Merge tag 'trace-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "New tracing features:

   - New PERMANENT flag to ftrace_ops when attaching a callback to a
     function.

     As /proc/sys/kernel/ftrace_enabled when set to zero will disable
     all attached callbacks in ftrace, this has a detrimental impact on
     live kernel tracing, as it disables all that it patched. If a
     ftrace_ops is registered to ftrace with the PERMANENT flag set, it
     will prevent ftrace_enabled from being disabled, and if
     ftrace_enabled is already disabled, it will prevent a ftrace_ops
     with PREMANENT flag set from being registered.

   - New register_ftrace_direct().

     As eBPF would like to register its own trampolines to be called by
     the ftrace nop locations directly, without going through the ftrace
     trampoline, this function has been added. This allows for eBPF
     trampolines to live along side of ftrace, perf, kprobe and live
     patching. It also utilizes the ftrace enabled_functions file that
     keeps track of functions that have been modified in the kernel, to
     allow for security auditing.

   - Allow for kernel internal use of ftrace instances.

     Subsystems in the kernel can now create and destroy their own
     tracing instances which allows them to have their own tracing
     buffer, and be able to record events without worrying about other
     users from writing over their data.

   - New seq_buf_hex_dump() that lets users use the hex_dump() in their
     seq_buf usage.

   - Notifications now added to tracing_max_latency to allow user space
     to know when a new max latency is hit by one of the latency
     tracers.

   - Wider spread use of generic compare operations for use of bsearch
     and friends.

   - More synthetic event fields may be defined (32 up from 16)

   - Use of xarray for architectures with sparse system calls, for the
     system call trace events.

  This along with small clean ups and fixes"

* tag 'trace-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (51 commits)
  tracing: Enable syscall optimization for MIPS
  tracing: Use xarray for syscall trace events
  tracing: Sample module to demonstrate kernel access to Ftrace instances.
  tracing: Adding new functions for kernel access to Ftrace instances
  tracing: Fix Kconfig indentation
  ring-buffer: Fix typos in function ring_buffer_producer
  ftrace: Use BIT() macro
  ftrace: Return ENOTSUPP when DYNAMIC_FTRACE_WITH_DIRECT_CALLS is not configured
  ftrace: Rename ftrace_graph_stub to ftrace_stub_graph
  ftrace: Add a helper function to modify_ftrace_direct() to allow arch optimization
  ftrace: Add helper find_direct_entry() to consolidate code
  ftrace: Add another check for match in register_ftrace_direct()
  ftrace: Fix accounting bug with direct->count in register_ftrace_direct()
  ftrace/selftests: Fix spelling mistake "wakeing" -> "waking"
  tracing: Increase SYNTH_FIELDS_MAX for synthetic_events
  ftrace/samples: Add a sample module that implements modify_ftrace_direct()
  ftrace: Add modify_ftrace_direct()
  tracing: Add missing "inline" in stub function of latency_fsnotify()
  tracing: Remove stray tab in TRACE_EVAL_MAP_FILE's help text
  tracing: Use seq_buf_hex_dump() to dump buffers
  ...

1 files changed, 182 insertions, 32 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6a0ee9178365..02a23a6e5e00 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -45,6 +45,9 @@
 #include <linux/trace.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/rt.h>
+#include <linux/fsnotify.h>
+#include <linux/irq_work.h>
+#include <linux/workqueue.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -298,12 +301,24 @@ static void __trace_array_put(struct trace_array *this_tr)
 	this_tr->ref--;
 }
 
+/**
+ * trace_array_put - Decrement the reference counter for this trace array.
+ *
+ * NOTE: Use this when we no longer need the trace array returned by
+ * trace_array_get_by_name(). This ensures the trace array can be later
+ * destroyed.
+ *
+ */
 void trace_array_put(struct trace_array *this_tr)
 {
+	if (!this_tr)
+		return;
+
 	mutex_lock(&trace_types_lock);
 	__trace_array_put(this_tr);
 	mutex_unlock(&trace_types_lock);
 }
+EXPORT_SYMBOL_GPL(trace_array_put);
 
 int tracing_check_open_get_tr(struct trace_array *tr)
 {
@@ -1497,6 +1512,74 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 }
 
