Merge tag 'trace-v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:
 "Major changes:

   - Changed location of tracing repo from personal git repo to:
     git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git

   - Added Masami Hiramatsu as co-maintainer

   - Updated MAINTAINERS file to separate out FTRACE as it is more than
     just TRACING.

  Minor changes:

   - Added Mark Rutland as FTRACE reviewer

   - Updated user_events to make it on its way to remove the BROKEN tag.
     The changes should now be acceptable but will run it through a
     cycle and hopefully we can remove the BROKEN tag next release.

   - Added filtering to eprobes

   - Added a delta time to the benchmark trace event

   - Have the histogram and filter callbacks called via a switch
     statement instead of indirect functions. This speeds it up to avoid
     retpolines.

   - Add a way to wake up ring buffer waiters waiting for the ring
     buffer to fill up to its watermark.

   - New ioctl() on the trace_pipe_raw file to wake up ring buffer
     waiters.

   - Wake up waiters when the ring buffer is disabled. A reader may
     block when the ring buffer is disabled, but if it was blocked when
     the ring buffer is disabled it should then wake up.

  Fixes:

   - Allow splice to read partially read ring buffer pages. This fixes
     splice never moving forward.

   - Fix inverted compare that made the "shortest" ring buffer wait
     queue actually the longest.

   - Fix a race in the ring buffer between resetting a page when a
     writer goes to another page, and the reader.

   - Fix ftrace accounting bug when function hooks are added at boot up
     before the weak functions are set to "disabled".

   - Fix bug that freed a user allocated snapshot buffer when enabling a
     tracer.

   - Fix possible recursive locks in osnoise tracer

   - Fix recursive locking direct functions

   - Other minor clean ups and fixes"

* tag 'trace-v6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (44 commits)
  ftrace: Create separate entry in MAINTAINERS for function hooks
  tracing: Update MAINTAINERS to reflect new tracing git repo
  tracing: Do not free snapshot if tracer is on cmdline
  ftrace: Still disable enabled records marked as disabled
  tracing/user_events: Move pages/locks into groups to prepare for namespaces
  tracing: Add Masami Hiramatsu as co-maintainer
  tracing: Remove unused variable 'dups'
  MAINTAINERS: add myself as a tracing reviewer
  ring-buffer: Fix race between reset page and reading page
  tracing/user_events: Update ABI documentation to align to bits vs bytes
  tracing/user_events: Use bits vs bytes for enabled status page data
  tracing/user_events: Use refcount instead of atomic for ref tracking
  tracing/user_events: Ensure user provided strings are safely formatted
  tracing/user_events: Use WRITE instead of READ for io vector import
  tracing/user_events: Use NULL for strstr checks
  tracing: Fix spelling mistake "preapre" -> "prepare"
  tracing: Wake up waiters when tracing is disabled
  tracing: Add ioctl() to force ring buffer waiters to wake up
  tracing: Wake up ring buffer waiters on closing of the file
  ring-buffer: Add ring_buffer_wake_waiters()
  ...

17 files changed, 1114 insertions, 358 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 447d2e2a8549..02e18c436439 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1644,6 +1644,18 @@ ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_ex
 static struct ftrace_ops *
 ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
 
+static bool skip_record(struct dyn_ftrace *rec)
+{
+	/*
+	 * At boot up, weak functions are set to disable. Function tracing
+	 * can be enabled before they are, and they still need to be disabled now.
+	 * If the record is disabled, still continue if it is marked as already
+	 * enabled (this is needed to keep the accounting working).
+	 */
+	return rec->flags & FTRACE_FL_DISABLED &&
+		!(rec->flags & FTRACE_FL_ENABLED);
+}
+
 static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
@@ -1693,7 +1705,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		int in_hash = 0;
 		int match = 0;
 
-		if (rec->flags & FTRACE_FL_DISABLED)
+		if (skip_record(rec))
 			continue;
 
 		if (all) {
@@ -2126,7 +2138,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
 
 	ftrace_bug_type = FTRACE_BUG_UNKNOWN;
 
