16 files changed, 153 insertions, 63 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e16dafeb2450..3e23b3fa79ff 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5688,7 +5688,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			}
 			if (check_ptr_off_reg(env, reg, regno))
 				return -EINVAL;
-		} else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) {
+		} else if (is_kfunc && (reg->type == PTR_TO_BTF_ID ||
+			   (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) {
 			const struct btf_type *reg_ref_t;
 			const struct btf *reg_btf;
 			const char *reg_ref_tname;
@@ -5706,7 +5707,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 				reg_ref_id = reg->btf_id;
 			} else {
 				reg_btf = btf_vmlinux;
-				reg_ref_id = *reg2btf_ids[reg->type];
+				reg_ref_id = *reg2btf_ids[base_type(reg->type)];
 			}
 
 			reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id,
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 01cfdf40c838..55c084251fab 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  */
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/rcupdate.h>
 #include <linux/random.h>
@@ -1075,6 +1076,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 	void *key;
 	u32 idx;
 
+	BTF_TYPE_EMIT(struct bpf_timer);
 	callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held());
 	if (!callback_fn)
 		goto out;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fa4505f9b611..ca70fe6fba38 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1355,6 +1355,7 @@ int generic_map_delete_batch(struct bpf_map *map,
 		maybe_wait_bpf_programs(map);
 		if (err)
 			break;
+		cond_resched();
 	}
 	if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
 		err = -EFAULT;
@@ -1412,6 +1413,7 @@ int generic_map_update_batch(struct bpf_map *map,
 
 		if (err)
 			break;
+		cond_resched();
 	}
 
 	if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
@@ -1509,6 +1511,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
 		swap(prev_key, key);
 		retry = MAP_LOOKUP_RETRIES;
 		cp++;
+		cond_resched();
 	}
 
 	if (err == -EFAULT)
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 0e877dbcfeea..afc6c0e9c966 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -546,6 +546,7 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes, loff_t off)
 {
 	struct cgroup *cgrp;
+	struct cgroup_file_ctx *ctx;
 
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
 
@@ -553,8 +554,9 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 	 * Release agent gets called with all capabilities,
 	 * require capabilities to set release agent.
 	 */
-	if ((of->file->f_cred->user_ns != &init_user_ns) ||
-	    !capable(CAP_SYS_ADMIN))
+	ctx = of->priv;
+	if ((ctx->ns->user_ns != &init_user_ns) ||
+	    !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9d05c3ca2d5e..a557eea7166f 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6166,6 +6166,20 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
 	if (ret)
 		goto err;
 
+	/*
+	 * Spawning a task directly into a cgroup works by passing a file
+	 * descriptor to the target cgroup directory. This can even be an O_PATH
+	 * file descriptor. But it can never be a cgroup.procs file descriptor.
+	 * This was done on purpose so spawning into a cgroup could be
+	 * conceptualized as an atomic
+	 *
+	 *   fd = openat(dfd_cgroup, "cgroup.procs", ...);
+	 *   write(fd, <child-pid>, ...);
+	 *
+	 * sequence, i.e. it's a shorthand for the caller opening and writing
+	 * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us
+	 * to always use the caller's credentials.
+	 */
 	ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
 					!(kargs->flags & CLONE_THREAD),
 					current->nsproxy->cgroup_ns);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4c7254e8f49a..5de18448016c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2289,6 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
+	cpus_read_lock();
 	percpu_down_write(&cpuset_rwsem);
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@@ -2342,6 +2343,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 		wake_up(&cpuset_attach_wq);
 
 	percpu_up_write(&cpuset_rwsem);
+	cpus_read_unlock();
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -3522,8 +3524,8 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 	return cs;
 }
 
-/**
- * cpuset_node_allowed - Can we allocate on a memory node?
+/*
+ * __cpuset_node_allowed - Can we allocate on a memory node?
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
@@ -3694,8 +3696,8 @@ void cpuset_print_current_mems_allowed(void)
 
 int cpuset_memory_pressure_enabled __read_mostly;
 
