Merge branch 'v6.0-rc7'

Merge upstream to get RAPTORLAKE_S

Signed-off-by: Peter Zijlstra <peterz@infradead.org>

30 files changed, 152 insertions, 132 deletions

diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 6432a37ac1c9..c565fbf66ac8 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 
 	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0);
 	if (ret < 0) {
+		audit_mark->path = NULL;
 		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
 	}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index dd8d9ab747c3..79a5da1bc5bb 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1940,6 +1940,7 @@ void __audit_uring_exit(int success, long code)
 		goto out;
 	}
 
+	audit_return_fixup(ctx, success, code);
 	if (ctx->context == AUDIT_CTX_SYSCALL) {
 		/*
 		 * NOTE: See the note in __audit_uring_entry() about the case
@@ -1981,7 +1982,6 @@ void __audit_uring_exit(int success, long code)
 	audit_filter_inodes(current, ctx);
 	if (ctx->current_state != AUDIT_STATE_RECORD)
 		goto out;
-	audit_return_fixup(ctx, success, code);
 	audit_log_exit();
 
 out:
@@ -2065,13 +2065,13 @@ void __audit_syscall_exit(int success, long return_code)
 	if (!list_empty(&context->killed_trees))
 		audit_kill_trees(context);
 
+	audit_return_fixup(context, success, return_code);
 	/* run through both filters to ensure we set the filterkey properly */
 	audit_filter_syscall(current, context);
 	audit_filter_inodes(current, context);
 	if (context->current_state < AUDIT_STATE_RECORD)
 		goto out;
 
-	audit_return_fixup(context, success, return_code);
 	audit_log_exit();
 
 out:
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 59b7eb60d5b4..4a400cd63731 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -921,8 +921,10 @@ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,
 				pos++;
 			}
 		}
+
+		/* no link or prog match, skip the cgroup of this layer */
+		continue;
 found:
-		BUG_ON(!cg);
 		progs = rcu_dereference_protected(
 				desc->bpf.effective[atype],
 				lockdep_is_held(&cgroup_mutex));
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c1e10d088dbb..3d9eb3ae334c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -971,7 +971,7 @@ pure_initcall(bpf_jit_charge_init);
 
 int bpf_jit_charge_modmem(u32 size)
 {
-	if (atomic_long_add_return(size, &bpf_jit_current) > bpf_jit_limit) {
+	if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) {
 		if (!bpf_capable()) {
 			atomic_long_sub(size, &bpf_jit_current);
 			return -EPERM;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a4d40d98428a..27760627370d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5197,7 +5197,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sys_bpf:
-		return &bpf_sys_bpf_proto;
+		return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
 	case BPF_FUNC_btf_find_by_name_kind:
 		return &bpf_btf_find_by_name_kind_proto;
 	case BPF_FUNC_sys_close:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 096fdac70165..3eadb14e090b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6066,6 +6066,9 @@ skip_type_check:
 			return -EACCES;
 		}
 		meta->mem_size = reg->var_off.value;
+		err = mark_chain_precision(env, regno);
+		if (err)
+			return err;
 		break;
 	case ARG_PTR_TO_INT:
 	case ARG_PTR_TO_LONG:
@@ -7030,8 +7033,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
 	struct bpf_reg_state *regs = cur_regs(env), *reg;
 	struct bpf_map *map = meta->map_ptr;
-	struct tnum range;
-	u64 val;
+	u64 val, max;
 	int err;
 
 	if (func_id != BPF_FUNC_tail_call)
@@ -7041,10 +7043,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 		return -EINVAL;
 	}
 
-	range = tnum_range(0, map->max_entries - 1);
 	reg = &regs[BPF_REG_3];
+	val = reg->var_off.value;
+	max = map->max_entries;
 
