Merge 6.13-rc7 into driver-core-next

We need the debugfs / driver-core fixes in here as well for testing and
to build on top of.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

22 files changed, 422 insertions, 351 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f7f892a52a37..77f56674aaa9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21281,11 +21281,15 @@ patch_map_ops_generic:
 			 * changed in some incompatible and hard to support
 			 * way, it's fine to back out this inlining logic
 			 */
+#ifdef CONFIG_SMP
 			insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
 			insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
 			insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
 			cnt = 3;
-
+#else
+			insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0);
+			cnt = 1;
+#endif
 			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
 			if (!new_prog)
 				return -ENOMEM;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index f321ed515f3a..0f910c828973 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -197,10 +197,8 @@ static struct cpuset top_cpuset = {
 
 /*
  * There are two global locks guarding cpuset structures - cpuset_mutex and
- * callback_lock. We also require taking task_lock() when dereferencing a
- * task's cpuset pointer. See "The task_lock() exception", at the end of this
- * comment.  The cpuset code uses only cpuset_mutex. Other kernel subsystems
- * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
+ * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel
+ * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
  * structures. Note that cpuset_mutex needs to be a mutex as it is used in
  * paths that rely on priority inheritance (e.g. scheduler - on RT) for
  * correctness.
@@ -229,9 +227,6 @@ static struct cpuset top_cpuset = {
  * The cpuset_common_seq_show() handlers only hold callback_lock across
  * small pieces of code, such as when reading out possibly multi-word
  * cpumasks and nodemasks.
- *
- * Accessing a task's cpuset should be done in accordance with the
- * guidelines for accessing subsystem state in kernel/cgroup.c
  */
 
 static DEFINE_MUTEX(cpuset_mutex);
@@ -890,7 +885,15 @@ v2:
 	 */
 	if (cgrpv2) {
 		for (i = 0; i < ndoms; i++) {
-			cpumask_copy(doms[i], csa[i]->effective_cpus);
+			/*
+			 * The top cpuset may contain some boot time isolated
+			 * CPUs that need to be excluded from the sched domain.
+			 */
+			if (csa[i] == &top_cpuset)
+				cpumask_and(doms[i], csa[i]->effective_cpus,
+					    housekeeping_cpumask(HK_TYPE_DOMAIN));
+			else
+				cpumask_copy(doms[i], csa[i]->effective_cpus);
 			if (dattr)
 				dattr[i] = SD_ATTR_INIT;
 		}
@@ -3121,29 +3124,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	int retval = -ENODEV;
 
 	buf = strstrip(buf);
-
-	/*
-	 * CPU or memory hotunplug may leave @cs w/o any execution
-	 * resources, in which case the hotplug code asynchronously updates
-	 * configuration and transfers all tasks to the nearest ancestor
-	 * which can execute.
-	 *
-	 * As writes to "cpus" or "mems" may restore @cs's execution
-	 * resources, wait for the previously scheduled operations before
-	 * proceeding, so that we don't end up keep removing tasks added
-	 * after execution capability is restored.
-	 *
-	 * cpuset_handle_hotplug may call back into cgroup core asynchronously
-	 * via cgroup_transfer_tasks() and waiting for it from a cgroupfs
-	 * operation like this one can lead to a deadlock through kernfs
-	 * active_ref protection.  Let's break the protection.  Losing the
-	 * protection is okay as we check whether @cs is online after
-	 * grabbing cpuset_mutex anyway.  This only happens on the legacy
-	 * hierarchies.
-	 */
-	css_get(&cs->css);
-	kernfs_break_active_protection(of->kn);
-
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
@@ -3176,8 +3156,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
-	kernfs_unbreak_active_protection(of->kn);
-	css_put(&cs->css);
 	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index fa04b14a7d72..5d71ef85420c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1915,6 +1915,7 @@ void uprobe_free_utask(struct task_struct *t)
 	if (!utask)
 		return;
 
+	t->utask = NULL;
 	WARN_ON_ONCE(utask->active_uprobe || utask->xol_vaddr);
 
 	timer_delete_sync(&utask->ri_timer);
@@ -1924,7 +1925,6 @@ void uprobe_free_utask(struct task_struct *t)
 		ri = free_ret_instance(ri, true /* cleanup_hprobe */);
 
 	kfree(utask);
-	t->utask = NULL;
 }
 
 #define RI_TIMER_PERIOD (HZ / 10) /* 100 ms */
diff --git a/kernel/fork.c b/kernel/fork.c
index 1450b461d196..9b301180fd41 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -639,11 +639,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	LIST_HEAD(uf);
 	VMA_ITERATOR(vmi, mm, 0);
 
-	uprobe_start_dup_mmap();
-	if (mmap_write_lock_killable(oldmm)) {
-		retval = -EINTR;
-		goto fail_uprobe_end;
-	}
+	if (mmap_write_lock_killable(oldmm))
+		return -EINTR;
 	flush_cache_dup_mm(oldmm);
 	uprobe_dup_mmap(oldmm, mm);
 	/*
@@ -782,8 +779,6 @@ out:
 		dup_userfaultfd_complete(&uf);
 	else
 		dup_userfaultfd_fail(&uf);
-fail_uprobe_end:
-	uprobe_end_dup_mmap();
 	return retval;
 
 fail_nomem_anon_vma_fork:
@@ -1692,9 +1687,11 @@ 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;
@@ -1709,6 +1706,8 @@ free_pt:
 	mm->binfmt = NULL;
 	mm_init_owner(mm, NULL);
 	mmput(mm);
+	if (err)
+		uprobe_end_dup_mmap();
 
 fail_nomem:
 	return NULL;
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 383fd43ac612..7e1340da5aca 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -89,6 +89,7 @@ find $cpio_dir -type f -print0 |
 
