Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

1 files changed, 150 insertions, 13 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index bfe73db1c26c..4342200d5e2b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -451,13 +451,49 @@ static struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+#ifdef CONFIG_PER_VMA_LOCK
+
+/* SLAB cache for vm_area_struct.lock */
+static struct kmem_cache *vma_lock_cachep;
+
+static bool vma_lock_alloc(struct vm_area_struct *vma)
+{
+	vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL);
+	if (!vma->vm_lock)
+		return false;
+
+	init_rwsem(&vma->vm_lock->lock);
+	vma->vm_lock_seq = -1;
+
+	return true;
+}
+
+static inline void vma_lock_free(struct vm_area_struct *vma)
+{
+	kmem_cache_free(vma_lock_cachep, vma->vm_lock);
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; }
+static inline void vma_lock_free(struct vm_area_struct *vma) {}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
 struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
 
 	vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
-	if (vma)
-		vma_init(vma, mm);
+	if (!vma)
+		return NULL;
+
+	vma_init(vma, mm);
+	if (!vma_lock_alloc(vma)) {
+		kmem_cache_free(vm_area_cachep, vma);
+		return NULL;
+	}
+
 	return vma;
 }
 
@@ -465,26 +501,56 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 {
 	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 
-	if (new) {
-		ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);
-		ASSERT_EXCLUSIVE_WRITER(orig->vm_file);
-		/*
-		 * orig->shared.rb may be modified concurrently, but the clone
-		 * will be reinitialized.
-		 */
-		data_race(memcpy(new, orig, sizeof(*new)));
-		INIT_LIST_HEAD(&new->anon_vma_chain);
-		dup_anon_vma_name(orig, new);
+	if (!new)
+		return NULL;
+
+	ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);
+	ASSERT_EXCLUSIVE_WRITER(orig->vm_file);
+	/*
+	 * orig->shared.rb may be modified concurrently, but the clone
+	 * will be reinitialized.
+	 */
+	data_race(memcpy(new, orig, sizeof(*new)));
+	if (!vma_lock_alloc(new)) {
+		kmem_cache_free(vm_area_cachep, new);
+		return NULL;
 	}
+	INIT_LIST_HEAD(&new->anon_vma_chain);
+	vma_numab_state_init(new);
+	dup_anon_vma_name(orig, new);
+
 	return new;
 }
 
-void vm_area_free(struct vm_area_struct *vma)
+void __vm_area_free(struct vm_area_struct *vma)
 {
+	vma_numab_state_free(vma);
 	free_anon_vma_name(vma);
+	vma_lock_free(vma);
 	kmem_cache_free(vm_area_cachep, vma);
 }
 
+#ifdef CONFIG_PER_VMA_LOCK
+static void vm_area_free_rcu_cb(struct rcu_head *head)
+{
+	struct vm_area_struct *vma = container_of(head, struct vm_area_struct,
+						  vm_rcu);
+
+	/* The vma should not be locked while being destroyed. */
+	VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma);
+	__vm_area_free(vma);
+}
+#endif
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+#ifdef CONFIG_PER_VMA_LOCK
+	call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb);
+#else
+	__vm_area_free(vma);
+#endif
+}
+
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
@@ -775,6 +841,67 @@ static void check_mm(struct mm_struct *mm)
 #define allocate_mm()	(kmem_cache_alloc(mm_cachep, GFP_KERNEL))
 #define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))
 
+static void do_check_lazy_tlb(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	WARN_ON_ONCE(current->active_mm == mm);
+}
+
+static void do_shoot_lazy_tlb(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (current->active_mm == mm) {
+		WARN_ON_ONCE(current->mm);
+		current->active_mm = &init_mm;
+		switch_mm(mm, &init_mm, current);
+	}
+}
+
+static void cleanup_lazy_tlbs(struct mm_struct *mm)
+{
+	if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) {
+		/*
+		 * In this case, lazy tlb mms are refounted and would not reach
+		 * __mmdrop until all CPUs have switched away and mmdrop()ed.
+		 */
+		return;
+	}
+
+	/*
+	 * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it
+	 * requires lazy mm users to switch to another mm when the refcount
+	 * drops to zero, before the mm is freed. This requires IPIs here to
+	 * switch kernel threads to init_mm.
+	 *
+	 * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm
+	 * switch with the final userspace teardown TLB flush which leaves the
+	 * mm lazy on this CPU but no others, reducing the need for additional
+	 * IPIs here. There are cases where a final IPI is still required here,
+	 * such as the final mmdrop being performed on a different CPU than the
+	 * one exiting, or kernel threads using the mm when userspace exits.
+	 *
+	 * IPI overheads have not found to be expensive, but they could be
+	 * reduced in a number of possible ways, for example (roughly
+	 * increasing order of complexity):
+	 * - The last lazy reference created by exit_mm() could instead switch
+	 *   to init_mm, however it's probable this will run on the same CPU
+	 *   immediately afterwards, so this may not reduce IPIs much.
+	 * - A batch of mms requiring IPIs could be gathered and freed at once.
+	 * - CPUs store active_mm where it can be remotely checked without a
+	 *   lock, to filter out false-positives in the cpumask.
+	 * - After mm_users or mm_count reaches zero, switching away from the
+	 *   mm could clear mm_cpumask to reduce some IPIs, perhaps together
+	 *   with some batching or delaying of the final IPIs.
+	 * - A delayed freeing and RCU-like quiescing sequence based on mm
+	 *   switching to avoid IPIs completely.
+	 */
+	on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1);
+	if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES))
+		on_each_cpu(do_check_lazy_tlb, (void *)mm, 1);
+}
+
 /*
  * Called when the last reference to the mm
  * is dropped: either by a lazy thread or by
@@ -786,6 +913,10 @@ void __mmdrop(struct mm_struct *mm)
 
 	BUG_ON(mm == &init_mm);
 	WARN_ON_ONCE(mm == current->mm);
+
+	/* Ensure no CPUs are using this as their lazy tlb mm */
+	cleanup_lazy_tlbs(mm);
+
 	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
@@ -1128,6 +1259,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
+#ifdef CONFIG_PER_VMA_LOCK
+	mm->mm_lock_seq = 0;
+#endif
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
@@ -3159,6 +3293,9 @@ void __init proc_caches_init(void)
 			NULL);
 
 	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
+#ifdef CONFIG_PER_VMA_LOCK
+	vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT);
+#endif
 	mmap_init();
 	nsproxy_cache_init();
 }