1 files changed, 166 insertions, 22 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index bfe73db1c26c..81cba91f30bb 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)) {
@@ -775,6 +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
@@ -786,6 +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);
@@ -793,6 +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]);
@@ -1057,7 +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;
 
@@ -1128,6 +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;
@@ -1162,18 +1301,22 @@ 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);
@@ -2193,16 +2336,16 @@ __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) {
+	if (args->user_worker) {
 		/*
-		 * Mark us an IO worker, and block any signal that isn't
+		 * Mark us a user worker, and block any signal that isn't
 		 * fatal or STOP
 		 */
-		p->flags |= PF_IO_WORKER;
+		p->flags |= PF_USER_WORKER;
 		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
 	}
+	if (args->io_thread)
+		p->flags |= PF_IO_WORKER;
 
 	if (args->name)
 		strscpy_pad(p->comm, args->name, sizeof(p->comm));
@@ -2374,9 +2517,6 @@ __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) {
@@ -2594,6 +2734,7 @@ __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);
 
@@ -3159,6 +3300,9 @@ 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();
 }