 # Create archive and try to normalize metadata for reproducibility.
 tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+    --exclude=".__afs*" --exclude=".nfs*" \
     --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \
     -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null
 
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 28a6be6e64fd..187ba1b80bda 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -166,7 +166,7 @@ static void kcov_remote_area_put(struct kcov_remote_area *area,
  * Unlike in_serving_softirq(), this function returns false when called during
  * a hardirq or an NMI that happened in the softirq context.
  */
-static inline bool in_softirq_really(void)
+static __always_inline bool in_softirq_really(void)
 {
 	return in_serving_softirq() && !in_hardirq() && !in_nmi();
 }
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index e858de203eb6..697a56d3d949 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1292,7 +1292,13 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 	 */
 	get_task_struct(owner);
 
+	preempt_disable();
 	raw_spin_unlock_irq(&lock->wait_lock);
+	/* wake up any tasks on the wake_q before calling rt_mutex_adjust_prio_chain */
+	wake_up_q(wake_q);
+	wake_q_init(wake_q);
+	preempt_enable();
+
 
 	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
@@ -1596,6 +1602,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
  *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
+ * @wake_q:		 wake_q of tasks to wake when we drop the lock->wait_lock
  *
  * Must be called with lock->wait_lock held and interrupts disabled
  */
@@ -1603,7 +1610,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 					   struct ww_acquire_ctx *ww_ctx,
 					   unsigned int state,
 					   struct hrtimer_sleeper *timeout,
-					   struct rt_mutex_waiter *waiter)
+					   struct rt_mutex_waiter *waiter,
+					   struct wake_q_head *wake_q)
 	__releases(&lock->wait_lock) __acquires(&lock->wait_lock)
 {
 	struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex);
@@ -1634,7 +1642,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
 			owner = rt_mutex_owner(lock);
 		else
 			owner = NULL;
+		preempt_disable();
 		raw_spin_unlock_irq(&lock->wait_lock);
+		if (wake_q) {
+			wake_up_q(wake_q);
+			wake_q_init(wake_q);
+		}
+		preempt_enable();
 
 		if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner))
 			rt_mutex_schedule();
@@ -1708,7 +1722,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q);
 	if (likely(!ret))
-		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter);
+		ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q);
 
 	if (likely(!ret)) {
 		/* acquired the lock */
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index 33ea31d6a7b3..191e4720e546 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter);
+	ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 7fff1d045477..19813b387ef9 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2747,6 +2747,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 {
 	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
 	bool prev_on_scx = prev->sched_class == &ext_sched_class;
+	bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED;
 	int nr_loops = SCX_DSP_MAX_LOOPS;
 
 	lockdep_assert_rq_held(rq);
@@ -2779,8 +2780,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		 * See scx_ops_disable_workfn() for the explanation on the
 		 * bypassing test.
 		 */
-		if ((prev->scx.flags & SCX_TASK_QUEUED) &&
-		    prev->scx.slice && !scx_rq_bypassing(rq)) {
+		if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) {
 			rq->scx.flags |= SCX_RQ_BAL_KEEP;
 			goto has_tasks;
 		}
@@ -2813,6 +2813,10 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 
 		flush_dispatch_buf(rq);
 
+		if (prev_on_rq && prev->scx.slice) {
+			rq->scx.flags |= SCX_RQ_BAL_KEEP;
+			goto has_tasks;
+		}
 		if (rq->scx.local_dsq.nr)
 			goto has_tasks;
 		if (consume_global_dsq(rq))
@@ -2838,8 +2842,7 @@ no_tasks:
 	 * Didn't find another task to run. Keep running @prev unless
 	 * %SCX_OPS_ENQ_LAST is in effect.
 	 */
-	if ((prev->scx.flags & SCX_TASK_QUEUED) &&
-	    (!static_branch_unlikely(&scx_ops_enq_last) ||
+	if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) ||
 	     scx_rq_bypassing(rq))) {
 		rq->scx.flags |= SCX_RQ_BAL_KEEP;
 		goto has_tasks;
@@ -3034,7 +3037,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		 */
 		if (p->scx.slice && !scx_rq_bypassing(rq)) {
 			dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
-			return;
+			goto switch_class;
 		}
 
 		/*
@@ -3051,6 +3054,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		}
 	}
 
+switch_class:
 	if (next && next->sched_class != &ext_sched_class)
 		switch_class(rq, next);
 }
@@ -3586,16 +3590,8 @@ static void reset_idle_masks(void)
 	cpumask_copy(idle_masks.smt, cpu_online_mask);
 }
 
-void __scx_update_idle(struct rq *rq, bool idle)
+static void update_builtin_idle(int cpu, bool idle)
 {
-	int cpu = cpu_of(rq);
-
-	if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) {
-		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
-		if (!static_branch_unlikely(&scx_builtin_idle_enabled))
-			return;
-	}
-
 	if (idle)
 		cpumask_set_cpu(cpu, idle_masks.cpu);
 	else
@@ -3622,6 +3618,57 @@ void __scx_update_idle(struct rq *rq, bool idle)
 #endif
 }
 
