3 files changed, 352 insertions, 41 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a8c275c01e8..f2a163db52f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -61,6 +61,8 @@ enum {
 
 static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
 
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
+
 /**
  * tracing_on - enable all tracing buffers
  *
@@ -132,7 +134,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
-#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	28
 
@@ -234,6 +236,18 @@ static void rb_init_page(struct buffer_data_page *bpage)
 	local_set(&bpage->commit, 0);
 }
 
+/**
+ * ring_buffer_page_len - the size of data on the page.
+ * @page: The page to read
+ *
+ * Returns the amount of data on the page, including buffer page header.
+ */
+size_t ring_buffer_page_len(void *page)
+{
+	return local_read(&((struct buffer_data_page *)page)->commit)
+		+ BUF_PAGE_HDR_SIZE;
+}
+
 /*
  * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
  * this issue out.
@@ -254,7 +268,7 @@ static inline int test_time_stamp(u64 delta)
 	return 0;
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
+#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
 
 /*
  * head_page == tail_page && head == tail then buffer is empty.
@@ -2378,8 +2392,8 @@ static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
  */
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
 {
-	unsigned long addr;
 	struct buffer_data_page *bpage;
+	unsigned long addr;
 
 	addr = __get_free_page(GFP_KERNEL);
 	if (!addr)
@@ -2387,6 +2401,8 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
 
 	bpage = (void *)addr;
 
+	rb_init_page(bpage);
+
 	return bpage;
 }
 
@@ -2406,6 +2422,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
  * ring_buffer_read_page - extract a page from the ring buffer
  * @buffer: buffer to extract from
  * @data_page: the page to use allocated from ring_buffer_alloc_read_page
+ * @len: amount to extract
  * @cpu: the cpu of the buffer to extract
  * @full: should the extraction only happen when the page is full.
  *
@@ -2418,7 +2435,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
  *	rpage = ring_buffer_alloc_read_page(buffer);
  *	if (!rpage)
  *		return error;
- *	ret = ring_buffer_read_page(buffer, &rpage, cpu, 0);
+ *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
  *	if (ret >= 0)
  *		process_page(rpage, ret);
  *
@@ -2435,70 +2452,103 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
  *  <0 if no data has been transferred.
  */
 int ring_buffer_read_page(struct ring_buffer *buffer,
-			    void **data_page, int cpu, int full)
+			  void **data_page, size_t len, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
 	struct buffer_data_page *bpage;
+	struct buffer_page *reader;
 	unsigned long flags;
+	unsigned int commit;
 	unsigned int read;
 	int ret = -1;
 
+	/*
+	 * If len is not big enough to hold the page header, then
+	 * we can not copy anything.
+	 */
+	if (len <= BUF_PAGE_HDR_SIZE)
+		return -1;
+
+	len -= BUF_PAGE_HDR_SIZE;
+
 	if (!data_page)
-		return 0;
+		return -1;
 
 	bpage = *data_page;
 	if (!bpage)
-		return 0;
+		return -1;
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
-	/*
-	 * rb_buffer_peek will get the next ring buffer if
-	 * the current reader page is empty.
-	 */
-	event = rb_buffer_peek(buffer, cpu, NULL);
-	if (!event)
+	reader = rb_get_reader_page(cpu_buffer);
+	if (!reader)
 		goto out;
 
-	/* check for data */
-	if (!local_read(&cpu_buffer->reader_page->page->commit))
-		goto out;
+	event = rb_reader_event(cpu_buffer);
+
+	read = reader->read;
+	commit = rb_page_commit(reader);
 
-	read = cpu_buffer->reader_page->read;
 	/*
-	 * If the writer is already off of the read page, then simply
-	 * switch the read page with the given page. Otherwise
-	 * we need to copy the data from the reader to the writer.
+	 * If this page has been partially read or
+	 * if len is not big enough to read the rest of the page or
+	 * a writer is still on the page, then
+	 * we must copy the data from the page to the buffer.
+	 * Otherwise, we can simply swap the page with the one passed in.
 	 */
-	if (cpu_buffer->reader_page == cpu_buffer->commit_page) {
-		unsigned int commit = rb_page_commit(cpu_buffer->reader_page);
+	if (read || (len < (commit - read)) ||
+	    cpu_buffer->reader_page == cpu_buffer->commit_page) {
 		struct buffer_data_page *rpage = cpu_buffer->reader_page->page;
+		unsigned int rpos = read;
+		unsigned int pos = 0;
+		unsigned int size;
 
 		if (full)
 			goto out;
-		/* The writer is still on the reader page, we must copy */
-		memcpy(bpage->data + read, rpage->data + read, commit - read);
 
-		/* consume what was read */
-		cpu_buffer->reader_page->read = commit;
+		if (len > (commit - read))
+			len = (commit - read);
+
+		size = rb_event_length(event);
+
+		if (len < size)
+			goto out;
+
+		/* Need to copy one event at a time */
+		do {
+			memcpy(bpage->data + pos, rpage->data + rpos, size);
+
+			len -= size;
+
+			rb_advance_reader(cpu_buffer);
+			rpos = reader->read;
+			pos += size;
+
+			event = rb_reader_event(cpu_buffer);
+			size = rb_event_length(event);
+		} while (len > size);
 
