1 files changed, 417 insertions, 106 deletions
diff --git a/mm/memory.c b/mm/memory.c
index fb7b8dc75167..2d8c265fc7d6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -94,14 +94,6 @@
 #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
 #endif
 
-#ifndef CONFIG_NUMA
-unsigned long max_mapnr;
-EXPORT_SYMBOL(max_mapnr);
-
-struct page *mem_map;
-EXPORT_SYMBOL(mem_map);
-#endif
-
 static vm_fault_t do_fault(struct vm_fault *vmf);
 static vm_fault_t do_anonymous_page(struct vm_fault *vmf);
 static bool vmf_pte_changed(struct vm_fault *vmf);
@@ -121,14 +113,6 @@ static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf)
 }
 
 /*
- * A number of key systems in x86 including ioremap() rely on the assumption
- * that high_memory defines the upper bound on direct map memory, then end
- * of ZONE_NORMAL.
- */
-void *high_memory;
-EXPORT_SYMBOL(high_memory);
-
-/*
  * Randomize the address space (stacks, mmaps, brk, etc.).
  *
  * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization,
@@ -715,42 +699,53 @@ struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma,
 }
 #endif
 
+/**
+ * restore_exclusive_pte - Restore a device-exclusive entry
+ * @vma: VMA covering @address
+ * @folio: the mapped folio
+ * @page: the mapped folio page
+ * @address: the virtual address
+ * @ptep: pte pointer into the locked page table mapping the folio page
+ * @orig_pte: pte value at @ptep
+ *
+ * Restore a device-exclusive non-swap entry to an ordinary present pte.
+ *
+ * The folio and the page table must be locked, and MMU notifiers must have
+ * been called to invalidate any (exclusive) device mappings.
+ *
+ * Locking the folio makes sure that anybody who just converted the pte to
+ * a device-exclusive entry can map it into the device to make forward
+ * progress without others converting it back until the folio was unlocked.
+ *
+ * If the folio lock ever becomes an issue, we can stop relying on the folio
+ * lock; it might make some scenarios with heavy thrashing less likely to
+ * make forward progress, but these scenarios might not be valid use cases.
+ *
+ * Note that the folio lock does not protect against all cases of concurrent
+ * page table modifications (e.g., MADV_DONTNEED, mprotect), so device drivers
+ * must use MMU notifiers to sync against any concurrent changes.
+ */
 static void restore_exclusive_pte(struct vm_area_struct *vma,
-				  struct page *page, unsigned long address,
-				  pte_t *ptep)
+		struct folio *folio, struct page *page, unsigned long address,
+		pte_t *ptep, pte_t orig_pte)
 {
-	struct folio *folio = page_folio(page);
-	pte_t orig_pte;
 	pte_t pte;
-	swp_entry_t entry;
 
-	orig_pte = ptep_get(ptep);
+	VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
+
 	pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot)));
 	if (pte_swp_soft_dirty(orig_pte))
 		pte = pte_mksoft_dirty(pte);
 
-	entry = pte_to_swp_entry(orig_pte);
 	if (pte_swp_uffd_wp(orig_pte))
 		pte = pte_mkuffd_wp(pte);
-	else if (is_writable_device_exclusive_entry(entry))
-		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
-
-	VM_BUG_ON_FOLIO(pte_write(pte) && (!folio_test_anon(folio) &&
-					   PageAnonExclusive(page)), folio);
-
-	/*
-	 * No need to take a page reference as one was already
-	 * created when the swap entry was made.
-	 */
-	if (folio_test_anon(folio))
-		folio_add_anon_rmap_pte(folio, page, vma, address, RMAP_NONE);
-	else
-		/*
-		 * Currently device exclusive access only supports anonymous
-		 * memory so the entry shouldn't point to a filebacked page.
-		 */
-		WARN_ON_ONCE(1);
 
+	if ((vma->vm_flags & VM_WRITE) &&
+	    can_change_pte_writable(vma, address, pte)) {
+		if (folio_test_dirty(folio))
+			pte = pte_mkdirty(pte);
+		pte = pte_mkwrite(pte, vma);
+	}
 	set_pte_at(vma->vm_mm, address, ptep, pte);
 