-	if (rec->flags & FTRACE_FL_DISABLED)
+	if (skip_record(rec))
 		return FTRACE_UPDATE_IGNORE;
 
 	/*
@@ -2241,7 +2253,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
 	if (update) {
 		/* If there's no more users, clear all flags */
 		if (!ftrace_rec_count(rec))
-			rec->flags = 0;
+			rec->flags &= FTRACE_FL_DISABLED;
 		else
 			/*
 			 * Just disable the record, but keep the ops TRAMP
@@ -2634,7 +2646,7 @@ void __weak ftrace_replace_code(int mod_flags)
 
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (rec->flags & FTRACE_FL_DISABLED)
+		if (skip_record(rec))
 			continue;
 
 		failed = __ftrace_replace_code(rec, enable);
@@ -5427,6 +5439,8 @@ static struct ftrace_ops stub_ops = {
  * it is safe to modify the ftrace record, where it should be
  * currently calling @old_addr directly, to call @new_addr.
  *
+ * This is called with direct_mutex locked.
+ *
  * Safety checks should be made to make sure that the code at
  * @rec->ip is currently calling @old_addr. And this must
  * also update entry->direct to @new_addr.
@@ -5439,6 +5453,8 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 	unsigned long ip = rec->ip;
 	int ret;
 
+	lockdep_assert_held(&direct_mutex);
+
 	/*
 	 * The ftrace_lock was used to determine if the record
 	 * had more than one registered user to it. If it did,
@@ -5461,7 +5477,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 	if (ret)
 		goto out_lock;
 
-	ret = register_ftrace_function(&stub_ops);
+	ret = register_ftrace_function_nolock(&stub_ops);
 	if (ret) {
 		ftrace_set_filter_ip(&stub_ops, ip, 1, 0);
 		goto out_lock;
@@ -6081,8 +6097,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 		if (filter_hash) {
 			orig_hash = &iter->ops->func_hash->filter_hash;
-			if (iter->tr && !list_empty(&iter->tr->mod_trace))
-				iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			if (iter->tr) {
+				if (list_empty(&iter->tr->mod_trace))
+					iter->hash->flags &= ~FTRACE_HASH_FL_MOD;
+				else
+					iter->hash->flags |= FTRACE_HASH_FL_MOD;
+			}
 		} else
 			orig_hash = &iter->ops->func_hash->notrace_hash;
 
diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c
index 18b0f1cbb947..80e04a1e1977 100644
--- a/kernel/trace/kprobe_event_gen_test.c
+++ b/kernel/trace/kprobe_event_gen_test.c
@@ -35,6 +35,45 @@
 static struct trace_event_file *gen_kprobe_test;
 static struct trace_event_file *gen_kretprobe_test;
 
+#define KPROBE_GEN_TEST_FUNC	"do_sys_open"
+
+/* X86 */
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_32)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%ax"
+#define KPROBE_GEN_TEST_ARG1	"filename=%dx"
+#define KPROBE_GEN_TEST_ARG2	"flags=%cx"
+#define KPROBE_GEN_TEST_ARG3	"mode=+4($stack)"
+
+/* ARM64 */
+#elif defined(CONFIG_ARM64)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%x0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%x1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%x2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%x3"
+
+/* ARM */
+#elif defined(CONFIG_ARM)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%r0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%r1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%r2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%r3"
+
+/* RISCV */
+#elif defined(CONFIG_RISCV)
+#define KPROBE_GEN_TEST_ARG0	"dfd=%a0"
+#define KPROBE_GEN_TEST_ARG1	"filename=%a1"
+#define KPROBE_GEN_TEST_ARG2	"flags=%a2"
+#define KPROBE_GEN_TEST_ARG3	"mode=%a3"
+
+/* others */
+#else
+#define KPROBE_GEN_TEST_ARG0	NULL
+#define KPROBE_GEN_TEST_ARG1	NULL
+#define KPROBE_GEN_TEST_ARG2	NULL
+#define KPROBE_GEN_TEST_ARG3	NULL
+#endif
+
+
 /*
  * Test to make sure we can create a kprobe event, then add more
  * fields.
@@ -58,14 +97,14 @@ static int __init test_gen_kprobe_cmd(void)
 	 * fields.
 	 */
 	ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test",
-					 "do_sys_open",
-					 "dfd=%ax", "filename=%dx");
+					 KPROBE_GEN_TEST_FUNC,
+					 KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1);
 	if (ret)
 		goto free;
 