-/**
- * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+/*
+ * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
  *
  * Keep a running average of the rate of synchronous (direct)
  * page reclaim efforts initiated by tasks in each cpuset.
@@ -3710,7 +3712,7 @@ int cpuset_memory_pressure_enabled __read_mostly;
  * "memory_pressure".  Value displayed is an integer
  * representing the recent rate of entry into the synchronous
  * (direct) page reclaim by any task attached to the cpuset.
- **/
+ */
 
 void __cpuset_memory_pressure_bump(void)
 {
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index f1e7ea160b43..bfc56cb21705 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -628,7 +628,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
 		mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
 	tlb_addr = slot_addr(mem->start, index) + offset;
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+	    (!(attrs & DMA_ATTR_OVERWRITE) || dir == DMA_TO_DEVICE ||
+	    dir == DMA_BIDIRECTIONAL))
 		swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
 	return tlb_addr;
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f9feb197b2da..a4b462b6f944 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7191,7 +7191,6 @@ static int __init ftrace_nodyn_init(void)
 core_initcall(ftrace_nodyn_init);
 
 static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; }
-static inline void ftrace_startup_enable(int command) { }
 static inline void ftrace_startup_all(int command) { }
 
 # define ftrace_startup_sysctl()	do { } while (0)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7c2578efde26..3050892d1812 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1474,10 +1474,12 @@ static int __init set_buf_size(char *str)
 	if (!str)
 		return 0;
 	buf_size = memparse(str, &str);
-	/* nr_entries can not be zero */
-	if (buf_size == 0)
-		return 0;
-	trace_buf_size = buf_size;
+	/*
+	 * nr_entries can not be zero and the startup
+	 * tests require some buffer space. Therefore
+	 * ensure we have at least 4096 bytes of buffer.
+	 */
+	trace_buf_size = max(4096UL, buf_size);
 	return 1;
 }
 __setup("trace_buf_size=", set_buf_size);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d038ddbf1bea..c5b09c31e077 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -136,7 +136,6 @@ struct kprobe_trace_entry_head {
 
 struct eprobe_trace_entry_head {
 	struct trace_entry	ent;
-	unsigned int		type;
 };
 
 struct kretprobe_trace_entry_head {
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 191db32dec46..541aa13581b9 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -242,7 +242,6 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 
 static int eprobe_event_define_fields(struct trace_event_call *event_call)
 {
-	int ret;
 	struct eprobe_trace_entry_head field;
 	struct trace_probe *tp;
 
@@ -250,8 +249,6 @@ static int eprobe_event_define_fields(struct trace_event_call *event_call)
 	if (WARN_ON_ONCE(!tp))
 		return -ENOENT;
 
-	DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0);
-
 	return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
 }
 
@@ -270,7 +267,9 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	struct trace_event_call *pevent;
 	struct trace_event *probed_event;
 	struct trace_seq *s = &iter->seq;
+	struct trace_eprobe *ep;
 	struct trace_probe *tp;
+	unsigned int type;
 
 	field = (struct eprobe_trace_entry_head *)iter->ent;
 	tp = trace_probe_primary_from_call(
@@ -278,15 +277,18 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	if (WARN_ON_ONCE(!tp))
 		goto out;
 
+	ep = container_of(tp, struct trace_eprobe, tp);
+	type = ep->event->event.type;
+
 	trace_seq_printf(s, "%s: (", trace_probe_name(tp));
 
-	probed_event = ftrace_find_event(field->type);
+	probed_event = ftrace_find_event(type);
 	if (probed_event) {
 		pevent = container_of(probed_event, struct trace_event_call, event);
 		trace_seq_printf(s, "%s.%s", pevent->class->system,
 				 trace_event_name(pevent));
 	} else {
-		trace_seq_printf(s, "%u", field->type);
+		trace_seq_printf(s, "%u", type);
 	}
 
 	trace_seq_putc(s, ')');
@@ -498,10 +500,6 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
 		return;
 