+/*
+ * Update the idle state of a CPU to @idle.
+ *
+ * If @do_notify is true, ops.update_idle() is invoked to notify the scx
+ * scheduler of an actual idle state transition (idle to busy or vice
+ * versa). If @do_notify is false, only the idle state in the idle masks is
+ * refreshed without invoking ops.update_idle().
+ *
+ * This distinction is necessary, because an idle CPU can be "reserved" and
+ * awakened via scx_bpf_pick_idle_cpu() + scx_bpf_kick_cpu(), marking it as
+ * busy even if no tasks are dispatched. In this case, the CPU may return
+ * to idle without a true state transition. Refreshing the idle masks
+ * without invoking ops.update_idle() ensures accurate idle state tracking
+ * while avoiding unnecessary updates and maintaining balanced state
+ * transitions.
+ */
+void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
+{
+	int cpu = cpu_of(rq);
+
+	lockdep_assert_rq_held(rq);
+
+	/*
+	 * Trigger ops.update_idle() only when transitioning from a task to
+	 * the idle thread and vice versa.
+	 *
+	 * Idle transitions are indicated by do_notify being set to true,
+	 * managed by put_prev_task_idle()/set_next_task_idle().
+	 */
+	if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq))
+		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
+
+	/*
+	 * Update the idle masks:
+	 * - for real idle transitions (do_notify == true)
+	 * - for idle-to-idle transitions (indicated by the previous task
+	 *   being the idle thread, managed by pick_task_idle())
+	 *
+	 * Skip updating idle masks if the previous task is not the idle
+	 * thread, since set_next_task_idle() has already handled it when
+	 * transitioning from a task to the idle thread (calling this
+	 * function with do_notify == true).
+	 *
+	 * In this way we can avoid updating the idle masks twice,
+	 * unnecessarily.
+	 */
+	if (static_branch_likely(&scx_builtin_idle_enabled))
+		if (do_notify || is_idle_task(rq->curr))
+			update_builtin_idle(cpu, idle);
+}
+
 static void handle_hotplug(struct rq *rq, bool online)
 {
 	int cpu = cpu_of(rq);
@@ -4744,10 +4791,9 @@ static void scx_ops_bypass(bool bypass)
 	 */
 	for_each_possible_cpu(cpu) {
 		struct rq *rq = cpu_rq(cpu);
-		struct rq_flags rf;
 		struct task_struct *p, *n;
 
-		rq_lock(rq, &rf);
+		raw_spin_rq_lock(rq);
 
 		if (bypass) {
 			WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING);
@@ -4763,7 +4809,7 @@ static void scx_ops_bypass(bool bypass)
 		 * sees scx_rq_bypassing() before moving tasks to SCX.
 		 */
 		if (!scx_enabled()) {
-			rq_unlock_irqrestore(rq, &rf);
+			raw_spin_rq_unlock(rq);
 			continue;
 		}
 
@@ -4783,10 +4829,11 @@ static void scx_ops_bypass(bool bypass)
 			sched_enq_and_set_task(&ctx);
 		}
 
-		rq_unlock(rq, &rf);
-
 		/* resched to restore ticks and idle state */
-		resched_cpu(cpu);
+		if (cpu_online(cpu) || cpu == smp_processor_id())
+			resched_curr(rq);
+
+		raw_spin_rq_unlock(rq);
 	}
 
 	atomic_dec(&scx_ops_breather_depth);
@@ -7013,7 +7060,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
 		return -ENOENT;
 
 	INIT_LIST_HEAD(&kit->cursor.node);
-	kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags;
+	kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags;
 	kit->cursor.priv = READ_ONCE(kit->dsq->seq);
 
 	return 0;
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index b1675bb59fc4..4d022d17ac7d 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -57,15 +57,15 @@ static inline void init_sched_ext_class(void) {}
 #endif	/* CONFIG_SCHED_CLASS_EXT */
 
 #if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP)
-void __scx_update_idle(struct rq *rq, bool idle);
+void __scx_update_idle(struct rq *rq, bool idle, bool do_notify);
 
-static inline void scx_update_idle(struct rq *rq, bool idle)
+static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify)
 {
 	if (scx_enabled())
-		__scx_update_idle(rq, idle);
+		__scx_update_idle(rq, idle, do_notify);
 }
 #else
-static inline void scx_update_idle(struct rq *rq, bool idle) {}
+static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
 #endif
 
 #ifdef CONFIG_CGROUP_SCHED
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 621696269584..2c85c86b455f 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -452,19 +452,20 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
 	dl_server_update_idle_time(rq, prev);
-	scx_update_idle(rq, false);
+	scx_update_idle(rq, false, true);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
-	scx_update_idle(rq, true);
+	scx_update_idle(rq, true, true);
 	schedstat_inc(rq->sched_goidle);
 	next->se.exec_start = rq_clock_task(rq);
 }
 
 struct task_struct *pick_task_idle(struct rq *rq)
 {
+	scx_update_idle(rq, true, false);
 	return rq->idle;
 }
 
diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c
index 5259cda486d0..bb7d066a7c39 100644
--- a/kernel/static_call_inline.c
+++ b/kernel/static_call_inline.c
@@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[],
 extern struct static_call_tramp_key __start_static_call_tramp_key[],
 				    __stop_static_call_tramp_key[];
 
-static int static_call_initialized;
+int static_call_initialized;
 
 /*
  * Must be called before early_initcall() to be effective.
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 0bf78517b5d4..30e3ddc8a8a8 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -833,7 +833,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 #endif
 	{
 		for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) {
-			struct fgraph_ops *gops = fgraph_array[i];
+			struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]);
 
 			if (gops == &fgraph_stub)
 				continue;
@@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void)
 static int start_graph_tracing(void)
 {
 	unsigned long **ret_stack_list;
-	int ret;
+	int ret, cpu;
 
