Merge branches 'topic/twl4030' and 'topic/twl6040' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into asoc-twl-breakage

23 files changed, 971 insertions, 438 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 434c840e2d82..af7dad126c13 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -160,6 +160,17 @@ config FUNCTION_GRAPH_TRACER
 	  address on the current task structure into a stack of calls.
 
 
+config PREEMPTIRQ_EVENTS
+	bool "Enable trace events for preempt and irq disable/enable"
+	select TRACE_IRQFLAGS
+	depends on DEBUG_PREEMPT || !PROVE_LOCKING
+	default n
+	help
+	  Enable tracing of disable and enable events for preemption and irqs.
+	  For tracing preempt disable/enable events, DEBUG_PREEMPT must be
+	  enabled. For tracing irq disable/enable events, PROVE_LOCKING must
+	  be disabled.
+
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
@@ -224,7 +235,7 @@ config HWLAT_TRACER
 	select GENERIC_TRACER
 	help
 	 This tracer, when enabled will create one or more kernel threads,
-	 depening on what the cpumask file is set to, which each thread
+	 depending on what the cpumask file is set to, which each thread
 	 spinning in a loop looking for interruptions caused by
 	 something other than the kernel. For example, if a
 	 System Management Interrupt (SMI) takes a noticeable amount of
@@ -239,7 +250,7 @@ config HWLAT_TRACER
 				     iteration
 
 	 A kernel thread is created that will spin with interrupts disabled
-	 for "width" microseconds in every "widow" cycle. It will not spin
+	 for "width" microseconds in every "window" cycle. It will not spin
 	 for "window - width" microseconds, where the system can
 	 continue to operate.
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 19a15b2f1190..e2538c7638d4 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -35,6 +35,7 @@ obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_TRACING_MAP) += tracing_map.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
+obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 45a3928544ce..206e0e2ace53 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -66,7 +66,8 @@ static struct tracer_flags blk_tracer_flags = {
 };
 
 /* Global reference count of probes */
-static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+static DEFINE_MUTEX(blk_probe_mutex);
+static int blk_probes_ref;
 
 static void blk_register_tracepoints(void);
 static void blk_unregister_tracepoints(void);
@@ -329,14 +330,29 @@ static void blk_trace_free(struct blk_trace *bt)
 	kfree(bt);
 }
 
+static void get_probe_ref(void)
+{
+	mutex_lock(&blk_probe_mutex);
+	if (++blk_probes_ref == 1)
+		blk_register_tracepoints();
+	mutex_unlock(&blk_probe_mutex);
+}
+
+static void put_probe_ref(void)
+{
+	mutex_lock(&blk_probe_mutex);
+	if (!--blk_probes_ref)
+		blk_unregister_tracepoints();
+	mutex_unlock(&blk_probe_mutex);
+}
+
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
 	blk_trace_free(bt);
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
+	put_probe_ref();
 }
 
-int blk_trace_remove(struct request_queue *q)
+static int __blk_trace_remove(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
@@ -349,6 +365,17 @@ int blk_trace_remove(struct request_queue *q)
 
 	return 0;
 }
+
+int blk_trace_remove(struct request_queue *q)
+{
+	int ret;
+
+	mutex_lock(&q->blk_trace_mutex);
+	ret = __blk_trace_remove(q);
+	mutex_unlock(&q->blk_trace_mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(blk_trace_remove);
 
 static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
@@ -538,8 +565,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto err;
 
-	if (atomic_inc_return(&blk_probes_ref) == 1)
-		blk_register_tracepoints();
+	get_probe_ref();
 
 	ret = 0;
 err:
@@ -550,9 +576,8 @@ err:
 	return ret;
 }
 
-int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-		    struct block_device *bdev,
-		    char __user *arg)
+static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			     struct block_device *bdev, char __user *arg)
 {
 	struct blk_user_trace_setup buts;
 	int ret;
@@ -571,6 +596,19 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	}
 	return 0;
 }
+
+int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+		    struct block_device *bdev,
+		    char __user *arg)
+{
+	int ret;
+
+	mutex_lock(&q->blk_trace_mutex);
+	ret = __blk_trace_setup(q, name, dev, bdev, arg);
+	mutex_unlock(&q->blk_trace_mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(blk_trace_setup);
 
