16 files changed, 120 insertions, 66 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b7d51fc937c7..e04e33893cff 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6485,6 +6485,27 @@ struct bpf_sanitize_info {
 	bool mask_to_left;
 };
 
+static struct bpf_verifier_state *
+sanitize_speculative_path(struct bpf_verifier_env *env,
+			  const struct bpf_insn *insn,
+			  u32 next_idx, u32 curr_idx)
+{
+	struct bpf_verifier_state *branch;
+	struct bpf_reg_state *regs;
+
+	branch = push_stack(env, next_idx, curr_idx, true);
+	if (branch && insn) {
+		regs = branch->frame[branch->curframe]->regs;
+		if (BPF_SRC(insn->code) == BPF_K) {
+			mark_reg_unknown(env, regs, insn->dst_reg);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			mark_reg_unknown(env, regs, insn->dst_reg);
+			mark_reg_unknown(env, regs, insn->src_reg);
+		}
+	}
+	return branch;
+}
+
 static int sanitize_ptr_alu(struct bpf_verifier_env *env,
 			    struct bpf_insn *insn,
 			    const struct bpf_reg_state *ptr_reg,
@@ -6568,12 +6589,26 @@ do_sim:
 		tmp = *dst_reg;
 		*dst_reg = *ptr_reg;
 	}
-	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
+	ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
+					env->insn_idx);
 	if (!ptr_is_dst_reg && ret)
 		*dst_reg = tmp;
 	return !ret ? REASON_STACK : 0;
 }
 
+static void sanitize_mark_insn_seen(struct bpf_verifier_env *env)
+{
+	struct bpf_verifier_state *vstate = env->cur_state;
+
+	/* If we simulate paths under speculation, we don't update the
+	 * insn as 'seen' such that when we verify unreachable paths in
+	 * the non-speculative domain, sanitize_dead_code() can still
+	 * rewrite/sanitize them.
+	 */
+	if (!vstate->speculative)
+		env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
+}
+
 static int sanitize_err(struct bpf_verifier_env *env,
 			const struct bpf_insn *insn, int reason,
 			const struct bpf_reg_state *off_reg,
@@ -8752,14 +8787,28 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		if (err)
 			return err;
 	}
+
 	if (pred == 1) {
-		/* only follow the goto, ignore fall-through */
+		/* Only follow the goto, ignore fall-through. If needed, push
+		 * the fall-through branch for simulation under speculative
+		 * execution.
+		 */
+		if (!env->bypass_spec_v1 &&
+		    !sanitize_speculative_path(env, insn, *insn_idx + 1,
+					       *insn_idx))
+			return -EFAULT;
 		*insn_idx += insn->off;
 		return 0;
 	} else if (pred == 0) {
-		/* only follow fall-through branch, since
-		 * that's where the program will go
+		/* Only follow the fall-through branch, since that's where the
+		 * program will go. If needed, push the goto branch for
+		 * simulation under speculative execution.
 		 */
+		if (!env->bypass_spec_v1 &&
+		    !sanitize_speculative_path(env, insn,
+					       *insn_idx + insn->off + 1,
+					       *insn_idx))
+			return -EFAULT;
 		return 0;
 	}
 
@@ -10621,7 +10670,7 @@ static int do_check(struct bpf_verifier_env *env)
 		}
 
 		regs = cur_regs(env);
-		env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
+		sanitize_mark_insn_seen(env);
 		prev_insn_idx = env->insn_idx;
 
 		if (class == BPF_ALU || class == BPF_ALU64) {
@@ -10848,7 +10897,7 @@ process_bpf_exit:
 					return err;
 
 				env->insn_idx++;
-				env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
+				sanitize_mark_insn_seen(env);
 			} else {
 				verbose(env, "invalid BPF_LD mode\n");
 				return -EINVAL;
@@ -11381,6 +11430,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env,
 {
 	struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
 	struct bpf_insn *insn = new_prog->insnsi;
+	u32 old_seen = old_data[off].seen;
 	u32 prog_len;
 	int i;
 
