1 files changed, 178 insertions, 126 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index f11ac96b7587..85afccfdf3b1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -311,11 +311,9 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 	 * so memcg accounting is performed manually on assigning/releasing
 	 * stacks to tasks. Drop __GFP_ACCOUNT.
 	 */
-	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
-				     VMALLOC_START, VMALLOC_END,
+	stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN,
 				     THREADINFO_GFP & ~__GFP_ACCOUNT,
-				     PAGE_KERNEL,
-				     0, node, __builtin_return_address(0));
+				     node, __builtin_return_address(0));
 	if (!stack)
 		return -ENOMEM;
 
@@ -436,35 +434,6 @@ 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 = UINT_MAX;
-
-	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;
@@ -474,14 +443,46 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 		return NULL;
 
 	vma_init(vma, mm);
-	if (!vma_lock_alloc(vma)) {
-		kmem_cache_free(vm_area_cachep, vma);
-		return NULL;
-	}
 
 	return vma;
 }
 
+static void vm_area_init_from(const struct vm_area_struct *src,
+			      struct vm_area_struct *dest)
+{
+	dest->vm_mm = src->vm_mm;
+	dest->vm_ops = src->vm_ops;
+	dest->vm_start = src->vm_start;
+	dest->vm_end = src->vm_end;
+	dest->anon_vma = src->anon_vma;
+	dest->vm_pgoff = src->vm_pgoff;
+	dest->vm_file = src->vm_file;
+	dest->vm_private_data = src->vm_private_data;
+	vm_flags_init(dest, src->vm_flags);
+	memcpy(&dest->vm_page_prot, &src->vm_page_prot,
+	       sizeof(dest->vm_page_prot));
+	/*
+	 * src->shared.rb may be modified concurrently when called from
+	 * dup_mmap(), but the clone will reinitialize it.
+	 */
+	data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared)));
+	memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx,
+	       sizeof(dest->vm_userfaultfd_ctx));
+#ifdef CONFIG_ANON_VMA_NAME
+	dest->anon_name = src->anon_name;
+#endif
+#ifdef CONFIG_SWAP
+	memcpy(&dest->swap_readahead_info, &src->swap_readahead_info,
+	       sizeof(dest->swap_readahead_info));
+#endif
+#ifndef CONFIG_MMU
+	dest->vm_region = src->vm_region;
+#endif
+#ifdef CONFIG_NUMA
+	dest->vm_policy = src->vm_policy;
+#endif
+}
+
 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);
@@ -491,15 +492,8 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 
 	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;
-	}
+	vm_area_init_from(orig, new);
+	vma_lock_init(new, true);
 	INIT_LIST_HEAD(&new->anon_vma_chain);
 	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
@@ -507,35 +501,15 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	return new;
 }
 
-void __vm_area_free(struct vm_area_struct *vma)
+void vm_area_free(struct vm_area_struct *vma)
 {
+	/* The vma should be detached while being destroyed. */
+	vma_assert_detached(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)) {
@@ -694,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		tmp = vm_area_dup(mpnt);
 		if (!tmp)
 			goto fail_nomem;
+
+		/* track_pfn_copy() will later take care of copying internal state. */
+		if (unlikely(tmp->vm_flags & VM_PFNMAP))
+			untrack_pfn_clear(tmp);
+
 		retval = vma_dup_policy(mpnt, tmp);
 		if (retval)
 			goto fail_nomem_policy;
@@ -826,6 +805,36 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 #define mm_free_pgd(mm)
 #endif /* CONFIG_MMU */
 
+#ifdef CONFIG_MM_ID
+static DEFINE_IDA(mm_ida);
+
+static inline int mm_alloc_id(struct mm_struct *mm)
+{
+	int ret;
+
+	ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
+	mm->mm_id = ret;
+	return 0;
+}
+
+static inline void mm_free_id(struct mm_struct *mm)
+{
+	const mm_id_t id = mm->mm_id;
+
+	mm->mm_id = MM_ID_DUMMY;
+	if (id == MM_ID_DUMMY)
+		return;
+	if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX))
+		return;
+	ida_free(&mm_ida, id);
+}
+#else /* !CONFIG_MM_ID */
+static inline int mm_alloc_id(struct mm_struct *mm) { return 0; }
+static inline void mm_free_id(struct mm_struct *mm) {}
+#endif /* CONFIG_MM_ID */
+
 static void check_mm(struct mm_struct *mm)
 {
 	int i;
@@ -929,6 +938,7 @@ void __mmdrop(struct mm_struct *mm)
 
