1 files changed, 274 insertions, 35 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index f68954d05e89..ed4e01daccaa 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -97,6 +97,8 @@
 #include <linux/io_uring.h>
 #include <linux/bpf.h>
 #include <linux/stackprotector.h>
+#include <linux/user_events.h>
+#include <linux/iommu.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -451,13 +453,49 @@ 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 +503,56 @@ 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)) {
@@ -617,6 +685,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	if (retval)
 		goto out;
 
+	mt_clear_in_rcu(vmi.mas.tree);
 	for_each_vma(old_vmi, mpnt) {
 		struct file *file;
 
@@ -700,6 +769,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	retval = arch_dup_mmap(oldmm, mm);
 loop_out:
 	vma_iter_free(&vmi);
+	if (!retval)
+		mt_set_in_rcu(vmi.mas.tree);
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
@@ -755,11 +826,6 @@ static void check_mm(struct mm_struct *mm)
 	for (i = 0; i < NR_MM_COUNTERS; i++) {
 		long x = percpu_counter_sum(&mm->rss_stat[i]);
 
-		if (likely(!x))
-			continue;
-
-		/* Making sure this is not due to race with CPU offlining. */
-		x = percpu_counter_sum_all(&mm->rss_stat[i]);
 		if (unlikely(x))
 			pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
 				 mm, resident_page_types[i], x);
@@ -777,6 +843,67 @@ 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
@@ -788,6 +915,10 @@ 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);
@@ -795,6 +926,7 @@ void __mmdrop(struct mm_struct *mm)
 	check_mm(mm);
 	put_user_ns(mm->user_ns);
 	mm_pasid_drop(mm);
+	mm_destroy_cid(mm);
 
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		percpu_counter_destroy(&mm->rss_stat[i]);
@@ -1059,7 +1191,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 
 #ifdef CONFIG_SCHED_MM_CID
 	tsk->mm_cid = -1;
+	tsk->last_mm_cid = -1;
 	tsk->mm_cid_active = 0;
+	tsk->migrate_from_cpu = -1;
 #endif
 	return tsk;
 
@@ -1130,6 +1264,9 @@ 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;
@@ -1164,18 +1301,23 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	if (init_new_context(p, mm))
 		goto fail_nocontext;
 
+	if (mm_alloc_cid(mm))
+		goto fail_cid;
+
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		if (percpu_counter_init(&mm->rss_stat[i], 0, GFP_KERNEL_ACCOUNT))
 			goto fail_pcpu;
 
 	mm->user_ns = get_user_ns(user_ns);
 	lru_gen_init_mm(mm);
-	mm_init_cid(mm);
 	return mm;
 
 fail_pcpu:
 	while (i > 0)
 		percpu_counter_destroy(&mm->rss_stat[--i]);
+	mm_destroy_cid(mm);
+fail_cid:
+	destroy_context(mm);
 fail_nocontext:
 	mm_free_pgd(mm);
 fail_nopgd:
@@ -1627,7 +1769,8 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
+static int copy_files(unsigned long clone_flags, struct task_struct *tsk,
+		      int no_files)
 {
 	struct files_struct *oldf, *newf;
 	int error = 0;
@@ -1639,6 +1782,11 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldf)
 		goto out;
 
+	if (no_files) {
+		tsk->files = NULL;
+		goto out;
+	}
+
 	if (clone_flags & CLONE_FILES) {
 		atomic_inc(&oldf->count);
 		goto out;
@@ -1956,6 +2104,91 @@ const struct file_operations pidfd_fops = {
 #endif
 };
 