 	/* Use kprobe_event_add_fields to add the rest of the fields */
 
-	ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)");
+	ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3);
 	if (ret)
 		goto free;
 
@@ -128,7 +167,7 @@ static int __init test_gen_kretprobe_cmd(void)
 	 * Define the kretprobe event.
 	 */
 	ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test",
-					    "do_sys_open",
+					    KPROBE_GEN_TEST_FUNC,
 					    "$retval");
 	if (ret)
 		goto free;
@@ -206,7 +245,7 @@ static void __exit kprobe_event_gen_test_exit(void)
 	WARN_ON(kprobe_event_delete("gen_kprobe_test"));
 
 	/* Disable the event or you can't remove it */
-	WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
+	WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
 					  "kprobes",
 					  "gen_kretprobe_test", false));
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d59b6a328b7f..c3f354cfc5ba 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -413,6 +413,7 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
+	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -917,13 +918,45 @@ static void rb_wake_up_waiters(struct irq_work *work)
 	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);
 
 	wake_up_all(&rbwork->waiters);
-	if (rbwork->wakeup_full) {
+	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
 		rbwork->wakeup_full = false;
+		rbwork->full_waiters_pending = false;
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
 
 /**
+ * ring_buffer_wake_waiters - wake up any waiters on this ring buffer
+ * @buffer: The ring buffer to wake waiters on
+ *
+ * In the case of a file that represents a ring buffer is closing,
+ * it is prudent to wake up any waiters that are on this.
+ */
+void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct rb_irq_work *rbwork;
+
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+
+		/* Wake up individual ones too. One level recursion */
+		for_each_buffer_cpu(buffer, cpu)
+			ring_buffer_wake_waiters(buffer, cpu);
+
+		rbwork = &buffer->irq_work;
+	} else {
+		cpu_buffer = buffer->buffers[cpu];
+		rbwork = &cpu_buffer->irq_work;
+	}
+
+	rbwork->wait_index++;
+	/* make sure the waiters see the new index */
+	smp_wmb();
+
+	rb_wake_up_waiters(&rbwork->work);
+}
+
+/**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
  * @cpu: the cpu buffer to wait on
@@ -938,6 +971,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
+	long wait_index;
 	int ret = 0;
 
 	/*
@@ -956,6 +990,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		work = &cpu_buffer->irq_work;
 	}
 
+	wait_index = READ_ONCE(work->wait_index);
 
 	while (true) {
 		if (full)
@@ -1011,7 +1046,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 			nr_pages = cpu_buffer->nr_pages;
 			dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
 			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full < full)
+			    cpu_buffer->shortest_full > full)
 				cpu_buffer->shortest_full = full;
 			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 			if (!pagebusy &&
@@ -1020,6 +1055,11 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		}
 
 		schedule();
+
+		/* Make sure to see the new wait index */
+		smp_rmb();
+		if (wait_index != work->wait_index)
+			break;
 	}
 
 	if (full)
@@ -2608,6 +2648,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 		/* Mark the rest of the page with padding */
 		rb_event_set_padding(event);
 