 		/* update bpage */
-		local_set(&bpage->commit, commit);
-		if (!read)
-			bpage->time_stamp = rpage->time_stamp;
+		local_set(&bpage->commit, pos);
+		bpage->time_stamp = rpage->time_stamp;
+
+		/* we copied everything to the beginning */
+		read = 0;
 	} else {
 		/* swap the pages */
 		rb_init_page(bpage);
-		bpage = cpu_buffer->reader_page->page;
-		cpu_buffer->reader_page->page = *data_page;
-		cpu_buffer->reader_page->read = 0;
+		bpage = reader->page;
+		reader->page = *data_page;
+		local_set(&reader->write, 0);
+		reader->read = 0;
 		*data_page = bpage;
+
+		/* update the entry counter */
+		rb_remove_entries(cpu_buffer, bpage, read);
 	}
 	ret = read;
 
-	/* update the entry counter */
-	rb_remove_entries(cpu_buffer, bpage, read);
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ea055aa21cd..12539f72f4a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -11,31 +11,30 @@
  *  Copyright (C) 2004-2006 Ingo Molnar
  *  Copyright (C) 2004 William Lee Irwin III
  */
+#include <linux/ring_buffer.h>
 #include <linux/utsrelease.h>
+#include <linux/stacktrace.h>
+#include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
+#include <linux/irqflags.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
 #include <linux/linkage.h>
 #include <linux/uaccess.h>
+#include <linux/kprobes.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/splice.h>
 #include <linux/kdebug.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/gfp.h>
 #include <linux/fs.h>
-#include <linux/kprobes.h>
-#include <linux/writeback.h>
-#include <linux/splice.h>
-
-#include <linux/stacktrace.h>
-#include <linux/ring_buffer.h>
-#include <linux/irqflags.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -3005,6 +3004,246 @@ static struct file_operations tracing_mark_fops = {
 	.write		= tracing_mark_write,
 };
 
