1 files changed, 206 insertions, 408 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index aebb3e6c96dc..1ee8eb11f38b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -16,13 +16,13 @@
 #include <linux/slab.h>
 #include <linux/sched/autogroup.h>
 #include <linux/sched/mm.h>
-#include <linux/sched/coredump.h>
 #include <linux/sched/user.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/ext.h>
 #include <linux/seq_file.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
@@ -44,6 +44,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mm_inline.h>
+#include <linux/memblock.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -103,6 +104,7 @@
 #include <linux/rseq.h>
 #include <uapi/linux/pidfd.h>
 #include <linux/pidfs.h>
+#include <linux/tick.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -110,11 +112,16 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+/* For dup_mmap(). */
+#include "../mm/internal.h"
+
 #include <trace/events/sched.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/task.h>
 
+#include <kunit/visibility.h>
+
 /*
  * Minimum number of threads to boot the kernel
  */
@@ -205,9 +212,10 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm)
 	unsigned int i;
 
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL)
-			continue;
-		return true;
+		struct vm_struct *tmp = NULL;
+
+		if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm))
+			return true;
 	}
 	return false;
 }
@@ -306,11 +314,9 @@ 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;
 
@@ -425,112 +431,9 @@ struct kmem_cache *files_cachep;
 /* SLAB cache for fs_struct structures (tsk->fs) */
 struct kmem_cache *fs_cachep;
 
-/* SLAB cache for vm_area_struct structures */
-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)
-		return NULL;
-
-	vma_init(vma, mm);
-	if (!vma_lock_alloc(vma)) {
-		kmem_cache_free(vm_area_cachep, vma);
-		return NULL;
-	}
-
-	return vma;
-}
-
-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)
-		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)
-{
-	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)) {
@@ -610,7 +513,7 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
-static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
+void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	struct file *exe_file;
 
@@ -620,177 +523,11 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
 	 * We depend on the oldmm having properly denied write access to the
 	 * exe_file already.
 	 */
-	if (exe_file && deny_write_access(exe_file))
-		pr_warn_once("deny_write_access() failed in %s\n", __func__);
+	if (exe_file && exe_file_deny_write_access(exe_file))
+		pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__);
 }
 