 unsigned long __read_mostly	tracing_thresh;
+static const struct file_operations tracing_max_lat_fops;
+
+#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+	defined(CONFIG_FSNOTIFY)
+
+static struct workqueue_struct *fsnotify_wq;
+
+static void latency_fsnotify_workfn(struct work_struct *work)
+{
+	struct trace_array *tr = container_of(work, struct trace_array,
+					      fsnotify_work);
+	fsnotify(tr->d_max_latency->d_inode, FS_MODIFY,
+		 tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
+static void latency_fsnotify_workfn_irq(struct irq_work *iwork)
+{
+	struct trace_array *tr = container_of(iwork, struct trace_array,
+					      fsnotify_irqwork);
+	queue_work(fsnotify_wq, &tr->fsnotify_work);
+}
+
+static void trace_create_maxlat_file(struct trace_array *tr,
+				     struct dentry *d_tracer)
+{
+	INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn);
+	init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq);
+	tr->d_max_latency = trace_create_file("tracing_max_latency", 0644,
+					      d_tracer, &tr->max_latency,
+					      &tracing_max_lat_fops);
+}
+
+__init static int latency_fsnotify_init(void)
+{
+	fsnotify_wq = alloc_workqueue("tr_max_lat_wq",
+				      WQ_UNBOUND | WQ_HIGHPRI, 0);
+	if (!fsnotify_wq) {
+		pr_err("Unable to allocate tr_max_lat_wq\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+late_initcall_sync(latency_fsnotify_init);
+
+void latency_fsnotify(struct trace_array *tr)
+{
+	if (!fsnotify_wq)
+		return;
+	/*
+	 * We cannot call queue_work(&tr->fsnotify_work) from here because it's
+	 * possible that we are called from __schedule() or do_idle(), which
+	 * could cause a deadlock.
+	 */
+	irq_work_queue(&tr->fsnotify_irqwork);
+}
+
+/*
+ * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \
+ *  defined(CONFIG_FSNOTIFY)
+ */
+#else
+
+#define trace_create_maxlat_file(tr, d_tracer)				\
+	trace_create_file("tracing_max_latency", 0644, d_tracer,	\
+			  &tr->max_latency, &tracing_max_lat_fops)
+
+#endif
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 /*
@@ -1536,6 +1619,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	/* record this tasks comm */
 	tracing_record_cmdline(tsk);
+	latency_fsnotify(tr);
 }
 
 /**
@@ -3225,6 +3309,9 @@ int trace_array_printk(struct trace_array *tr,
 	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
+	if (!tr)
+		return -ENOENT;
+
 	va_start(ap, fmt);
 	ret = trace_array_vprintk(tr, ip, fmt, ap);
 	va_end(ap);
@@ -3654,6 +3741,8 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		   "desktop",
 #elif defined(CONFIG_PREEMPT)
 		   "preempt",
+#elif defined(CONFIG_PREEMPT_RT)
+		   "preempt_rt",
 #else
 		   "unknown",
 #endif
@@ -4609,7 +4698,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 
 	if (mask == TRACE_ITER_RECORD_TGID) {
 		if (!tgid_map)
-			tgid_map = kcalloc(PID_MAX_DEFAULT + 1,
+			tgid_map = kvcalloc(PID_MAX_DEFAULT + 1,
 					   sizeof(*tgid_map),
 					   GFP_KERNEL);
 		if (!tgid_map) {
@@ -7583,14 +7672,23 @@ static ssize_t
 tracing_read_dyn_info(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
-	unsigned long *p = filp->private_data;
-	char buf[64]; /* Not too big for a shallow stack */
+	ssize_t ret;
+	char *buf;
 	int r;
 
-	r = scnprintf(buf, 63, "%ld", *p);
-	buf[r++] = '\n';
+	/* 256 should be plenty to hold the amount needed */
+	buf = kmalloc(256, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+	r = scnprintf(buf, 256, "%ld pages:%ld groups: %ld\n",
+		      ftrace_update_tot_cnt,
+		      ftrace_number_of_pages,
+		      ftrace_number_of_groups);
+
+	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+	kfree(buf);
+	return ret;
 }
 
 static const struct file_operations tracing_dyn_info_fops = {
@@ -8351,24 +8449,15 @@ static void update_tracer_options(struct trace_array *tr)
 	mutex_unlock(&trace_types_lock);
 }
 
-struct trace_array *trace_array_create(const char *name)
+static struct trace_array *trace_array_create(const char *name)
 {
 	struct trace_array *tr;
 	int ret;
 