 	ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
 				 sizeof(*ret_stack_list), GFP_KERNEL);
@@ -1223,6 +1223,12 @@ static int start_graph_tracing(void)
 	if (!ret_stack_list)
 		return -ENOMEM;
 
+	/* The cpu_boot init_task->ret_stack will never be freed */
+	for_each_online_cpu(cpu) {
+		if (!idle_task(cpu)->ret_stack)
+			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
+	}
+
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9b17efb1a87d..2e113f8b13a2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -902,16 +902,13 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 }
 
 static struct fgraph_ops fprofiler_ops = {
-	.ops = {
-		.flags = FTRACE_OPS_FL_INITIALIZED,
-		INIT_OPS_HASH(fprofiler_ops.ops)
-	},
 	.entryfunc = &profile_graph_entry,
 	.retfunc = &profile_graph_return,
 };
 
 static int register_ftrace_profiler(void)
 {
+	ftrace_ops_set_global_filter(&fprofiler_ops.ops);
 	return register_ftrace_graph(&fprofiler_ops);
 }
 
@@ -922,12 +919,11 @@ static void unregister_ftrace_profiler(void)
 #else
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
-	.flags		= FTRACE_OPS_FL_INITIALIZED,
-	INIT_OPS_HASH(ftrace_profile_ops)
 };
 
 static int register_ftrace_profiler(void)
 {
+	ftrace_ops_set_global_filter(&ftrace_profile_ops);
 	return register_ftrace_function(&ftrace_profile_ops);
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7e257e855dd1..60210fb5b211 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 	lockdep_assert_held(&cpu_buffer->mapping_lock);
 
 	nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */
-	nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */
+	nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */
+	if (nr_pages <= pgoff)
+		return -EINVAL;
+
+	nr_pages -= pgoff;
 
 	nr_vma_pages = vma_pages(vma);
 	if (!nr_vma_pages || nr_vma_pages > nr_pages)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index be62f0ea1814..f8aebcb01e62 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter)
 }
 
 /* Returns true if the string is safe to dereference from an event */
-static bool trace_safe_str(struct trace_iterator *iter, const char *str,
-			   bool star, int len)
+static bool trace_safe_str(struct trace_iterator *iter, const char *str)
 {
 	unsigned long addr = (unsigned long)str;
 	struct trace_event *trace_event;
 	struct trace_event_call *event;
 
-	/* Ignore strings with no length */
-	if (star && !len)
-		return true;
-
 	/* OK if part of the event data */
 	if ((addr >= (unsigned long)iter->ent) &&
 	    (addr < (unsigned long)iter->ent + iter->ent_size))
@@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
 	return false;
 }
 
-static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
-
-static int test_can_verify_check(const char *fmt, ...)
-{
-	char buf[16];
-	va_list ap;
-	int ret;
-
-	/*
-	 * The verifier is dependent on vsnprintf() modifies the va_list
-	 * passed to it, where it is sent as a reference. Some architectures
-	 * (like x86_32) passes it by value, which means that vsnprintf()
-	 * does not modify the va_list passed to it, and the verifier
-	 * would then need to be able to understand all the values that
-	 * vsnprintf can use. If it is passed by value, then the verifier
-	 * is disabled.
-	 */
-	va_start(ap, fmt);
-	vsnprintf(buf, 16, "%d", ap);
-	ret = va_arg(ap, int);
-	va_end(ap);
-
-	return ret;
-}
-
-static void test_can_verify(void)
-{
-	if (!test_can_verify_check("%d %d", 0, 1)) {
-		pr_info("trace event string verifier disabled\n");
-		static_branch_inc(&trace_no_verify);
-	}
-}
-
 /**
- * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer
+ * ignore_event - Check dereferenced fields while writing to the seq buffer
  * @iter: The iterator that holds the seq buffer and the event being printed
- * @fmt: The format used to print the event
- * @ap: The va_list holding the data to print from @fmt.
  *
- * This writes the data into the @iter->seq buffer using the data from
- * @fmt and @ap. If the format has a %s, then the source of the string
- * is examined to make sure it is safe to print, otherwise it will
- * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string
- * pointer.
+ * At boot up, test_event_printk() will flag any event that dereferences
+ * a string with "%s" that does exist in the ring buffer. It may still
+ * be valid, as the string may point to a static string in the kernel
+ * rodata that never gets freed. But if the string pointer is pointing
+ * to something that was allocated, there's a chance that it can be freed
+ * by the time the user reads the trace. This would cause a bad memory
+ * access by the kernel and possibly crash the system.
+ *
+ * This function will check if the event has any fields flagged as needing
+ * to be checked at runtime and perform those checks.
+ *
+ * If it is found that a field is unsafe, it will write into the @iter->seq
+ * a message stating what was found to be unsafe.
+ *
+ * @return: true if the event is unsafe and should be ignored,
+ *          false otherwise.
  */
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
-			 va_list ap)
+bool ignore_event(struct trace_iterator *iter)
 {
-	long text_delta = 0;
-	long data_delta = 0;
-	const char *p = fmt;
-	const char *str;
-	bool good;
-	int i, j;
+	struct ftrace_event_field *field;
+	struct trace_event *trace_event;
+	struct trace_event_call *event;
+	struct list_head *head;
+	struct trace_seq *seq;
+	const void *ptr;
 
-	if (WARN_ON_ONCE(!fmt))
-		return;
+	trace_event = ftrace_find_event(iter->ent->type);
 
-	if (static_branch_unlikely(&trace_no_verify))
-		goto print;
+	seq = &iter->seq;
 
