Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (413 commits)
  tracing, net: fix net tree and tracing tree merge interaction
  tracing, powerpc: fix powerpc tree and tracing tree interaction
  ring-buffer: do not remove reader page from list on ring buffer free
  function-graph: allow unregistering twice
  trace: make argument 'mem' of trace_seq_putmem() const
  tracing: add missing 'extern' keywords to trace_output.h
  tracing: provide trace_seq_reserve()
  blktrace: print out BLK_TN_MESSAGE properly
  blktrace: extract duplidate code
  blktrace: fix memory leak when freeing struct blk_io_trace
  blktrace: fix blk_probes_ref chaos
  blktrace: make classic output more classic
  blktrace: fix off-by-one bug
  blktrace: fix the original blktrace
  blktrace: fix a race when creating blk_tree_root in debugfs
  blktrace: fix timestamp in binary output
  tracing, Text Edit Lock: cleanup
  tracing: filter fix for TRACE_EVENT_FORMAT events
  ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release()
  x86: kretprobe-booster interrupt emulation code fix
  ...

Fix up trivial conflicts in
 arch/parisc/include/asm/ftrace.h
 include/linux/memory.h
 kernel/extable.c
 kernel/module.c

39 files changed, 11202 insertions, 2492 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 504086ab4443..2246141bda4d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -9,6 +9,9 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool
 
+config HAVE_FTRACE_NMI_ENTER
+	bool
+
 config HAVE_FUNCTION_TRACER
 	bool
 
@@ -31,12 +34,20 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config HAVE_HW_BRANCH_TRACER
 	bool
 
+config HAVE_FTRACE_SYSCALLS
+	bool
+
 config TRACER_MAX_TRACE
 	bool
 
 config RING_BUFFER
 	bool
 
+config FTRACE_NMI_ENTER
+       bool
+       depends on HAVE_FTRACE_NMI_ENTER
+       default y
+
 config TRACING
 	bool
 	select DEBUG_FS
@@ -44,13 +55,29 @@ config TRACING
 	select STACKTRACE if STACKTRACE_SUPPORT
 	select TRACEPOINTS
 	select NOP_TRACER
+	select BINARY_PRINTF
+
+#
+# Minimum requirements an architecture has to meet for us to
+# be able to offer generic tracing facilities:
+#
+config TRACING_SUPPORT
+	bool
+	# PPC32 has no irqflags tracing support, but it can use most of the
+	# tracers anyway, they were tested to build and work. Note that new
+	# exceptions to this list aren't welcomed, better implement the
+	# irqflags tracing for your architecture.
+	depends on TRACE_IRQFLAGS_SUPPORT || PPC32
+	depends on STACKTRACE_SUPPORT
+	default y
+
+if TRACING_SUPPORT
 
 menu "Tracers"
 
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	depends on DEBUG_KERNEL
 	select FRAME_POINTER
 	select KALLSYMS
 	select TRACING
@@ -82,7 +109,6 @@ config IRQSOFF_TRACER
 	default n
 	depends on TRACE_IRQFLAGS_SUPPORT
 	depends on GENERIC_TIME
-	depends on DEBUG_KERNEL
 	select TRACE_IRQFLAGS
 	select TRACING
 	select TRACER_MAX_TRACE
@@ -105,7 +131,6 @@ config PREEMPT_TRACER
 	default n
 	depends on GENERIC_TIME
 	depends on PREEMPT
-	depends on DEBUG_KERNEL
 	select TRACING
 	select TRACER_MAX_TRACE
 	help
@@ -126,13 +151,13 @@ config SYSPROF_TRACER
 	bool "Sysprof Tracer"
 	depends on X86
 	select TRACING
+	select CONTEXT_SWITCH_TRACER
 	help
 	  This tracer provides the trace needed by the 'Sysprof' userspace
 	  tool.
 