 #ifdef CONFIG_MMU
-static __latent_entropy int dup_mmap(struct mm_struct *mm,
-					struct mm_struct *oldmm)
-{
-	struct vm_area_struct *mpnt, *tmp;
-	int retval;
-	unsigned long charge = 0;
-	LIST_HEAD(uf);
-	VMA_ITERATOR(vmi, mm, 0);
-
-	uprobe_start_dup_mmap();
-	if (mmap_write_lock_killable(oldmm)) {
-		retval = -EINTR;
-		goto fail_uprobe_end;
-	}
-	flush_cache_dup_mm(oldmm);
-	uprobe_dup_mmap(oldmm, mm);
-	/*
-	 * Not linked in yet - no deadlock potential:
-	 */
-	mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
-
-	/* No ordering required: file already has been exposed. */
-	dup_mm_exe_file(mm, oldmm);
-
-	mm->total_vm = oldmm->total_vm;
-	mm->data_vm = oldmm->data_vm;
-	mm->exec_vm = oldmm->exec_vm;
-	mm->stack_vm = oldmm->stack_vm;
-
-	retval = ksm_fork(mm, oldmm);
-	if (retval)
-		goto out;
-	khugepaged_fork(mm, oldmm);
-
-	/* Use __mt_dup() to efficiently build an identical maple tree. */
-	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
-	if (unlikely(retval))
-		goto out;
-
-	mt_clear_in_rcu(vmi.mas.tree);
-	for_each_vma(vmi, mpnt) {
-		struct file *file;
-
-		vma_start_write(mpnt);
-		if (mpnt->vm_flags & VM_DONTCOPY) {
-			retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
-						    mpnt->vm_end, GFP_KERNEL);
-			if (retval)
-				goto loop_out;
-
-			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
-			continue;
-		}
-		charge = 0;
-		/*
-		 * Don't duplicate many vmas if we've been oom-killed (for
-		 * example)
-		 */
-		if (fatal_signal_pending(current)) {
-			retval = -EINTR;
-			goto loop_out;
-		}
-		if (mpnt->vm_flags & VM_ACCOUNT) {
-			unsigned long len = vma_pages(mpnt);
-
-			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
-				goto fail_nomem;
-			charge = len;
-		}
-		tmp = vm_area_dup(mpnt);
-		if (!tmp)
-			goto fail_nomem;
-		retval = vma_dup_policy(mpnt, tmp);
-		if (retval)
-			goto fail_nomem_policy;
-		tmp->vm_mm = mm;
-		retval = dup_userfaultfd(tmp, &uf);
-		if (retval)
-			goto fail_nomem_anon_vma_fork;
-		if (tmp->vm_flags & VM_WIPEONFORK) {
-			/*
-			 * VM_WIPEONFORK gets a clean slate in the child.
-			 * Don't prepare anon_vma until fault since we don't
-			 * copy page for current vma.
-			 */
-			tmp->anon_vma = NULL;
-		} else if (anon_vma_fork(tmp, mpnt))
-			goto fail_nomem_anon_vma_fork;
-		vm_flags_clear(tmp, VM_LOCKED_MASK);
-		/*
-		 * Copy/update hugetlb private vma information.
-		 */
-		if (is_vm_hugetlb_page(tmp))
-			hugetlb_dup_vma_private(tmp);
-
-		/*
-		 * Link the vma into the MT. After using __mt_dup(), memory
-		 * allocation is not necessary here, so it cannot fail.
-		 */
-		vma_iter_bulk_store(&vmi, tmp);
-
-		mm->map_count++;
-
-		if (tmp->vm_ops && tmp->vm_ops->open)
-			tmp->vm_ops->open(tmp);
-
-		file = tmp->vm_file;
-		if (file) {
-			struct address_space *mapping = file->f_mapping;
-
-			get_file(file);
-			i_mmap_lock_write(mapping);
-			if (vma_is_shared_maywrite(tmp))
-				mapping_allow_writable(mapping);
-			flush_dcache_mmap_lock(mapping);
-			/* insert tmp into the share list, just after mpnt */
-			vma_interval_tree_insert_after(tmp, mpnt,
-					&mapping->i_mmap);
-			flush_dcache_mmap_unlock(mapping);
-			i_mmap_unlock_write(mapping);
-		}
-
-		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(tmp, mpnt);
-
-		if (retval) {
-			mpnt = vma_next(&vmi);
-			goto loop_out;
-		}
-	}
-	/* a new mm has just been created */
-	retval = arch_dup_mmap(oldmm, mm);
-loop_out:
-	vma_iter_free(&vmi);
-	if (!retval) {
-		mt_set_in_rcu(vmi.mas.tree);
-	} else if (mpnt) {
-		/*
-		 * The entire maple tree has already been duplicated. If the
-		 * mmap duplication fails, mark the failure point with
-		 * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered,
-		 * stop releasing VMAs that have not been duplicated after this
-		 * point.
-		 */
-		mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
-		mas_store(&vmi.mas, XA_ZERO_ENTRY);
-	}
-out:
-	mmap_write_unlock(mm);
-	flush_tlb_mm(oldmm);
-	mmap_write_unlock(oldmm);
-	dup_userfaultfd_complete(&uf);
-fail_uprobe_end:
-	uprobe_end_dup_mmap();
-	return retval;
-
-fail_nomem_anon_vma_fork:
-	mpol_put(vma_policy(tmp));
-fail_nomem_policy:
-	vm_area_free(tmp);
-fail_nomem:
-	retval = -ENOMEM;
-	vm_unacct_memory(charge);
-	goto loop_out;
-}
-
 static inline int mm_alloc_pgd(struct mm_struct *mm)
 {
 	mm->pgd = pgd_alloc(mm);
@@ -804,17 +541,40 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 	pgd_free(mm, mm->pgd);
 }
 #else
-static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-	mmap_write_lock(oldmm);
-	dup_mm_exe_file(mm, oldmm);
-	mmap_write_unlock(oldmm);
-	return 0;
-}
 #define mm_alloc_pgd(mm)	(0)
 #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;
@@ -834,7 +594,7 @@ static void check_mm(struct mm_struct *mm)
 		pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
 				mm_pgtables_bytes(mm));
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
 	VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
 #endif
 }
@@ -918,6 +678,7 @@ 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);
@@ -971,6 +732,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	sched_ext_free(tsk);
 	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
@@ -996,10 +758,10 @@ void __init __weak arch_task_cache_init(void) { }
 /*
  * set_max_threads
  */
-static void set_max_threads(unsigned int max_threads_suggested)
+static void __init set_max_threads(unsigned int max_threads_suggested)
 {
 	u64 threads;
-	unsigned long nr_pages = totalram_pages();
+	unsigned long nr_pages = memblock_estimated_nr_free_pages();
 