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
-	if (edata->ep->event)
-		entry->type = edata->ep->event->event.type;
-	else
-		entry->type = 0;
 	store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d00fee705f9c..7eb9d04f1c2e 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -84,6 +84,20 @@ event_triggers_call(struct trace_event_file *file,
 }
 EXPORT_SYMBOL_GPL(event_triggers_call);
 
+bool __trace_trigger_soft_disabled(struct trace_event_file *file)
+{
+	unsigned long eflags = file->flags;
+
+	if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
+		event_triggers_call(file, NULL, NULL, NULL);
+	if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
+		return true;
+	if (eflags & EVENT_FILE_FL_PID_FILTER)
+		return trace_event_ignore_this_pid(file);
+	return false;
+}
+EXPORT_SYMBOL_GPL(__trace_trigger_soft_disabled);
+
 /**
  * event_triggers_post_call - Call 'post_triggers' for a trace event
  * @file: The trace_event_file associated with the event
@@ -1295,6 +1309,16 @@ traceon_trigger(struct event_trigger_data *data,
 		struct trace_buffer *buffer, void *rec,
 		struct ring_buffer_event *event)
 {
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (tracer_tracing_is_on(file->tr))
+			return;
+
+		tracer_tracing_on(file->tr);
+		return;
+	}
+
 	if (tracing_is_on())
 		return;
 
@@ -1306,8 +1330,15 @@ traceon_count_trigger(struct event_trigger_data *data,
 		      struct trace_buffer *buffer, void *rec,
 		      struct ring_buffer_event *event)
 {
-	if (tracing_is_on())
-		return;
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (tracer_tracing_is_on(file->tr))
+			return;
+	} else {
+		if (tracing_is_on())
+			return;
+	}
 
 	if (!data->count)
 		return;
@@ -1315,7 +1346,10 @@ traceon_count_trigger(struct event_trigger_data *data,
 	if (data->count != -1)
 		(data->count)--;
 
-	tracing_on();
+	if (file)
+		tracer_tracing_on(file->tr);
+	else
+		tracing_on();
 }
 
 static void
@@ -1323,6 +1357,16 @@ traceoff_trigger(struct event_trigger_data *data,
 		 struct trace_buffer *buffer, void *rec,
 		 struct ring_buffer_event *event)
 {
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (!tracer_tracing_is_on(file->tr))
+			return;
+
+		tracer_tracing_off(file->tr);
+		return;
+	}
+
 	if (!tracing_is_on())
 		return;
 
@@ -1334,8 +1378,15 @@ traceoff_count_trigger(struct event_trigger_data *data,
 		       struct trace_buffer *buffer, void *rec,
 		       struct ring_buffer_event *event)
 {
-	if (!tracing_is_on())
-		return;
+	struct trace_event_file *file = data->private_data;
+
+	if (file) {
+		if (!tracer_tracing_is_on(file->tr))
+			return;
+	} else {
+		if (!tracing_is_on())
+			return;
+	}
 
 	if (!data->count)
 		return;
@@ -1343,7 +1394,10 @@ traceoff_count_trigger(struct event_trigger_data *data,
 	if (data->count != -1)
 		(data->count)--;
 
-	tracing_off();
+	if (file)
+		tracer_tracing_off(file->tr);
+	else
+		tracing_off();
 }
 
 static int
@@ -1540,7 +1594,12 @@ stacktrace_trigger(struct event_trigger_data *data,
 		   struct trace_buffer *buffer,  void *rec,
 		   struct ring_buffer_event *event)
 {
-	trace_dump_stack(STACK_SKIP);
+	struct trace_event_file *file = data->private_data;
+
+	if (file)
+		__trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+	else
+		trace_dump_stack(STACK_SKIP);
 }
 
 static void
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 870a08da5b48..cfddb30e65ab 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1437,6 +1437,37 @@ static struct cpumask osnoise_cpumask;
 static struct cpumask save_cpumask;
 