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
-	depends on DEBUG_KERNEL
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
@@ -142,16 +167,30 @@ config SCHED_TRACER
 
 config CONTEXT_SWITCH_TRACER
 	bool "Trace process context switches"
-	depends on DEBUG_KERNEL
 	select TRACING
 	select MARKERS
 	help
 	  This tracer gets called from the context switch and records
 	  all switching of tasks.
 
+config EVENT_TRACER
+	bool "Trace various events in the kernel"
+	select TRACING
+	help
+	  This tracer hooks to various trace points in the kernel
+	  allowing the user to pick and choose which trace point they
+	  want to trace.
+
+config FTRACE_SYSCALLS
+	bool "Trace syscalls"
+	depends on HAVE_FTRACE_SYSCALLS
+	select TRACING
+	select KALLSYMS
+	help
+	  Basic tracer to catch the syscall entry and exit events.
+
 config BOOT_TRACER
 	bool "Trace boot initcalls"
-	depends on DEBUG_KERNEL
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	help
@@ -164,13 +203,11 @@ config BOOT_TRACER
 	  representation of the delays during initcalls - but the raw
 	  /debug/tracing/trace text output is readable too.
 
-	  ( Note that tracing self tests can't be enabled if this tracer is
-	    selected, because the self-tests are an initcall as well and that
-	    would invalidate the boot trace. )
+	  You must pass in ftrace=initcall to the kernel command line
+	  to enable this on bootup.
 
 config TRACE_BRANCH_PROFILING
 	bool "Trace likely/unlikely profiler"
-	depends on DEBUG_KERNEL
 	select TRACING
 	help
 	  This tracer profiles all the the likely and unlikely macros
@@ -223,7 +260,6 @@ config BRANCH_TRACER
 
 config POWER_TRACER
 	bool "Trace power consumption behavior"
-	depends on DEBUG_KERNEL
 	depends on X86
 	select TRACING
 	help
@@ -235,7 +271,6 @@ config POWER_TRACER
 config STACK_TRACER
 	bool "Trace max stack"
 	depends on HAVE_FUNCTION_TRACER
-	depends on DEBUG_KERNEL
 	select FUNCTION_TRACER
 	select STACKTRACE
 	select KALLSYMS
@@ -265,11 +300,66 @@ config HW_BRANCH_TRACER
 	  This tracer records all branches on the system in a circular
 	  buffer giving access to the last N branches for each cpu.
 
+config KMEMTRACE
+	bool "Trace SLAB allocations"
+	select TRACING
+	help
+	  kmemtrace provides tracing for slab allocator functions, such as
+	  kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
+	  data is then fed to the userspace application in order to analyse
+	  allocation hotspots, internal fragmentation and so on, making it
+	  possible to see how well an allocator performs, as well as debug
+	  and profile kernel code.
+
+	  This requires an userspace application to use. See
+	  Documentation/vm/kmemtrace.txt for more information.
+
+	  Saying Y will make the kernel somewhat larger and slower. However,
+	  if you disable kmemtrace at run-time or boot-time, the performance
+	  impact is minimal (depending on the arch the kernel is built for).
+
+	  If unsure, say N.
+
+config WORKQUEUE_TRACER
+	bool "Trace workqueues"
+	select TRACING
+	help
+	  The workqueue tracer provides some statistical informations
+          about each cpu workqueue thread such as the number of the
+          works inserted and executed since their creation. It can help
+          to evaluate the amount of work each of them have to perform.
+          For example it can help a developer to decide whether he should
+          choose a per cpu workqueue instead of a singlethreaded one.
+
+config BLK_DEV_IO_TRACE
+	bool "Support for tracing block io actions"
+	depends on SYSFS
+	depends on BLOCK
+	select RELAY
+	select DEBUG_FS
+	select TRACEPOINTS
+	select TRACING
+	select STACKTRACE
+	help
+	  Say Y here if you want to be able to trace the block layer actions
+	  on a given queue. Tracing allows you to see any traffic happening
+	  on a block device queue. For more information (and the userspace
+	  support tools needed), fetch the blktrace tools from:
+
+	  git://git.kernel.dk/blktrace.git
+
+	  Tracing also is possible using the ftrace interface, e.g.:
+
+	    echo 1 > /sys/block/sda/sda1/trace/enable
+	    echo blk > /sys/kernel/debug/tracing/current_tracer
+	    cat /sys/kernel/debug/tracing/trace_pipe
+
+	  If unsure, say N.
+
 config DYNAMIC_FTRACE
 	bool "enable/disable ftrace tracepoints dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
-	depends on DEBUG_KERNEL
 	default y
 	help
          This option will modify all the calls to ftrace dynamically
@@ -295,7 +385,7 @@ config FTRACE_SELFTEST
 