 	/*
@@ -764,16 +759,15 @@ static void restore_exclusive_pte(struct vm_area_struct *vma,
  * Tries to restore an exclusive pte if the page lock can be acquired without
  * sleeping.
  */
-static int
-try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma,
-			unsigned long addr)
+static int try_restore_exclusive_pte(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep, pte_t orig_pte)
 {
-	swp_entry_t entry = pte_to_swp_entry(ptep_get(src_pte));
-	struct page *page = pfn_swap_entry_to_page(entry);
+	struct page *page = pfn_swap_entry_to_page(pte_to_swp_entry(orig_pte));
+	struct folio *folio = page_folio(page);
 
-	if (trylock_page(page)) {
-		restore_exclusive_pte(vma, page, addr, src_pte);
-		unlock_page(page);
+	if (folio_trylock(folio)) {
+		restore_exclusive_pte(vma, folio, page, addr, ptep, orig_pte);
+		folio_unlock(folio);
 		return 0;
 	}
 
@@ -853,7 +847,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		folio_get(folio);
 		rss[mm_counter(folio)]++;
 		/* Cannot fail as these pages cannot get pinned. */
-		folio_try_dup_anon_rmap_pte(folio, page, src_vma);
+		folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma);
 
 		/*
 		 * We do not preserve soft-dirty information, because so
@@ -879,7 +873,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * (ie. COW) mappings.
 		 */
 		VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags));
-		if (try_restore_exclusive_pte(src_pte, src_vma, addr))
+		if (try_restore_exclusive_pte(src_vma, addr, src_pte, orig_pte))
 			return -EBUSY;
 		return -ENOENT;
 	} else if (is_pte_marker_entry(entry)) {
@@ -1007,14 +1001,14 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		folio_ref_add(folio, nr);
 		if (folio_test_anon(folio)) {
 			if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
-								  nr, src_vma))) {
+								  nr, dst_vma, src_vma))) {
 				folio_ref_sub(folio, nr);
 				return -EAGAIN;
 			}
 			rss[MM_ANONPAGES] += nr;
 			VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
 		} else {
-			folio_dup_file_rmap_ptes(folio, page, nr);
+			folio_dup_file_rmap_ptes(folio, page, nr, dst_vma);
 			rss[mm_counter_file(folio)] += nr;
 		}
 		if (any_writable)
@@ -1032,7 +1026,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		 * guarantee the pinned page won't be randomly replaced in the
 		 * future.
 		 */
-		if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) {
+		if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma))) {
 			/* Page may be pinned, we have to copy. */
 			folio_put(folio);
 			err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
@@ -1042,7 +1036,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		rss[MM_ANONPAGES]++;
 		VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
 	} else {
-		folio_dup_file_rmap_pte(folio, page);
+		folio_dup_file_rmap_pte(folio, page, dst_vma);
 		rss[mm_counter_file(folio)]++;
 	}
 
@@ -1362,12 +1356,12 @@ int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	pgd_t *src_pgd, *dst_pgd;
-	unsigned long next;
 	unsigned long addr = src_vma->vm_start;
 	unsigned long end = src_vma->vm_end;
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
 	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct mmu_notifier_range range;
+	unsigned long next, pfn;
 	bool is_cow;
 	int ret;
 
@@ -1378,11 +1372,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma);
 
 	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
-		/*
-		 * We do not free on error cases below as remove_vma
-		 * gets called on error from higher level routine
-		 */
-		ret = track_pfn_copy(src_vma);
+		ret = track_pfn_copy(dst_vma, src_vma, &pfn);
 		if (ret)
 			return ret;
 	}
@@ -1419,7 +1409,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 			continue;
 		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
 					    addr, next))) {
-			untrack_pfn_clear(dst_vma);
 			ret = -ENOMEM;
 			break;
 		}
@@ -1429,6 +1418,8 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		raw_write_seqcount_end(&src_mm->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
 	}
+	if (ret && unlikely(src_vma->vm_flags & VM_PFNMAP))
+		untrack_pfn_copy(dst_vma, pfn);
 	return ret;
 }
 