@@ -11401,7 +11451,8 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env,
 	memcpy(new_data + off + cnt - 1, old_data + off,
 	       sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
 	for (i = off; i < off + cnt - 1; i++) {
-		new_data[i].seen = env->pass_cnt;
+		/* Expand insni[off]'s seen count to the patched range. */
+		new_data[i].seen = old_seen;
 		new_data[i].zext_dst = insn_has_def32(env, insn + i);
 	}
 	env->insn_aux_data = new_data;
@@ -12725,6 +12776,9 @@ static void free_states(struct bpf_verifier_env *env)
  * insn_aux_data was touched. These variables are compared to clear temporary
  * data from failed pass. For testing and experiments do_check_common() can be
  * run multiple times even when prior attempt to verify is unsuccessful.
+ *
+ * Note that special handling is needed on !env->bypass_spec_v1 if this is
+ * ever called outside of error path with subsequent program rejection.
  */
 static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
 {
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 8190b6bfc978..1f274d7fc934 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -820,6 +820,10 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent
 	struct cgroup *cgrp = kn->priv;
 	int ret;
 
+	/* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */
+	if (strchr(new_name_str, '\n'))
+		return -EINVAL;
+
 	if (kernfs_type(kn) != KERNFS_DIR)
 		return -ENOTDIR;
 	if (kn->parent != new_parent)
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 825284baaf46..684a6061a13a 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -464,6 +464,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
 	VMCOREINFO_STRUCT_SIZE(mem_section);
 	VMCOREINFO_OFFSET(mem_section, section_mem_map);
+	VMCOREINFO_NUMBER(SECTION_SIZE_BITS);
 	VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
 #endif
 	VMCOREINFO_STRUCT_SIZE(page);
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index a0b3b04fb596..bf16395b9e13 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -5,6 +5,7 @@
 #include <linux/highmem.h>
 #include <linux/livepatch.h>
 #include <linux/audit.h>
+#include <linux/tick.h>
 
 #include "common.h"
 
@@ -186,7 +187,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		local_irq_disable_exit_to_user();
 
 		/* Check if any of the above work has queued a deferred wakeup */
-		rcu_nocb_flush_deferred_wakeup();
+		tick_nohz_user_enter_prepare();
 
 		ti_work = READ_ONCE(current_thread_info()->flags);
 	}
@@ -202,7 +203,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 	lockdep_assert_irqs_disabled();
 
 	/* Flush pending rcuog wakeup before the last need_resched() check */
-	rcu_nocb_flush_deferred_wakeup();
+	tick_nohz_user_enter_prepare();
 
 	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
 		ti_work = exit_to_user_mode_loop(regs, ti_work);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6fee4a7e88d7..fe88d6eea3c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4609,7 +4609,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
+		raw_spin_lock_irqsave(&ctx->lock, flags);
 		++ctx->pin_count;
+		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 
 		return ctx;
 	}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 23a7a0ba1388..db8c248ebc8c 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -70,9 +70,6 @@ bool irq_work_queue(struct irq_work *work)
 	if (!irq_work_claim(work))
 		return false;
 
-	/*record irq_work call stack in order to print it in KASAN reports*/
-	kasan_record_aux_stack(work);
-
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 	__irq_work_queue_local(work);
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 7a1414622051..94232186fccb 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -391,6 +391,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	/* No obstacles. */
 	return vprintk_default(fmt, args);
 }
+EXPORT_SYMBOL(vprintk);
 
 void __init printk_safe_init(void)
 {
@@ -411,4 +412,3 @@ void __init printk_safe_init(void)
 	/* Flush pending messages that did not have scheduled IRQ works. */
 	printk_safe_flush();
 }
-EXPORT_SYMBOL(vprintk);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5226cc26a095..4ca80df205ce 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6389,7 +6389,6 @@ int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, false, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
 