 config FTRACE_STARTUP_TEST
 	bool "Perform a startup test on ftrace"
-	depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER
+	depends on TRACING
 	select FTRACE_SELFTEST
 	help
 	  This option performs a series of startup tests on ftrace. On bootup
@@ -305,7 +395,7 @@ config FTRACE_STARTUP_TEST
 
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
-	depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+	depends on HAVE_MMIOTRACE_SUPPORT && PCI
 	select TRACING
 	help
 	  Mmiotrace traces Memory Mapped I/O access and is meant for
@@ -327,3 +417,6 @@ config MMIOTRACE_TEST
 	  Say N, unless you absolutely know what you are doing.
 
 endmenu
+
+endif # TRACING_SUPPORT
+
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 349d5a93653f..2630f5121ec1 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -19,6 +19,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
 obj-$(CONFIG_TRACING) += trace.o
+obj-$(CONFIG_TRACING) += trace_clock.o
+obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_stat.o
+obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
@@ -33,5 +37,14 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_POWER_TRACER) += trace_power.o
+obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
+obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events.o
+obj-$(CONFIG_EVENT_TRACER) += events.o
+obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
new file mode 100644
index 000000000000..947c5b3f90c4
--- /dev/null
+++ b/kernel/trace/blktrace.c
@@ -0,0 +1,1549 @@
+/*
+ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blktrace_api.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/time.h>
+#include <trace/block.h>
+#include <linux/uaccess.h>
+#include "trace_output.h"
+
+static unsigned int blktrace_seq __read_mostly = 1;
+
+static struct trace_array *blk_tr;
+static bool blk_tracer_enabled __read_mostly;
+
+/* Select an alternative, minimalistic output than the original one */
+#define TRACE_BLK_OPT_CLASSIC	0x1
+
+static struct tracer_opt blk_tracer_opts[] = {
+	/* Default disable the minimalistic output */
+	{ TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) },
+	{ }
+};
+
+static struct tracer_flags blk_tracer_flags = {
+	.val  = 0,
+	.opts = blk_tracer_opts,
+};
+
+/* Global reference count of probes */
+static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+
+static void blk_register_tracepoints(void);
+static void blk_unregister_tracepoints(void);
+
+/*
+ * Send out a notify message.
+ */
+static void trace_note(struct blk_trace *bt, pid_t pid, int action,
+		       const void *data, size_t len)
+{
+	struct blk_io_trace *t;
+	struct ring_buffer_event *event = NULL;
+	int pc = 0;
+	int cpu = smp_processor_id();
+	bool blk_tracer = blk_tracer_enabled;
+
+	if (blk_tracer) {
+		pc = preempt_count();
+		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+						  sizeof(*t) + len,
+						  0, pc);
+		if (!event)
+			return;
+		t = ring_buffer_event_data(event);
+		goto record_it;
+	}
+
+	if (!bt->rchan)
+		return;
+
+	t = relay_reserve(bt->rchan, sizeof(*t) + len);
+	if (t) {
+		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+		t->time = ktime_to_ns(ktime_get());
+record_it:
+		t->device = bt->dev;
+		t->action = action;
+		t->pid = pid;
+		t->cpu = cpu;
+		t->pdu_len = len;
+		memcpy((void *) t + sizeof(*t), data, len);
+
+		if (blk_tracer)
+			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+	}
+}
+
+/*
+ * Send out a notify for this process, if we haven't done so since a trace
+ * started
+ */