+/**
+ * __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
+ * @pidfd: the pidfd to return
+ *
+ * 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.
+ *
+ * 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.
+ */
+static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+{
+	int pidfd;
+	struct file *pidfd_file;
+
+	if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC))
+		return -EINVAL;
+
+	pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	if (pidfd < 0)
+		return pidfd;
+
+	pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
+					flags | O_RDWR | O_CLOEXEC);
+	if (IS_ERR(pidfd_file)) {
+		put_unused_fd(pidfd);
+		return PTR_ERR(pidfd_file);
+	}
+	get_pid(pid); /* held by pidfd_file now */
+	*ret = pidfd_file;
+	return 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
+ * @pidfd: the pidfd to return
+ *
+ * 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 used as 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)
+{
+	if (!pid || !pid_has_task(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);
@@ -2010,7 +2243,7 @@ static void rv_task_fork(struct task_struct *p)
  * parts of the process environment (as per the clone
  * flags). The actual kick-off is left to the caller.
  */
-static __latent_entropy struct task_struct *copy_process(
+__latent_entropy struct task_struct *copy_process(
 					struct pid *pid,
 					int trace,
 					int node,
@@ -2103,6 +2336,8 @@ static __latent_entropy struct task_struct *copy_process(
 	p->flags &= ~PF_KTHREAD;
 	if (args->kthread)
 		p->flags |= PF_KTHREAD;
+	if (args->user_worker)
+		p->flags |= PF_USER_WORKER;
 	if (args->io_thread) {
 		/*
 		 * Mark us an IO worker, and block any signal that isn't
@@ -2112,6 +2347,9 @@ static __latent_entropy struct task_struct *copy_process(
 		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
 	}
 
+	if (args->name)
+		strscpy_pad(p->comm, args->name, sizeof(p->comm));
+
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
 	/*
 	 * Clear TID on mm_release()?
@@ -2254,7 +2492,7 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_security;
-	retval = copy_files(clone_flags, p);
+	retval = copy_files(clone_flags, p, args->no_files);
 	if (retval)
 		goto bad_fork_cleanup_semundo;
 	retval = copy_fs(clone_flags, p);
@@ -2279,6 +2517,9 @@ static __latent_entropy struct task_struct *copy_process(
 	if (retval)
 		goto bad_fork_cleanup_io;
 
+	if (args->ignore_signals)
+		ignore_signals(p);
+
 	stackleak_task_init(p);
 
 	if (pid != &init_struct_pid) {
@@ -2296,21 +2537,12 @@ static __latent_entropy struct task_struct *copy_process(
 	 * if the fd table isn't shared).
 	 */
 	if (clone_flags & CLONE_PIDFD) {
-		retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+		/* Note that no task has been attached to @pid yet. */
+		retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
-
 		pidfd = retval;
 
-		pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
-					      O_RDWR | O_CLOEXEC);
-		if (IS_ERR(pidfile)) {
-			put_unused_fd(pidfd);
-			retval = PTR_ERR(pidfile);
-			goto bad_fork_free_pid;
-		}
-		get_pid(pid);	/* held by pidfile now */
-
 		retval = put_user(pidfd, args->pidfd);
 		if (retval)
 			goto bad_fork_put_pidfd;
@@ -2505,6 +2737,7 @@ static __latent_entropy struct task_struct *copy_process(
 
 	trace_task_newtask(p, clone_flags);
 	uprobe_copy_process(p, clone_flags);
+	user_events_fork(p, clone_flags);
 
 	copy_oom_score_adj(clone_flags, p);
 
@@ -2627,6 +2860,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.fn		= fn,
 		.fn_arg		= arg,
 		.io_thread	= 1,
+		.user_worker	= 1,
 	};
 
 	return copy_process(NULL, 0, node, &args);
@@ -2730,7 +2964,8 @@ pid_t kernel_clone(struct kernel_clone_args *args)
 /*
  * Create a kernel thread.
  */
-pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
+pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name,
+		    unsigned long flags)
 {
 	struct kernel_clone_args args = {
 		.flags		= ((lower_32_bits(flags) | CLONE_VM |
@@ -2738,6 +2973,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
 		.fn		= fn,
 		.fn_arg		= arg,
+		.name		= name,
 		.kthread	= 1,
 	};
 
@@ -2936,7 +3172,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 	 * - make the CLONE_DETACHED bit reusable for clone3
 	 * - make the CSIGNAL bits reusable for clone3
 	 */
-	if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
+	if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME))))
 		return false;
 
 	if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) ==
@@ -3067,6 +3303,9 @@ 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();
 }