Merge branch 'for-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup into for-7.1

To receive 5b30afc20b3f ("cgroup: Expose some cgroup helpers") which will be
used by sub-sched support.

Signed-off-by: Tejun Heo <tj@kernel.org>

14 files changed, 129 insertions, 161 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 3bfe37693d68..58797123b752 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -184,11 +184,6 @@ extern bool cgrp_dfl_visible;
 	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT &&		\
 	     (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
 
-static inline bool cgroup_is_dead(const struct cgroup *cgrp)
-{
-	return !(cgrp->self.flags & CSS_ONLINE);
-}
-
 static inline bool notify_on_release(const struct cgroup *cgrp)
 {
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -222,7 +217,6 @@ static inline void get_css_set(struct css_set *cset)
 }
 
 bool cgroup_ssid_enabled(int ssid);
-bool cgroup_on_dfl(const struct cgroup *cgrp);
 
 struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root);
 struct cgroup *task_cgroup_from_root(struct task_struct *task,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index be1d71dda317..cdc63be63f2c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -69,14 +69,6 @@
 #define CGROUP_FILE_NOTIFY_MIN_INTV	DIV_ROUND_UP(HZ, 100)
 
 /*
- * To avoid confusing the compiler (and generating warnings) with code
- * that attempts to access what would be a 0-element array (i.e. sized
- * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this
- * constant expression can be added.
- */
-#define CGROUP_HAS_SUBSYS_CONFIG	(CGROUP_SUBSYS_COUNT > 0)
-
-/*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
  *
@@ -510,27 +502,6 @@ static u32 cgroup_ss_mask(struct cgroup *cgrp)
 }
 
 /**
- * cgroup_css - obtain a cgroup's css for the specified subsystem
- * @cgrp: the cgroup of interest
- * @ss: the subsystem of interest (%NULL returns @cgrp->self)
- *
- * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
- * function must be called either under cgroup_mutex or rcu_read_lock() and
- * the caller is responsible for pinning the returned css if it wants to
- * keep accessing it outside the said locks.  This function may return
- * %NULL if @cgrp doesn't have @subsys_id enabled.
- */
-static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
-					      struct cgroup_subsys *ss)
-{
-	if (CGROUP_HAS_SUBSYS_CONFIG && ss)
-		return rcu_dereference_check(cgrp->subsys[ss->id],
-					lockdep_is_held(&cgroup_mutex));
-	else
-		return &cgrp->self;
-}
-
-/**
  * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest (%NULL returns @cgrp->self)
@@ -741,32 +712,6 @@ EXPORT_SYMBOL_GPL(of_css);
 	}								\
 } while (false)
 
-/* iterate over child cgrps, lock should be held throughout iteration */
-#define cgroup_for_each_live_child(child, cgrp)				\
-	list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       cgroup_is_dead(child); }))			\
-			;						\
-		else
-
-/* walk live descendants in pre order */
-#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)		\
-	css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL))	\
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       (dsct) = (d_css)->cgroup;			\
-		       cgroup_is_dead(dsct); }))			\
-			;						\
-		else
-
-/* walk live descendants in postorder */
-#define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp)		\
-	css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL))	\
-		if (({ lockdep_assert_held(&cgroup_mutex);		\
-		       (dsct) = (d_css)->cgroup;			\
-		       cgroup_is_dead(dsct); }))			\
-			;						\
-		else
-
 /*
  * The default css_set - used by init and its children prior to any
  * hierarchies being mounted. It contains a pointer to the root state
diff --git a/kernel/exit.c b/kernel/exit.c
index 8a87021211ae..ede3117fa7d4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
+	struct kthread *kthread;
 	int group_dead;
 
 	WARN_ON(irqs_disabled());
 	WARN_ON(tsk->plug);
 
+	kthread = tsk_is_kthread(tsk);
+	if (unlikely(kthread))
+		kthread_do_exit(kthread, code);
+
 	kcov_task_exit(tsk);
 	kmsan_task_exit(tsk);
 
@@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code)
 	lockdep_free_task(tsk);
 	do_task_dead();
 }
+EXPORT_SYMBOL(do_exit);
 
 void __noreturn make_task_dead(int signr)
 {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 20451b624b67..791210daf8b4 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 	return k->worker_private;
 }
 