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9c882f20803e..c5aacbd492a1 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -885,6 +885,7 @@ static const struct seq_operations sched_debug_sops = {
 #define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F))
 #define __P(F) __PS(#F, F)
 #define   P(F) __PS(#F, p->F)
+#define   PM(F, M) __PS(#F, p->F & (M))
 #define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F)))
 #define __PN(F) __PSN(#F, F)
 #define   PN(F) __PSN(#F, p->F)
@@ -1011,7 +1012,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 	P(se.avg.util_est.ewma);
-	P(se.avg.util_est.enqueued);
+	PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
 #endif
 #ifdef CONFIG_UCLAMP_TASK
 	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3248e24a90b0..2c8a9352590d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3499,10 +3499,9 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 static inline void
 update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
-	long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
+	long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
 	unsigned long load_avg;
 	u64 load_sum = 0;
-	s64 delta_sum;
 	u32 divider;
 
 	if (!runnable_sum)
@@ -3549,13 +3548,13 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	load_sum = (s64)se_weight(se) * runnable_sum;
 	load_avg = div_s64(load_sum, divider);
 
-	delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
-	delta_avg = load_avg - se->avg.load_avg;
+	delta = load_avg - se->avg.load_avg;
 
 	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
-	add_positive(&cfs_rq->avg.load_avg, delta_avg);
-	add_positive(&cfs_rq->avg.load_sum, delta_sum);
+
+	add_positive(&cfs_rq->avg.load_avg, delta);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider;
 }
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
@@ -3766,11 +3765,17 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
  */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	u32 divider = get_pelt_divider(&cfs_rq->avg);
+
 	dequeue_load_avg(cfs_rq, se);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
-	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider;
 	sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
-	sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
+	cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;
 
 	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 
@@ -3902,7 +3907,7 @@ static inline unsigned long _task_util_est(struct task_struct *p)
 {
 	struct util_est ue = READ_ONCE(p->se.avg.util_est);
 
-	return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED);
+	return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -4002,7 +4007,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	 * Reset EWMA on utilization increases, the moving average is used only
 	 * to smooth utilization decreases.
 	 */
-	ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED);
+	ue.enqueued = task_util(p);
 	if (sched_feat(UTIL_EST_FASTUP)) {
 		if (ue.ewma < ue.enqueued) {
 			ue.ewma = ue.enqueued;
@@ -4051,6 +4056,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	ue.ewma  += last_ewma_diff;
 	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
 done:
+	ue.enqueued |= UTIL_AVG_UNCHANGED;
 	WRITE_ONCE(p->se.avg.util_est, ue);
 
 	trace_sched_util_est_se_tp(&p->se);
@@ -8030,7 +8036,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done)
 		/* Propagate pending load changes to the parent, if any: */
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
-			update_load_avg(cfs_rq_of(se), se, 0);
+			update_load_avg(cfs_rq_of(se), se, UPDATE_TG);
 
 		/*
 		 * There can be a lot of idle CPU cgroups.  Don't let fully
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 1462846d244e..cfe94ffd2b38 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -42,15 +42,6 @@ static inline u32 get_pelt_divider(struct sched_avg *avg)
 	return LOAD_AVG_MAX - 1024 + avg->period_contrib;
 }
 
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
 static inline void cfs_se_util_change(struct sched_avg *avg)
 {
 	unsigned int enqueued;
@@ -58,7 +49,7 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/* Avoid store if the flag has been already set */
+	/* Avoid store if the flag has been already reset */
 	enqueued = avg->util_est.enqueued;
 	if (!(enqueued & UTIL_AVG_UNCHANGED))
 		return;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 6ecd3f3a52b5..9f58049ac16d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1105,28 +1105,30 @@ static int seccomp_do_user_notification(int this_syscall,
 
 	up(&match->notif->request);
 	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
-	mutex_unlock(&match->notify_lock);
 
 	/*
 	 * This is where we wait for a reply from userspace.
 	 */
-wait:
-	err = wait_for_completion_interruptible(&n.ready);
-	mutex_lock(&match->notify_lock);
-	if (err == 0) {
-		/* Check if we were woken up by a addfd message */
+	do {
+		mutex_unlock(&match->notify_lock);
+		err = wait_for_completion_interruptible(&n.ready);
+		mutex_lock(&match->notify_lock);
+		if (err != 0)
+			goto interrupted;
+
 		addfd = list_first_entry_or_null(&n.addfd,
 						 struct seccomp_kaddfd, list);
-		if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) {
+		/* Check if we were woken up by a addfd message */
+		if (addfd)
 			seccomp_handle_addfd(addfd);
-			mutex_unlock(&match->notify_lock);
-			goto wait;
-		}
-		ret = n.val;
-		err = n.error;
-		flags = n.flags;
-	}
 