-	/*
-	 * When the kernel is booted with the tp_printk command line
-	 * parameter, trace events go directly through to printk().
-	 * It also is checked by this function, but it does not
-	 * have an associated trace_array (tr) for it.
-	 */
-	if (iter->tr) {
-		text_delta = iter->tr->text_delta;
-		data_delta = iter->tr->data_delta;
+	if (!trace_event) {
+		trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type);
+		return true;
 	}
 
-	/* Don't bother checking when doing a ftrace_dump() */
-	if (iter->fmt == static_fmt_buf)
-		goto print;
-
-	while (*p) {
-		bool star = false;
-		int len = 0;
-
-		j = 0;
-
-		/*
-		 * We only care about %s and variants
-		 * as well as %p[sS] if delta is non-zero
-		 */
-		for (i = 0; p[i]; i++) {
-			if (i + 1 >= iter->fmt_size) {
-				/*
-				 * If we can't expand the copy buffer,
-				 * just print it.
-				 */
-				if (!trace_iter_expand_format(iter))
-					goto print;
-			}
-
-			if (p[i] == '\\' && p[i+1]) {
-				i++;
-				continue;
-			}
-			if (p[i] == '%') {
-				/* Need to test cases like %08.*s */
-				for (j = 1; p[i+j]; j++) {
-					if (isdigit(p[i+j]) ||
-					    p[i+j] == '.')
-						continue;
-					if (p[i+j] == '*') {
-						star = true;
-						continue;
-					}
-					break;
-				}
-				if (p[i+j] == 's')
-					break;
-
-				if (text_delta && p[i+1] == 'p' &&
-				    ((p[i+2] == 's' || p[i+2] == 'S')))
-					break;
-
-				star = false;
-			}
-			j = 0;
-		}
-		/* If no %s found then just print normally */
-		if (!p[i])
-			break;
-
-		/* Copy up to the %s, and print that */
-		strncpy(iter->fmt, p, i);
-		iter->fmt[i] = '\0';
-		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+	event = container_of(trace_event, struct trace_event_call, event);
+	if (!(event->flags & TRACE_EVENT_FL_TEST_STR))
+		return false;
 
-		/* Add delta to %pS pointers */
-		if (p[i+1] == 'p') {
-			unsigned long addr;
-			char fmt[4];
+	head = trace_get_fields(event);
+	if (!head) {
+		trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n",
+				 trace_event_name(event));
+		return true;
+	}
 
-			fmt[0] = '%';
-			fmt[1] = 'p';
-			fmt[2] = p[i+2]; /* Either %ps or %pS */
-			fmt[3] = '\0';
+	/* Offsets are from the iter->ent that points to the raw event */
+	ptr = iter->ent;
 
-			addr = va_arg(ap, unsigned long);
-			addr += text_delta;
-			trace_seq_printf(&iter->seq, fmt, (void *)addr);
+	list_for_each_entry(field, head, link) {
+		const char *str;
+		bool good;
 
-			p += i + 3;
+		if (!field->needs_test)
 			continue;
-		}
-
-		/*
-		 * If iter->seq is full, the above call no longer guarantees
-		 * that ap is in sync with fmt processing, and further calls
-		 * to va_arg() can return wrong positional arguments.
-		 *
-		 * Ensure that ap is no longer used in this case.
-		 */
-		if (iter->seq.full) {
-			p = "";
-			break;
-		}
 
-		if (star)
-			len = va_arg(ap, int);
+		str = *(const char **)(ptr + field->offset);
 
-		/* The ap now points to the string data of the %s */
-		str = va_arg(ap, const char *);
-
-		good = trace_safe_str(iter, str, star, len);
-
-		/* Could be from the last boot */
-		if (data_delta && !good) {
-			str += data_delta;
-			good = trace_safe_str(iter, str, star, len);
-		}
+		good = trace_safe_str(iter, str);
 
 		/*
 		 * If you hit this warning, it is likely that the
@@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		 * instead. See samples/trace_events/trace-events-sample.h
 		 * for reference.
 		 */
-		if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'",
-			      fmt, seq_buf_str(&iter->seq.seq))) {
-			int ret;
-
-			/* Try to safely read the string */
-			if (star) {
-				if (len + 1 > iter->fmt_size)
-					len = iter->fmt_size - 1;
-				if (len < 0)
-					len = 0;
-				ret = copy_from_kernel_nofault(iter->fmt, str, len);
-				iter->fmt[len] = 0;
-				star = false;
-			} else {
-				ret = strncpy_from_kernel_nofault(iter->fmt, str,
-								  iter->fmt_size);
-			}
-			if (ret < 0)
-				trace_seq_printf(&iter->seq, "(0x%px)", str);
-			else
-				trace_seq_printf(&iter->seq, "(0x%px:%s)",
-						 str, iter->fmt);
-			str = "[UNSAFE-MEMORY]";
-			strcpy(iter->fmt, "%s");
-		} else {
-			strncpy(iter->fmt, p + i, j + 1);
-			iter->fmt[j+1] = '\0';
+		if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'",
+			      trace_event_name(event), field->name)) {
+			trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n",
+					 trace_event_name(event), field->name);
+			return true;
 		}
-		if (star)
-			trace_seq_printf(&iter->seq, iter->fmt, len, str);
-		else
-			trace_seq_printf(&iter->seq, iter->fmt, str);
-
-		p += i + j + 1;
 	}
- print:
-	if (*p)
-		trace_seq_vprintf(&iter->seq, p, ap);
+	return false;
 }
 