-/*
- * Variant of to_kthread() that doesn't assume @p is a kthread.
- *
- * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
- * always remain a kthread.  For kthreads p->worker_private always
- * points to a struct kthread.  For tasks that are not kthreads
- * p->worker_private is used to point to other things.
- *
- * Return NULL for any task that is not a kthread.
- */
-static inline struct kthread *__to_kthread(struct task_struct *p)
-{
-	void *kthread = p->worker_private;
-	if (kthread && !(p->flags & PF_KTHREAD))
-		kthread = NULL;
-	return kthread;
-}
-
 void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
 {
 	struct kthread *kthread = to_kthread(tsk);
@@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park);
 
 bool kthread_should_stop_or_park(void)
 {
-	struct kthread *kthread = __to_kthread(current);
+	struct kthread *kthread = tsk_is_kthread(current);
 
 	if (!kthread)
 		return false;
@@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
  */
 void *kthread_func(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	if (kthread)
 		return kthread->threadfn;
 	return NULL;
@@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data);
  */
 void *kthread_probe_data(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	void *data = NULL;
 
 	if (kthread)
@@ -309,19 +291,8 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
-/**
- * kthread_exit - Cause the current kthread return @result to kthread_stop().
- * @result: The integer value to return to kthread_stop().
- *
- * While kthread_exit can be called directly, it exists so that
- * functions which do some additional work in non-modular code such as
- * module_put_and_kthread_exit can be implemented.
- *
- * Does not return.
- */
-void __noreturn kthread_exit(long result)
+void kthread_do_exit(struct kthread *kthread, long result)
 {
-	struct kthread *kthread = to_kthread(current);
 	kthread->result = result;
 	if (!list_empty(&kthread->affinity_node)) {
 		mutex_lock(&kthread_affinity_lock);
@@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result)
 			kthread->preferred_affinity = NULL;
 		}
 	}
-	do_exit(0);
 }
-EXPORT_SYMBOL(kthread_exit);
 
 /**
  * kthread_complete_and_exit - Exit the current kthread.
@@ -683,7 +652,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
 
 bool kthread_is_per_cpu(struct task_struct *p)
 {
-	struct kthread *kthread = __to_kthread(p);
+	struct kthread *kthread = tsk_is_kthread(p);
 	if (!kthread)
 		return false;
 
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index be74917802ad..43b1bb01fd27 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -169,9 +169,10 @@ config MODVERSIONS
 	  make them incompatible with the kernel you are running.  If
 	  unsure, say N.
 
+if MODVERSIONS
+
 choice
 	prompt "Module versioning implementation"
-	depends on MODVERSIONS
 	help
 	  Select the tool used to calculate symbol versions for modules.
 
@@ -206,7 +207,7 @@ endchoice
 
 config ASM_MODVERSIONS
 	bool
-	default HAVE_ASM_MODVERSIONS && MODVERSIONS
+	default HAVE_ASM_MODVERSIONS
 	help
 	  This enables module versioning for exported symbols also from
 	  assembly. This can be enabled only when the target architecture
@@ -214,7 +215,6 @@ config ASM_MODVERSIONS
 
 config EXTENDED_MODVERSIONS
 	bool "Extended Module Versioning Support"
-	depends on MODVERSIONS
 	help
 	  This enables extended MODVERSIONs support, allowing long symbol
 	  names to be versioned.
@@ -224,7 +224,6 @@ config EXTENDED_MODVERSIONS
 
 config BASIC_MODVERSIONS
 	bool "Basic Module Versioning Support"
-	depends on MODVERSIONS
 	default y
 	help
 	  This enables basic MODVERSIONS support, allowing older tools or
@@ -237,6 +236,8 @@ config BASIC_MODVERSIONS
 	  This is enabled by default when MODVERSIONS are enabled.
 	  If unsure, say Y.
 
+endif # MODVERSIONS
+
 config MODULE_SRCVERSION_ALL
 	bool "Source checksum for all modules"
 	help
@@ -277,10 +278,11 @@ config MODULE_SIG_FORCE
 	  Reject unsigned modules or signed modules for which we don't have a
 	  key.  Without this, such modules will simply taint the kernel.
 