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
@@ -607,7 +645,7 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 }
 #endif
 
-int blk_trace_startstop(struct request_queue *q, int start)
+static int __blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
 	struct blk_trace *bt = q->blk_trace;
@@ -646,6 +684,17 @@ int blk_trace_startstop(struct request_queue *q, int start)
 
 	return ret;
 }
+
+int blk_trace_startstop(struct request_queue *q, int start)
+{
+	int ret;
+
+	mutex_lock(&q->blk_trace_mutex);
+	ret = __blk_trace_startstop(q, start);
+	mutex_unlock(&q->blk_trace_mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(blk_trace_startstop);
 
 /*
@@ -676,7 +725,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	switch (cmd) {
 	case BLKTRACESETUP:
 		bdevname(bdev, b);
-		ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
+		ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
 	case BLKTRACESETUP32:
@@ -687,10 +736,10 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	case BLKTRACESTART:
 		start = 1;
 	case BLKTRACESTOP:
-		ret = blk_trace_startstop(q, start);
+		ret = __blk_trace_startstop(q, start);
 		break;
 	case BLKTRACETEARDOWN:
-		ret = blk_trace_remove(q);
+		ret = __blk_trace_remove(q);
 		break;
 	default:
 		ret = -ENOTTY;
@@ -708,10 +757,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
+	mutex_lock(&q->blk_trace_mutex);
+
 	if (q->blk_trace) {
-		blk_trace_startstop(q, 0);
-		blk_trace_remove(q);
+		__blk_trace_startstop(q, 0);
+		__blk_trace_remove(q);
 	}
+
+	mutex_unlock(&q->blk_trace_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1558,9 +1611,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
-
+	put_probe_ref();
 	blk_trace_free(bt);
 	return 0;
 }
@@ -1591,8 +1642,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto free_bt;
 
-	if (atomic_inc_return(&blk_probes_ref) == 1)
-		blk_register_tracepoints();
+	get_probe_ref();
 	return 0;
 
 free_bt:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index dc498b605d5d..27d1f4ffa3de 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -15,9 +15,11 @@
 #include <linux/ctype.h>
 #include "trace.h"
 
+u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+
 /**
  * trace_call_bpf - invoke BPF program
- * @prog: BPF program
+ * @call: tracepoint event
  * @ctx: opaque context pointer
  *
  * kprobe handlers execute BPF programs via this helper.
@@ -29,7 +31,7 @@
  * 1 - store kprobe event into ring buffer
  * Other values are reserved and currently alias to 1
  */
-unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 {
 	unsigned int ret;
 
@@ -49,9 +51,22 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
 		goto out;
 	}
 
-	rcu_read_lock();
-	ret = BPF_PROG_RUN(prog, ctx);
-	rcu_read_unlock();
+	/*
+	 * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock
+	 * to all call sites, we did a bpf_prog_array_valid() there to check
+	 * whether call->prog_array is empty or not, which is
+	 * a heurisitc to speed up execution.
+	 *
+	 * If bpf_prog_array_valid() fetched prog_array was
+	 * non-NULL, we go into trace_call_bpf() and do the actual
+	 * proper rcu_dereference() under RCU lock.
+	 * If it turns out that prog_array is NULL then, we bail out.
+	 * For the opposite, if the bpf_prog_array_valid() fetched pointer
+	 * was NULL, you'll skip the prog_array with the risk of missing
+	 * out of events when it was updated in between this and the
+	 * rcu_dereference() which is accepted risk.
+	 */
+	ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN);
 
  out:
 	__this_cpu_dec(bpf_prog_active);
@@ -77,7 +92,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -255,14 +270,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
-BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+static __always_inline int
+get_map_perf_counter(struct bpf_map *map, u64 flags,
+		     u64 *value, u64 *enabled, u64 *running)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	unsigned int cpu = smp_processor_id();
 	u64 index = flags & BPF_F_INDEX_MASK;
 	struct bpf_event_entry *ee;
-	u64 value = 0;
-	int err;
 