 	/*
 	 * The number of threads shall be limited such that the thread
@@ -1022,7 +784,7 @@ static void set_max_threads(unsigned int max_threads_suggested)
 int arch_task_struct_size __read_mostly;
 #endif
 
-static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
+static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size)
 {
 	/* Fetch thread_struct whitelist for the architecture. */
 	arch_thread_struct_whitelist(offset, size);
@@ -1184,7 +946,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->active_memcg = NULL;
 #endif
 
-#ifdef CONFIG_CPU_SUP_INTEL
+#ifdef CONFIG_X86_BUS_LOCK_DETECT
 	tsk->reported_split_lock = 0;
 #endif
 
@@ -1251,6 +1013,15 @@ 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)
 {
@@ -1261,9 +1032,6 @@ 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;
@@ -1278,7 +1046,8 @@ 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);
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+	futex_mm_init(mm);
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
 	mm->pmd_huge_pte = NULL;
 #endif
 	mm_init_uprobes_state(mm);
@@ -1295,10 +1064,13 @@ 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;
 
-	if (mm_alloc_cid(mm))
+	if (mm_alloc_cid(mm, p))
 		goto fail_cid;
 
 	if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT,
@@ -1314,6 +1086,8 @@ fail_pcpu:
 fail_cid:
 	destroy_context(mm);
 fail_nocontext:
+	mm_free_id(mm);
+fail_noid:
 	mm_free_pgd(mm);
 fail_nopgd:
 	free_mm(mm);
@@ -1334,6 +1108,7 @@ struct mm_struct *mm_alloc(void)
 	memset(mm, 0, sizeof(*mm));
 	return mm_init(mm, current, current_user_ns());
 }
+EXPORT_SYMBOL_IF_KUNIT(mm_alloc);
 
 static inline void __mmput(struct mm_struct *mm)
 {
@@ -1344,7 +1119,7 @@ static inline void __mmput(struct mm_struct *mm)
 	ksm_exit(mm);
 	khugepaged_exit(mm); /* must run before exit_mmap */
 	exit_mmap(mm);
-	mm_put_huge_zero_page(mm);
+	mm_put_huge_zero_folio(mm);
 	set_mm_exe_file(mm, NULL);
 	if (!list_empty(&mm->mmlist)) {
 		spin_lock(&mmlist_lock);
@@ -1354,6 +1129,7 @@ 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);
 }
 
@@ -1417,13 +1193,13 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 		 * We expect the caller (i.e., sys_execve) to already denied
 		 * write access, so this is unlikely to fail.
 		 */
-		if (unlikely(deny_write_access(new_exe_file)))
+		if (unlikely(exe_file_deny_write_access(new_exe_file)))
 			return -EACCES;
 		get_file(new_exe_file);
 	}
 	rcu_assign_pointer(mm->exe_file, new_exe_file);
 	if (old_exe_file) {
-		allow_write_access(old_exe_file);
+		exe_file_allow_write_access(old_exe_file);
 		fput(old_exe_file);
 	}
 	return 0;
@@ -1464,7 +1240,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 			return ret;
 	}
 
-	ret = deny_write_access(new_exe_file);
+	ret = exe_file_deny_write_access(new_exe_file);
 	if (ret)
 		return -EACCES;
 	get_file(new_exe_file);
@@ -1476,7 +1252,7 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	mmap_write_unlock(mm);
 
 	if (old_exe_file) {
-		allow_write_access(old_exe_file);
+		exe_file_allow_write_access(old_exe_file);
 		fput(old_exe_file);
 	}
 	return 0;
@@ -1512,12 +1288,13 @@ struct file *get_task_exe_file(struct task_struct *task)
 	struct file *exe_file = NULL;
 	struct mm_struct *mm;
 
+	if (task->flags & PF_KTHREAD)
+		return NULL;
+
 	task_lock(task);
 	mm = task->mm;
-	if (mm) {
-		if (!(task->flags & PF_KTHREAD))
-			exe_file = get_mm_exe_file(mm);
-	}
+	if (mm)
+		exe_file = get_mm_exe_file(mm);
 	task_unlock(task);
 	return exe_file;
 }
@@ -1536,19 +1313,29 @@ struct mm_struct *get_task_mm(struct task_struct *task)
 {
 	struct mm_struct *mm;
 
