Merge branch 'sched/urgent' into sched/core, to resolve conflicts

This commit in sched/urgent moved the cfs_rq_is_decayed() function:

  a7b359fc6a37: ("sched/fair: Correctly insert cfs_rq's to list on unthrottle")

and this fresh commit in sched/core modified it in the old location:

  9e077b52d86a: ("sched/pelt: Check that *_avg are null when *_sum are")

Merge the two variants.

Conflicts:
	kernel/sched/fair.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 71 insertions, 68 deletions

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 73443498d88f..a2f1f15ce432 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -14,6 +14,7 @@
 #include <linux/jiffies.h>
 #include <linux/pid_namespace.h>
 #include <linux/proc_ns.h>
+#include <linux/security.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -1069,11 +1070,13 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_probe_read_user:
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
-		return &bpf_probe_read_kernel_proto;
+		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		       NULL : &bpf_probe_read_kernel_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
-		return &bpf_probe_read_kernel_str_proto;
+		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		       NULL : &bpf_probe_read_kernel_str_proto;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_snprintf:
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/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/sched/debug.c b/kernel/sched/debug.c
index 3bdee5fd7d29..0c5ec2776ddf 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 3af4afe2165b..5d1a6aace138 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3252,6 +3252,33 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->avg.runnable_sum)
+		return false;
+
+	/*
+	 * _avg must be null when _sum are null because _avg = _sum / divider
+	 * Make sure that rounding and/or propagation of PELT values never
+	 * break this.
+	 */
+	SCHED_WARN_ON(cfs_rq->avg.load_avg ||
+		      cfs_rq->avg.util_avg ||
+		      cfs_rq->avg.runnable_avg);
+
+	return true;
+}
+
 /**
  * update_tg_load_avg - update the tg's load avg
  * @cfs_rq: the cfs_rq whose avg changed
@@ -3864,7 +3891,7 @@ 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)
@@ -3964,7 +3991,7 @@ 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;
@@ -4013,6 +4040,7 @@ 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);
@@ -4047,6 +4075,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 
 #else /* CONFIG_SMP */
 
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	return true;
+}
+
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
 #define DO_ATTACH	0x0
@@ -4705,8 +4738,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 
-		/* Add cfs_rq with already running entity in the list */
-		if (cfs_rq->nr_running >= 1)
+		/* Add cfs_rq with load or one or more already running entities to the list */
+		if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
 			list_add_leaf_cfs_rq(cfs_rq);
 	}
 
@@ -8037,32 +8070,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
-	if (cfs_rq->load.weight)
-		return false;
-
-	if (cfs_rq->avg.load_sum)
-		return false;
-
-	if (cfs_rq->avg.util_sum)
-		return false;
-
-	if (cfs_rq->avg.runnable_sum)
-		return false;
-
-	/*
-	 * _avg must be null when _sum are null because _avg = _sum / divider
-	 * Make sure that rounding and/or propagation of PELT values never
-	 * break this.
-	 */
-	SCHED_WARN_ON(cfs_rq->avg.load_avg ||
-		      cfs_rq->avg.util_avg ||
-		      cfs_rq->avg.runnable_avg);
-
-	return true;
-}
-
 static bool __update_blocked_fair(struct rq *rq, bool *done)
 {
 	struct cfs_rq *cfs_rq, *pos;
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 9ed6d8c414ad..e06071bf3472 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/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d2d7cf6cfe83..7a52bc172841 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -215,16 +215,11 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
 static __always_inline int
 bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 {
-	int ret = security_locked_down(LOCKDOWN_BPF_READ);
+	int ret;
 
-	if (unlikely(ret < 0))
-		goto fail;
 	ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
-		goto fail;
-	return ret;
-fail:
-	memset(dst, 0, size);
+		memset(dst, 0, size);
 	return ret;
 }
 
@@ -246,10 +241,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_proto = {
 static __always_inline int
 bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
 {
-	int ret = security_locked_down(LOCKDOWN_BPF_READ);
-
-	if (unlikely(ret < 0))
-		goto fail;
+	int ret;
 
 	/*
 	 * The strncpy_from_kernel_nofault() call will likely not fill the
@@ -262,11 +254,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
 	 */
 	ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
-		goto fail;
-
-	return ret;
-fail:
-	memset(dst, 0, size);
+		memset(dst, 0, size);
 	return ret;
 }
 
@@ -1011,16 +999,20 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_probe_read_user:
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
-		return &bpf_probe_read_kernel_proto;
+		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		       NULL : &bpf_probe_read_kernel_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
-		return &bpf_probe_read_kernel_str_proto;
+		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		       NULL : &bpf_probe_read_kernel_str_proto;
 #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	case BPF_FUNC_probe_read:
-		return &bpf_probe_read_compat_proto;
+		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		       NULL : &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_str:
-		return &bpf_probe_read_compat_str_proto;
+		return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+		       NULL : &bpf_probe_read_compat_str_proto;
 #endif
 #ifdef CONFIG_CGROUPS
 	case BPF_FUNC_get_current_cgroup_id:
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..9299057feb56 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2736,7 +2736,7 @@ 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;