+static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+{
+	tsk->btrace_seq = blktrace_seq;
+	trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
+}
+
+static void trace_note_time(struct blk_trace *bt)
+{
+	struct timespec now;
+	unsigned long flags;
+	u32 words[2];
+
+	getnstimeofday(&now);
+	words[0] = now.tv_sec;
+	words[1] = now.tv_nsec;
+
+	local_irq_save(flags);
+	trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words));
+	local_irq_restore(flags);
+}
+
+void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
+{
+	int n;
+	va_list args;
+	unsigned long flags;
+	char *buf;
+
+	if (unlikely(bt->trace_state != Blktrace_running &&
+		     !blk_tracer_enabled))
+		return;
+
+	local_irq_save(flags);
+	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
+	va_start(args, fmt);
+	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
+	va_end(args);
+
+	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(__trace_note_message);
+
+static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
+			 pid_t pid)
+{
+	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
+		return 1;
+	if (sector < bt->start_lba || sector > bt->end_lba)
+		return 1;
+	if (bt->pid && pid != bt->pid)
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Data direction bit lookup
+ */
+static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
+				 BLK_TC_ACT(BLK_TC_WRITE) };
+
+/* The ilog2() calls fall out because they're constant */
+#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
+	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name))
+
+/*
+ * The worker for the various blk_add_trace*() types. Fills out a
+ * blk_io_trace structure and places it in a per-cpu subbuffer.
+ */
+static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
+		     int rw, u32 what, int error, int pdu_len, void *pdu_data)
+{
+	struct task_struct *tsk = current;
+	struct ring_buffer_event *event = NULL;
+	struct blk_io_trace *t;
+	unsigned long flags = 0;
+	unsigned long *sequence;
+	pid_t pid;
+	int cpu, pc = 0;
+	bool blk_tracer = blk_tracer_enabled;
+
+	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
+		return;
+
+	what |= ddir_act[rw & WRITE];
+	what |= MASK_TC_BIT(rw, BARRIER);
+	what |= MASK_TC_BIT(rw, SYNCIO);
+	what |= MASK_TC_BIT(rw, AHEAD);
+	what |= MASK_TC_BIT(rw, META);
+	what |= MASK_TC_BIT(rw, DISCARD);
+
+	pid = tsk->pid;
+	if (unlikely(act_log_check(bt, what, sector, pid)))
+		return;
+	cpu = raw_smp_processor_id();
+
+	if (blk_tracer) {
+		tracing_record_cmdline(current);
+
+		pc = preempt_count();
+		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+						  sizeof(*t) + pdu_len,
+						  0, pc);
+		if (!event)
+			return;
+		t = ring_buffer_event_data(event);
+		goto record_it;
+	}
+
+	/*
+	 * A word about the locking here - we disable interrupts to reserve
+	 * some space in the relay per-cpu buffer, to prevent an irq
+	 * from coming in and stepping on our toes.
+	 */
+	local_irq_save(flags);
+
+	if (unlikely(tsk->btrace_seq != blktrace_seq))
+		trace_note_tsk(bt, tsk);
+
+	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
+	if (t) {
+		sequence = per_cpu_ptr(bt->sequence, cpu);
+
+		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+		t->sequence = ++(*sequence);
+		t->time = ktime_to_ns(ktime_get());
+record_it:
+		/*
+		 * These two are not needed in ftrace as they are in the
+		 * generic trace_entry, filled by tracing_generic_entry_update,
+		 * but for the trace_event->bin() synthesizer benefit we do it
+		 * here too.
+		 */
+		t->cpu = cpu;