@@ -1622,8 +1613,7 @@ static inline int zap_nonpresent_ptes(struct mmu_gather *tlb,
 		 */
 		WARN_ON_ONCE(!vma_is_anonymous(vma));
 		rss[mm_counter(folio)]--;
-		if (is_device_private_entry(entry))
-			folio_remove_rmap_pte(folio, page, vma);
+		folio_remove_rmap_pte(folio, page, vma);
 		folio_put(folio);
 	} else if (!non_swap_entry(entry)) {
 		/* Genuine swap entries, hence a private anon pages */
@@ -2135,19 +2125,39 @@ static int validate_page_before_insert(struct vm_area_struct *vma,
 }
 
 static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
-			unsigned long addr, struct page *page, pgprot_t prot)
+				unsigned long addr, struct page *page,
+				pgprot_t prot, bool mkwrite)
 {
 	struct folio *folio = page_folio(page);
-	pte_t pteval;
+	pte_t pteval = ptep_get(pte);
+
+	if (!pte_none(pteval)) {
+		if (!mkwrite)
+			return -EBUSY;
+
+		/* see insert_pfn(). */
+		if (pte_pfn(pteval) != page_to_pfn(page)) {
+			WARN_ON_ONCE(!is_zero_pfn(pte_pfn(pteval)));
+			return -EFAULT;
+		}
+		pteval = maybe_mkwrite(pteval, vma);
+		pteval = pte_mkyoung(pteval);
+		if (ptep_set_access_flags(vma, addr, pte, pteval, 1))
+			update_mmu_cache(vma, addr, pte);
+		return 0;
+	}
 
-	if (!pte_none(ptep_get(pte)))
-		return -EBUSY;
 	/* Ok, finally just insert the thing.. */
 	pteval = mk_pte(page, prot);
 	if (unlikely(is_zero_folio(folio))) {
 		pteval = pte_mkspecial(pteval);
 	} else {
 		folio_get(folio);
+		pteval = mk_pte(page, prot);
+		if (mkwrite) {
+			pteval = pte_mkyoung(pteval);
+			pteval = maybe_mkwrite(pte_mkdirty(pteval), vma);
+		}
 		inc_mm_counter(vma->vm_mm, mm_counter_file(folio));
 		folio_add_file_rmap_pte(folio, page, vma);
 	}
@@ -2156,7 +2166,7 @@ static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte,
 }
 
 static int insert_page(struct vm_area_struct *vma, unsigned long addr,
-			struct page *page, pgprot_t prot)
+			struct page *page, pgprot_t prot, bool mkwrite)
 {
 	int retval;
 	pte_t *pte;
@@ -2169,7 +2179,8 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 	pte = get_locked_pte(vma->vm_mm, addr, &ptl);
 	if (!pte)
 		goto out;
-	retval = insert_page_into_pte_locked(vma, pte, addr, page, prot);
+	retval = insert_page_into_pte_locked(vma, pte, addr, page, prot,
+					mkwrite);
 	pte_unmap_unlock(pte, ptl);
 out:
 	return retval;
@@ -2183,7 +2194,7 @@ static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte,
 	err = validate_page_before_insert(vma, page);
 	if (err)
 		return err;
-	return insert_page_into_pte_locked(vma, pte, addr, page, prot);
+	return insert_page_into_pte_locked(vma, pte, addr, page, prot, false);
 }
 
 /* insert_pages() amortizes the cost of spinlock operations
@@ -2319,7 +2330,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 		BUG_ON(vma->vm_flags & VM_PFNMAP);
 		vm_flags_set(vma, VM_MIXEDMAP);
 	}
-	return insert_page(vma, addr, page, vma->vm_page_prot);
+	return insert_page(vma, addr, page, vma->vm_page_prot, false);
 }
 EXPORT_SYMBOL(vm_insert_page);
 