-	if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) {
+	if (!(register_is_const(reg) && val < max)) {
 		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
 		return 0;
 	}
@@ -7052,8 +7055,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	err = mark_chain_precision(env, BPF_REG_3);
 	if (err)
 		return err;
-
-	val = reg->var_off.value;
 	if (bpf_map_key_unseen(aux))
 		bpf_map_key_store(aux, val);
 	else if (!bpf_map_key_poisoned(aux) &&
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 2ade21b54dc4..ff6a8099eb2a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 	int retval = 0;
 
 	mutex_lock(&cgroup_mutex);
+	cpus_read_lock();
 	percpu_down_write(&cgroup_threadgroup_rwsem);
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
@@ -72,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 			break;
 	}
 	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
 	mutex_unlock(&cgroup_mutex);
 
 	return retval;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index ffaccd6373f1..5f2090d051ac 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 
 		if (ss->css_rstat_flush) {
 			list_del_rcu(&css->rstat_css_node);
+			synchronize_rcu();
 			list_add_rcu(&css->rstat_css_node,
 				     &dcgrp->rstat_css_list);
 		}
@@ -2370,6 +2371,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
 /**
+ * cgroup_attach_lock - Lock for ->attach()
+ * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
+ *
+ * cgroup migration sometimes needs to stabilize threadgroups against forks and
+ * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
+ * implementations (e.g. cpuset), also need to disable CPU hotplug.
+ * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
+ * lead to deadlocks.
+ *
+ * Bringing up a CPU may involve creating and destroying tasks which requires
+ * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
+ * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
+ * write-locking threadgroup_rwsem, the locking order is reversed and we end up
+ * waiting for an on-going CPU hotplug operation which in turn is waiting for
+ * the threadgroup_rwsem to be released to create new tasks. For more details:
+ *
+ *   http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
+ *
+ * Resolve the situation by always acquiring cpus_read_lock() before optionally
+ * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
+ * CPU hotplug is disabled on entry.
+ */
+static void cgroup_attach_lock(bool lock_threadgroup)
+{
+	cpus_read_lock();
+	if (lock_threadgroup)
+		percpu_down_write(&cgroup_threadgroup_rwsem);
+}
+
+/**
+ * cgroup_attach_unlock - Undo cgroup_attach_lock()
+ * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
+ */
+static void cgroup_attach_unlock(bool lock_threadgroup)
+{
+	if (lock_threadgroup)
+		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cpus_read_unlock();
+}
+
+/**
  * cgroup_migrate_add_task - add a migration target task to a migration context
  * @task: target task
  * @mgctx: target migration context
@@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 }
 
 struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
-					     bool *locked)
-	__acquires(&cgroup_threadgroup_rwsem)
+					     bool *threadgroup_locked)
 {
 	struct task_struct *tsk;
 	pid_t pid;
@@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	 * Therefore, we can skip the global lock.
 	 */
 	lockdep_assert_held(&cgroup_mutex);
-	if (pid || threadgroup) {
-		percpu_down_write(&cgroup_threadgroup_rwsem);
-		*locked = true;
-	} else {
-		*locked = false;
-	}
+	*threadgroup_locked = pid || threadgroup;
+	cgroup_attach_lock(*threadgroup_locked);
 
 	rcu_read_lock();
 	if (pid) {
@@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
 	goto out_unlock_rcu;
 
 out_unlock_threadgroup:
-	if (*locked) {
-		percpu_up_write(&cgroup_threadgroup_rwsem);
-		*locked = false;
-	}
+	cgroup_attach_unlock(*threadgroup_locked);
+	*threadgroup_locked = false;
 out_unlock_rcu:
 	rcu_read_unlock();
 	return tsk;
 }
 
-void cgroup_procs_write_finish(struct task_struct *task, bool locked)
-	__releases(&cgroup_threadgroup_rwsem)
+void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
 {
 	struct cgroup_subsys *ss;
 	int ssid;
@@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
 	/* release reference from cgroup_procs_write_start() */
 	put_task_struct(task);
 
-	if (locked)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(threadgroup_locked);
+
 	for_each_subsys(ss, ssid)
 		if (ss->post_attach)
 			ss->post_attach();
@@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	 * write-locking can be skipped safely.
 	 */
 	has_tasks = !list_empty(&mgctx.preloaded_src_csets);
-	if (has_tasks)
-		percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(has_tasks);
 
