1 files changed, 209 insertions, 121 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ee9c921d7f2..17a2d44e1af 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -343,26 +343,27 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
 
+static void wakeup_work_handler(struct work_struct *work)
+{
+        wake_up(&trace_wait);
+}
+
+static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler);
+
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
- * Simply wakes up any task that is blocked on the trace_wait
- * queue. These is used with trace_poll for tasks polling the trace.
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * trace_wait queue. These is used with trace_poll for tasks polling the
+ * trace.
  */
 void trace_wake_up(void)
 {
-        int cpu;
+        const unsigned long delay = msecs_to_jiffies(2);
 
         if (trace_flags & TRACE_ITER_BLOCK)
                 return;
-        /*
-         * The runqueue_is_locked() can fail, but this is the best we
-         * have for now:
-         */
-        cpu = get_cpu();
-        if (!runqueue_is_locked(cpu))
-                wake_up(&trace_wait);
-        put_cpu();
+        schedule_delayed_work(&wakeup_work, delay);
 }
 
 static int __init set_buf_size(char *str)
@@ -424,6 +425,7 @@ static const char *trace_options[] = {
         "graph-time",
         "record-cmd",
         "overwrite",
+        "disable_on_free",
         NULL
 };
 
@@ -1191,6 +1193,18 @@ void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
+void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+                                            struct ring_buffer_event *event,
+                                            unsigned long flags, int pc,
+                                            struct pt_regs *regs)
+{
+        ring_buffer_unlock_commit(buffer, event);
+
+        ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
+        ftrace_trace_userstack(buffer, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs);
+
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
                                          struct ring_buffer_event *event)
 {
@@ -1234,30 +1248,103 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 }
 
 #ifdef CONFIG_STACKTRACE
+
+#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+struct ftrace_stack {
+        unsigned long           calls[FTRACE_STACK_MAX_ENTRIES];
+};
+
+static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(int, ftrace_stack_reserve);
+
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
                                  unsigned long flags,
-                                 int skip, int pc)
+                                 int skip, int pc, struct pt_regs *regs)
 {
         struct ftrace_event_call *call = &event_kernel_stack;
         struct ring_buffer_event *event;
         struct stack_entry *entry;
         struct stack_trace trace;
+        int use_stack;
+        int size = FTRACE_STACK_ENTRIES;
+
+        trace.nr_entries        = 0;
+        trace.skip              = skip;
+
+        /*
+         * Since events can happen in NMIs there's no safe way to
+         * use the per cpu ftrace_stacks. We reserve it and if an interrupt
+         * or NMI comes in, it will just have to use the default
+         * FTRACE_STACK_SIZE.
+         */
+        preempt_disable_notrace();
+
+        use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+        /*
+         * We don't need any atomic variables, just a barrier.
+         * If an interrupt comes in, we don't care, because it would
+         * have exited and put the counter back to what we want.
+         * We just need a barrier to keep gcc from moving things
+         * around.
+         */
+        barrier();
+        if (use_stack == 1) {
+                trace.entries           = &__get_cpu_var(ftrace_stack).calls[0];
+                trace.max_entries       = FTRACE_STACK_MAX_ENTRIES;
+
+                if (regs)
+                        save_stack_trace_regs(regs, &trace);
+                else
+                        save_stack_trace(&trace);
+
+                if (trace.nr_entries > size)
+                        size = trace.nr_entries;
+        } else
+                /* From now on, use_stack is a boolean */
+                use_stack = 0;
+
+        size *= sizeof(unsigned long);
 
         event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-                                          sizeof(*entry), flags, pc);
+                                          sizeof(*entry) + size, flags, pc);
         if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        memset(&entry->caller, 0, sizeof(entry->caller));
+                goto out;
+        entry = ring_buffer_event_data(event);
 
-        trace.nr_entries        = 0;
-        trace.max_entries       = FTRACE_STACK_ENTRIES;
-        trace.skip              = skip;
-        trace.entries           = entry->caller;
+        memset(&entry->caller, 0, size);
+
+        if (use_stack)
+                memcpy(&entry->caller, trace.entries,
+                       trace.nr_entries * sizeof(unsigned long));
+        else {
+                trace.max_entries       = FTRACE_STACK_ENTRIES;
+                trace.entries           = entry->caller;
+                if (regs)
+                        save_stack_trace_regs(regs, &trace);
+                else
+                        save_stack_trace(&trace);
+        }
+
+        entry->size = trace.nr_entries;
 