+	if (task->flags & PF_KTHREAD)
+		return NULL;
+
 	task_lock(task);
 	mm = task->mm;
-	if (mm) {
-		if (task->flags & PF_KTHREAD)
-			mm = NULL;
-		else
-			mmget(mm);
-	}
+	if (mm)
+		mmget(mm);
 	task_unlock(task);
 	return mm;
 }
 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;
@@ -1559,8 +1346,9 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 		return ERR_PTR(err);
 
 	mm = get_task_mm(task);
-	if (mm && mm != current->mm &&
-			!ptrace_may_access(task, mode)) {
+	if (!mm) {
+		mm = ERR_PTR(-ESRCH);
+	} else if (!may_access_mm(mm, task, mode)) {
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
@@ -1685,9 +1473,11 @@ static struct mm_struct *dup_mm(struct task_struct *tsk,
 	if (!mm_init(mm, tsk, mm->user_ns))
 		goto fail_nomem;
 
+	uprobe_start_dup_mmap();
 	err = dup_mmap(mm, oldmm);
 	if (err)
 		goto free_pt;
+	uprobe_end_dup_mmap();
 
 	mm->hiwater_rss = get_mm_rss(mm);
 	mm->hiwater_vm = mm->total_vm;
@@ -1702,6 +1492,8 @@ free_pt:
 	mm->binfmt = NULL;
 	mm_init_owner(mm, NULL);
 	mmput(mm);
+	if (err)
+		uprobe_end_dup_mmap();
 
 fail_nomem:
 	return NULL;
@@ -1770,33 +1562,30 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk,
 		      int no_files)
 {
 	struct files_struct *oldf, *newf;
-	int error = 0;
 
 	/*
 	 * A background process may not have any files ...
 	 */
 	oldf = current->files;
 	if (!oldf)
-		goto out;
+		return 0;
 
 	if (no_files) {
 		tsk->files = NULL;
-		goto out;
+		return 0;
 	}
 
 	if (clone_flags & CLONE_FILES) {
 		atomic_inc(&oldf->count);
-		goto out;
+		return 0;
 	}
 
-	newf = dup_fd(oldf, NR_OPEN_MAX, &error);
-	if (!newf)
-		goto out;
+	newf = dup_fd(oldf, NULL);
+	if (IS_ERR(newf))
+		return PTR_ERR(newf);
 
 	tsk->files = newf;
-	error = 0;
-out:
-	return error;
+	return 0;
 }
 
 static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
@@ -1877,9 +1666,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	prev_cputime_init(&sig->prev_cputime);
 
 #ifdef CONFIG_POSIX_TIMERS
-	INIT_LIST_HEAD(&sig->posix_timers);
-	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sig->real_timer.function = it_real_fn;
+	INIT_HLIST_HEAD(&sig->posix_timers);
+	INIT_HLIST_HEAD(&sig->ignored_posix_timers);
+	hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 #endif
 
 	task_lock(current->group_leader);
@@ -1990,17 +1779,16 @@ 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
@@ -2017,64 +1805,48 @@ 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)
 {
-	int pidfd;
-	struct file *pidfd_file;
+	struct file *pidfs_file;
 
-	pidfd = get_unused_fd_flags(O_CLOEXEC);
-	if (pidfd < 0)
-		return pidfd;
-
-	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
-	if (IS_ERR(pidfd_file)) {
-		put_unused_fd(pidfd);
-		return PTR_ERR(pidfd_file);
-	}
 	/*
-	 * anon_inode_getfile() ignores everything outside of the
-	 * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually.
+	 * 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.
 	 */
-	pidfd_file->f_flags |= (flags & PIDFD_THREAD);
-	*ret = pidfd_file;
-	return pidfd;
-}
+	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);
 
-/**
- * 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;
+		/* 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;
+	}
 
-	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
-		return -EINVAL;
+	CLASS(get_unused_fd, pidfd)(O_CLOEXEC);
+	if (pidfd < 0)
+		return pidfd;
+
+	pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR);
+	if (IS_ERR(pidfs_file))
+		return PTR_ERR(pidfs_file);
 
-	return __pidfd_prepare(pid, flags, ret);
+	*ret_file = pidfs_file;
+	return take_fd(pidfd);
 }
 
 static void __delayed_free_task(struct rcu_head *rhp)
@@ -2123,6 +1895,13 @@ 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.
@@ -2309,6 +2088,7 @@ __latent_entropy struct task_struct *copy_process(
 	acct_clear_integrals(p);
 
 	posix_cputimers_init(&p->posix_cputimers);
+	tick_dep_init_task(p);
 
 	p->io_context = NULL;
 	audit_set_context(p, NULL);
@@ -2327,7 +2107,6 @@ __latent_entropy struct task_struct *copy_process(
 #endif
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
-	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
 	seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -2363,7 +2142,7 @@ __latent_entropy struct task_struct *copy_process(
 
 	retval = perf_event_init_task(p, clone_flags);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_sched_cancel_fork;
 	retval = audit_alloc(p);
 	if (retval)
 		goto bad_fork_cleanup_perf;
@@ -2419,8 +2198,11 @@ __latent_entropy struct task_struct *copy_process(
 	if (clone_flags & CLONE_PIDFD) {
 		int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0;
 