 	/* NULL dst indicates self on default hierarchy */
 	ret = cgroup_migrate_prepare_dst(&mgctx);
@@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 	ret = cgroup_migrate_execute(&mgctx);
 out_finish:
 	cgroup_migrate_finish(&mgctx);
-	if (has_tasks)
-		percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(has_tasks);
 	return ret;
 }
 
@@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
-	new = psi_trigger_create(psi, buf, nbytes, res);
+	new = psi_trigger_create(psi, buf, res);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
@@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	struct task_struct *task;
 	const struct cred *saved_cred;
 	ssize_t ret;
-	bool locked;
+	bool threadgroup_locked;
 
 	dst_cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!dst_cgrp)
 		return -ENODEV;
 
-	task = cgroup_procs_write_start(buf, threadgroup, &locked);
+	task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
 	ret = PTR_ERR_OR_ZERO(task);
 	if (ret)
 		goto out_unlock;
@@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
 
 out_finish:
-	cgroup_procs_write_finish(task, locked);
+	cgroup_procs_write_finish(task, threadgroup_locked);
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 
@@ -6017,6 +6049,9 @@ struct cgroup *cgroup_get_from_id(u64 id)
 	if (!kn)
 		goto out;
 
+	if (kernfs_type(kn) != KERNFS_DIR)
+		goto put;
+
 	rcu_read_lock();
 
 	cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
@@ -6024,7 +6059,7 @@ struct cgroup *cgroup_get_from_id(u64 id)
 		cgrp = NULL;
 
 	rcu_read_unlock();
-
+put:
 	kernfs_put(kn);
 out:
 	return cgrp;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58aadfda9b8b..1f3a55297f39 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	cpus_read_lock();
+	lockdep_assert_cpus_held();	/* see cgroup_attach_lock() */
 	percpu_down_write(&cpuset_rwsem);
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	percpu_up_write(&cpuset_rwsem);
-	cpus_read_unlock();
 }
 
 /* The various types of files and directories in a cpuset file system */
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 07b26df453a9..a0eb4d5cf557 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -494,6 +494,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 
 #ifdef CONFIG_KALLSYMS
 	VMCOREINFO_SYMBOL(kallsyms_names);
+	VMCOREINFO_SYMBOL(kallsyms_num_syms);
 	VMCOREINFO_SYMBOL(kallsyms_token_table);
 	VMCOREINFO_SYMBOL(kallsyms_token_index);
 #ifdef CONFIG_KALLSYMS_BASE_RELATIVE
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 2caafd13f8aa..18c93c2276ca 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -350,11 +350,10 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 						   unsigned long *flags)
 {
 
-	unsigned int max_range = dma_get_max_seg_size(ref->dev);
 	struct dma_debug_entry *entry, index = *ref;
-	unsigned int range = 0;
+	int limit = min(HASH_SIZE, (index.dev_addr >> HASH_FN_SHIFT) + 1);
 
-	while (range <= max_range) {
+	for (int i = 0; i < limit; i++) {
 		entry = __hash_bucket_find(*bucket, ref, containing_match);
 
 		if (entry)
@@ -364,7 +363,6 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
 		 * Nothing found, go back a hash bucket
 		 */
 		put_hash_bucket(*bucket, *flags);
-		range          += (1 << HASH_FN_SHIFT);
 		index.dev_addr -= (1 << HASH_FN_SHIFT);
 		*bucket = get_hash_bucket(&index, flags);
 	}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 49cbf3e33de7..27f272381cf2 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -707,7 +707,7 @@ int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous);
 
-int dma_supported(struct device *dev, u64 mask)
+static int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -721,7 +721,6 @@ int dma_supported(struct device *dev, u64 mask)
 		return 1;
 	return ops->dma_supported(dev, mask);
 }
-EXPORT_SYMBOL(dma_supported);
 
 bool dma_pci_p2pdma_supported(struct device *dev)
 {
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c5a9190b218f..0ef6b12f961d 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -326,9 +326,6 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 		swiotlb_adjust_nareas(num_possible_cpus());
 
 	nslabs = default_nslabs;
-	if (nslabs < IO_TLB_MIN_SLABS)
-		panic("%s: nslabs = %lu too small\n", __func__, nslabs);
-
 	/*
 	 * By default allocate the bounce buffer memory from low memory, but
 	 * allow to pick a location everywhere for hypervisors with guest
@@ -341,8 +338,7 @@ retry:
 	else
 		tlb = memblock_alloc_low(bytes, PAGE_SIZE);
 	if (!tlb) {
-		pr_warn("%s: Failed to allocate %zu bytes tlb structure\n",
-			__func__, bytes);
+		pr_warn("%s: failed to allocate tlb structure\n", __func__);
 		return;
 	}
 