 	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
+	mm_free_id(mm);
 	destroy_context(mm);
 	mmu_notifier_subscriptions_destroy(mm);
 	check_mm(mm);
@@ -1263,6 +1273,15 @@ static void mm_init_uprobes_state(struct mm_struct *mm)
 #endif
 }
 
+static void mmap_init_lock(struct mm_struct *mm)
+{
+	init_rwsem(&mm->mmap_lock);
+	mm_lock_seqcount_init(mm);
+#ifdef CONFIG_PER_VMA_LOCK
+	rcuwait_init(&mm->vma_writer_wait);
+#endif
+}
+
 static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	struct user_namespace *user_ns)
 {
@@ -1287,6 +1306,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_subscriptions_init(mm);
 	init_tlb_flush_pending(mm);
+	futex_mm_init(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
 	mm->pmd_huge_pte = NULL;
 #endif
@@ -1304,6 +1324,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	if (mm_alloc_pgd(mm))
 		goto fail_nopgd;
 
+	if (mm_alloc_id(mm))
+		goto fail_noid;
+
 	if (init_new_context(p, mm))
 		goto fail_nocontext;
 
@@ -1323,6 +1346,8 @@ fail_pcpu:
 fail_cid:
 	destroy_context(mm);
 fail_nocontext:
+	mm_free_id(mm);
+fail_noid:
 	mm_free_pgd(mm);
 fail_nopgd:
 	free_mm(mm);
@@ -1364,6 +1389,7 @@ static inline void __mmput(struct mm_struct *mm)
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
 	lru_gen_del_mm(mm);
+	futex_hash_free(mm);
 	mmdrop(mm);
 }
 
@@ -1559,6 +1585,17 @@ struct mm_struct *get_task_mm(struct task_struct *task)
 }
 EXPORT_SYMBOL_GPL(get_task_mm);
 
+static bool may_access_mm(struct mm_struct *mm, struct task_struct *task, unsigned int mode)
+{
+	if (mm == current->mm)
+		return true;
+	if (ptrace_may_access(task, mode))
+		return true;
+	if ((mode & PTRACE_MODE_READ) && perfmon_capable())
+		return true;
+	return false;
+}
+
 struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 {
 	struct mm_struct *mm;
@@ -1571,7 +1608,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	mm = get_task_mm(task);
 	if (!mm) {
 		mm = ERR_PTR(-ESRCH);
-	} else if (mm != current->mm && !ptrace_may_access(task, mode)) {
+	} else if (!may_access_mm(mm, task, mode)) {
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
@@ -1891,8 +1928,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_POSIX_TIMERS
 	INIT_HLIST_HEAD(&sig->posix_timers);
 	INIT_HLIST_HEAD(&sig->ignored_posix_timers);
-	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sig->real_timer.function = it_real_fn;
+	hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 #endif
 
 	task_lock(current->group_leader);
@@ -2003,17 +2039,16 @@ static inline void rcu_copy_process(struct task_struct *p)
 }
 
 /**
- * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
+ * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
  * @pid:   the struct pid for which to create a pidfd
  * @flags: flags of the new @pidfd
- * @ret: Where to return the file for the pidfd.
+ * @ret_file: return the new pidfs file
  *
  * Allocate a new file that stashes @pid and reserve a new pidfd number in the
  * caller's file descriptor table. The pidfd is reserved but not installed yet.
  *
- * The helper doesn't perform checks on @pid which makes it useful for pidfds
- * created via CLONE_PIDFD where @pid has no task attached when the pidfd and
- * pidfd file are prepared.
+ * The helper verifies that @pid is still in use, without PIDFD_THREAD the
+ * task identified by @pid must be a thread-group leader.
  *
  * If this function returns successfully the caller is responsible to either
  * call fd_install() passing the returned pidfd and pidfd file as arguments in
@@ -2030,59 +2065,50 @@ static inline void rcu_copy_process(struct task_struct *p)
  *         error, a negative error code is returned from the function and the
  *         last argument remains unchanged.
  */
-static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file)
 {
-	struct file *pidfd_file;
+	struct file *pidfs_file;
+
+	/*
+	 * PIDFD_STALE is only allowed to be passed if the caller knows
+	 * that @pid is already registered in pidfs and thus
+	 * PIDFD_INFO_EXIT information is guaranteed to be available.
+	 */
+	if (!(flags & PIDFD_STALE)) {
+		/*
+		 * While holding the pidfd waitqueue lock removing the
+		 * task linkage for the thread-group leader pid
+		 * (PIDTYPE_TGID) isn't possible. Thus, if there's still
+		 * task linkage for PIDTYPE_PID not having thread-group
+		 * leader linkage for the pid means it wasn't a
+		 * thread-group leader in the first place.
+		 */
+		guard(spinlock_irq)(&pid->wait_pidfd.lock);
+
+		/* Task has already been reaped. */
+		if (!pid_has_task(pid, PIDTYPE_PID))
+			return -ESRCH;
+		/*
+		 * If this struct pid isn't used as a thread-group
+		 * leader but the caller requested to create a
+		 * thread-group leader pidfd then report ENOENT.
+		 */
+		if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID))
+			return -ENOENT;
+	}
 
