mm: introduce __vm_flags_mod and use it in untrack_pfn

There are scenarios when vm_flags can be modified without exclusive
mmap_lock, such as:
- after VMA was isolated and mmap_lock was downgraded or dropped
- in exit_mmap when there are no other mm users and locking is unnecessary
Introduce __vm_flags_mod to avoid assertions when the caller takes
responsibility for the required locking.
Pass a hint to untrack_pfn to conditionally use __vm_flags_mod for
flags modification to avoid assertion.

Link: https://lkml.kernel.org/r/20230126193752.297968-7-surenb@google.comSigned-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjun Roy <arjunroy@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Minchan Kim <minchan@google.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Peter Oskolkov <posk@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Punit Agrawal <punit.agrawal@bytedance.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Sebastian Reichel <sebastian.reichel@collabora.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/x86/mm/pat/memtype.c

@@ -1046,7 +1046,7 @@ void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
  * can be for the entire vma (in which case pfn, size are zero).
  */
 void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
-		 unsigned long size)
+		 unsigned long size, bool mm_wr_locked)
 {
 	resource_size_t paddr;
 	unsigned long prot;
@@ -1065,8 +1065,12 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
-	if (vma)
-		vm_flags_clear(vma, VM_PAT);
+	if (vma) {
+		if (mm_wr_locked)
+			vm_flags_clear(vma, VM_PAT);
+		else
+			__vm_flags_mod(vma, 0, VM_PAT);
+	}
 }
 
 /*

include/linux/mm.h

@@ -656,6 +656,16 @@ static inline void vm_flags_clear(struct vm_area_struct *vma,
 	ACCESS_PRIVATE(vma, __vm_flags) &= ~flags;
 }
 
+/*
+ * Use only if VMA is not part of the VMA tree or has no other users and
+ * therefore needs no locking.
+ */
+static inline void __vm_flags_mod(struct vm_area_struct *vma,
+				  vm_flags_t set, vm_flags_t clear)
+{
+	vm_flags_init(vma, (vma->vm_flags | set) & ~clear);
+}
+
 /*
  * Use only when the order of set/clear operations is unimportant, otherwise
  * use vm_flags_{set|clear} explicitly.
@@ -664,7 +674,7 @@ static inline void vm_flags_mod(struct vm_area_struct *vma,
 				vm_flags_t set, vm_flags_t clear)
 {
 	mmap_assert_write_locked(vma->vm_mm);
-	vm_flags_init(vma, (vma->vm_flags | set) & ~clear);
+	__vm_flags_mod(vma, set, clear);
 }
 
 static inline void vma_set_anonymous(struct vm_area_struct *vma)
@@ -2085,7 +2095,7 @@ static inline void zap_vma_pages(struct vm_area_struct *vma)
 }
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *start_vma, unsigned long start,
-		unsigned long end);
+		unsigned long end, bool mm_wr_locked);
 
 struct mmu_notifier_range;
 

include/linux/pgtable.h

@@ -1185,7 +1185,8 @@ static inline int track_pfn_copy(struct vm_area_struct *vma)
  * can be for the entire vma (in which case pfn, size are zero).
  */
 static inline void untrack_pfn(struct vm_area_struct *vma,
-			       unsigned long pfn, unsigned long size)
+			       unsigned long pfn, unsigned long size,
+			       bool mm_wr_locked)
 {
 }
 
@@ -1203,7 +1204,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 			     pfn_t pfn);
 extern int track_pfn_copy(struct vm_area_struct *vma);
 extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
-			unsigned long size);
+			unsigned long size, bool mm_wr_locked);
 extern void untrack_pfn_moved(struct vm_area_struct *vma);
 #endif
 

mm/memory.c

@@ -1613,7 +1613,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 static void unmap_single_vma(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, unsigned long start_addr,
 		unsigned long end_addr,
-		struct zap_details *details)
+		struct zap_details *details, bool mm_wr_locked)
 {
 	unsigned long start = max(vma->vm_start, start_addr);
 	unsigned long end;
@@ -1628,7 +1628,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 		uprobe_munmap(vma, start, end);
 