@@ -2599,7 +2610,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 		 * result in pfn_t_has_page() == false.
 		 */
 		page = pfn_to_page(pfn_t_to_pfn(pfn));
-		err = insert_page(vma, addr, page, pgprot);
+		err = insert_page(vma, addr, page, pgprot, mkwrite);
 	} else {
 		return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
 	}
@@ -2612,6 +2623,26 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
+vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
+			bool write)
+{
+	pgprot_t pgprot = vmf->vma->vm_page_prot;
+	unsigned long addr = vmf->address;
+	int err;
+
+	if (addr < vmf->vma->vm_start || addr >= vmf->vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	err = insert_page(vmf->vma, addr, page, pgprot, write);
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+EXPORT_SYMBOL_GPL(vmf_insert_page_mkwrite);
+
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 		pfn_t pfn)
 {
@@ -3676,19 +3707,86 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio)
 	return ret;
 }
 
-static bool wp_can_reuse_anon_folio(struct folio *folio,
-				    struct vm_area_struct *vma)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
+		struct vm_area_struct *vma)
 {
+	bool exclusive = false;
+
+	/* Let's just free up a large folio if only a single page is mapped. */
+	if (folio_large_mapcount(folio) <= 1)
+		return false;
+
 	/*
-	 * We could currently only reuse a subpage of a large folio if no
-	 * other subpages of the large folios are still mapped. However,
-	 * let's just consistently not reuse subpages even if we could
-	 * reuse in that scenario, and give back a large folio a bit
-	 * sooner.
+	 * The assumption for anonymous folios is that each page can only get
+	 * mapped once into each MM. The only exception are KSM folios, which
+	 * are always small.
+	 *
+	 * Each taken mapcount must be paired with exactly one taken reference,
+	 * whereby the refcount must be incremented before the mapcount when
+	 * mapping a page, and the refcount must be decremented after the
+	 * mapcount when unmapping a page.
+	 *
+	 * If all folio references are from mappings, and all mappings are in
+	 * the page tables of this MM, then this folio is exclusive to this MM.
 	 */
-	if (folio_test_large(folio))
+	if (folio_test_large_maybe_mapped_shared(folio))
+		return false;
+
+	VM_WARN_ON_ONCE(folio_test_ksm(folio));
+	VM_WARN_ON_ONCE(folio_mapcount(folio) > folio_nr_pages(folio));
+	VM_WARN_ON_ONCE(folio_entire_mapcount(folio));
+
+	if (unlikely(folio_test_swapcache(folio))) {
+		/*
+		 * Note: freeing up the swapcache will fail if some PTEs are
+		 * still swap entries.
+		 */
+		if (!folio_trylock(folio))
+			return false;
+		folio_free_swap(folio);
+		folio_unlock(folio);
+	}
+
+	if (folio_large_mapcount(folio) != folio_ref_count(folio))
 		return false;
 
+	/* Stabilize the mapcount vs. refcount and recheck. */
+	folio_lock_large_mapcount(folio);
+	VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+
+	if (folio_test_large_maybe_mapped_shared(folio))
+		goto unlock;
+	if (folio_large_mapcount(folio) != folio_ref_count(folio))
+		goto unlock;
+
+	VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id &&
+			folio_mm_id(folio, 1) != vma->vm_mm->mm_id);
+
+	/*
+	 * Do we need the folio lock? Likely not. If there would have been
+	 * references from page migration/swapout, we would have detected
+	 * an additional folio reference and never ended up here.
+	 */
+	exclusive = true;
+unlock:
+	folio_unlock_large_mapcount(folio);
+	return exclusive;
+}
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
+		struct vm_area_struct *vma)
+{
+	BUILD_BUG();
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static bool wp_can_reuse_anon_folio(struct folio *folio,
+				    struct vm_area_struct *vma)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && folio_test_large(folio))
+		return __wp_can_reuse_large_anon_folio(folio, vma);
+
 	/*
 	 * We have to verify under folio lock: these early checks are
 	 * just an optimization to avoid locking the folio and freeing
@@ -3797,13 +3895,15 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
 		/*
 		 * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
-		 * VM_PFNMAP VMA.
+		 * VM_PFNMAP VMA. FS DAX also wants ops->pfn_mkwrite called.
 		 *
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable and/or call ops->pfn_mkwrite.
 		 */
-		if (!vmf->page)
+		if (!vmf->page || is_fsdax_page(vmf->page)) {
+			vmf->page = NULL;
 			return wp_pfn_shared(vmf);
+		}
 		return wp_page_shared(vmf, folio);
 	}
 