+		t->pid = pid;
+
+		t->sector = sector;
+		t->bytes = bytes;
+		t->action = what;
+		t->device = bt->dev;
+		t->error = error;
+		t->pdu_len = pdu_len;
+
+		if (pdu_len)
+			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
+
+		if (blk_tracer) {
+			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			return;
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+static struct dentry *blk_tree_root;
+static DEFINE_MUTEX(blk_tree_mutex);
+
+static void blk_trace_free(struct blk_trace *bt)
+{
+	debugfs_remove(bt->msg_file);
+	debugfs_remove(bt->dropped_file);
+	relay_close(bt->rchan);
+	free_percpu(bt->sequence);
+	free_percpu(bt->msg_data);
+	kfree(bt);
+}
+
+static void blk_trace_cleanup(struct blk_trace *bt)
+{
+	blk_trace_free(bt);
+	if (atomic_dec_and_test(&blk_probes_ref))
+		blk_unregister_tracepoints();
+}
+
+int blk_trace_remove(struct request_queue *q)
+{
+	struct blk_trace *bt;
+
+	bt = xchg(&q->blk_trace, NULL);
+	if (!bt)
+		return -EINVAL;
+
+	if (bt->trace_state != Blktrace_running)
+		blk_trace_cleanup(bt);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_trace_remove);
+
+static int blk_dropped_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = inode->i_private;
+
+	return 0;
+}
+
+static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
+				size_t count, loff_t *ppos)
+{
+	struct blk_trace *bt = filp->private_data;
+	char buf[16];
+
+	snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
+
+	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+static const struct file_operations blk_dropped_fops = {
+	.owner =	THIS_MODULE,
+	.open =		blk_dropped_open,
+	.read =		blk_dropped_read,
+};
+
+static int blk_msg_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = inode->i_private;
+
+	return 0;
+}
+
+static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
+				size_t count, loff_t *ppos)
+{
+	char *msg;
+	struct blk_trace *bt;
+
+	if (count > BLK_TN_MAX_MSG)
+		return -EINVAL;
+
+	msg = kmalloc(count, GFP_KERNEL);
+	if (msg == NULL)
+		return -ENOMEM;
+
+	if (copy_from_user(msg, buffer, count)) {
+		kfree(msg);
+		return -EFAULT;
+	}
+
+	bt = filp->private_data;
+	__trace_note_message(bt, "%s", msg);
+	kfree(msg);
+
+	return count;
+}
+
+static const struct file_operations blk_msg_fops = {
+	.owner =	THIS_MODULE,
+	.open =		blk_msg_open,
+	.write =	blk_msg_write,
+};
+
+/*
+ * Keep track of how many times we encountered a full subbuffer, to aid
+ * the user space app in telling how many lost events there were.
+ */
+static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
+				     void *prev_subbuf, size_t prev_padding)
+{
+	struct blk_trace *bt;
+
+	if (!relay_buf_full(buf))
+		return 1;
+
+	bt = buf->chan->private_data;
+	atomic_inc(&bt->dropped);
+	return 0;
+}
+
+static int blk_remove_buf_file_callback(struct dentry *dentry)
+{
+	struct dentry *parent = dentry->d_parent;
+	debugfs_remove(dentry);
+
+	/*
+	* this will fail for all but the last file, but that is ok. what we
+	* care about is the top level buts->name directory going away, when
+	* the last trace file is gone. Then we don't have to rmdir() that
+	* manually on trace stop, so it nicely solves the issue with
+	* force killing of running traces.
+	*/
+
+	debugfs_remove(parent);
+	return 0;
+}
+
+static struct dentry *blk_create_buf_file_callback(const char *filename,
+						   struct dentry *parent,
+						   int mode,
+						   struct rchan_buf *buf,
+						   int *is_global)
+{
+	return debugfs_create_file(filename, mode, parent, buf,