-        save_stack_trace(&trace);
         if (!filter_check_discard(call, entry, buffer, event))
                 ring_buffer_unlock_commit(buffer, event);
+
+ out:
+        /* Again, don't let gcc optimize things here */
+        barrier();
+        __get_cpu_var(ftrace_stack_reserve)--;
+        preempt_enable_notrace();
+
+}
+
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+                             int skip, int pc, struct pt_regs *regs)
+{
+        if (!(trace_flags & TRACE_ITER_STACKTRACE))
+                return;
+
+        __ftrace_trace_stack(buffer, flags, skip, pc, regs);
 }
 
 void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
@@ -1266,13 +1353,13 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
         if (!(trace_flags & TRACE_ITER_STACKTRACE))
                 return;
 
-        __ftrace_trace_stack(buffer, flags, skip, pc);
+        __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
 }
 
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
                    int pc)
 {
-        __ftrace_trace_stack(tr->buffer, flags, skip, pc);
+        __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
 }
 
 /**
@@ -1288,7 +1375,7 @@ void trace_dump_stack(void)
         local_save_flags(flags);
 
         /* skipping 3 traces, seems to get us at the caller of this function */
-        __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
+        __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL);
 }
 
 static DEFINE_PER_CPU(int, user_stack_count);
@@ -1536,7 +1623,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 
         ftrace_enable_cpu();
 
-        return event ? ring_buffer_event_data(event) : NULL;
+        if (event) {
+                iter->ent_size = ring_buffer_event_length(event);
+                return ring_buffer_event_data(event);
+        }
+        iter->ent_size = 0;
+        return NULL;
 }
 
 static struct trace_entry *
@@ -2051,6 +2143,9 @@ void trace_default_header(struct seq_file *m)
 {
         struct trace_iterator *iter = m->private;
 
+        if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+                return;
+
         if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
                 /* print nothing if the buffers are empty */
                 if (trace_empty(iter))
@@ -2701,20 +2796,11 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
                    size_t cnt, loff_t *ppos)
 {
         struct trace_array *tr = filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         val = !!val;
@@ -2767,7 +2853,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
         return t->init(tr);
 }
 
-static int tracing_resize_ring_buffer(unsigned long size)
+static int __tracing_resize_ring_buffer(unsigned long size)
 {
         int ret;
 
@@ -2819,6 +2905,41 @@ static int tracing_resize_ring_buffer(unsigned long size)
         return ret;
 }
 
+static ssize_t tracing_resize_ring_buffer(unsigned long size)
+{
+        int cpu, ret = size;
+
+        mutex_lock(&trace_types_lock);
+
+        tracing_stop();
+
+        /* disable all cpu buffers */
+        for_each_tracing_cpu(cpu) {
+                if (global_trace.data[cpu])
+                        atomic_inc(&global_trace.data[cpu]->disabled);
+                if (max_tr.data[cpu])
+                        atomic_inc(&max_tr.data[cpu]->disabled);
+        }
+
+        if (size != global_trace.entries)
+                ret = __tracing_resize_ring_buffer(size);
+
+        if (ret < 0)
+                ret = -ENOMEM;
+
+        for_each_tracing_cpu(cpu) {
+                if (global_trace.data[cpu])
+                        atomic_dec(&global_trace.data[cpu]->disabled);
+                if (max_tr.data[cpu])
+                        atomic_dec(&max_tr.data[cpu]->disabled);
+        }
+
+        tracing_start();
+        mutex_unlock(&trace_types_lock);
+
+        return ret;
+}
+
 
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
@@ -2836,7 +2957,7 @@ int tracing_update_buffers(void)
 
         mutex_lock(&trace_types_lock);
         if (!ring_buffer_expanded)
-                ret = tracing_resize_ring_buffer(trace_buf_size);
+                ret = __tracing_resize_ring_buffer(trace_buf_size);
         mutex_unlock(&trace_types_lock);
 
         return ret;
@@ -2860,7 +2981,7 @@ static int tracing_set_tracer(const char *buf)
         mutex_lock(&trace_types_lock);
 
         if (!ring_buffer_expanded) {
-                ret = tracing_resize_ring_buffer(trace_buf_size);
+                ret = __tracing_resize_ring_buffer(trace_buf_size);
                 if (ret < 0)
                         goto out;
                 ret = 0;
@@ -2966,20 +3087,11 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
                       size_t cnt, loff_t *ppos)
 {
         unsigned long *ptr = filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         *ptr = val * 1000;
@@ -3434,67 +3546,54 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
                       size_t cnt, loff_t *ppos)
 {
         unsigned long val;
-        char buf[64];
-        int ret, cpu;
-
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
+        int ret;
 
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         /* must have at least 1 entry */
         if (!val)
                 return -EINVAL;
 
