Merge tag 'mm-hotfixes-stable-2023-09-05-11-51' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "Seven hotfixes. Four are cc:stable and the remainder pertain to issues
  which were introduced in the current merge window"

* tag 'mm-hotfixes-stable-2023-09-05-11-51' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  sparc64: add missing initialization of folio in tlb_batch_add()
  mm: memory-failure: use rcu lock instead of tasklist_lock when collect_procs()
  revert "memfd: improve userspace warnings for missing exec-related flags".
  rcu: dump vmalloc memory info safely
  mm/vmalloc: add a safer version of find_vm_area() for debug
  tools/mm: fix undefined reference to pthread_once
  memcontrol: ensure memcg acquired by id is properly set up

7 files changed, 53 insertions, 24 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index bf6219d9aaac..582f5317ff71 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -121,9 +121,6 @@
  *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->block_dirty_folio)
- *
- * ->i_mmap_rwsem
- *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
 static void page_cache_delete(struct address_space *mapping,
diff --git a/mm/ksm.c b/mm/ksm.c
index 8d6aee05421d..981af9c72e7a 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2925,7 +2925,7 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill,
 		struct anon_vma *av = rmap_item->anon_vma;
 
 		anon_vma_lock_read(av);
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		for_each_process(tsk) {
 			struct anon_vma_chain *vmac;
 			unsigned long addr;
@@ -2944,7 +2944,7 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill,
 				}
 			}
 		}
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 		anon_vma_unlock_read(av);
 	}
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b29b850cf399..a4d3282493b6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5326,7 +5326,6 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
 	memcg->deferred_split_queue.split_queue_len = 0;
 #endif
-	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	lru_gen_init_memcg(memcg);
 	return memcg;
 fail:
@@ -5398,14 +5397,27 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	if (alloc_shrinker_info(memcg))
 		goto offline_kmem;
 
-	/* Online state pins memcg ID, memcg ID pins CSS */
-	refcount_set(&memcg->id.ref, 1);
-	css_get(css);
-
 	if (unlikely(mem_cgroup_is_root(memcg)))
 		queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
 				   FLUSH_TIME);
 	lru_gen_online_memcg(memcg);
+
+	/* Online state pins memcg ID, memcg ID pins CSS */
+	refcount_set(&memcg->id.ref, 1);
+	css_get(css);
+
+	/*
+	 * Ensure mem_cgroup_from_id() works once we're fully online.
+	 *
+	 * We could do this earlier and require callers to filter with
+	 * css_tryget_online(). But right now there are no users that
+	 * need earlier access, and the workingset code relies on the
+	 * cgroup tree linkage (mem_cgroup_get_nr_swap_pages()). So
+	 * publish it here at the end of onlining. This matches the
+	 * regular ID destruction during offlining.
+	 */
+	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
+
 	return 0;
 offline_kmem:
 	memcg_offline_kmem(memcg);
diff --git a/mm/memfd.c b/mm/memfd.c
index 1cad1904fc26..2dba2cb6f0d0 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -316,7 +316,7 @@ SYSCALL_DEFINE2(memfd_create,
 		return -EINVAL;
 
 	if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) {
-		pr_info_ratelimited(
+		pr_warn_once(
 			"%s[%d]: memfd_create() called without MFD_EXEC or MFD_NOEXEC_SEAL set\n",
 			current->comm, task_pid_nr(current));
 	}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7b01fffe7a79..4d6e43c88489 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -547,8 +547,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
  * on behalf of the thread group. Return task_struct of the (first found)
  * dedicated thread if found, and return NULL otherwise.
  *
- * We already hold read_lock(&tasklist_lock) in the caller, so we don't
- * have to call rcu_read_lock/unlock() in this function.
+ * We already hold rcu lock in the caller, so we don't have to call
+ * rcu_read_lock/unlock() in this function.
  */
 static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
 {
@@ -609,7 +609,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 		return;
 
 	pgoff = page_to_pgoff(page);
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	for_each_process(tsk) {
 		struct anon_vma_chain *vmac;
 		struct task_struct *t = task_early_kill(tsk, force_early);
@@ -626,7 +626,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			add_to_kill_anon_file(t, page, vma, to_kill);
 		}
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	anon_vma_unlock_read(av);
 }
 
@@ -642,7 +642,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	pgoff_t pgoff;
 
 	i_mmap_lock_read(mapping);
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	pgoff = page_to_pgoff(page);
 	for_each_process(tsk) {
 		struct task_struct *t = task_early_kill(tsk, force_early);
@@ -662,7 +662,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 				add_to_kill_anon_file(t, page, vma, to_kill);
 		}
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	i_mmap_unlock_read(mapping);
 }
 
@@ -685,7 +685,7 @@ static void collect_procs_fsdax(struct page *page,
 	struct task_struct *tsk;
 
 	i_mmap_lock_read(mapping);
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	for_each_process(tsk) {
 		struct task_struct *t = task_early_kill(tsk, true);
 
@@ -696,7 +696,7 @@ static void collect_procs_fsdax(struct page *page,
 				add_to_kill_fsdax(t, page, vma, to_kill, pgoff);
 		}
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	i_mmap_unlock_read(mapping);
 }
 #endif /* CONFIG_FS_DAX */
diff --git a/mm/util.c b/mm/util.c
index f08b655da917..8cbbfd3a3d59 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1068,7 +1068,9 @@ void mem_dump_obj(void *object)
 	if (vmalloc_dump_obj(object))
 		return;
 
-	if (virt_addr_valid(object))
+	if (is_vmalloc_addr(object))
+		type = "vmalloc memory";
+	else if (virt_addr_valid(object))
 		type = "non-slab/vmalloc memory";
 	else if (object == NULL)
 		type = "NULL pointer";
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 228a4a5312f2..ef8599d394fd 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -4278,14 +4278,32 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 #ifdef CONFIG_PRINTK
 bool vmalloc_dump_obj(void *object)
 {
-	struct vm_struct *vm;
 	void *objp = (void *)PAGE_ALIGN((unsigned long)object);
+	const void *caller;
+	struct vm_struct *vm;
+	struct vmap_area *va;
+	unsigned long addr;
+	unsigned int nr_pages;
 
-	vm = find_vm_area(objp);
-	if (!vm)
+	if (!spin_trylock(&vmap_area_lock))
+		return false;
+	va = __find_vmap_area((unsigned long)objp, &vmap_area_root);
+	if (!va) {
+		spin_unlock(&vmap_area_lock);
 		return false;
+	}
+
+	vm = va->vm;
+	if (!vm) {
+		spin_unlock(&vmap_area_lock);
+		return false;
+	}
+	addr = (unsigned long)vm->addr;
+	caller = vm->caller;
+	nr_pages = vm->nr_pages;
+	spin_unlock(&vmap_area_lock);
 	pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n",
-		vm->nr_pages, (unsigned long)vm->addr, vm->caller);
+		nr_pages, addr, caller);
 	return true;
 }
 #endif