 	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
 		return -EINVAL;
@@ -275,7 +290,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
 	if (!ee)
 		return -ENOENT;
 
-	err = perf_event_read_local(ee->event, &value);
+	return perf_event_read_local(ee->event, value, enabled, running);
+}
+
+BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
+{
+	u64 value = 0;
+	int err;
+
+	err = get_map_perf_counter(map, flags, &value, NULL, NULL);
 	/*
 	 * this api is ugly since we miss [-22..-2] range of valid
 	 * counter values, but that's uapi
@@ -293,6 +316,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled,
+				   &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
+	.func		= bpf_perf_event_read_value,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
 
 static __always_inline u64
@@ -353,7 +403,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
-	.arg5_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
 static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
@@ -444,7 +494,7 @@ static const struct bpf_func_proto bpf_probe_read_str_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -499,6 +549,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_perf_event_output_proto;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
+	case BPF_FUNC_perf_event_read_value:
+		return &bpf_perf_event_read_value_proto;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -524,11 +576,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
 	return true;
 }
 
-const struct bpf_verifier_ops kprobe_prog_ops = {
+const struct bpf_verifier_ops kprobe_verifier_ops = {
 	.get_func_proto  = kprobe_prog_func_proto,
 	.is_valid_access = kprobe_prog_is_valid_access,
 };
 
+const struct bpf_prog_ops kprobe_prog_ops = {
+};
+
 BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
@@ -550,7 +605,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
-	.arg5_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
 BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map,
@@ -576,6 +631,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_perf_event_value *, buf, u32, size)
+{
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_perf_event_value)))
+		goto clear;
+	err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled,
+				    &buf->running);
+	if (unlikely(err))
+		goto clear;
+	return 0;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = {
+         .func           = bpf_perf_prog_read_value_tp,
+         .gpl_only       = true,
+         .ret_type       = RET_INTEGER,
+         .arg1_type      = ARG_PTR_TO_CTX,
+         .arg2_type      = ARG_PTR_TO_UNINIT_MEM,
+         .arg3_type      = ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -583,6 +664,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto_tp;
+	case BPF_FUNC_perf_prog_read_value:
+		return &bpf_perf_prog_read_value_proto_tp;
 	default:
 		return tracing_func_proto(func_id);
 	}
@@ -602,11 +685,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type
 	return true;
 }
 
-const struct bpf_verifier_ops tracepoint_prog_ops = {
+const struct bpf_verifier_ops tracepoint_verifier_ops = {
 	.get_func_proto  = tp_prog_func_proto,
 	.is_valid_access = tp_prog_is_valid_access,
 };
 