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
-		untrack_pfn(vma, 0, 0);
+		untrack_pfn(vma, 0, 0, mm_wr_locked);
 
 	if (start != end) {
 		if (unlikely(is_vm_hugetlb_page(vma))) {
@@ -1675,7 +1675,7 @@ static void unmap_single_vma(struct mmu_gather *tlb,
  */
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *vma, unsigned long start_addr,
-		unsigned long end_addr)
+		unsigned long end_addr, bool mm_wr_locked)
 {
 	struct mmu_notifier_range range;
 	struct zap_details details = {
@@ -1689,7 +1689,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 				start_addr, end_addr);
 	mmu_notifier_invalidate_range_start(&range);
 	do {
-		unmap_single_vma(tlb, vma, start_addr, end_addr, &details);
+		unmap_single_vma(tlb, vma, start_addr, end_addr, &details,
+				 mm_wr_locked);
 	} while ((vma = mas_find(&mas, end_addr - 1)) != NULL);
 	mmu_notifier_invalidate_range_end(&range);
 }
@@ -1723,7 +1724,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	 * unmap 'address-end' not 'range.start-range.end' as range
 	 * could have been expanded for hugetlb pmd sharing.
 	 */
-	unmap_single_vma(&tlb, vma, address, end, details);
+	unmap_single_vma(&tlb, vma, address, end, details, false);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb);
 }
@@ -2492,7 +2493,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 
 	err = remap_pfn_range_notrack(vma, addr, pfn, size, prot);
 	if (err)
-		untrack_pfn(vma, pfn, PAGE_ALIGN(size));
+		untrack_pfn(vma, pfn, PAGE_ALIGN(size), true);
 	return err;
 }
 EXPORT_SYMBOL(remap_pfn_range);

mm/memremap.c

@@ -129,7 +129,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 	}
 	mem_hotplug_done();
 
-	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
 	pgmap_array_delete(range);
 }
 
@@ -276,7 +276,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	if (!is_private)
 		kasan_remove_zero_shadow(__va(range->start), range_len(range));
 err_kasan:
-	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range), true);
 err_pfn_remap:
 	pgmap_array_delete(range);
 	return error;

mm/mmap.c

@@ -78,7 +78,7 @@ core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
 		struct vm_area_struct *next, unsigned long start,
-		unsigned long end);
+		unsigned long end, bool mm_wr_locked);
 
 static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
 {
@@ -2133,14 +2133,14 @@ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas)
 static void unmap_region(struct mm_struct *mm, struct maple_tree *mt,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
 		struct vm_area_struct *next,
-		unsigned long start, unsigned long end)
+		unsigned long start, unsigned long end, bool mm_wr_locked)
 {
 	struct mmu_gather tlb;
 
 	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
-	unmap_vmas(&tlb, mt, vma, start, end);
+	unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked);
 	free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
 				 next ? next->vm_start : USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb);
@@ -2388,7 +2388,11 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 			mmap_write_downgrade(mm);
 	}
 
-	unmap_region(mm, &mt_detach, vma, prev, next, start, end);
+	/*
+	 * We can free page tables without write-locking mmap_lock because VMAs
+	 * were isolated before we downgraded mmap_lock.
+	 */
+	unmap_region(mm, &mt_detach, vma, prev, next, start, end, !downgrade);
 	/* Statistics and freeing VMAs */
 	mas_set(&mas_detach, start);
 	remove_mt(mm, &mas_detach);
@@ -2701,7 +2705,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 
 		/* Undo any partial mapping done by a device driver. */
 		unmap_region(mm, &mm->mm_mt, vma, prev, next, vma->vm_start,
-			     vma->vm_end);
+			     vma->vm_end, true);
 	}
 	if (file && (vm_flags & VM_SHARED))
 		mapping_unmap_writable(file->f_mapping);
@@ -3029,7 +3033,7 @@ void exit_mmap(struct mm_struct *mm)
 	tlb_gather_mmu_fullmm(&tlb, mm);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */
-	unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX);
+	unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX, false);
 	mmap_read_unlock(mm);
 
 	/*