 /*
+ * osnoise_sleep - sleep until the next period
+ */
+static void osnoise_sleep(void)
+{
+	u64 interval;
+	ktime_t wake_time;
+
+	mutex_lock(&interface_lock);
+	interval = osnoise_data.sample_period - osnoise_data.sample_runtime;
+	mutex_unlock(&interface_lock);
+
+	/*
+	 * differently from hwlat_detector, the osnoise tracer can run
+	 * without a pause because preemption is on.
+	 */
+	if (!interval) {
+		/* Let synchronize_rcu_tasks() make progress */
+		cond_resched_tasks_rcu_qs();
+		return;
+	}
+
+	wake_time = ktime_add_us(ktime_get(), interval);
+	__set_current_state(TASK_INTERRUPTIBLE);
+
+	while (schedule_hrtimeout_range(&wake_time, 0, HRTIMER_MODE_ABS)) {
+		if (kthread_should_stop())
+			break;
+	}
+}
+
+/*
  * osnoise_main - The osnoise detection kernel thread
  *
  * Calls run_osnoise() function to measure the osnoise for the configured runtime,
@@ -1444,30 +1475,10 @@ static struct cpumask save_cpumask;
  */
 static int osnoise_main(void *data)
 {
-	u64 interval;
 
 	while (!kthread_should_stop()) {
-
 		run_osnoise();
-
-		mutex_lock(&interface_lock);
-		interval = osnoise_data.sample_period - osnoise_data.sample_runtime;
-		mutex_unlock(&interface_lock);
-
-		do_div(interval, USEC_PER_MSEC);
-
-		/*
-		 * differently from hwlat_detector, the osnoise tracer can run
-		 * without a pause because preemption is on.
-		 */
-		if (interval < 1) {
-			/* Let synchronize_rcu_tasks() make progress */
-			cond_resched_tasks_rcu_qs();
-			continue;
-		}
-
-		if (msleep_interruptible(interval))
-			break;
+		osnoise_sleep();
 	}
 
 	return 0;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 73d90179b51b..80863c6508e5 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -871,15 +871,15 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
 	switch (ptype) {
 	case PROBE_PRINT_NORMAL:
 		fmt = "(%lx)";
-		arg = "REC->" FIELD_STRING_IP;
+		arg = ", REC->" FIELD_STRING_IP;
 		break;
 	case PROBE_PRINT_RETURN:
 		fmt = "(%lx <- %lx)";
-		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+		arg = ", REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
 		break;
 	case PROBE_PRINT_EVENT:
-		fmt = "(%u)";
-		arg = "REC->" FIELD_STRING_TYPE;
+		fmt = "";
+		arg = "";
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -903,7 +903,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
 					parg->type->fmt);
 	}
 
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", arg);
 
 	for (i = 0; i < tp->nr_args; i++) {
 		parg = tp->args + i;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 99e7a5df025e..92cc149af0fd 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -38,7 +38,6 @@
 #define FIELD_STRING_IP		"__probe_ip"
 #define FIELD_STRING_RETIP	"__probe_ret_ip"
 #define FIELD_STRING_FUNC	"__probe_func"
-#define FIELD_STRING_TYPE	"__probe_type"
 
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)			\
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index afd937a46496..abcadbe933bb 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -784,9 +784,7 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 	.retfunc		= &trace_graph_return,
 };
 
-#if defined(CONFIG_DYNAMIC_FTRACE) && \
-    defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
-#define TEST_DIRECT_TRAMP
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 noinline __noclone static void trace_direct_tramp(void) { }
 #endif
 
@@ -849,7 +847,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		goto out;
 	}
 
-#ifdef TEST_DIRECT_TRAMP
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	tracing_reset_online_cpus(&tr->array_buffer);
 	set_graph_array(tr);