+const struct bpf_prog_ops tracepoint_prog_ops = {
+};
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    struct bpf_insn_access_aux *info)
 {
@@ -662,8 +748,67 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
-const struct bpf_verifier_ops perf_event_prog_ops = {
+const struct bpf_verifier_ops perf_event_verifier_ops = {
 	.get_func_proto		= tp_prog_func_proto,
 	.is_valid_access	= pe_prog_is_valid_access,
 	.convert_ctx_access	= pe_prog_convert_ctx_access,
 };
+
+const struct bpf_prog_ops perf_event_prog_ops = {
+};
+
+static DEFINE_MUTEX(bpf_event_mutex);
+
+int perf_event_attach_bpf_prog(struct perf_event *event,
+			       struct bpf_prog *prog)
+{
+	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *new_array;
+	int ret = -EEXIST;
+
+	mutex_lock(&bpf_event_mutex);
+
+	if (event->prog)
+		goto unlock;
+
+	old_array = event->tp_event->prog_array;
+	ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+	if (ret < 0)
+		goto unlock;
+
+	/* set the new array to event->tp_event and set event->prog */
+	event->prog = prog;
+	rcu_assign_pointer(event->tp_event->prog_array, new_array);
+	bpf_prog_array_free(old_array);
+
+unlock:
+	mutex_unlock(&bpf_event_mutex);
+	return ret;
+}
+
+void perf_event_detach_bpf_prog(struct perf_event *event)
+{
+	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *new_array;
+	int ret;
+
+	mutex_lock(&bpf_event_mutex);
+
+	if (!event->prog)
+		goto unlock;
+
+	old_array = event->tp_event->prog_array;
+	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+	if (ret < 0) {
+		bpf_prog_array_delete_safe(old_array, event->prog);
+	} else {
+		rcu_assign_pointer(event->tp_event->prog_array, new_array);
+		bpf_prog_array_free(old_array);
+	}
+
+	bpf_prog_put(event->prog);
+	event->prog = NULL;
+
+unlock:
+	mutex_unlock(&bpf_event_mutex);
+}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8319e09e15b9..ccdf3664e4a9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -203,30 +203,6 @@ void clear_ftrace_function(void)
 	ftrace_trace_function = ftrace_stub;
 }
 
-static void per_cpu_ops_disable_all(struct ftrace_ops *ops)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(ops->disabled, cpu) = 1;
-}
-
-static int per_cpu_ops_alloc(struct ftrace_ops *ops)
-{
-	int __percpu *disabled;
-
-	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
-		return -EINVAL;
-
-	disabled = alloc_percpu(int);
-	if (!disabled)
-		return -ENOMEM;
-
-	ops->disabled = disabled;
-	per_cpu_ops_disable_all(ops);
-	return 0;
-}
-
 static void ftrace_sync(struct work_struct *work)
 {
 	/*
@@ -262,8 +238,8 @@ static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops)
 	 * If this is a dynamic, RCU, or per CPU ops, or we force list func,
 	 * then it needs to call the list anyway.
 	 */
-	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU |
-			  FTRACE_OPS_FL_RCU) || FTRACE_FORCE_LIST_FUNC)
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_RCU) ||
+	    FTRACE_FORCE_LIST_FUNC)
 		return ftrace_ops_list_func;
 
 	return ftrace_ops_get_func(ops);
@@ -422,11 +398,6 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
-	if (ops->flags & FTRACE_OPS_FL_PER_CPU) {
-		if (per_cpu_ops_alloc(ops))
-			return -ENOMEM;
-	}
-
 	add_ftrace_ops(&ftrace_ops_list, ops);
 
 	/* Always save the function, and reset at unregistering */
@@ -2727,11 +2698,6 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
-static void per_cpu_ops_free(struct ftrace_ops *ops)
-{
-	free_percpu(ops->disabled);
-}
-
 static void ftrace_startup_enable(int command)
 {
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -2833,7 +2799,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		 * not currently active, we can just free them
 		 * without synchronizing all CPUs.
 		 */
-		if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU))
+		if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
 			goto free_ops;
 
 		return 0;
@@ -2880,7 +2846,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * The same goes for freeing the per_cpu data of the per_cpu
 	 * ops.
 	 */
-	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) {
+	if (ops->flags & FTRACE_OPS_FL_DYNAMIC) {
 		/*
 		 * We need to do a hard force of sched synchronization.
 		 * This is because we use preempt_disable() to do RCU, but
@@ -2903,9 +2869,6 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 
  free_ops:
 		arch_ftrace_trampoline_free(ops);
-
-		if (ops->flags & FTRACE_OPS_FL_PER_CPU)
-			per_cpu_ops_free(ops);
 	}
 
 	return 0;
@@ -5672,10 +5635,29 @@ static int ftrace_process_locs(struct module *mod,
 	return ret;
 }
 