-		/* Note that no task has been attached to @pid yet. */
-		retval = __pidfd_prepare(pid, flags, &pidfile);
+		/*
+		 * Note that no task has been attached to @pid yet indicate
+		 * that via CLONE_PIDFD.
+		 */
+		retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;
@@ -2496,9 +2278,26 @@ __latent_entropy struct task_struct *copy_process(
 	 * cgroup specific, it unconditionally needs to place the task on a
 	 * runqueue.
 	 */
-	sched_cgroup_fork(p, args);
+	retval = sched_cgroup_fork(p, args);
+	if (retval)
+		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
@@ -2542,13 +2341,13 @@ __latent_entropy struct task_struct *copy_process(
 	/* Don't start children in a dying pid namespace */
 	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
 		retval = -ENOMEM;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* Let kill terminate clone/fork in the middle */
 	if (fatal_signal_pending(current)) {
 		retval = -EINTR;
-		goto bad_fork_cancel_cgroup;
+		goto bad_fork_core_free;
 	}
 
 	/* No more failure paths after this point. */
@@ -2622,10 +2421,11 @@ __latent_entropy struct task_struct *copy_process(
 
 	return p;
 
-bad_fork_cancel_cgroup:
+bad_fork_core_free:
 	sched_core_free(p);
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
@@ -2664,6 +2464,8 @@ bad_fork_cleanup_audit:
 	audit_free(p);
 bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_sched_cancel_fork:
+	sched_cancel_fork(p);
 bad_fork_cleanup_policy:
 	lockdep_free_task(p);
 #ifdef CONFIG_NUMA
@@ -2941,8 +2743,6 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 }
 #endif
 
-#ifdef __ARCH_WANT_SYS_CLONE3
-
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
 					      size_t usize)
@@ -3086,6 +2886,11 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 	struct kernel_clone_args kargs;
 	pid_t set_tid[MAX_PID_NS_LEVEL];
 
+#ifdef __ARCH_BROKEN_SYS_CLONE3
+#warning clone3() entry point is missing, please fix
+	return -ENOSYS;
+#endif
+
 	kargs.set_tid = set_tid;
 
 	err = copy_clone_args_from_user(&kargs, uargs, size);
@@ -3097,7 +2902,6 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 
 	return kernel_clone(&kargs);
 }
-#endif
 
 void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data)
 {
@@ -3180,11 +2984,6 @@ 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
 	mmap_init();
 	nsproxy_cache_init();
 }
@@ -3246,17 +3045,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 /*
  * Unshare file descriptor table if it is being shared
  */
-int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
-	       struct files_struct **new_fdp)
+static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
 {
 	struct files_struct *fd = current->files;
-	int error = 0;
 
 	if ((unshare_flags & CLONE_FILES) &&
 	    (fd && atomic_read(&fd->count) > 1)) {
-		*new_fdp = dup_fd(fd, max_fds, &error);
-		if (!*new_fdp)
-			return error;
+		fd = dup_fd(fd, NULL);
+		if (IS_ERR(fd))
+			return PTR_ERR(fd);
+		*new_fdp = fd;
 	}
 
 	return 0;
@@ -3314,7 +3112,7 @@ int ksys_unshare(unsigned long unshare_flags)
 	err = unshare_fs(unshare_flags, &new_fs);
 	if (err)
 		goto bad_unshare_out;
-	err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
+	err = unshare_fd(unshare_flags, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
 	err = unshare_userns(unshare_flags, &new_cred);
@@ -3406,7 +3204,7 @@ int unshare_files(void)
 	struct files_struct *old, *copy = NULL;
 	int error;
 
-	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
+	error = unshare_fd(CLONE_FILES, &copy);
 	if (error || !copy)
 		return error;
 
@@ -3418,7 +3216,7 @@ int unshare_files(void)
 	return 0;
 }
 
-int sysctl_max_threads(struct ctl_table *table, int write,
+int sysctl_max_threads(const struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;