd642 100644
@@ -33,7 +33,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
 	 * Hugepages under user process are always in RAM and never
 	 * swapped out, but theoretically it needs to be checked.
 	 */
-	present = pte && !huge_pte_none_mostly(huge_ptep_get(pte));
+	present = pte && !huge_pte_none_mostly(huge_ptep_get(walk->mm, addr, pte));
 	for (; addr != end; vec++, addr += PAGE_SIZE)
 		*vec = present;
 	walk->private = vec;

index 99438f0950e3c..ed76ad3ab4fd0 100644
@@ -482,7 +482,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
 		}
 
 		if (!uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE) &&
-		    !huge_pte_none_mostly(huge_ptep_get(dst_pte))) {
+		    !huge_pte_none_mostly(huge_ptep_get(dst_mm, dst_addr, dst_pte))) {
 			err = -EEXIST;
 			hugetlb_vma_unlock_read(dst_vma);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);

index dcc1ee3d059e9..23c098a35c234 100644
@@ -97,7 +97,13 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp)
 static bool check_pte(struct page_vma_mapped_walk *pvmw, unsigned long pte_nr)
 {
 	unsigned long pfn;
-	pte_t ptent = ptep_get(pvmw->pte);
+	pte_t ptent;
+
+	if (is_vm_hugetlb_page(pvmw->vma))
+		ptent = huge_ptep_get(pvmw->vma->vm_mm, pvmw->address,
+				      pvmw->pte);
+	else
+		ptent = ptep_get(pvmw->pte);
 
 	if (pvmw->flags & PVMW_MIGRATION) {
 		swp_entry_t entry;