+		/* Make sure the padding is visible before the write update */
+		smp_wmb();
+
 		/* Set the write back to the previous setting */
 		local_sub(length, &tail_page->write);
 		return;
@@ -2619,6 +2662,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
+	/* Make sure the padding is visible before the tail_page->write update */
+	smp_wmb();
+
 	/* Set write to end of buffer */
 	length = (tail + length) - BUF_PAGE_SIZE;
 	local_sub(length, &tail_page->write);
@@ -4587,6 +4633,33 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
+	/*
+	 * The writer has preempt disable, wait for it. But not forever
+	 * Although, 1 second is pretty much "forever"
+	 */
+#define USECS_WAIT	1000000
+        for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
+		/* If the write is past the end of page, a writer is still updating it */
+		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+			break;
+
+		udelay(1);
+
+		/* Get the latest version of the reader write value */
+		smp_rmb();
+	}
+
+	/* The writer is not moving forward? Something is wrong */
+	if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT))
+		reader = NULL;
+
+	/*
+	 * Make sure we see any padding after the write update
+	 * (see rb_reset_tail())
+	 */
+	smp_rmb();
+
+
 	return reader;
 }
 
@@ -5616,7 +5689,15 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		unsigned int pos = 0;
 		unsigned int size;
 
-		if (full)
+		/*
+		 * If a full page is expected, this can still be returned
+		 * if there's been a previous partial read and the
+		 * rest of the page can be read and the commit page is off
+		 * the reader page.
+		 */
+		if (full &&
+		    (!read || (len < (commit - read)) ||
+		     cpu_buffer->reader_page == cpu_buffer->commit_page))
 			goto out_unlock;
 
 		if (len > (commit - read))
diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c
index 83cace53b9fa..b2b49a27e886 100644
--- a/kernel/trace/rv/monitors/wip/wip.c
+++ b/kernel/trace/rv/monitors/wip/wip.c
@@ -16,7 +16,7 @@
 
 #include "wip.h"
 
-struct rv_monitor rv_wip;
+static struct rv_monitor rv_wip;
 DECLARE_DA_MON_PER_CPU(wip, unsigned char);
 
 static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
@@ -60,7 +60,7 @@ static void disable_wip(void)
 	da_monitor_destroy_wip();
 }
 
-struct rv_monitor rv_wip = {
+static struct rv_monitor rv_wip = {
 	.name = "wip",
 	.description = "wakeup in preemptive per-cpu testing monitor.",
 	.enable = enable_wip,
@@ -69,13 +69,13 @@ struct rv_monitor rv_wip = {
 	.enabled = 0,
 };
 
-static int register_wip(void)
+static int __init register_wip(void)
 {
 	rv_register_monitor(&rv_wip);
 	return 0;
 }
 
-static void unregister_wip(void)
+static void __exit unregister_wip(void)
 {
 	rv_unregister_monitor(&rv_wip);
 }
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c
index 599225d9cf38..0e43dd2db685 100644
--- a/kernel/trace/rv/monitors/wwnr/wwnr.c
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.c
@@ -15,7 +15,7 @@
 
 #include "wwnr.h"
 
-struct rv_monitor rv_wwnr;
+static struct rv_monitor rv_wwnr;
 DECLARE_DA_MON_PER_TASK(wwnr, unsigned char);
 
 static void handle_switch(void *data, bool preempt, struct task_struct *p,
@@ -59,7 +59,7 @@ static void disable_wwnr(void)
 	da_monitor_destroy_wwnr();
 }
 
-struct rv_monitor rv_wwnr = {
+static struct rv_monitor rv_wwnr = {
 	.name = "wwnr",
 	.description = "wakeup while not running per-task testing model.",
 	.enable = enable_wwnr,
@@ -68,13 +68,13 @@ struct rv_monitor rv_wwnr = {
 	.enabled = 0,
 };
 
-static int register_wwnr(void)
+static int __init register_wwnr(void)
 {
 	rv_register_monitor(&rv_wwnr);
 	return 0;
 }
 
