8 files changed, 206 insertions, 94 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0d88ce9b9fb8..fa7ece649fe1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -381,12 +381,19 @@ static int function_stat_show(struct seq_file *m, void *v)
 {
         struct ftrace_profile *rec = v;
         char str[KSYM_SYMBOL_LEN];
+        int ret = 0;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-        static DEFINE_MUTEX(mutex);
         static struct trace_seq s;
         unsigned long long avg;
         unsigned long long stddev;
 #endif
+        mutex_lock(&ftrace_profile_lock);
+
+        /* we raced with function_profile_reset() */
+        if (unlikely(rec->counter == 0)) {
+                ret = -EBUSY;
+                goto out;
+        }
 
         kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
         seq_printf(m, "  %-30.30s  %10lu", str, rec->counter);
@@ -408,7 +415,6 @@ static int function_stat_show(struct seq_file *m, void *v)
                 do_div(stddev, (rec->counter - 1) * 1000);
         }
 
-        mutex_lock(&mutex);
         trace_seq_init(&s);
         trace_print_graph_duration(rec->time, &s);
         trace_seq_puts(&s, "    ");
@@ -416,11 +422,12 @@ static int function_stat_show(struct seq_file *m, void *v)
         trace_seq_puts(&s, "    ");
         trace_print_graph_duration(stddev, &s);
         trace_print_seq(m, &s);
-        mutex_unlock(&mutex);
 #endif
         seq_putc(m, '\n');
+out:
+        mutex_unlock(&ftrace_profile_lock);
 
-        return 0;
+        return ret;
 }
 
 static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
@@ -1503,6 +1510,8 @@ static void *t_start(struct seq_file *m, loff_t *pos)
                 if (*pos > 0)
                         return t_hash_start(m, pos);
                 iter->flags |= FTRACE_ITER_PRINTALL;
+                /* reset in case of seek/pread */
+                iter->flags &= ~FTRACE_ITER_HASH;
                 return iter;
         }
 
@@ -2409,7 +2418,7 @@ static const struct file_operations ftrace_filter_fops = {
         .open = ftrace_filter_open,
         .read = seq_read,
         .write = ftrace_filter_write,
-        .llseek = ftrace_regex_lseek,
+        .llseek = no_llseek,
         .release = ftrace_filter_release,
 };
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3632ce87674f..492197e2f86c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2985,13 +2985,11 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 static void rb_advance_iter(struct ring_buffer_iter *iter)
 {
-        struct ring_buffer *buffer;
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
         unsigned length;
 
         cpu_buffer = iter->cpu_buffer;
-        buffer = cpu_buffer->buffer;
 
         /*
          * Check if we are at the end of the buffer.
@@ -3846,6 +3844,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                         rpos = reader->read;
                         pos += size;
 
+                        if (rpos >= commit)
+                                break;
+
                         event = rb_reader_event(cpu_buffer);
                         size = rb_event_length(event);
                 } while (len > size);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ba14a22be4cc..9ec59f541156 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3463,6 +3463,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
                                         size_t cnt, loff_t *fpos)
 {
         char *buf;
+        size_t written;
 
         if (tracing_disabled)
                 return -EINVAL;
@@ -3484,11 +3485,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
         } else
                 buf[cnt] = '\0';
 
-        cnt = mark_printk("%s", buf);
+        written = mark_printk("%s", buf);
         kfree(buf);
-        *fpos += cnt;
+        *fpos += written;
 
-        return cnt;
+        /* don't tell userspace we wrote more - it might confuse them */
+        if (written > cnt)
+                written = cnt;
+
+        return written;
 }
 
 static int tracing_clock_show(struct seq_file *m, void *v)
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 000e6e85b445..31cc4cb0dbf2 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -91,6 +91,8 @@ int perf_trace_init(struct perf_event *p_event)
                     tp_event->class && tp_event->class->reg &&
                     try_module_get(tp_event->mod)) {
                         ret = perf_trace_event_init(tp_event, p_event);
+                        if (ret)
+                                module_put(tp_event->mod);
                         break;
                 }
         }
@@ -146,6 +148,7 @@ void perf_trace_destroy(struct perf_event *p_event)
                 }
         }
 out:
+        module_put(tp_event->mod);
         mutex_unlock(&event_mutex);
 }
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 09b4fa6e4d3b..4c758f146328 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -598,88 +598,165 @@ out:
         return ret;
 }
 
-static void print_event_fields(struct trace_seq *s, struct list_head *head)
+enum {
+        FORMAT_HEADER           = 1,
+        FORMAT_PRINTFMT         = 2,
+};
+
+static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
+        struct ftrace_event_call *call = m->private;
         struct ftrace_event_field *field;
+        struct list_head *head;
 
-        list_for_each_entry_reverse(field, head, link) {
-                /*
-                 * Smartly shows the array type(except dynamic array).
-                 * Normal:
-                 *      field:TYPE VAR
-                 * If TYPE := TYPE[LEN], it is shown:
-                 *      field:TYPE VAR[LEN]
-                 */
-                const char *array_descriptor = strchr(field->type, '[');
+        (*pos)++;
 