+	}  while (n.state != SECCOMP_NOTIFY_REPLIED);
+
+	ret = n.val;
+	err = n.error;
+	flags = n.flags;
+
+interrupted:
 	/* If there were any pending addfd calls, clear them out */
 	list_for_each_entry_safe(addfd, tmp, &n.addfd, list) {
 		/* The process went away before we got a chance to handle it */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 828b091501ca..6784f27a3099 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -230,6 +230,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
+EXPORT_SYMBOL_GPL(tick_nohz_full_mask);
 bool tick_nohz_full_running;
 EXPORT_SYMBOL_GPL(tick_nohz_full_running);
 static atomic_t tick_dep_mask;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2e8a3fde7104..72ef4dccbcc4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1967,12 +1967,18 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
 
 static void print_ip_ins(const char *fmt, const unsigned char *p)
 {
+	char ins[MCOUNT_INSN_SIZE];
 	int i;
 
+	if (copy_from_kernel_nofault(ins, p, MCOUNT_INSN_SIZE)) {
+		printk(KERN_CONT "%s[FAULT] %px\n", fmt, p);
+		return;
+	}
+
 	printk(KERN_CONT "%s", fmt);
 
 	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
-		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
+		printk(KERN_CONT "%s%02x", i ? ":" : "", ins[i]);
 }
 
 enum ftrace_bug_type ftrace_bug_type;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a21ef9cd2aae..d23a09d3eb37 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2198,9 +2198,6 @@ struct saved_cmdlines_buffer {
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
-/* temporary disable recording */
-static atomic_t trace_record_taskinfo_disabled __read_mostly;
-
 static inline char *get_saved_cmdlines(int idx)
 {
 	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
@@ -2486,8 +2483,6 @@ static bool tracing_record_taskinfo_skip(int flags)
 {
 	if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
 		return true;
-	if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on())
-		return true;
 	if (!__this_cpu_read(trace_taskinfo_save))
 		return true;
 	return false;
@@ -2736,7 +2731,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 	    (entry = this_cpu_read(trace_buffered_event))) {
 		/* Try to use the per cpu buffer first */
 		val = this_cpu_inc_return(trace_buffered_event_cnt);
-		if ((len < (PAGE_SIZE - sizeof(*entry))) && val == 1) {
+		if ((len < (PAGE_SIZE - sizeof(*entry) - sizeof(entry->array[0]))) && val == 1) {
 			trace_event_setup(entry, type, trace_ctx);
 			entry->array[0] = len;
 			return entry;
@@ -3998,9 +3993,6 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		return ERR_PTR(-EBUSY);
 #endif
 
-	if (!iter->snapshot)
-		atomic_inc(&trace_record_taskinfo_disabled);
-
 	if (*pos != iter->pos) {
 		iter->ent = NULL;
 		iter->cpu = 0;
@@ -4043,9 +4035,6 @@ static void s_stop(struct seq_file *m, void *p)
 		return;
 #endif
 
-	if (!iter->snapshot)
-		atomic_dec(&trace_record_taskinfo_disabled);
-
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index c1637f90c8a3..4702efb00ff2 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -115,9 +115,9 @@ u64 notrace trace_clock_global(void)
 	prev_time = READ_ONCE(trace_clock_struct.prev_time);
 	now = sched_clock_cpu(this_cpu);
 
-	/* Make sure that now is always greater than prev_time */
+	/* Make sure that now is always greater than or equal to prev_time */
 	if ((s64)(now - prev_time) < 0)
-		now = prev_time + 1;
+		now = prev_time;
 
 	/*
 	 * If in an NMI context then dont risk lockups and simply return
@@ -131,7 +131,7 @@ u64 notrace trace_clock_global(void)
 		/* Reread prev_time in case it was already updated */
 		prev_time = READ_ONCE(trace_clock_struct.prev_time);
 		if ((s64)(now - prev_time) < 0)
-			now = prev_time + 1;
+			now = prev_time;
 
 		trace_clock_struct.prev_time = now;