-	mutex_lock(&event_mutex);
-	mutex_lock(&trace_types_lock);
-
-	ret = -EEXIST;
-	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
-		if (tr->name && strcmp(tr->name, name) == 0)
-			goto out_unlock;
-	}
-
 	ret = -ENOMEM;
 	tr = kzalloc(sizeof(*tr), GFP_KERNEL);
 	if (!tr)
-		goto out_unlock;
+		return ERR_PTR(ret);
 
 	tr->name = kstrdup(name, GFP_KERNEL);
 	if (!tr->name)
@@ -8413,8 +8502,8 @@ struct trace_array *trace_array_create(const char *name)
 
 	list_add(&tr->list, &ftrace_trace_arrays);
 
-	mutex_unlock(&trace_types_lock);
-	mutex_unlock(&event_mutex);
+	tr->ref++;
+
 
 	return tr;
 
@@ -8424,24 +8513,77 @@ struct trace_array *trace_array_create(const char *name)
 	kfree(tr->name);
 	kfree(tr);
 
- out_unlock:
-	mutex_unlock(&trace_types_lock);
-	mutex_unlock(&event_mutex);
-
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(trace_array_create);
 
 static int instance_mkdir(const char *name)
 {
-	return PTR_ERR_OR_ZERO(trace_array_create(name));
+	struct trace_array *tr;
+	int ret;
+
+	mutex_lock(&event_mutex);
+	mutex_lock(&trace_types_lock);
+
+	ret = -EEXIST;
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr->name && strcmp(tr->name, name) == 0)
+			goto out_unlock;
+	}
+
+	tr = trace_array_create(name);
+
+	ret = PTR_ERR_OR_ZERO(tr);
+
+out_unlock:
+	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
+	return ret;
+}
+
+/**
+ * trace_array_get_by_name - Create/Lookup a trace array, given its name.
+ * @name: The name of the trace array to be looked up/created.
+ *
+ * Returns pointer to trace array with given name.
+ * NULL, if it cannot be created.
+ *
+ * NOTE: This function increments the reference counter associated with the
+ * trace array returned. This makes sure it cannot be freed while in use.
+ * Use trace_array_put() once the trace array is no longer needed.
+ *
+ */
+struct trace_array *trace_array_get_by_name(const char *name)
+{
+	struct trace_array *tr;
+
+	mutex_lock(&event_mutex);
+	mutex_lock(&trace_types_lock);
+
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr->name && strcmp(tr->name, name) == 0)
+			goto out_unlock;
+	}
+
+	tr = trace_array_create(name);
+
+	if (IS_ERR(tr))
+		tr = NULL;
+out_unlock:
+	if (tr)
+		tr->ref++;
+
+	mutex_unlock(&trace_types_lock);
+	mutex_unlock(&event_mutex);
+	return tr;
 }
+EXPORT_SYMBOL_GPL(trace_array_get_by_name);
 
 static int __remove_instance(struct trace_array *tr)
 {
 	int i;
 
-	if (tr->ref || (tr->current_trace && tr->current_trace->ref))
+	/* Reference counter for a newly created trace array = 1. */
+	if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref))
 		return -EBUSY;
 
 	list_del(&tr->list);
@@ -8473,17 +8615,26 @@ static int __remove_instance(struct trace_array *tr)
 	return 0;
 }
 
-int trace_array_destroy(struct trace_array *tr)
+int trace_array_destroy(struct trace_array *this_tr)
 {
+	struct trace_array *tr;
 	int ret;
 
-	if (!tr)
+	if (!this_tr)
 		return -EINVAL;
 
 	mutex_lock(&event_mutex);
 	mutex_lock(&trace_types_lock);
 
-	ret = __remove_instance(tr);
+	ret = -ENODEV;
+
+	/* Making sure trace array exists before destroying it. */
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr == this_tr) {
+			ret = __remove_instance(tr);
+			break;
+		}
+	}
 
 	mutex_unlock(&trace_types_lock);
 	mutex_unlock(&event_mutex);
@@ -8585,8 +8736,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	create_trace_options_dir(tr);
 
 #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
-	trace_create_file("tracing_max_latency", 0644, d_tracer,
-			&tr->max_latency, &tracing_max_lat_fops);
+	trace_create_maxlat_file(tr, d_tracer);
 #endif
 
 	if (ftrace_create_function_files(tr, d_tracer))
@@ -8782,7 +8932,7 @@ static __init int tracer_init_tracefs(void)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
-			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
+			NULL, &tracing_dyn_info_fops);
 #endif
 
 	create_trace_instances(d_tracer);