@@ -579,7 +575,10 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	}
 }
 
-#define slot_addr(start, idx)	((start) + ((idx) << IO_TLB_SHIFT))
+static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
+{
+	return start + (idx << IO_TLB_SHIFT);
+}
 
 /*
  * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
@@ -765,7 +764,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 	/*
 	 * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
 	 * to the tlb buffer, if we knew for sure the device will
-	 * overwirte the entire current content. But we don't. Thus
+	 * overwrite the entire current content. But we don't. Thus
 	 * unconditional bounce may prevent leaking swiotlb content (i.e.
 	 * kernel memory) to user-space.
 	 */
diff --git a/kernel/fork.c b/kernel/fork.c
index 90c85b17bf69..2b6bd511c6ed 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1225,6 +1225,7 @@ void mmput_async(struct mm_struct *mm)
 		schedule_work(&mm->async_put_work);
 	}
 }
+EXPORT_SYMBOL_GPL(mmput_async);
 #endif
 
 /**
@@ -2046,11 +2047,8 @@ static __latent_entropy struct task_struct *copy_process(
 	/*
 	 * If the new process will be in a different time namespace
 	 * do not allow it to share VM or a thread group with the forking task.
-	 *
-	 * On vfork, the child process enters the target time namespace only
-	 * after exec.
 	 */
-	if ((clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) {
+	if (clone_flags & (CLONE_THREAD | CLONE_VM)) {
 		if (nsp->time_ns != nsp->time_ns_for_children)
 			return ERR_PTR(-EINVAL);
 	}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 80697e5e03e4..ca9d834d0b84 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1562,6 +1562,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	/* Ensure it is not in reserved area nor out of text */
 	if (!(core_kernel_text((unsigned long) p->addr) ||
 	    is_module_text_address((unsigned long) p->addr)) ||
+	    in_gate_area_no_mm((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
@@ -1707,11 +1708,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
 		/* Try to disarm and disable this/parent probe */
 		if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
 			/*
-			 * If 'kprobes_all_disarmed' is set, 'orig_p'
-			 * should have already been disarmed, so
-			 * skip unneed disarming process.
+			 * Don't be lazy here.  Even if 'kprobes_all_disarmed'
+			 * is false, 'orig_p' might not have been armed yet.
+			 * Note arm_all_kprobes() __tries__ to arm all kprobes
+			 * on the best effort basis.
 			 */
-			if (!kprobes_all_disarmed) {
+			if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) {
 				ret = disarm_kprobe(orig_p, true);
 				if (ret) {
 					p->flags &= ~KPROBE_FLAG_DISABLED;
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 6a477c622544..a4e4d84b6f4e 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2099,7 +2099,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					      sizeof(*mod->static_call_sites),
 					      &mod->num_static_call_sites);
 #endif
-#ifdef CONFIG_KUNIT
+#if IS_ENABLED(CONFIG_KUNIT)
 	mod->kunit_suites = section_objs(info, ".kunit_test_suites",
 					      sizeof(*mod->kunit_suites),
 					      &mod->num_kunit_suites);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index b4cbb406bc28..eec72ca962e2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -179,8 +179,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	if (IS_ERR(new_ns))
 		return  PTR_ERR(new_ns);
 