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
@@ -4353,6 +4206,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 	if (event) {
 		if (tr->trace_flags & TRACE_ITER_FIELDS)
 			return print_event_fields(iter, event);
+		/*
+		 * For TRACE_EVENT() events, the print_fmt is not
+		 * safe to use if the array has delta offsets
+		 * Force printing via the fields.
+		 */
+		if ((tr->text_delta || tr->data_delta) &&
+		    event->type > __TRACE_LAST_TYPE)
+			return print_event_fields(iter, event);
+
 		return event->funcs->trace(iter, sym_flags, event);
 	}
 
@@ -5225,6 +5087,9 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	cpumask_var_t tracing_cpumask_new;
 	int err;
 
+	if (count == 0 || count > KMALLOC_MAX_SIZE)
+		return -EINVAL;
+
 	if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -10777,8 +10642,6 @@ __init static int tracer_alloc_buffers(void)
 
 	register_snapshot_cmd();
 
-	test_can_verify();
-
 	return 0;
 
 out_free_pipe_cpumask:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 266740b4e121..9691b47b5f3d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 
 bool trace_is_tracepoint_string(const char *str);
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
-			 va_list ap) __printf(2, 0);
 char *trace_iter_expand_format(struct trace_iterator *iter);
+bool ignore_event(struct trace_iterator *iter);
 
 int trace_empty(struct trace_iterator *iter);
 
@@ -1413,7 +1412,8 @@ struct ftrace_event_field {
 	int			filter_type;
 	int			offset;
 	int			size;
-	int			is_signed;
+	unsigned int		is_signed:1;
+	unsigned int		needs_test:1;
 	int			len;
 };
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 77e68efbd43e..770e7ed91716 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system)
 	}
 
 static struct ftrace_event_field *
-__find_event_field(struct list_head *head, char *name)
+__find_event_field(struct list_head *head, const char *name)
 {
 	struct ftrace_event_field *field;
 
@@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 
 static int __trace_define_field(struct list_head *head, const char *type,
 				const char *name, int offset, int size,
-				int is_signed, int filter_type, int len)
+				int is_signed, int filter_type, int len,
+				int need_test)
 {
 	struct ftrace_event_field *field;
 
@@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
 	field->offset = offset;
 	field->size = size;
 	field->is_signed = is_signed;
+	field->needs_test = need_test;
 	field->len = len;
 
 	list_add(&field->link, head);
@@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type,
 
 	head = trace_get_fields(call);
 	return __trace_define_field(head, type, name, offset, size,
-				    is_signed, filter_type, 0);
+				    is_signed, filter_type, 0, 0);
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
 static int trace_define_field_ext(struct trace_event_call *call, const char *type,
 		       const char *name, int offset, int size, int is_signed,
-		       int filter_type, int len)
+		       int filter_type, int len, int need_test)
 {
 	struct list_head *head;
 
@@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
 
 	head = trace_get_fields(call);
 	return __trace_define_field(head, type, name, offset, size,
-				    is_signed, filter_type, len);
+				    is_signed, filter_type, len, need_test);
 }
 
 #define __generic_field(type, item, filter_type)			\
 	ret = __trace_define_field(&ftrace_generic_fields, #type,	\
 				   #item, 0, 0, is_signed_type(type),	\
-				   filter_type, 0);			\
+				   filter_type, 0, 0);			\
 	if (ret)							\
 		return ret;
 
@@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
 				   "common_" #item,			\
 				   offsetof(typeof(ent), item),		\
 				   sizeof(ent.item),			\
-				   is_signed_type(type), FILTER_OTHER, 0);	\
+				   is_signed_type(type), FILTER_OTHER,	\
+				   0, 0);				\
 	if (ret)							\
 		return ret;
 
@@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call)
 	return tail->offset + tail->size;
 }
 
-/*
- * Check if the referenced field is an array and return true,
- * as arrays are OK to dereference.
- */
-static bool test_field(const char *fmt, struct trace_event_call *call)
+
+static struct trace_event_fields *find_event_field(const char *fmt,
+						   struct trace_event_call *call)
 {
 	struct trace_event_fields *field = call->class->fields_array;
-	const char *array_descriptor;
 	const char *p = fmt;
 	int len;
 
 	if (!(len = str_has_prefix(fmt, "REC->")))
-		return false;
+		return NULL;
 	fmt += len;
 	for (p = fmt; *p; p++) {
 		if (!isalnum(*p) && *p != '_')
@@ -265,16 +265,141 @@ static bool test_field(const char *fmt, struct trace_event_call *call)
 	len = p - fmt;
 
 	for (; field->type; field++) {
-		if (strncmp(field->name, fmt, len) ||
-		    field->name[len])
+		if (strncmp(field->name, fmt, len) || field->name[len])
 			continue;
-		array_descriptor = strchr(field->type, '[');
-		/* This is an array and is OK to dereference. */
-		return array_descriptor != NULL;
+
+		return field;
+	}
+	return NULL;
+}
+
+/*
+ * Check if the referenced field is an array and return true,
+ * as arrays are OK to dereference.
+ */
+static bool test_field(const char *fmt, struct trace_event_call *call)
+{
+	struct trace_event_fields *field;
+
+	field = find_event_field(fmt, call);
+	if (!field)
+		return false;
+
+	/* This is an array and is OK to dereference. */
+	return strchr(field->type, '[') != NULL;
+}
+
+/* Look for a string within an argument */
+static bool find_print_string(const char *arg, const char *str, const char *end)
+{
+	const char *r;
+
+	r = strstr(arg, str);
+	return r && r < end;
+}
+
+/* Return true if the argument pointer is safe */
+static bool process_pointer(const char *fmt, int len, struct trace_event_call *call)
+{
+	const char *r, *e, *a;
+
+	e = fmt + len;
+
+	/* Find the REC-> in the argument */
+	r = strstr(fmt, "REC->");
+	if (r && r < e) {
+		/*
+		 * Addresses of events on the buffer, or an array on the buffer is
+		 * OK to dereference. There's ways to fool this, but
+		 * this is to catch common mistakes, not malicious code.
+		 */
+		a = strchr(fmt, '&');
+		if ((a && (a < r)) || test_field(r, call))
+			return true;
+	} else if (find_print_string(fmt, "__get_dynamic_array(", e)) {
+		return true;
+	} else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) {
+		return true;
+	} else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) {
+		return true;
+	} else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) {
+		return true;
+	} else if (find_print_string(fmt, "__get_sockaddr(", e)) {
+		return true;
+	} else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) {
+		return true;
 	}
 	return false;
 }
 