@@ -3993,7 +4093,7 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
 		folio_put(folio);
 		return ret;
 	}
-	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0,
+	mmu_notifier_range_init_owner(&range, MMU_NOTIFY_CLEAR, 0,
 				vma->vm_mm, vmf->address & PAGE_MASK,
 				(vmf->address & PAGE_MASK) + PAGE_SIZE, NULL);
 	mmu_notifier_invalidate_range_start(&range);
@@ -4001,7 +4101,8 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf)
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 				&vmf->ptl);
 	if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte)))
-		restore_exclusive_pte(vma, vmf->page, vmf->address, vmf->pte);
+		restore_exclusive_pte(vma, folio, vmf->page, vmf->address,
+				      vmf->pte, vmf->orig_pte);
 
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -4349,10 +4450,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 			 * Get a page reference while we know the page can't be
 			 * freed.
 			 */
-			get_page(vmf->page);
-			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			ret = vmf->page->pgmap->ops->migrate_to_ram(vmf);
-			put_page(vmf->page);
+			if (trylock_page(vmf->page)) {
+				struct dev_pagemap *pgmap;
+
+				get_page(vmf->page);
+				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				pgmap = page_pgmap(vmf->page);
+				ret = pgmap->ops->migrate_to_ram(vmf);
+				unlock_page(vmf->page);
+				put_page(vmf->page);
+			} else {
+				pte_unmap_unlock(vmf->pte, vmf->ptl);
+			}
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
 		} else if (is_pte_marker_entry(entry)) {
@@ -4406,7 +4515,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 				}
 				need_clear_cache = true;
 
-				mem_cgroup_swapin_uncharge_swap(entry, nr_pages);
+				memcg1_swapin(entry, nr_pages);
 
 				shadow = get_shadow_from_swap_cache(entry);
 				if (shadow)
@@ -5575,7 +5684,7 @@ int numa_migrate_check(struct folio *folio, struct vm_fault *vmf,
 	 * Flag if the folio is shared between multiple address spaces. This
 	 * is later used when determining whether to group tasks together
 	 */
-	if (folio_likely_mapped_shared(folio) && (vma->vm_flags & VM_SHARED))
+	if (folio_maybe_mapped_shared(folio) && (vma->vm_flags & VM_SHARED))
 		*flags |= TNF_SHARED;
 	/*
 	 * For memory tiering mode, cpupid of slow memory page is used
@@ -6346,6 +6455,88 @@ fail:
 #endif
 