+struct ftrace_mod_func {
+	struct list_head	list;
+	char			*name;
+	unsigned long		ip;
+	unsigned int		size;
+};
+
+struct ftrace_mod_map {
+	struct rcu_head		rcu;
+	struct list_head	list;
+	struct module		*mod;
+	unsigned long		start_addr;
+	unsigned long		end_addr;
+	struct list_head	funcs;
+	unsigned int		num_funcs;
+};
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
 
+static LIST_HEAD(ftrace_mod_maps);
+
 static int referenced_filters(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *ops;
@@ -5729,8 +5711,26 @@ static void clear_mod_from_hashes(struct ftrace_page *pg)
 	mutex_unlock(&trace_types_lock);
 }
 
+static void ftrace_free_mod_map(struct rcu_head *rcu)
+{
+	struct ftrace_mod_map *mod_map = container_of(rcu, struct ftrace_mod_map, rcu);
+	struct ftrace_mod_func *mod_func;
+	struct ftrace_mod_func *n;
+
+	/* All the contents of mod_map are now not visible to readers */
+	list_for_each_entry_safe(mod_func, n, &mod_map->funcs, list) {
+		kfree(mod_func->name);
+		list_del(&mod_func->list);
+		kfree(mod_func);
+	}
+
+	kfree(mod_map);
+}
+
 void ftrace_release_mod(struct module *mod)
 {
+	struct ftrace_mod_map *mod_map;
+	struct ftrace_mod_map *n;
 	struct dyn_ftrace *rec;
 	struct ftrace_page **last_pg;
 	struct ftrace_page *tmp_page = NULL;
@@ -5742,6 +5742,14 @@ void ftrace_release_mod(struct module *mod)
 	if (ftrace_disabled)
 		goto out_unlock;
 
+	list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) {
+		if (mod_map->mod == mod) {
+			list_del_rcu(&mod_map->list);
+			call_rcu_sched(&mod_map->rcu, ftrace_free_mod_map);
+			break;
+		}
+	}
+
 	/*
 	 * Each module has its own ftrace_pages, remove
 	 * them from the list.
@@ -5749,7 +5757,8 @@ void ftrace_release_mod(struct module *mod)
 	last_pg = &ftrace_pages_start;
 	for (pg = ftrace_pages_start; pg; pg = *last_pg) {
 		rec = &pg->records[0];
-		if (within_module_core(rec->ip, mod)) {
+		if (within_module_core(rec->ip, mod) ||
+		    within_module_init(rec->ip, mod)) {
 			/*
 			 * As core pages are first, the first
 			 * page should never be a module page.
@@ -5818,7 +5827,8 @@ void ftrace_module_enable(struct module *mod)
 		 * not part of this module, then skip this pg,
 		 * which the "break" will do.
 		 */
-		if (!within_module_core(rec->ip, mod))
+		if (!within_module_core(rec->ip, mod) &&
+		    !within_module_init(rec->ip, mod))
 			break;
 