+if MODULE_SIG || IMA_APPRAISE_MODSIG
+
 config MODULE_SIG_ALL
 	bool "Automatically sign all modules"
 	default y
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	help
 	  Sign all modules during make modules_install. Without this option,
 	  modules must be signed manually, using the scripts/sign-file tool.
@@ -290,7 +292,6 @@ comment "Do not forget to sign required modules with scripts/sign-file"
 
 choice
 	prompt "Hash algorithm to sign modules"
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	default MODULE_SIG_SHA512
 	help
 	  This determines which sort of hashing algorithm will be used during
@@ -327,7 +328,6 @@ endchoice
 
 config MODULE_SIG_HASH
 	string
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	default "sha256" if MODULE_SIG_SHA256
 	default "sha384" if MODULE_SIG_SHA384
 	default "sha512" if MODULE_SIG_SHA512
@@ -335,6 +335,8 @@ config MODULE_SIG_HASH
 	default "sha3-384" if MODULE_SIG_SHA3_384
 	default "sha3-512" if MODULE_SIG_SHA3_512
 
+endif # MODULE_SIG || IMA_APPRAISE_MODSIG
+
 config MODULE_COMPRESS
 	bool "Module compression"
 	help
@@ -350,9 +352,10 @@ config MODULE_COMPRESS
 
 	  If unsure, say N.
 
+if MODULE_COMPRESS
+
 choice
 	prompt "Module compression type"
-	depends on MODULE_COMPRESS
 	help
 	  Choose the supported algorithm for module compression.
 
@@ -379,7 +382,6 @@ endchoice
 config MODULE_COMPRESS_ALL
 	bool "Automatically compress all modules"
 	default y
-	depends on MODULE_COMPRESS
 	help
 	  Compress all modules during 'make modules_install'.
 
@@ -389,7 +391,6 @@ config MODULE_COMPRESS_ALL
 
 config MODULE_DECOMPRESS
 	bool "Support in-kernel module decompression"
-	depends on MODULE_COMPRESS
 	select ZLIB_INFLATE if MODULE_COMPRESS_GZIP
 	select XZ_DEC if MODULE_COMPRESS_XZ
 	select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD
@@ -400,6 +401,8 @@ config MODULE_DECOMPRESS
 
 	  If unsure, say N.
 
+endif # MODULE_COMPRESS
+
 config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS
 	bool "Allow loading of modules with missing namespace imports"
 	help
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 2bac4c7cd019..c3ce106c70af 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1568,6 +1568,13 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
 			break;
 
 		default:
+			if (sym[i].st_shndx >= info->hdr->e_shnum) {
+				pr_err("%s: Symbol %s has an invalid section index %u (max %u)\n",
+				       mod->name, name, sym[i].st_shndx, info->hdr->e_shnum - 1);
+				ret = -ENOEXEC;
+				break;
+			}
+
 			/* Divert to percpu allocation if a percpu var. */
 			if (sym[i].st_shndx == info->index.pcpu)
 				secbase = (unsigned long)mod_percpu(mod);
@@ -3544,12 +3551,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_unlock(&module_mutex);
  free_module:
 	mod_stat_bump_invalid(info, flags);
-	/* Free lock-classes; relies on the preceding sync_rcu() */
-	for_class_mod_mem_type(type, core_data) {
-		lockdep_free_key_range(mod->mem[type].base,
-				       mod->mem[type].size);
-	}
-
 	module_memory_restore_rox(mod);
 	module_deallocate(mod, info);
  free_copy:
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index bdc3c86231d3..3166c1fd844a 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns)
 			return;
 	}
 }
+
+bool may_see_all_namespaces(void)
+{
+	return (task_active_pid_ns(current) == &init_pid_ns) &&
+	       ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN);
+}
diff --git a/kernel/nstree.c b/kernel/nstree.c
index f36c59e6951d..6d12e5900ac0 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls,
 static inline bool __must_check may_list_ns(const struct klistns *kls,
 					    struct ns_common *ns)
 {
-	if (kls->user_ns) {
-		if (kls->userns_capable)
-			return true;
-	} else {
-		struct ns_common *owner;
-		struct user_namespace *user_ns;
-
-		owner = ns_owner(ns);
-		if (owner)
-			user_ns = to_user_ns(owner);
-		else
-			user_ns = &init_user_ns;
-		if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN))
-			return true;
-	}
-
-	if (is_current_namespace(ns))
+	if (kls->user_ns && kls->userns_capable)
 		return true;
-
-	if (ns->ns_type != CLONE_NEWUSER)
-		return false;
-
-	if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN))
+	if (is_current_namespace(ns))
 		return true;
-
-	return false;
+	return may_see_all_namespaces();
 }
 
 static inline void ns_put(struct ns_common *ns)
@@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls)
 