-        mutex_lock(&trace_types_lock);
-
-        tracing_stop();
-
-        /* disable all cpu buffers */
-        for_each_tracing_cpu(cpu) {
-                if (global_trace.data[cpu])
-                        atomic_inc(&global_trace.data[cpu]->disabled);
-                if (max_tr.data[cpu])
-                        atomic_inc(&max_tr.data[cpu]->disabled);
-        }
-
         /* value is in KB */
         val <<= 10;
 
-        if (val != global_trace.entries) {
-                ret = tracing_resize_ring_buffer(val);
-                if (ret < 0) {
-                        cnt = ret;
-                        goto out;
-                }
-        }
+        ret = tracing_resize_ring_buffer(val);
+        if (ret < 0)
+                return ret;
 
         *ppos += cnt;
 
-        /* If check pages failed, return ENOMEM */
-        if (tracing_disabled)
-                cnt = -ENOMEM;
- out:
-        for_each_tracing_cpu(cpu) {
-                if (global_trace.data[cpu])
-                        atomic_dec(&global_trace.data[cpu]->disabled);
-                if (max_tr.data[cpu])
-                        atomic_dec(&max_tr.data[cpu]->disabled);
-        }
+        return cnt;
+}
 
-        tracing_start();
-        mutex_unlock(&trace_types_lock);
+static ssize_t
+tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
+                          size_t cnt, loff_t *ppos)
+{
+        /*
+         * There is no need to read what the user has written, this function
+         * is just to make sure that there is no error when "echo" is used
+         */
+
+        *ppos += cnt;
 
         return cnt;
 }
 
+static int
+tracing_free_buffer_release(struct inode *inode, struct file *filp)
+{
+        /* disable tracing ? */
+        if (trace_flags & TRACE_ITER_STOP_ON_FREE)
+                tracing_off();
+        /* resize the ring buffer to 0 */
+        tracing_resize_ring_buffer(0);
+
+        return 0;
+}
+
 static int mark_printk(const char *fmt, ...)
 {
         int ret;
@@ -3640,6 +3739,11 @@ static const struct file_operations tracing_entries_fops = {
         .llseek         = generic_file_llseek,
 };
 
+static const struct file_operations tracing_free_buffer_fops = {
+        .write          = tracing_free_buffer_write,
+        .release        = tracing_free_buffer_release,
+};
+
 static const struct file_operations tracing_mark_fops = {
         .open           = tracing_open_generic,
         .write          = tracing_mark_write,
@@ -3696,7 +3800,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
                 return 0;
 
         if (!info->spare)
-                info->spare = ring_buffer_alloc_read_page(info->tr->buffer);
+                info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu);
         if (!info->spare)
                 return -ENOMEM;
 
@@ -3704,8 +3808,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
         if (info->read < PAGE_SIZE)
                 goto read;
 
-        info->read = 0;
-
         trace_access_lock(info->cpu);
         ret = ring_buffer_read_page(info->tr->buffer,
                                     &info->spare,
@@ -3715,6 +3817,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
         if (ret < 0)
                 return 0;
 
+        info->read = 0;
+
 read:
         size = PAGE_SIZE - info->read;
         if (size > count)
@@ -3853,7 +3957,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
                 ref->ref = 1;
                 ref->buffer = info->tr->buffer;
-                ref->page = ring_buffer_alloc_read_page(ref->buffer);
+                ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu);
                 if (!ref->page) {
                         kfree(ref);
                         break;
@@ -3862,8 +3966,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 r = ring_buffer_read_page(ref->buffer, &ref->page,
                                           len, info->cpu, 1);
                 if (r < 0) {
-                        ring_buffer_free_read_page(ref->buffer,
-                                                   ref->page);
+                        ring_buffer_free_read_page(ref->buffer, ref->page);
                         kfree(ref);
                         break;
                 }
@@ -4099,19 +4202,10 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 {
         struct trace_option_dentry *topt = filp->private_data;
         unsigned long val;
-        char buf[64];
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         if (val != 0 && val != 1)
@@ -4159,20 +4253,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
                          loff_t *ppos)
 {
         long index = (long)filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         if (val != 0 && val != 1)
@@ -4365,6 +4450,9 @@ static __init int tracer_init_debugfs(void)
         trace_create_file("buffer_size_kb", 0644, d_tracer,
                         &global_trace, &tracing_entries_fops);
 
+        trace_create_file("free_buffer", 0644, d_tracer,
+                        &global_trace, &tracing_free_buffer_fops);
+
         trace_create_file("trace_marker", 0220, d_tracer,
                         NULL, &tracing_mark_fops);