 	CLASS(get_unused_fd, pidfd)(O_CLOEXEC);
 	if (pidfd < 0)
 		return pidfd;
 
-	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
-	if (IS_ERR(pidfd_file))
-		return PTR_ERR(pidfd_file);
+	pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR);
+	if (IS_ERR(pidfs_file))
+		return PTR_ERR(pidfs_file);
 
-	*ret = pidfd_file;
+	*ret_file = pidfs_file;
 	return take_fd(pidfd);
 }
 
-/**
- * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
- * @pid:   the struct pid for which to create a pidfd
- * @flags: flags of the new @pidfd
- * @ret: Where to return the pidfd.
- *
- * Allocate a new file that stashes @pid and reserve a new pidfd number in the
- * caller's file descriptor table. The pidfd is reserved but not installed yet.
- *
- * The helper verifies that @pid is still in use, without PIDFD_THREAD the
- * task identified by @pid must be a thread-group leader.
- *
- * If this function returns successfully the caller is responsible to either
- * call fd_install() passing the returned pidfd and pidfd file as arguments in
- * order to install the pidfd into its file descriptor table or they must use
- * put_unused_fd() and fput() on the returned pidfd and pidfd file
- * respectively.
- *
- * This function is useful when a pidfd must already be reserved but there
- * might still be points of failure afterwards and the caller wants to ensure
- * that no pidfd is leaked into its file descriptor table.
- *
- * Return: On success, a reserved pidfd is returned from the function and a new
- *         pidfd file is returned in the last argument to the function. On
- *         error, a negative error code is returned from the function and the
- *         last argument remains unchanged.
- */
-int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
-{
-	bool thread = flags & PIDFD_THREAD;
-
-	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
-		return -EINVAL;
-
-	return __pidfd_prepare(pid, flags, ret);
-}
-
 static void __delayed_free_task(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
@@ -2129,6 +2155,13 @@ static void rv_task_fork(struct task_struct *p)
 #define rv_task_fork(p) do {} while (0)
 #endif
 
+static bool need_futex_hash_allocate_default(u64 clone_flags)
+{
+	if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM))
+		return false;
+	return true;
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -2429,7 +2462,7 @@ __latent_entropy struct task_struct *copy_process(
 		 * Note that no task has been attached to @pid yet indicate
 		 * that via CLONE_PIDFD.
 		 */
-		retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile);
+		retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;
@@ -2510,6 +2543,21 @@ __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cancel_cgroup;
 
 	/*
+	 * Allocate a default futex hash for the user process once the first
+	 * thread spawns.
+	 */
+	if (need_futex_hash_allocate_default(clone_flags)) {
+		retval = futex_hash_allocate_default();
+		if (retval)
+			goto bad_fork_core_free;
+		/*
+		 * If we fail beyond this point we don't free the allocated
+		 * futex hash map. We assume that another thread will be created
+		 * and makes use of it. The hash map will be freed once the main
+		 * thread terminates.
+		 */
+	}
+	/*
 	 * From this point on we must avoid any synchronous user-space
 	 * communication until we take the tasklist-lock. In particular, we do
 	 * not want user-space to be able to predict the process start-time by
@@ -3180,6 +3228,11 @@ void __init mm_cache_init(void)
 
 void __init proc_caches_init(void)
 {
+	struct kmem_cache_args args = {
+		.use_freeptr_offset = true,
+		.freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr),
+	};
+
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -3196,11 +3249,10 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			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
+	vm_area_cachep = kmem_cache_create("vm_area_struct",
+			sizeof(struct vm_area_struct), &args,
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
+			SLAB_ACCOUNT);
 	mmap_init();
 	nsproxy_cache_init();
 }