 	ret = 0;
 	head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head;
-	kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN);
+	kls->userns_capable = may_see_all_namespaces();
 
 	rcu_read_lock();
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a5c7d15fce72..9daf8c5d9687 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies);
 int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ)
-		return -EINVAL;
 	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
 				  do_proc_int_conv_userhz_jiffies);
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 827fb9a0bf0d..2f72af0357e5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8611,6 +8611,7 @@ ftrace_pid_follow_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
@@ -8624,6 +8625,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f16f053ef77d..17d0ea0cc3e6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	return err;
 }
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask)))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	guard(mutex)(&cpu_buffer->mapping_lock);
+
+	if (cpu_buffer->user_mapped)
+		__rb_inc_dec_mapped(cpu_buffer, true);
+	else
+		WARN(1, "Unexpected buffer stat, it should be mapped");
+}
+
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23de3719f495..1e7c032a72d2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
 static inline void put_snapshot_map(struct trace_array *tr) { }
 #endif
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file);
+}
+
 static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
 {
 	struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a
 }
 
 static const struct vm_operations_struct tracing_buffers_vmops = {
+	.open		= tracing_buffers_mmap_open,
 	.close		= tracing_buffers_mmap_close,
 	.may_split      = tracing_buffers_may_split,
 };
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9928da636c9d..b7343fdfd7b0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_raw(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
@@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
@@ -4668,26 +4670,22 @@ static __init int event_trace_memsetup(void)
 	return 0;
 }
 
-__init void
-early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+/*
+ * Helper function to enable or disable a comma-separated list of events
+ * from the bootup buffer.
+ */
+static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable)
 {
 	char *token;
-	int ret;
-
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
 
+	while ((token = strsep(&buf, ","))) {
 		if (*token) {
-			/* Restarting syscalls requires that we stop them first */
-			if (disable_first)
+			if (enable) {
+				if (ftrace_set_clr_event(tr, token, 1))
+					pr_warn("Failed to enable trace event: %s\n", token);
+			} else {
 				ftrace_set_clr_event(tr, token, 0);
-
-			ret = ftrace_set_clr_event(tr, token, 1);
-			if (ret)
-				pr_warn("Failed to enable trace event: %s\n", token);
+			}
 		}
 
 		/* Put back the comma to allow this to be called again */
@@ -4696,6 +4694,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
 	}
 }
 
+/**
+ * early_enable_events - enable events from the bootup buffer
+ * @tr: The trace array to enable the events in
+ * @buf: The buffer containing the comma separated list of events
+ * @disable_first: If true, disable all events in @buf before enabling them
+ *
+ * This function enables events from the bootup buffer. If @disable_first
+ * is true, it will first disable all events in the buffer before enabling
+ * them.
+ *
+ * For syscall events, which rely on a global refcount to register the
+ * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must
+ * ensure the refcount hits zero before re-enabling them. A simple
+ * "disable then enable" per-event is not enough if multiple syscalls are
+ * used, as the refcount will stay above zero. Thus, we need a two-phase
+ * approach: disable all, then enable all.
+ */
+__init void
+early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+{
+	if (disable_first)
+		__early_set_events(tr, buf, false);
+
+	__early_set_events(tr, buf, true);
+}
+
 static __init int event_trace_enable(void)
 {
 	struct trace_array *tr = top_trace_array();
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3d8239fee004..0d2d3a2ea7dd 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -400,14 +400,19 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops,
 				      struct ftrace_regs *fregs)
 {
+	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
+	unsigned int trace_ctx;
+	u64 calltime, rettime;
 	int size;
 
+	rettime = trace_clock_local();
+
 	ftrace_graph_addr_finish(gops, trace);
 
-	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
-		trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+	if (*task_var & TRACE_GRAPH_NOTRACE) {
+		*task_var &= ~TRACE_GRAPH_NOTRACE;
 		return;
 	}
 
@@ -418,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	tr = gops->private;
 	handle_nosleeptime(tr, trace, ftimes, size);
 
-	if (tracing_thresh &&
-	    (trace_clock_local() - ftimes->calltime < tracing_thresh))
+	calltime = ftimes->calltime;
+
+	if (tracing_thresh && (rettime - calltime < tracing_thresh))
 		return;
-	else
-		trace_graph_return(trace, gops, fregs);
+
+	trace_ctx = tracing_gen_ctx();
+	__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 }
 
 static struct fgraph_ops funcgraph_ops = {