+/* Return true if the string is safe */
+static bool process_string(const char *fmt, int len, struct trace_event_call *call)
+{
+	struct trace_event_fields *field;
+	const char *r, *e, *s;
+
+	e = fmt + len;
+
+	/*
+	 * There are several helper functions that return strings.
+	 * If the argument contains a function, then assume its field is valid.
+	 * It is considered that the argument has a function if it has:
+	 *   alphanumeric or '_' before a parenthesis.
+	 */
+	s = fmt;
+	do {
+		r = strstr(s, "(");
+		if (!r || r >= e)
+			break;
+		for (int i = 1; r - i >= s; i++) {
+			char ch = *(r - i);
+			if (isspace(ch))
+				continue;
+			if (isalnum(ch) || ch == '_')
+				return true;
+			/* Anything else, this isn't a function */
+			break;
+		}
+		/* A function could be wrapped in parethesis, try the next one */
+		s = r + 1;
+	} while (s < e);
+
+	/*
+	 * Check for arrays. If the argument has: foo[REC->val]
+	 * then it is very likely that foo is an array of strings
+	 * that are safe to use.
+	 */
+	r = strstr(s, "[");
+	if (r && r < e) {
+		r = strstr(r, "REC->");
+		if (r && r < e)
+			return true;
+	}
+
+	/*
+	 * If there's any strings in the argument consider this arg OK as it
+	 * could be: REC->field ? "foo" : "bar" and we don't want to get into
+	 * verifying that logic here.
+	 */
+	if (find_print_string(fmt, "\"", e))
+		return true;
+
+	/* Dereferenced strings are also valid like any other pointer */
+	if (process_pointer(fmt, len, call))
+		return true;
+
+	/* Make sure the field is found */
+	field = find_event_field(fmt, call);
+	if (!field)
+		return false;
+
+	/* Test this field's string before printing the event */
+	call->flags |= TRACE_EVENT_FL_TEST_STR;
+	field->needs_test = 1;
+
+	return true;
+}
+
 /*
  * Examine the print fmt of the event looking for unsafe dereference
  * pointers using %p* that could be recorded in the trace event and
@@ -284,13 +409,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call)
 static void test_event_printk(struct trace_event_call *call)
 {
 	u64 dereference_flags = 0;
+	u64 string_flags = 0;
 	bool first = true;
-	const char *fmt, *c, *r, *a;
+	const char *fmt;
 	int parens = 0;
 	char in_quote = 0;
 	int start_arg = 0;
 	int arg = 0;
-	int i;
+	int i, e;
 
 	fmt = call->print_fmt;
 
@@ -374,8 +500,16 @@ static void test_event_printk(struct trace_event_call *call)
 						star = true;
 						continue;
 					}
-					if ((fmt[i + j] == 's') && star)
-						arg++;
+					if ((fmt[i + j] == 's')) {
+						if (star)
+							arg++;
+						if (WARN_ONCE(arg == 63,
+							      "Too many args for event: %s",
+							      trace_event_name(call)))
+							return;
+						dereference_flags |= 1ULL << arg;
+						string_flags |= 1ULL << arg;
+					}
 					break;
 				}
 				break;
@@ -403,42 +537,47 @@ static void test_event_printk(struct trace_event_call *call)
 		case ',':
 			if (in_quote || parens)
 				continue;
+			e = i;
 			i++;
 			while (isspace(fmt[i]))
 				i++;
-			start_arg = i;
-			if (!(dereference_flags & (1ULL << arg)))
-				goto next_arg;
 
-			/* Find the REC-> in the argument */
-			c = strchr(fmt + i, ',');
-			r = strstr(fmt + i, "REC->");
-			if (r && (!c || r < c)) {
-				/*
-				 * Addresses of events on the buffer,
-				 * or an array on the buffer is
-				 * OK to dereference.
-				 * There's ways to fool this, but
-				 * this is to catch common mistakes,
-				 * not malicious code.
-				 */
-				a = strchr(fmt + i, '&');
-				if ((a && (a < r)) || test_field(r, call))
+			/*
+			 * If start_arg is zero, then this is the start of the
+			 * first argument. The processing of the argument happens
+			 * when the end of the argument is found, as it needs to
+			 * handle paranthesis and such.
+			 */
+			if (!start_arg) {
+				start_arg = i;
+				/* Balance out the i++ in the for loop */
+				i--;
+				continue;
+			}
+
+			if (dereference_flags & (1ULL << arg)) {
+				if (string_flags & (1ULL << arg)) {
+					if (process_string(fmt + start_arg, e - start_arg, call))
+						dereference_flags &= ~(1ULL << arg);
+				} else if (process_pointer(fmt + start_arg, e - start_arg, call))
 					dereference_flags &= ~(1ULL << arg);
-			} else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
-				   (!c || r < c)) {
-				dereference_flags &= ~(1ULL << arg);
-			} else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
-				   (!c || r < c)) {
-				dereference_flags &= ~(1ULL << arg);
 			}
 