 		cnt = 0;
@@ -5863,23 +5873,245 @@ void ftrace_module_init(struct module *mod)
 	ftrace_process_locs(mod, mod->ftrace_callsites,
 			    mod->ftrace_callsites + mod->num_ftrace_callsites);
 }
+
+static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map,
+				struct dyn_ftrace *rec)
+{
+	struct ftrace_mod_func *mod_func;
+	unsigned long symsize;
+	unsigned long offset;
+	char str[KSYM_SYMBOL_LEN];
+	char *modname;
+	const char *ret;
+
+	ret = kallsyms_lookup(rec->ip, &symsize, &offset, &modname, str);
+	if (!ret)
+		return;
+
+	mod_func = kmalloc(sizeof(*mod_func), GFP_KERNEL);
+	if (!mod_func)
+		return;
+
+	mod_func->name = kstrdup(str, GFP_KERNEL);
+	if (!mod_func->name) {
+		kfree(mod_func);
+		return;
+	}
+
+	mod_func->ip = rec->ip - offset;
+	mod_func->size = symsize;
+
+	mod_map->num_funcs++;
+
+	list_add_rcu(&mod_func->list, &mod_map->funcs);
+}
+
+static struct ftrace_mod_map *
+allocate_ftrace_mod_map(struct module *mod,
+			unsigned long start, unsigned long end)
+{
+	struct ftrace_mod_map *mod_map;
+
+	mod_map = kmalloc(sizeof(*mod_map), GFP_KERNEL);
+	if (!mod_map)
+		return NULL;
+
+	mod_map->mod = mod;
+	mod_map->start_addr = start;
+	mod_map->end_addr = end;
+	mod_map->num_funcs = 0;
+
+	INIT_LIST_HEAD_RCU(&mod_map->funcs);
+
+	list_add_rcu(&mod_map->list, &ftrace_mod_maps);
+
+	return mod_map;
+}
+
+static const char *
+ftrace_func_address_lookup(struct ftrace_mod_map *mod_map,
+			   unsigned long addr, unsigned long *size,
+			   unsigned long *off, char *sym)
+{
+	struct ftrace_mod_func *found_func =  NULL;
+	struct ftrace_mod_func *mod_func;
+
+	list_for_each_entry_rcu(mod_func, &mod_map->funcs, list) {
+		if (addr >= mod_func->ip &&
+		    addr < mod_func->ip + mod_func->size) {
+			found_func = mod_func;
+			break;
+		}
+	}
+
+	if (found_func) {
+		if (size)
+			*size = found_func->size;
+		if (off)
+			*off = addr - found_func->ip;
+		if (sym)
+			strlcpy(sym, found_func->name, KSYM_NAME_LEN);
+
+		return found_func->name;
+	}
+
+	return NULL;
+}
+
+const char *
+ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
+		   unsigned long *off, char **modname, char *sym)
+{
+	struct ftrace_mod_map *mod_map;
+	const char *ret = NULL;
+
+	/* mod_map is freed via call_rcu_sched() */
+	preempt_disable();
+	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
+		ret = ftrace_func_address_lookup(mod_map, addr, size, off, sym);
+		if (ret) {
+			if (modname)
+				*modname = mod_map->mod->name;
+			break;
+		}
+	}
+	preempt_enable();
+
+	return ret;
+}
+
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name,
+			   char *module_name, int *exported)
+{
+	struct ftrace_mod_map *mod_map;
+	struct ftrace_mod_func *mod_func;
+
+	preempt_disable();
+	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
+
+		if (symnum >= mod_map->num_funcs) {
+			symnum -= mod_map->num_funcs;
+			continue;
+		}
+
+		list_for_each_entry_rcu(mod_func, &mod_map->funcs, list) {
+			if (symnum > 1) {
+				symnum--;
+				continue;
+			}
+
+			*value = mod_func->ip;
+			*type = 'T';
+			strlcpy(name, mod_func->name, KSYM_NAME_LEN);
+			strlcpy(module_name, mod_map->mod->name, MODULE_NAME_LEN);
+			*exported = 1;
+			preempt_enable();
+			return 0;
+		}
+		WARN_ON(1);
+		break;
+	}
+	preempt_enable();
+	return -ERANGE;
+}
+
+#else
+static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map,
+				struct dyn_ftrace *rec) { }
+static inline struct ftrace_mod_map *
+allocate_ftrace_mod_map(struct module *mod,
+			unsigned long start, unsigned long end)
+{
+	return NULL;
+}
 #endif /* CONFIG_MODULES */
 
-void __init ftrace_free_init_mem(void)
+struct ftrace_init_func {
+	struct list_head list;
+	unsigned long ip;
+};
+
+/* Clear any init ips from hashes */
+static void
+clear_func_from_hash(struct ftrace_init_func *func, struct ftrace_hash *hash)
+{
+	struct ftrace_func_entry *entry;
+
+	if (ftrace_hash_empty(hash))
+		return;
+
+	entry = __ftrace_lookup_ip(hash, func->ip);
+
+	/*
+	 * Do not allow this rec to match again.