-                if (!strncmp(field->type, "__data_loc", 10))
-                        array_descriptor = NULL;
+        switch ((unsigned long)v) {
+        case FORMAT_HEADER:
+                head = &ftrace_common_fields;
 
-                if (!array_descriptor) {
-                        trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
-                                        "\tsize:%u;\tsigned:%d;\n",
-                                        field->type, field->name, field->offset,
-                                        field->size, !!field->is_signed);
-                } else {
-                        trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
-                                        "\tsize:%u;\tsigned:%d;\n",
-                                        (int)(array_descriptor - field->type),
-                                        field->type, field->name,
-                                        array_descriptor, field->offset,
-                                        field->size, !!field->is_signed);
-                }
+                if (unlikely(list_empty(head)))
+                        return NULL;
+
+                field = list_entry(head->prev, struct ftrace_event_field, link);
+                return field;
+
+        case FORMAT_PRINTFMT:
+                /* all done */
+                return NULL;
+        }
+
+        head = trace_get_fields(call);
+
+        /*
+         * To separate common fields from event fields, the
+         * LSB is set on the first event field. Clear it in case.
+         */
+        v = (void *)((unsigned long)v & ~1L);
+
+        field = v;
+        /*
+         * If this is a common field, and at the end of the list, then
+         * continue with main list.
+         */
+        if (field->link.prev == &ftrace_common_fields) {
+                if (unlikely(list_empty(head)))
+                        return NULL;
+                field = list_entry(head->prev, struct ftrace_event_field, link);
+                /* Set the LSB to notify f_show to print an extra newline */
+                field = (struct ftrace_event_field *)
+                        ((unsigned long)field | 1);
+                return field;
         }
+
+        /* If we are done tell f_show to print the format */
+        if (field->link.prev == head)
+                return (void *)FORMAT_PRINTFMT;
+
+        field = list_entry(field->link.prev, struct ftrace_event_field, link);
+
+        return field;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-                  loff_t *ppos)
+static void *f_start(struct seq_file *m, loff_t *pos)
 {
-        struct ftrace_event_call *call = filp->private_data;
-        struct list_head *head;
-        struct trace_seq *s;
-        char *buf;
-        int r;
+        loff_t l = 0;
+        void *p;
 
-        if (*ppos)
+        /* Start by showing the header */
+        if (!*pos)
+                return (void *)FORMAT_HEADER;
+
+        p = (void *)FORMAT_HEADER;
+        do {
+                p = f_next(m, p, &l);
+        } while (p && l < *pos);
+
+        return p;
+}
+
+static int f_show(struct seq_file *m, void *v)
+{
+        struct ftrace_event_call *call = m->private;
+        struct ftrace_event_field *field;
+        const char *array_descriptor;
+
+        switch ((unsigned long)v) {
+        case FORMAT_HEADER:
+                seq_printf(m, "name: %s\n", call->name);
+                seq_printf(m, "ID: %d\n", call->event.type);
+                seq_printf(m, "format:\n");
                 return 0;
 
-        s = kmalloc(sizeof(*s), GFP_KERNEL);
-        if (!s)
-                return -ENOMEM;
+        case FORMAT_PRINTFMT:
+                seq_printf(m, "\nprint fmt: %s\n",
+                           call->print_fmt);
+                return 0;
+        }
 
-        trace_seq_init(s);
+        /*
+         * To separate common fields from event fields, the
+         * LSB is set on the first event field. Clear it and
+         * print a newline if it is set.
+         */
+        if ((unsigned long)v & 1) {
+                seq_putc(m, '\n');
+                v = (void *)((unsigned long)v & ~1L);
+        }
 
-        trace_seq_printf(s, "name: %s\n", call->name);
-        trace_seq_printf(s, "ID: %d\n", call->event.type);
-        trace_seq_printf(s, "format:\n");
+        field = v;
 
-        /* print common fields */
-        print_event_fields(s, &ftrace_common_fields);
+        /*
+         * Smartly shows the array type(except dynamic array).
+         * Normal:
+         *      field:TYPE VAR
+         * If TYPE := TYPE[LEN], it is shown:
+         *      field:TYPE VAR[LEN]
+         */
+        array_descriptor = strchr(field->type, '[');
 
-        trace_seq_putc(s, '\n');
+        if (!strncmp(field->type, "__data_loc", 10))
+                array_descriptor = NULL;
 
-        /* print event specific fields */
-        head = trace_get_fields(call);
-        print_event_fields(s, head);
+        if (!array_descriptor)
+                seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+                           field->type, field->name, field->offset,
+                           field->size, !!field->is_signed);
+        else
+                seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+                           (int)(array_descriptor - field->type),
+                           field->type, field->name,
+                           array_descriptor, field->offset,
+                           field->size, !!field->is_signed);
 
-        r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
+        return 0;
+}
 
-        if (!r) {
-                /*
-                 * ug!  The format output is bigger than a PAGE!!
-                 */
-                buf = "FORMAT TOO BIG\n";
-                r = simple_read_from_buffer(ubuf, cnt, ppos,
-                                              buf, strlen(buf));
-                goto out;
-        }
+static void f_stop(struct seq_file *m, void *p)
+{
+}
 