-		next_arg:
-			i--;
+			start_arg = i;
 			arg++;
+			/* Balance out the i++ in the for loop */
+			i--;
 		}
 	}
 
+	if (dereference_flags & (1ULL << arg)) {
+		if (string_flags & (1ULL << arg)) {
+			if (process_string(fmt + start_arg, i - start_arg, call))
+				dereference_flags &= ~(1ULL << arg);
+		} else if (process_pointer(fmt + start_arg, i - start_arg, call))
+			dereference_flags &= ~(1ULL << arg);
+	}
+
 	/*
 	 * If you triggered the below warning, the trace event reported
 	 * uses an unsafe dereference pointer %p*. As the data stored
@@ -2471,7 +2610,7 @@ event_define_fields(struct trace_event_call *call)
 			ret = trace_define_field_ext(call, field->type, field->name,
 						 offset, field->size,
 						 field->is_signed, field->filter_type,
-						 field->len);
+						 field->len, field->needs_test);
 			if (WARN_ON_ONCE(ret)) {
 				pr_err("error code is %d\n", ret);
 				break;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 74c353164ca1..d358c9935164 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr)
 	tracing_reset_online_cpus(&tr->array_buffer);
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
 static __always_inline unsigned long
 function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs)
 {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 263fac44d3ca..0642ea174849 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -725,7 +725,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
 
 static struct notifier_block trace_kprobe_module_nb = {
 	.notifier_call = trace_kprobe_module_callback,
-	.priority = 1	/* Invoked after kprobe module callback */
+	.priority = 2	/* Invoked after kprobe and jump_label module callback */
 };
 static int trace_kprobe_register_module_notifier(void)
 {
@@ -940,8 +940,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		}
 		/* a symbol specified */
 		symbol = kstrdup(argv[1], GFP_KERNEL);
-		if (!symbol)
-			return -ENOMEM;
+		if (!symbol) {
+			ret = -ENOMEM;
+			goto error;
+		}
 
 		tmp = strchr(symbol, '%');
 		if (tmp) {
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index da748b7cbc4d..03d56f711ad1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep);
 
 void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...)
 {
+	struct trace_seq *s = &iter->seq;
 	va_list ap;
 
+	if (ignore_event(iter))
+		return;
+
 	va_start(ap, fmt);
-	trace_check_vprintf(iter, trace_event_format(iter, fmt), ap);
+	trace_seq_vprintf(s, trace_event_format(iter, fmt), ap);
 	va_end(ap);
 }
 EXPORT_SYMBOL(trace_event_printf);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8b07576814a5..9362484a653c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2508,6 +2508,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 		return;
 	}
 
+	WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu));
 	dwork->wq = wq;
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
@@ -2533,6 +2534,12 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
  * @dwork: work to queue
  * @delay: number of jiffies to wait before queueing
  *
+ * We queue the delayed_work to a specific CPU, for non-zero delays the
+ * caller must ensure it is online and can't go away. Callers that fail
+ * to ensure this, may get @dwork->timer queued to an offlined CPU and
+ * this will prevent queueing of @dwork->work unless the offlined CPU
+ * becomes online again.
+ *
  * Return: %false if @work was already on a queue, %true otherwise.  If
  * @delay is zero and @dwork is idle, it will be scheduled for immediate
  * execution.
@@ -3680,23 +3687,27 @@ void workqueue_softirq_dead(unsigned int cpu)
  * check_flush_dependency - check for flush dependency sanity
  * @target_wq: workqueue being flushed
  * @target_work: work item being flushed (NULL for workqueue flushes)
+ * @from_cancel: are we called from the work cancel path
  *
  * %current is trying to flush the whole @target_wq or @target_work on it.
- * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not
- * reclaiming memory or running on a workqueue which doesn't have
- * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to
- * a deadlock.
+ * If this is not the cancel path (which implies work being flushed is either
+ * already running, or will not be at all), check if @target_wq doesn't have
+ * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running
+ * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward-
+ * progress guarantee leading to a deadlock.
  */
 static void check_flush_dependency(struct workqueue_struct *target_wq,
-				   struct work_struct *target_work)
+				   struct work_struct *target_work,
+				   bool from_cancel)
 {
-	work_func_t target_func = target_work ? target_work->func : NULL;
+	work_func_t target_func;
 	struct worker *worker;
 
-	if (target_wq->flags & WQ_MEM_RECLAIM)
+	if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM)
 		return;
 
 	worker = current_wq_worker();
+	target_func = target_work ? target_work->func : NULL;
 
 	WARN_ONCE(current->flags & PF_MEMALLOC,
 		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps",
@@ -3980,7 +3991,7 @@ void __flush_workqueue(struct workqueue_struct *wq)
 		list_add_tail(&this_flusher.list, &wq->flusher_overflow);
 	}
 
-	check_flush_dependency(wq, NULL);
+	check_flush_dependency(wq, NULL, false);
 
 	mutex_unlock(&wq->mutex);
 
@@ -4155,7 +4166,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	}
 
 	wq = pwq->wq;
-	check_flush_dependency(wq, work);
+	check_flush_dependency(wq, work, from_cancel);
 
 	insert_wq_barrier(pwq, barr, work, worker);
 	raw_spin_unlock_irq(&pool->lock);
@@ -5641,6 +5652,7 @@ static void wq_adjust_max_active(struct workqueue_struct *wq)
 	} while (activated);
 }
 
+__printf(1, 0)
 static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 						  unsigned int flags,
 						  int max_active, va_list args)