-	if ((flags & CLONE_VM) == 0)
-		timens_on_fork(new_ns, tsk);
+	timens_on_fork(new_ns, tsk);
 
 	tsk->nsproxy = new_ns;
 	return 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index bb3d63bdf4ae..667876da8382 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void)
 		char buf[32];
 
 		snprintf(buf, sizeof(buf), "cpu%d", cpu);
-		debugfs_remove(debugfs_lookup(buf, sd_dentry));
+		debugfs_lookup_and_remove(buf, sd_dentry);
 		d_cpu = debugfs_create_dir(buf, sd_dentry);
 
 		i = 0;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ec66b40bdd40..ecb4b4ff4ce0 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -190,12 +190,8 @@ static void group_init(struct psi_group *group)
 	/* Init trigger-related members */
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
-	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
-	group->poll_states = 0;
 	group->poll_min_period = U32_MAX;
-	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
-	group->polling_until = 0;
 	init_waitqueue_head(&group->poll_wait);
 	timer_setup(&group->poll_timer, poll_timer_fn, 0);
 	rcu_assign_pointer(group->poll_task, NULL);
@@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
 	if (static_branch_likely(&psi_disabled))
 		return 0;
 
-	cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL);
+	cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL);
 	if (!cgroup->psi)
 		return -ENOMEM;
 
@@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 }
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, size_t nbytes, enum psi_res res)
+			char *buf, enum psi_res res)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
@@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, nbytes, res);
+	new = psi_trigger_create(&psi_system, buf, res);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index d4788f810b55..0b1cd985dc27 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index a492f159624f..860b2dcf3ac4 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -277,6 +277,7 @@ COND_SYSCALL(landlock_restrict_self);
 
 /* mm/fadvise.c */
 COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
 
 /* mm/, CONFIG_MMU only */
 COND_SYSCALL(swapon);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 126c769d36c3..439e2ab6905e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1861,8 +1861,6 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
 	ftrace_hash_rec_update_modify(ops, filter_hash, 1);
 }
 
-static bool ops_references_ip(struct ftrace_ops *ops, unsigned long ip);
-
 /*
  * Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK
  * or no-needed to update, -EBUSY if it detects a conflict of the flag
@@ -3118,49 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
 		ftrace_hash_empty(ops->func_hash->notrace_hash);
 }
 
-/*
- * Check if the current ops references the given ip.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static bool
-ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
-{
-	/* If ops isn't enabled, ignore it */
-	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
-		return false;
-
-	/* If ops traces all then it includes this function */
-	if (ops_traces_mod(ops))
-		return true;
-
-	/* The function must be in the filter */
-	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
-	    !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
-		return false;
-
-	/* If in notrace hash, we ignore it too */
-	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
-		return false;
-
-	return true;
-}
-
-/*
- * Check if the current ops references the record.
- *
- * If the ops traces all functions, then it was already accounted for.
- * If the ops does not trace the current record function, skip it.
- * If the ops ignores the function via notrace filter, skip it.
- */
-static bool
-ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
-{
-	return ops_references_ip(ops, rec->ip);
-}
-
 static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 {
 	bool init_nop = ftrace_need_init_nop();
@@ -6822,6 +6777,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum,
 	return -ERANGE;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES)
+/*
+ * Check if the current ops references the given ip.
+ *
+ * If the ops traces all functions, then it was already accounted for.
+ * If the ops does not trace the current record function, skip it.
+ * If the ops ignores the function via notrace filter, skip it.
+ */
+static bool
+ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
+{
+	/* If ops isn't enabled, ignore it */
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return false;
+
+	/* If ops traces all then it includes this function */
+	if (ops_traces_mod(ops))
+		return true;
+
+	/* The function must be in the filter */
+	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+	    !__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
+		return false;
+
+	/* If in notrace hash, we ignore it too */
+	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
+		return false;
+
+	return true;
+}
+#endif
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6834,7 +6821,7 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec)) {
+		if (ops_references_ip(ops, rec->ip)) {
 			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
 				continue;
 			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
diff --git a/kernel/trace/rv/monitors/wip/wip.h b/kernel/trace/rv/monitors/wip/wip.h
index c1c47e2305ef..dacc37b62a2c 100644
--- a/kernel/trace/rv/monitors/wip/wip.h
+++ b/kernel/trace/rv/monitors/wip/wip.h
@@ -27,7 +27,7 @@ struct automaton_wip {
 	bool final_states[state_max_wip];
 };
 