-        r = simple_read_from_buffer(ubuf, cnt, ppos,
-                                    s->buffer, s->len);
- out:
-        kfree(s);
-        return r;
+static const struct seq_operations trace_format_seq_ops = {
+        .start          = f_start,
+        .next           = f_next,
+        .stop           = f_stop,
+        .show           = f_show,
+};
+
+static int trace_format_open(struct inode *inode, struct file *file)
+{
+        struct ftrace_event_call *call = inode->i_private;
+        struct seq_file *m;
+        int ret;
+
+        ret = seq_open(file, &trace_format_seq_ops);
+        if (ret < 0)
+                return ret;
+
+        m = file->private_data;
+        m->private = call;
+
+        return 0;
 }
 
 static ssize_t
@@ -877,8 +954,10 @@ static const struct file_operations ftrace_enable_fops = {
 };
 
 static const struct file_operations ftrace_event_format_fops = {
-        .open = tracing_open_generic,
-        .read = event_format_read,
+        .open = trace_format_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = seq_release,
 };
 
 static const struct file_operations ftrace_event_id_fops = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6bff23625781..6f233698518e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter,
                          * if the output fails.
                          */
                         data->ent = *curr;
-                        data->ret = *next;
+                        /*
+                         * If the next event is not a return type, then
+                         * we only care about what type it is. Otherwise we can
+                         * safely copy the entire event.
+                         */
+                        if (next->ent.type == TRACE_GRAPH_RET)
+                                data->ret = *next;
+                        else
+                                data->ret.ent.type = next->ent.type;
                 }
         }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8b27c9849b42..544301d29dee 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -514,8 +514,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
                                 struct pt_regs *regs);
 
-/* Check the name is good for event/group */
-static int check_event_name(const char *name)
+/* Check the name is good for event/group/fields */
+static int is_good_name(const char *name)
 {
         if (!isalpha(*name) && *name != '_')
                 return 0;
@@ -557,7 +557,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
         else
                 tp->rp.kp.pre_handler = kprobe_dispatcher;
 
-        if (!event || !check_event_name(event)) {
+        if (!event || !is_good_name(event)) {
                 ret = -EINVAL;
                 goto error;
         }
@@ -567,7 +567,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
         if (!tp->call.name)
                 goto error;
 
-        if (!group || !check_event_name(group)) {
+        if (!group || !is_good_name(group)) {
                 ret = -EINVAL;
                 goto error;
         }
@@ -883,7 +883,7 @@ static int create_trace_probe(int argc, char **argv)
         int i, ret = 0;
         int is_return = 0, is_delete = 0;
         char *symbol = NULL, *event = NULL, *group = NULL;
-        char *arg, *tmp;
+        char *arg;
         unsigned long offset = 0;
         void *addr = NULL;
         char buf[MAX_EVENT_NAME_LEN];
@@ -992,26 +992,36 @@ static int create_trace_probe(int argc, char **argv)
         /* parse arguments */
         ret = 0;
         for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+                /* Increment count for freeing args in error case */
+                tp->nr_args++;
+
                 /* Parse argument name */
                 arg = strchr(argv[i], '=');
-                if (arg)
+                if (arg) {
                         *arg++ = '\0';
-                else
+                        tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+                } else {
                         arg = argv[i];
+                        /* If argument name is omitted, set "argN" */
+                        snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
+                        tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+                }
 
-                tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
                 if (!tp->args[i].name) {
-                        pr_info("Failed to allocate argument%d name '%s'.\n",
-                                i, argv[i]);
+                        pr_info("Failed to allocate argument[%d] name.\n", i);
                         ret = -ENOMEM;
                         goto error;
                 }
-                tmp = strchr(tp->args[i].name, ':');
-                if (tmp)
-                        *tmp = '_';     /* convert : to _ */
+
+                if (!is_good_name(tp->args[i].name)) {
+                        pr_info("Invalid argument[%d] name: %s\n",
+                                i, tp->args[i].name);
+                        ret = -EINVAL;
+                        goto error;
+                }
 
                 if (conflict_field_name(tp->args[i].name, tp->args, i)) {
-                        pr_info("Argument%d name '%s' conflicts with "
+                        pr_info("Argument[%d] name '%s' conflicts with "
                                 "another field.\n", i, argv[i]);
                         ret = -EINVAL;
                         goto error;
@@ -1020,12 +1030,9 @@ static int create_trace_probe(int argc, char **argv)
                 /* Parse fetch argument */
                 ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
                 if (ret) {
-                        pr_info("Parse error at argument%d. (%d)\n", i, ret);
-                        kfree(tp->args[i].name);
+                        pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
                         goto error;
                 }
-
-                tp->nr_args++;
         }
 
         ret = register_trace_probe(tp);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 056468eae7cf..a6b7e0e0f3eb 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -249,7 +249,7 @@ static int trace_lookup_stack(struct seq_file *m, long i)
 {
         unsigned long addr = stack_dump_trace[i];
 
-        return seq_printf(m, "%pF\n", (void *)addr);
+        return seq_printf(m, "%pS\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)