 #ifdef CONFIG_PER_VMA_LOCK
+static inline bool __vma_enter_locked(struct vm_area_struct *vma, bool detaching)
+{
+	unsigned int tgt_refcnt = VMA_LOCK_OFFSET;
+
+	/* Additional refcnt if the vma is attached. */
+	if (!detaching)
+		tgt_refcnt++;
+
+	/*
+	 * If vma is detached then only vma_mark_attached() can raise the
+	 * vm_refcnt. mmap_write_lock prevents racing with vma_mark_attached().
+	 */
+	if (!refcount_add_not_zero(VMA_LOCK_OFFSET, &vma->vm_refcnt))
+		return false;
+
+	rwsem_acquire(&vma->vmlock_dep_map, 0, 0, _RET_IP_);
+	rcuwait_wait_event(&vma->vm_mm->vma_writer_wait,
+		   refcount_read(&vma->vm_refcnt) == tgt_refcnt,
+		   TASK_UNINTERRUPTIBLE);
+	lock_acquired(&vma->vmlock_dep_map, _RET_IP_);
+
+	return true;
+}
+
+static inline void __vma_exit_locked(struct vm_area_struct *vma, bool *detached)
+{
+	*detached = refcount_sub_and_test(VMA_LOCK_OFFSET, &vma->vm_refcnt);
+	rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
+}
+
+void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq)
+{
+	bool locked;
+
+	/*
+	 * __vma_enter_locked() returns false immediately if the vma is not
+	 * attached, otherwise it waits until refcnt is indicating that vma
+	 * is attached with no readers.
+	 */
+	locked = __vma_enter_locked(vma, false);
+
+	/*
+	 * We should use WRITE_ONCE() here because we can have concurrent reads
+	 * from the early lockless pessimistic check in vma_start_read().
+	 * We don't really care about the correctness of that early check, but
+	 * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
+	 */
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
+
+	if (locked) {
+		bool detached;
+
+		__vma_exit_locked(vma, &detached);
+		WARN_ON_ONCE(detached); /* vma should remain attached */
+	}
+}
+EXPORT_SYMBOL_GPL(__vma_start_write);
+
+void vma_mark_detached(struct vm_area_struct *vma)
+{
+	vma_assert_write_locked(vma);
+	vma_assert_attached(vma);
+
+	/*
+	 * We are the only writer, so no need to use vma_refcount_put().
+	 * The condition below is unlikely because the vma has been already
+	 * write-locked and readers can increment vm_refcnt only temporarily
+	 * before they check vm_lock_seq, realize the vma is locked and drop
+	 * back the vm_refcnt. That is a narrow window for observing a raised
+	 * vm_refcnt.
+	 */
+	if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) {
+		/* Wait until vma is detached with no readers. */
+		if (__vma_enter_locked(vma, true)) {
+			bool detached;
+
+			__vma_exit_locked(vma, &detached);
+			WARN_ON_ONCE(!detached);
+		}
+	}
+}
+
 /*
  * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be
  * stable and not isolated. If the VMA is not found or is being modified the
@@ -6363,15 +6554,17 @@ retry:
 	if (!vma)
 		goto inval;
 
-	if (!vma_start_read(vma))
-		goto inval;
+	vma = vma_start_read(mm, vma);
+	if (IS_ERR_OR_NULL(vma)) {
+		/* Check if the VMA got isolated after we found it */
+		if (PTR_ERR(vma) == -EAGAIN) {
+			count_vm_vma_lock_event(VMA_LOCK_MISS);
+			/* The area was replaced with another one */
+			goto retry;
+		}
 
-	/* Check if the VMA got isolated after we found it */
-	if (vma->detached) {
-		vma_end_read(vma);
-		count_vm_vma_lock_event(VMA_LOCK_MISS);
-		/* The area was replaced with another one */
-		goto retry;
+		/* Failed to lock the VMA */
+		goto inval;
 	}
 	/*
 	 * At this point, we have a stable reference to a VMA: The VMA is
@@ -6380,8 +6573,9 @@ retry:
 	 * fields are accessible for RCU readers.
 	 */
 
-	/* Check since vm_start/vm_end might change before we lock the VMA */
-	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
+	/* Check if the vma we locked is the right one. */
+	if (unlikely(vma->vm_mm != mm ||
+		     address < vma->vm_start || address >= vma->vm_end))
 		goto inval_end_read;
 
 	rcu_read_unlock();
@@ -6476,6 +6670,7 @@ static inline void pfnmap_args_setup(struct follow_pfnmap_args *args,
 	args->lock = lock;
 	args->ptep = ptep;
 	args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT);
+	args->addr_mask = addr_mask;
 	args->pgprot = pgprot;
 	args->writable = writable;
 	args->special = special;
@@ -6635,7 +6830,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 			void *buf, int len, int write)
 {
 	resource_size_t phys_addr;
-	unsigned long prot = 0;
+	pgprot_t prot = __pgprot(0);
 	void __iomem *maddr;
 	int offset = offset_in_page(addr);
 	int ret = -EINVAL;
@@ -6645,7 +6840,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 retry:
 	if (follow_pfnmap_start(&args))
 		return -EINVAL;
-	prot = pgprot_val(args.pgprot);
+	prot = args.pgprot;
 	phys_addr = (resource_size_t)args.pfn << PAGE_SHIFT;
 	writable = args.writable;
 	follow_pfnmap_end(&args);
@@ -6660,7 +6855,7 @@ retry:
 	if (follow_pfnmap_start(&args))
 		goto out_unmap;
 