+					&relay_file_operations);
+}
+
+static struct rchan_callbacks blk_relay_callbacks = {
+	.subbuf_start		= blk_subbuf_start_callback,
+	.create_buf_file	= blk_create_buf_file_callback,
+	.remove_buf_file	= blk_remove_buf_file_callback,
+};
+
+/*
+ * Setup everything required to start tracing
+ */
+int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			struct blk_user_trace_setup *buts)
+{
+	struct blk_trace *old_bt, *bt = NULL;
+	struct dentry *dir = NULL;
+	int ret, i;
+
+	if (!buts->buf_size || !buts->buf_nr)
+		return -EINVAL;
+
+	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
+	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
+
+	/*
+	 * some device names have larger paths - convert the slashes
+	 * to underscores for this to work as expected
+	 */
+	for (i = 0; i < strlen(buts->name); i++)
+		if (buts->name[i] == '/')
+			buts->name[i] = '_';
+
+	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
+	if (!bt)
+		return -ENOMEM;
+
+	ret = -ENOMEM;
+	bt->sequence = alloc_percpu(unsigned long);
+	if (!bt->sequence)
+		goto err;
+
+	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
+	if (!bt->msg_data)
+		goto err;
+
+	ret = -ENOENT;
+
+	mutex_lock(&blk_tree_mutex);
+	if (!blk_tree_root) {
+		blk_tree_root = debugfs_create_dir("block", NULL);
+		if (!blk_tree_root) {
+			mutex_unlock(&blk_tree_mutex);
+			goto err;
+		}
+	}
+	mutex_unlock(&blk_tree_mutex);
+
+	dir = debugfs_create_dir(buts->name, blk_tree_root);
+
+	if (!dir)
+		goto err;
+
+	bt->dir = dir;
+	bt->dev = dev;
+	atomic_set(&bt->dropped, 0);
+
+	ret = -EIO;
+	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
+					       &blk_dropped_fops);
+	if (!bt->dropped_file)
+		goto err;
+
+	bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
+	if (!bt->msg_file)
+		goto err;
+
+	bt->rchan = relay_open("trace", dir, buts->buf_size,
+				buts->buf_nr, &blk_relay_callbacks, bt);
+	if (!bt->rchan)
+		goto err;
+
+	bt->act_mask = buts->act_mask;
+	if (!bt->act_mask)
+		bt->act_mask = (u16) -1;
+
+	bt->start_lba = buts->start_lba;
+	bt->end_lba = buts->end_lba;
+	if (!bt->end_lba)
+		bt->end_lba = -1ULL;
+
+	bt->pid = buts->pid;
+	bt->trace_state = Blktrace_setup;
+
+	ret = -EBUSY;
+	old_bt = xchg(&q->blk_trace, bt);
+	if (old_bt) {
+		(void) xchg(&q->blk_trace, old_bt);
+		goto err;
+	}
+
+	if (atomic_inc_return(&blk_probes_ref) == 1)
+		blk_register_tracepoints();
+
+	return 0;
+err:
+	blk_trace_free(bt);
+	return ret;
+}
+
+int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+		    char __user *arg)
+{
+	struct blk_user_trace_setup buts;
+	int ret;
+
+	ret = copy_from_user(&buts, arg, sizeof(buts));
+	if (ret)
+		return -EFAULT;
+
+	ret = do_blk_trace_setup(q, name, dev, &buts);
+	if (ret)
+		return ret;
+
+	if (copy_to_user(arg, &buts, sizeof(buts)))
+		return -EFAULT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_trace_setup);
+
+int blk_trace_startstop(struct request_queue *q, int start)
+{
+	int ret;
+	struct blk_trace *bt = q->blk_trace;
+
+	if (bt == NULL)
+		return -EINVAL;
+
+	/*
+	 * For starting a trace, we can transition from a setup or stopped
+	 * trace. For stopping a trace, the state must be running
+	 */
+	ret = -EINVAL;
+	if (start) {
+		if (bt->trace_state == Blktrace_setup ||
+		    bt->trace_state == Blktrace_stopped) {
+			blktrace_seq++;
+			smp_mb();
+			bt->trace_state = Blktrace_running;
+
+			trace_note_time(bt);
+			ret = 0;
+		}
+	} else {
+		if (bt->trace_state == Blktrace_running) {
+			bt->trace_state = Blktrace_stopped;
+			relay_flush(bt->rchan);<