-static void unregister_wwnr(void)
+static void __exit unregister_wwnr(void)
 {
 	rv_unregister_monitor(&rv_wwnr);
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d3005279165d..47a44b055a1d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1193,12 +1193,14 @@ void *tracing_cond_snapshot_data(struct trace_array *tr)
 {
 	void *cond_data = NULL;
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 
 	if (tr->cond_snapshot)
 		cond_data = tr->cond_snapshot->cond_data;
 
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	return cond_data;
 }
@@ -1334,9 +1336,11 @@ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data,
 		goto fail_unlock;
 	}
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	tr->cond_snapshot = cond_snapshot;
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	mutex_unlock(&trace_types_lock);
 
@@ -1363,6 +1367,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 {
 	int ret = 0;
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 
 	if (!tr->cond_snapshot)
@@ -1373,6 +1378,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 	}
 
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 
 	return ret;
 }
@@ -2200,6 +2206,11 @@ static size_t tgid_map_max;
 
 #define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
+/*
+ * Preemption must be disabled before acquiring trace_cmdline_lock.
+ * The various trace_arrays' max_lock must be acquired in a context
+ * where interrupt is disabled.
+ */
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 struct saved_cmdlines_buffer {
 	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
@@ -2412,7 +2423,11 @@ static int trace_save_cmdline(struct task_struct *tsk)
 	 * the lock, but we also don't want to spin
 	 * nor do we want to disable interrupts,
 	 * so if we miss here, then better luck next time.
+	 *
+	 * This is called within the scheduler and wake up, so interrupts
+	 * had better been disabled and run queue lock been held.
 	 */
+	lockdep_assert_preemption_disabled();
 	if (!arch_spin_trylock(&trace_cmdline_lock))
 		return 0;
 
@@ -5890,9 +5905,11 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	char buf[64];
 	int r;
 
+	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
 	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
@@ -5917,10 +5934,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
 		return -ENOMEM;
 	}
 
+	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
 	savedcmd = s;
 	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
 	free_saved_cmdlines_buffer(savedcmd_temp);
 
 	return 0;
@@ -6373,10 +6392,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 	if (t->use_max_tr) {
+		local_irq_disable();
 		arch_spin_lock(&tr->max_lock);
 		if (tr->cond_snapshot)
 			ret = -EBUSY;
 		arch_spin_unlock(&tr->max_lock);
+		local_irq_enable();
 		if (ret)
 			goto out;
 	}
@@ -6407,12 +6428,12 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 	if (tr->current_trace->reset)
 		tr->current_trace->reset(tr);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+	had_max_tr = tr->current_trace->use_max_tr;
+
 	/* Current trace needs to be nop_trace before synchronize_rcu */
 	tr->current_trace = &nop_trace;
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-	had_max_tr = tr->allocated_snapshot;
-
 	if (had_max_tr && !t->use_max_tr) {
 		/*
 		 * We need to make sure that the update_max_tr sees that
@@ -6425,11 +6446,13 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 		free_snapshot(tr);
 	}
 
-	if (t->use_max_tr && !had_max_tr) {
+	if (t->use_max_tr && !tr->allocated_snapshot) {
 		ret = tracing_alloc_snapshot_instance(tr);
 		if (ret < 0)
 			goto out;
 	}
+#else
+	tr->current_trace = &nop_trace;
 #endif
 
 	if (t->init) {
@@ -7436,10 +7459,12 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		goto out;
 	}
 
+	local_irq_disable();
 	arch_spin_lock(&tr->max_lock);
 	if (tr->cond_snapshot)
 		ret = -EBUSY;
 	arch_spin_unlock(&tr->max_lock);
+	local_irq_enable();
 	if (ret)
 		goto out;
 
@@ -8137,6 +8162,12 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	__trace_array_put(iter->tr);
 
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
@@ -8290,6 +8321,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 	/* did we read anything? */
 	if (!spd.nr_pages) {
+		long wait_index;
+
 		if (ret)
 			goto out;
 
@@ -8297,10 +8330,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
 			goto out;
 