+struct ftrace_buffer_info {
+	struct trace_array	*tr;
+	void			*spare;
+	int			cpu;
+	unsigned int		read;
+};
+
+static int tracing_buffers_open(struct inode *inode, struct file *filp)
+{
+	int cpu = (int)(long)inode->i_private;
+	struct ftrace_buffer_info *info;
+
+	if (tracing_disabled)
+		return -ENODEV;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->tr	= &global_trace;
+	info->cpu	= cpu;
+	info->spare	= ring_buffer_alloc_read_page(info->tr->buffer);
+	/* Force reading ring buffer for first read */
+	info->read	= (unsigned int)-1;
+	if (!info->spare)
+		goto out;
+
+	filp->private_data = info;
+
+	return 0;
+
+ out:
+	kfree(info);
+	return -ENOMEM;
+}
+
+static ssize_t
+tracing_buffers_read(struct file *filp, char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	struct ftrace_buffer_info *info = filp->private_data;
+	unsigned int pos;
+	ssize_t ret;
+	size_t size;
+
+	/* Do we have previous read data to read? */
+	if (info->read < PAGE_SIZE)
+		goto read;
+
+	info->read = 0;
+
+	ret = ring_buffer_read_page(info->tr->buffer,
+				    &info->spare,
+				    count,
+				    info->cpu, 0);
+	if (ret < 0)
+		return 0;
+
+	pos = ring_buffer_page_len(info->spare);
+
+	if (pos < PAGE_SIZE)
+		memset(info->spare + pos, 0, PAGE_SIZE - pos);
+
+read:
+	size = PAGE_SIZE - info->read;
+	if (size > count)
+		size = count;
+
+	ret = copy_to_user(ubuf, info->spare + info->read, size);
+	if (ret)
+		return -EFAULT;
+	*ppos += size;
+	info->read += size;
+
+	return size;
+}
+
+static int tracing_buffers_release(struct inode *inode, struct file *file)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+
+	ring_buffer_free_read_page(info->tr->buffer, info->spare);
+	kfree(info);
+
+	return 0;
+}
+
+struct buffer_ref {
+	struct ring_buffer	*buffer;
+	void			*page;
+	int			ref;
+};
+
+static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+
+	if (--ref->ref)
+		return;
+
+	ring_buffer_free_read_page(ref->buffer, ref->page);
+	kfree(ref);
+	buf->private = 0;
+}
+
+static int buffer_pipe_buf_steal(struct pipe_inode_info *pipe,
+				 struct pipe_buffer *buf)
+{
+	return 1;
+}
+
+static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+				struct pipe_buffer *buf)
+{
+	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
+
+	ref->ref++;
+}
+
+/* Pipe buffer operations for a buffer. */
+static struct pipe_buf_operations buffer_pipe_buf_ops = {
+	.can_merge		= 0,
+	.map			= generic_pipe_buf_map,
+	.unmap			= generic_pipe_buf_unmap,
+	.confirm		= generic_pipe_buf_confirm,
+	.release		= buffer_pipe_buf_release,
+	.steal			= buffer_pipe_buf_steal,
+	.get			= buffer_pipe_buf_get,
+};
+
+/*
+ * Callback from splice_to_pipe(), if we need to release some pages
+ * at the end of the spd in case we error'ed out in filling the pipe.
+ */
+static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
+{
+	struct buffer_ref *ref =
+		(struct buffer_ref *)spd->partial[i].private;
+
+	if (--ref->ref)
+		return;
+
+	ring_buffer_free_read_page(ref->buffer, ref->page);
+	kfree(ref);
+	spd->partial[i].private = 0;
+}
+
+static ssize_t
+tracing_buffers_splice_read(struct file *file, loff_t *ppos,
+			    struct pipe_inode_info *pipe, size_t len,
+			    unsigned int flags)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct partial_page partial[PIPE_BUFFERS];
+	struct page *pages[PIPE_BUFFERS];
+	struct splice_pipe_desc spd = {
+		.pages		= pages,
+		.partial	= partial,
+		.flags		= flags,
+		.ops		= &buffer_pipe_buf_ops,
+		.spd_release	= buffer_spd_release,
+	};
+	struct buffer_ref *ref;
+	int size, i;
+	size_t ret;
+
+	/*
+	 * We can't seek on a buffer input
+	 */
+	if (unlikely(*ppos))
+		return -ESPIPE;
+
+
+	for (i = 0; i < PIPE_BUFFERS && len; i++, len -= size) {
+		struct page *page;
+		int r;
+
+		ref = kzalloc(sizeof(*ref), GFP_KERNEL);
+		if (!ref)
+			break;
+
+		ref->buffer = info->tr->buffer;
+		ref->page = ring_buffer_alloc_read_page(ref->buffer);
+		if (!ref->page) {
+			kfree(ref);
+			break;
+		}
+
+		r = ring_buffer_read_page(ref->buffer, &ref->page,
+					  len, info->cpu, 0);
+		if (r < 0) {
+			ring_buffer_free_read_page(ref->buffer,
+						   ref->page);
+			kfree(ref);
+			break;
+		}
+
+		/*
+		 * zero out any left over data, this is going to
+		 * user land.
+		 */
+		size = ring_buffer_page_len(ref->page);
+		if (size < PAGE_SIZE)
+			memset(ref->page + size, 0, PAGE_SIZE - size);
+
+		page = virt_to_page(ref->page);
+
+		spd.pages[i] = page;
+		spd.partial[i].len = PAGE_SIZE;
+		spd.partial[i].offset = 0;
+		spd.partial[i].private = (unsigned long)ref;
+		spd.nr_pages++;
+	}
+
+	spd.nr_pages = i;
+
+	/* did we read anything? */
+	if (!spd.nr_pages) {
+		if (flags & SPLICE_F_NONBLOCK)
+			ret = -EAGAIN;
+		else
+			ret = 0;
+		/* TODO: block */
+		return ret;
+	}
+
+	ret = splice_to_pipe(pipe, &spd);
+
+	return ret;
+}
+
+static const struct file_operations tracing_buffers_fops = {
+	.open		= tracing_buffers_open,
+	.read		= tracing_buffers_read,
+	.release	= tracing_buffers_release,
+	.splice_read	= tracing_buffers_splice_read,
+	.llseek		= no_llseek,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int __weak ftrace_arch_read_dyn_info(char *buf, int size)
@@ -3399,6 +3638,7 @@ static __init void create_trace_options_dir(void)
 static __init int tracer_init_debugfs(void)
 {
 	struct dentry *d_tracer;
+	struct dentry *buffers;
 	struct dentry *entry;
 	int cpu;
 
@@ -3471,6 +3711,26 @@ static __init int tracer_init_debugfs(void)
 		pr_warning("Could not create debugfs "
 			   "'trace_marker' entry\n");
 
+	buffers = debugfs_create_dir("binary_buffers", d_tracer);
+
+	if (!buffers)
+		pr_warning("Could not create buffers directory\n");
+	else {
+		int cpu;
+		char buf[64];
+
+		for_each_tracing_cpu(cpu) {
+			sprintf(buf, "%d", cpu);
+
+			entry = debugfs_create_file(buf, 0444, buffers,
+						    (void *)(long)cpu,
+						    &tracing_buffers_fops);
+			if (!entry)
+				pr_warning("Could not create debugfs buffers "
+					   "'%s' entry\n", buf);
+		}
+	}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 				    &ftrace_update_tot_cnt,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e606633fb49..561bb5c5d98 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -217,6 +217,7 @@ enum trace_flag_type {
  */
 struct trace_array_cpu {
 	atomic_t		disabled;
+	void			*buffer_page;	/* ring buffer spare */
 
 	/* these fields get copied into max-trace: */
 	unsigned long		trace_idx;