Merge branch 'perf/vlbr'

kernel/trace/blktrace.c

@@ -3,6 +3,9 @@
  * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
@@ -344,7 +347,8 @@ static int __blk_trace_remove(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->blk_trace_mutex));
 	if (!bt)
 		return -EINVAL;
 
@@ -494,6 +498,17 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	strreplace(buts->name, '/', '_');
 
+	/*
+	 * bdev can be NULL, as with scsi-generic, this is a helpful as
+	 * we can be.
+	 */
+	if (rcu_dereference_protected(q->blk_trace,
+				      lockdep_is_held(&q->blk_trace_mutex))) {
+		pr_warn("Concurrent blktraces are not allowed on %s\n",
+			buts->name);
+		return -EBUSY;
+	}
+
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
 		return -ENOMEM;
@@ -543,10 +558,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto err;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 
 	ret = 0;
@@ -1629,7 +1641,8 @@ static int blk_trace_remove_queue(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->blk_trace_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -1661,10 +1674,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	blk_trace_setup_lba(bt, bdev);
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto free_bt;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 	return 0;
 

kernel/trace/bpf_trace.c

@@ -141,7 +141,7 @@ bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr)
 {
 	int ret;
 
-	ret = probe_user_read(dst, unsafe_ptr, size);
+	ret = copy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
 	return ret;
@@ -196,7 +196,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 
 	if (unlikely(ret < 0))
 		goto fail;
-	ret = probe_kernel_read(dst, unsafe_ptr, size);
+	ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		goto fail;
 	return ret;
@@ -241,7 +241,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
 	if (unlikely(ret < 0))
 		goto fail;
 
-	return 0;
+	return ret;
 fail:
 	memset(dst, 0, size);
 	return ret;
@@ -326,7 +326,7 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
-	return probe_user_write(unsafe_ptr, src, size);
+	return copy_to_user_nofault(unsafe_ptr, src, size);
 }
 
 static const struct bpf_func_proto bpf_probe_write_user_proto = {
@@ -661,7 +661,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 
 			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
 
-			err = probe_kernel_read(bufs->buf[memcpy_cnt],
+			err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt],
 						(void *) (long) args[fmt_cnt],
 						copy_size);
 			if (err < 0)

kernel/trace/ftrace.c

@@ -2260,7 +2260,7 @@ ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
 
 		if (hash_contains_ip(ip, op->func_hash))
 			return op;
-	} 
+	}
 
 	return NULL;
 }
@@ -3643,7 +3643,7 @@ static int t_show(struct seq_file *m, void *v)
 			if (direct)
 				seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
 		}
-	}	
+	}
 
 	seq_putc(m, '\n');
 
@@ -7248,6 +7248,10 @@ static int pid_open(struct inode *inode, struct file *file, int type)
 	case TRACE_NO_PIDS:
 		seq_ops = &ftrace_no_pid_sops;
 		break;
+	default:
+		trace_array_put(tr);
+		WARN_ON_ONCE(1);
+		return -EINVAL;
 	}
 
 	ret = seq_open(file, seq_ops);
@@ -7326,6 +7330,10 @@ pid_write(struct file *filp, const char __user *ubuf,
 		other_pids = rcu_dereference_protected(tr->function_pids,
 					     lockdep_is_held(&ftrace_lock));
 		break;
+	default:
+		ret = -EINVAL;
+		WARN_ON_ONCE(1);
+		goto out;
 	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);

kernel/trace/ring_buffer.c

@@ -2427,7 +2427,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
 	if (unlikely(info->add_timestamp)) {
 		bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
 
-		event = rb_add_time_stamp(event, info->delta, abs);
+		event = rb_add_time_stamp(event, abs ? info->delta : delta, abs);
 		length -= RB_LEN_TIME_EXTEND;
 		delta = 0;
 	}

kernel/trace/trace.c

@@ -3570,7 +3570,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 {
-	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter;
 	unsigned long entries = 0;
 	u64 ts;
@@ -3588,7 +3587,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 	 * that a reset never took place on a cpu. This is evident
 	 * by the timestamp being before the start of the buffer.
 	 */
-	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+	while (ring_buffer_iter_peek(buf_iter, &ts)) {
 		if (ts >= iter->array_buffer->time_start)
 			break;
 		entries++;

kernel/trace/trace.h

@@ -61,6 +61,9 @@ enum trace_type {
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, size)	type	item[size];
 

kernel/trace/trace_boot.c

@@ -101,12 +101,16 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 		kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
 
 		ret = kprobe_event_gen_cmd_start(&cmd, event, val);
-		if (ret)
+		if (ret) {
+			pr_err("Failed to generate probe: %s\n", buf);
 			break;
+		}
 
 		ret = kprobe_event_gen_cmd_end(&cmd);
-		if (ret)
+		if (ret) {
 			pr_err("Failed to add probe: %s\n", buf);
+			break;
+		}
 	}
 
 	return ret;
@@ -120,7 +124,7 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 }
 #endif
 
-#ifdef CONFIG_HIST_TRIGGERS
+#ifdef CONFIG_SYNTH_EVENTS
 static int __init
 trace_boot_add_synth_event(struct xbc_node *node, const char *event)
 {

kernel/trace/trace_entries.h

@@ -78,8 +78,8 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
-		__field_desc(	unsigned long,	graph_ent,	func		)
-		__field_desc(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned long,	graph_ent,	func		)
+		__field_packed(	int,		graph_ent,	depth		)
 	),
 