+		wait_index = READ_ONCE(iter->wait_index);
+
 		ret = wait_on_pipe(iter, iter->tr->buffer_percent);
 		if (ret)
 			goto out;
 
+		/* No need to wait after waking up when tracing is off */
+		if (!tracer_tracing_is_on(iter->tr))
+			goto out;
+
+		/* Make sure we see the new wait_index */
+		smp_rmb();
+		if (wait_index != iter->wait_index)
+			goto out;
+
 		goto again;
 	}
 
@@ -8311,12 +8355,34 @@ out:
 	return ret;
 }
 
+/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */
+static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	if (cmd)
+		return -ENOIOCTLCMD;
+
+	mutex_lock(&trace_types_lock);
+
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+	mutex_unlock(&trace_types_lock);
+	return 0;
+}
+
 static const struct file_operations tracing_buffers_fops = {
 	.open		= tracing_buffers_open,
 	.read		= tracing_buffers_read,
 	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
 	.splice_read	= tracing_buffers_splice_read,
+	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,
 };
 
@@ -9005,6 +9071,8 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 			tracer_tracing_off(tr);
 			if (tr->current_trace->stop)
 				tr->current_trace->stop(tr);
+			/* Wake up any waiters */
+			ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS);
 		}
 		mutex_unlock(&trace_types_lock);
 	}
@@ -10091,7 +10159,7 @@ __init static int tracer_alloc_buffers(void)
 	 * buffer. The memory will be removed once the "instance" is removed.
 	 */
 	ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE,
-				      "trace/RB:preapre", trace_rb_cpu_prepare,
+				      "trace/RB:prepare", trace_rb_cpu_prepare,
 				      NULL);
 	if (ret < 0)
 		goto out_free_cpumask;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 900e75d96c84..54ee5711c729 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1435,8 +1435,6 @@ event_trigger_unlock_commit(struct trace_event_file *file,
 struct filter_pred;
 struct regex;
 
-typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
-
 typedef int (*regex_match_func)(char *str, struct regex *r, int len);
 
 enum regex_type {
@@ -1455,17 +1453,6 @@ struct regex {
 	regex_match_func	match;
 };
 
-struct filter_pred {
-	filter_pred_fn_t 	fn;
-	u64 			val;
-	struct regex		regex;
-	unsigned short		*ops;
-	struct ftrace_event_field *field;
-	int 			offset;
-	int			not;
-	int 			op;
-};
-
 static inline bool is_string_field(struct ftrace_event_field *field)
 {
 	return field->filter_type == FILTER_DYN_STRING ||
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 801c2a7f7605..54d5fa35c90a 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -51,7 +51,7 @@ static void trace_do_benchmark(void)
 
 	local_irq_disable();
 	start = trace_clock_local();
-	trace_benchmark_event(bm_str);
+	trace_benchmark_event(bm_str, bm_last);
 	stop = trace_clock_local();
 	local_irq_enable();
 
diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h
index 79e6fbe5b365..c3e91060dc94 100644
--- a/kernel/trace/trace_benchmark.h
+++ b/kernel/trace/trace_benchmark.h
@@ -14,19 +14,21 @@ extern void trace_benchmark_unreg(void);
 
 TRACE_EVENT_FN(benchmark_event,
 
-	TP_PROTO(const char *str),
+	TP_PROTO(const char *str, u64 delta),
 
-	TP_ARGS(str),
+	TP_ARGS(str, delta),
 
 	TP_STRUCT__entry(
 		__array(	char,	str,	BENCHMARK_EVENT_STRLEN	)
+		__field(	u64,	delta)
 	),
 
 	TP_fast_assign(
 		memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN);
+		__entry->delta = delta;
 	),
 
-	TP_printk("%s", __entry->str),
+	TP_printk("%s delta=%llu", __entry->str, __entry->delta),
 
 	trace_benchmark_reg, trace_benchmark_unreg
 );
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 1783e3478912..c08bde9871ec 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -26,6 +26,9 @@ struct trace_eprobe {
 	/* tracepoint event */
 	const char *event_name;
 