-	if ((prot != pgprot_val(args.pgprot)) ||
+	if ((pgprot_val(prot) != pgprot_val(args.pgprot)) ||
 	    (phys_addr != (args.pfn << PAGE_SHIFT)) ||
 	    (writable != args.writable)) {
 		follow_pfnmap_end(&args);
@@ -6802,6 +6997,124 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(access_process_vm);
 
+#ifdef CONFIG_BPF_SYSCALL
+/*
+ * Copy a string from another process's address space as given in mm.
+ * If there is any error return -EFAULT.
+ */
+static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr,
+				void *buf, int len, unsigned int gup_flags)
+{
+	void *old_buf = buf;
+	int err = 0;
+
+	*(char *)buf = '\0';
+
+	if (mmap_read_lock_killable(mm))
+		return -EFAULT;
+
+	addr = untagged_addr_remote(mm, addr);
+
+	/* Avoid triggering the temporary warning in __get_user_pages */
+	if (!vma_lookup(mm, addr)) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	while (len) {
+		int bytes, offset, retval;
+		void *maddr;
+		struct page *page;
+		struct vm_area_struct *vma = NULL;
+
+		page = get_user_page_vma_remote(mm, addr, gup_flags, &vma);
+		if (IS_ERR(page)) {
+			/*
+			 * Treat as a total failure for now until we decide how
+			 * to handle the CONFIG_HAVE_IOREMAP_PROT case and
+			 * stack expansion.
+			 */
+			*(char *)buf = '\0';
+			err = -EFAULT;
+			goto out;
+		}
+
+		bytes = len;
+		offset = addr & (PAGE_SIZE - 1);
+		if (bytes > PAGE_SIZE - offset)
+			bytes = PAGE_SIZE - offset;
+
+		maddr = kmap_local_page(page);
+		retval = strscpy(buf, maddr + offset, bytes);
+		if (retval >= 0) {
+			/* Found the end of the string */
+			buf += retval;
+			unmap_and_put_page(page, maddr);
+			break;
+		}
+
+		buf += bytes - 1;
+		/*
+		 * Because strscpy always NUL terminates we need to
+		 * copy the last byte in the page if we are going to
+		 * load more pages
+		 */
+		if (bytes != len) {
+			addr += bytes - 1;
+			copy_from_user_page(vma, page, addr, buf, maddr + (PAGE_SIZE - 1), 1);
+			buf += 1;
+			addr += 1;
+		}
+		len -= bytes;
+
+		unmap_and_put_page(page, maddr);
+	}
+
+out:
+	mmap_read_unlock(mm);
+	if (err)
+		return err;
+	return buf - old_buf;
+}
+
+/**
+ * copy_remote_vm_str - copy a string from another process's address space.
+ * @tsk:	the task of the target address space
+ * @addr:	start address to read from
+ * @buf:	destination buffer
+ * @len:	number of bytes to copy
+ * @gup_flags:	flags modifying lookup behaviour
+ *
+ * The caller must hold a reference on @mm.
+ *
+ * Return: number of bytes copied from @addr (source) to @buf (destination);
+ * not including the trailing NUL. Always guaranteed to leave NUL-terminated
+ * buffer. On any error, return -EFAULT.
+ */
+int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
+		       void *buf, int len, unsigned int gup_flags)
+{
+	struct mm_struct *mm;
+	int ret;
+
+	if (unlikely(len == 0))
+		return 0;
+
+	mm = get_task_mm(tsk);
+	if (!mm) {
+		*(char *)buf = '\0';
+		return -EFAULT;
+	}
+
+	ret = __copy_remote_vm_str(mm, addr, buf, len, gup_flags);
+
+	mmput(mm);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(copy_remote_vm_str);
+#endif /* CONFIG_BPF_SYSCALL */
+
 /*
  * Print the name of a VMA.
  */
@@ -6834,10 +7147,8 @@ void __might_fault(const char *file, int line)
 	if (pagefault_disabled())
 		return;
 	__might_sleep(file, line);
-#if defined(CONFIG_DEBUG_ATOMIC_SLEEP)
 	if (current->mm)
 		might_lock_read(&current->mm->mmap_lock);
-#endif
 }
 EXPORT_SYMBOL(__might_fault);
 #endif