 	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
@@ -92,11 +92,11 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
-		__field_desc(	unsigned long,	ret,		func	)
-		__field_desc(	unsigned long,	ret,		overrun	)
-		__field_desc(	unsigned long long, ret,	calltime)
-		__field_desc(	unsigned long long, ret,	rettime	)
-		__field_desc(	int,		ret,		depth	)
+		__field_packed(	unsigned long,	ret,		func	)
+		__field_packed(	unsigned long,	ret,		overrun	)
+		__field_packed(	unsigned long long, ret,	calltime)
+		__field_packed(	unsigned long long, ret,	rettime	)
+		__field_packed(	int,		ret,		depth	)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",

kernel/trace/trace_events_trigger.c

@@ -216,11 +216,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 int trigger_process_regex(struct trace_event_file *file, char *buff)
 {
-	char *command, *next = buff;
+	char *command, *next;
 	struct event_command *p;
 	int ret = -EINVAL;
 
+	next = buff = skip_spaces(buff);
 	command = strsep(&next, ": \t");
+	if (next) {
+		next = skip_spaces(next);
+		if (!*next)
+			next = NULL;
+	}
 	command = (command[0] != '!') ? command : command + 1;
 
 	mutex_lock(&trigger_cmd_mutex);
@@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops,
 	int ret;
 
 	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0]))
+	if (param && isdigit(param[0])) {
 		trigger = strsep(&param, " \t");
+		if (param) {
+			param = skip_spaces(param);
+			if (!*param)
+				param = NULL;
+		}
+	}
 
 	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
 
@@ -1368,6 +1380,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 	trigger = strsep(&param, " \t");
 	if (!trigger)
 		return -EINVAL;
+	if (param) {
+		param = skip_spaces(param);
+		if (!*param)
+			param = NULL;
+	}
 
 	system = strsep(&trigger, ":");
 	if (!trigger)

kernel/trace/trace_export.c

@@ -45,6 +45,9 @@ static int ftrace_event_register(struct trace_event_call *call,
 #undef __field_desc
 #define __field_desc(type, container, item)		type item;
 
+#undef __field_packed
+#define __field_packed(type, container, item)		type item;
+
 #undef __array
 #define __array(type, item, size)			type item[size];
 
@@ -85,6 +88,13 @@ static void __always_unused ____ftrace_check_##name(void)		\
 	.size = sizeof(_type), .align = __alignof__(_type),		\
 	is_signed_type(_type), .filter_type = _filter_type },
 
+
+#undef __field_ext_packed
+#define __field_ext_packed(_type, _item, _filter_type) {	\
+	.type = #_type, .name = #_item,				\
+	.size = sizeof(_type), .align = 1,			\
+	is_signed_type(_type), .filter_type = _filter_type },
+
 #undef __field
 #define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER)
 
@@ -94,6 +104,9 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __field_desc
 #define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER)
 
+#undef __field_packed
+#define __field_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER)
+
 #undef __array
 #define __array(_type, _item, _len) {					\
 	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
@@ -129,6 +142,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = {	\
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, len)
 

kernel/trace/trace_functions.c

@@ -42,7 +42,7 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 	if (!ops)
 		return -ENOMEM;
 
-	/* Currently only the non stack verision is supported */
+	/* Currently only the non stack version is supported */
 	ops->func = function_trace_call;
 	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
 

kernel/trace/trace_kprobe.c

@@ -1222,7 +1222,7 @@ fetch_store_strlen(unsigned long addr)
 #endif
 
 	do {
-		ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
+		ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
@@ -1290,7 +1290,7 @@ probe_mem_read_user(void *dest, void *src, size_t size)
 {
 	const void __user *uaddr =  (__force const void __user *)src;
 
-	return probe_user_read(dest, uaddr, size);
+	return copy_from_user_nofault(dest, uaddr, size);
 }
 
 static nokprobe_inline int
@@ -1300,7 +1300,7 @@ probe_mem_read(void *dest, void *src, size_t size)
 	if ((unsigned long)src < TASK_SIZE)
 		return probe_mem_read_user(dest, src, size);
 #endif
-	return probe_kernel_read(dest, src, size);
+	return copy_from_kernel_nofault(dest, src, size);
 }
 
 /* Note that we don't verify it, since the code does not come from user space */

kernel/trace/trace_probe.c

@@ -639,8 +639,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			ret = -EINVAL;
 			goto fail;
 		}
-		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
-		     parg->count) {
+		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM ||
+		     code->op == FETCH_OP_DATA) || parg->count) {
 			/*
 			 * IMM, DATA and COMM is pointing actual address, those
 			 * must be kept, and if parg->count != 0, this is an

kernel/trace/trace_probe.h

@@ -236,7 +236,7 @@ struct trace_probe_event {
 	struct trace_event_call		call;
 	struct list_head 		files;
 	struct list_head		probes;
-	struct trace_uprobe_filter	filter[0];
+	struct trace_uprobe_filter	filter[];
 };
 
 struct trace_probe {