+	/* filter string for the tracepoint */
+	char *filter_str;
+
 	struct trace_event_call *event;
 
 	struct dyn_event	devent;
@@ -664,14 +667,15 @@ static struct event_trigger_data *
 new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
 {
 	struct event_trigger_data *trigger;
+	struct event_filter *filter = NULL;
 	struct eprobe_data *edata;
+	int ret;
 
 	edata = kzalloc(sizeof(*edata), GFP_KERNEL);
 	trigger = kzalloc(sizeof(*trigger), GFP_KERNEL);
 	if (!trigger || !edata) {
-		kfree(edata);
-		kfree(trigger);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto error;
 	}
 
 	trigger->flags = EVENT_TRIGGER_FL_PROBE;
@@ -686,13 +690,25 @@ new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
 	trigger->cmd_ops = &event_trigger_cmd;
 
 	INIT_LIST_HEAD(&trigger->list);
-	RCU_INIT_POINTER(trigger->filter, NULL);
+
+	if (ep->filter_str) {
+		ret = create_event_filter(file->tr, file->event_call,
+					ep->filter_str, false, &filter);
+		if (ret)
+			goto error;
+	}
+	RCU_INIT_POINTER(trigger->filter, filter);
 
 	edata->file = file;
 	edata->ep = ep;
 	trigger->private_data = edata;
 
 	return trigger;
+error:
+	free_event_filter(filter);
+	kfree(edata);
+	kfree(trigger);
+	return ERR_PTR(ret);
 }
 
 static int enable_eprobe(struct trace_eprobe *ep,
@@ -726,6 +742,7 @@ static int disable_eprobe(struct trace_eprobe *ep,
 {
 	struct event_trigger_data *trigger = NULL, *iter;
 	struct trace_event_file *file;
+	struct event_filter *filter;
 	struct eprobe_data *edata;
 
 	file = find_event_file(tr, ep->event_system, ep->event_name);
@@ -752,6 +769,10 @@ static int disable_eprobe(struct trace_eprobe *ep,
 	/* Make sure nothing is using the edata or trigger */
 	tracepoint_synchronize_unregister();
 
+	filter = rcu_access_pointer(trigger->filter);
+
+	if (filter)
+		free_event_filter(filter);
 	kfree(edata);
 	kfree(trigger);
 
@@ -927,12 +948,62 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
 	return ret;
 }
 
+static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const char *argv[])
+{
+	struct event_filter *dummy;
+	int i, ret, len = 0;
+	char *p;
+
+	if (argc == 0) {
+		trace_probe_log_err(0, NO_EP_FILTER);
+		return -EINVAL;
+	}
+
+	/* Recover the filter string */
+	for (i = 0; i < argc; i++)
+		len += strlen(argv[i]) + 1;
+
+	ep->filter_str = kzalloc(len, GFP_KERNEL);
+	if (!ep->filter_str)
+		return -ENOMEM;
+
+	p = ep->filter_str;
+	for (i = 0; i < argc; i++) {
+		ret = snprintf(p, len, "%s ", argv[i]);
+		if (ret < 0)
+			goto error;
+		if (ret > len) {
+			ret = -E2BIG;
+			goto error;
+		}
+		p += ret;
+		len -= ret;
+	}
+	p[-1] = '\0';
+
+	/*
+	 * Ensure the filter string can be parsed correctly. Note, this
+	 * filter string is for the original event, not for the eprobe.
+	 */
+	ret = create_event_filter(top_trace_array(), ep->event, ep->filter_str,
+				  true, &dummy);
+	free_event_filter(dummy);
+	if (ret)
+		goto error;
+
+	return 0;
+error:
+	kfree(ep->filter_str);
+	ep->filter_str = NULL;
+	return ret;
+}