-struct automaton_wip automaton_wip = {
+static struct automaton_wip automaton_wip = {
 	.state_names = {
 		"preemptive",
 		"non_preemptive"
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.h b/kernel/trace/rv/monitors/wwnr/wwnr.h
index d1afe55cdd4c..118e576b91b4 100644
--- a/kernel/trace/rv/monitors/wwnr/wwnr.h
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.h
@@ -27,7 +27,7 @@ struct automaton_wwnr {
 	bool final_states[state_max_wwnr];
 };
 
-struct automaton_wwnr automaton_wwnr = {
+static struct automaton_wwnr automaton_wwnr = {
 	.state_names = {
 		"not_running",
 		"running"
diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c
index b698d05dd069..d65f6c25a87c 100644
--- a/kernel/trace/rv/reactor_panic.c
+++ b/kernel/trace/rv/reactor_panic.c
@@ -24,13 +24,13 @@ static struct rv_reactor rv_panic = {
 	.react = rv_panic_reaction
 };
 
-static int register_react_panic(void)
+static int __init register_react_panic(void)
 {
 	rv_register_reactor(&rv_panic);
 	return 0;
 }
 
-static void unregister_react_panic(void)
+static void __exit unregister_react_panic(void)
 {
 	rv_unregister_reactor(&rv_panic);
 }
diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c
index 31899f953af4..4b6b7106a477 100644
--- a/kernel/trace/rv/reactor_printk.c
+++ b/kernel/trace/rv/reactor_printk.c
@@ -23,13 +23,13 @@ static struct rv_reactor rv_printk = {
 	.react = rv_printk_reaction
 };
 
-static int register_react_printk(void)
+static int __init register_react_printk(void)
 {
 	rv_register_reactor(&rv_printk);
 	return 0;
 }
 
-static void unregister_react_printk(void)
+static void __exit unregister_react_printk(void)
 {
 	rv_unregister_reactor(&rv_printk);
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index cb866c3141af..918730d74932 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -142,7 +142,8 @@ static bool check_user_trigger(struct trace_event_file *file)
 {
 	struct event_trigger_data *data;
 
-	list_for_each_entry_rcu(data, &file->triggers, list) {
+	list_for_each_entry_rcu(data, &file->triggers, list,
+				lockdep_is_held(&event_mutex)) {
 		if (data->flags & EVENT_TRIGGER_FL_PROBE)
 			continue;
 		return true;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 95b58bd757ce..1e130da1b742 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -95,14 +95,14 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 	}
 
 	lockdep_hardirqs_on_prepare();
-	lockdep_hardirqs_on(CALLER_ADDR0);
+	lockdep_hardirqs_on(caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
-	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirqs_off(caller_addr);
 
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 64ea283f2f86..ef42c1a11920 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -571,7 +571,8 @@ static void for_each_tracepoint_range(
 bool trace_module_has_bad_taint(struct module *mod)
 {
 	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
-			       (1 << TAINT_UNSIGNED_MODULE));
+			       (1 << TAINT_UNSIGNED_MODULE) |
+			       (1 << TAINT_TEST));
 }
 
 static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list);
@@ -647,7 +648,7 @@ static int tracepoint_module_coming(struct module *mod)
 	/*
 	 * We skip modules that taint the kernel, especially those with different
 	 * module headers (for forced load), to make sure we don't cause a crash.
-	 * Staging, out-of-tree, and unsigned GPL modules are fine.
+	 * Staging, out-of-tree, unsigned GPL, and test modules are fine.
 	 */
 	if (trace_module_has_bad_taint(mod))
 		return 0;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index aeea9731ef80..39060a5d0905 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3066,10 +3066,8 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
 	if (WARN_ON(!work->func))
 		return false;
 
-	if (!from_cancel) {
-		lock_map_acquire(&work->lockdep_map);
-		lock_map_release(&work->lockdep_map);
-	}
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
 
 	if (start_flush_work(work, &barr, from_cancel)) {
 		wait_for_completion(&barr.done);