1 files changed, 285 insertions, 123 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0df1b0f..086d363 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -32,10 +32,11 @@
 #include <linux/splice.h>
 #include <linux/kdebug.h>
 #include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
-#include <linux/gfp.h>
 #include <linux/fs.h>
 
 #include "trace.h"
@@ -91,20 +92,17 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 static inline void ftrace_disable_cpu(void)
 {
 	preempt_disable();
-	__this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_inc(ftrace_cpu_disabled);
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-	__this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_dec(ftrace_cpu_disabled);
 	preempt_enable();
 }
 
 static cpumask_var_t __read_mostly	tracing_buffer_mask;
 
-/* Define which cpu buffers are currently read in trace_pipe */
-static cpumask_var_t			tracing_reader_cpumask;
-
 #define for_each_tracing_cpu(cpu)	\
 	for_each_cpu(cpu, tracing_buffer_mask)
 
@@ -119,9 +117,12 @@ static cpumask_var_t			tracing_reader_cpumask;
  *
  * It is default off, but you can enable it with either specifying
  * "ftrace_dump_on_oops" in the kernel command line, or setting
- * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ * /proc/sys/kernel/ftrace_dump_on_oops
+ * Set 1 if you want to dump buffers of all CPUs
+ * Set 2 if you want to dump the buffer of the CPU that triggered oops
  */
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
 
 static int tracing_set_tracer(const char *buf);
 
@@ -141,8 +142,17 @@ __setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {
-	ftrace_dump_on_oops = 1;
-	return 1;
+	if (*str++ != '=' || !*str) {
+		ftrace_dump_on_oops = DUMP_ALL;
+		return 1;
+	}
+
+	if (!strcmp("orig_cpu", str)) {
+		ftrace_dump_on_oops = DUMP_ORIG;
+                return 1;
+        }
+
+        return 0;
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
@@ -243,12 +253,91 @@ static struct tracer		*current_trace __read_mostly;
 
 /*
  * trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
  */
 static DEFINE_MUTEX(trace_types_lock);
 
+/*
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ *   A) the page of the consumed events may become a normal page
+ *      (not reader page) in ring buffer, and this page will be rewrited
+ *      by events producer.
+ *   B) The page of the consumed events may become a page for splice_read,
+ *      and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
+ */
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+	if (cpu == TRACE_PIPE_ALL_CPU) {
+		/* gain it for accessing the whole ring buffer. */
+		down_write(&all_cpu_access_lock);
+	} else {
+		/* gain it for accessing a cpu ring buffer. */
+
+		/* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+		down_read(&all_cpu_access_lock);
+
+		/* Secondly block other access to this @cpu ring buffer. */
+		mutex_lock(&per_cpu(cpu_access_lock, cpu));
+	}
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+	if (cpu == TRACE_PIPE_ALL_CPU) {
+		up_write(&all_cpu_access_lock);
+	} else {
+		mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+		up_read(&all_cpu_access_lock);
+	}
+}
+
+static inline void trace_access_lock_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+	(void)cpu;
+	mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+	(void)cpu;
+	mutex_unlock(&access_lock);
+}
+
+static inline void trace_access_lock_init(void)
+{
+}
+
+#endif
+
 /* trace_wait is a waitqueue for tasks blocked on trace_poll */
 static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
@@ -297,6 +386,21 @@ static int __init set_buf_size(char *str)
 }
 __setup("trace_buf_size=", set_buf_size);
 
+static int __init set_tracing_thresh(char *str)
+{
+	unsigned long threshhold;
+	int ret;
+
+	if (!str)
+		return 0;
+	ret = strict_strtoul(str, 0, &threshhold);
+	if (ret < 0)
+		return 0;
+	tracing_thresh = threshhold * 1000;
+	return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
 unsigned long nsecs_to_usecs(unsigned long nsecs)
 {
 	return nsecs / 1000;
@@ -502,9 +606,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 static arch_spinlock_t ftrace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
+unsigned long __read_mostly	tracing_thresh;
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 unsigned long __read_mostly	tracing_max_latency;
-unsigned long __read_mostly	tracing_thresh;
 
 /*
  * Copy the new maximum trace into the separate maximum-trace
@@ -515,7 +620,7 @@ static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct trace_array_cpu *data = tr->data[cpu];
-	struct trace_array_cpu *max_data = tr->data[cpu];
+	struct trace_array_cpu *max_data;
 
 	max_tr.cpu = cpu;
 	max_tr.time_start = data->preempt_timestamp;
@@ -525,7 +630,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
-	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+	memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
 	max_data->pid = tsk->pid;
 	max_data->uid = task_uid(tsk);
 	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
@@ -747,10 +852,10 @@ out:
 	mutex_unlock(&trace_types_lock);
 }
 
-static void __tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
 {
 	ftrace_disable_cpu();
-	ring_buffer_reset_cpu(tr->buffer, cpu);
+	ring_buffer_reset_cpu(buffer, cpu);
 	ftrace_enable_cpu();
 }
 
@@ -762,7 +867,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
 	/* Make sure all commits have finished */
 	synchronize_sched();
-	__tracing_reset(tr, cpu);
+	__tracing_reset(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -780,7 +885,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		__tracing_reset(tr, cpu);
+		__tracing_reset(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -857,6 +962,8 @@ void tracing_start(void)
 		goto out;
 	}
 
+	/* Prevent the buffers from switching */
+	arch_spin_lock(&ftrace_max_lock);
 
 	buffer = global_trace.buffer;
 	if (buffer)
@@ -866,6 +973,8 @@ void tracing_start(void)
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
+	arch_spin_unlock(&ftrace_max_lock);
+
 	ftrace_start();
  out:
 	spin_unlock_irqrestore(&tracing_start_lock, flags);
@@ -887,6 +996,9 @@ void tracing_stop(void)
 	if (trace_stop_count++)
 		goto out;
 
+	/* Prevent the buffers from switching */
+	arch_spin_lock(&ftrace_max_lock);
+
 	buffer = global_trace.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
@@ -895,6 +1007,8 @@ void tracing_stop(void)
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
+	arch_spin_unlock(&ftrace_max_lock);
+
  out:
 	spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
@@ -951,6 +1065,11 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
+	if (WARN_ON_ONCE(pid < 0)) {
+		strcpy(comm, "<XXX>");
+		return;
+	}
+
 	if (pid > PID_MAX_DEFAULT) {
 		strcpy(comm, "<...>");
 		return;
@@ -1084,7 +1203,7 @@ trace_function(struct trace_array *tr,
 	struct ftrace_entry *entry;
 
 	/* If we are reading the ring buffer, don't trace */
-	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -1177,6 +1296,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
+	/*
+	 * NMIs can not handle page faults, even with fix ups.
+	 * The save user stack can (and often does) fault.
+	 */
+	if (unlikely(in_nmi()))
+		return;
+
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -1315,8 +1441,10 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(buffer, flags, 6, pc);
+	}
 
 out_unlock:
 	arch_spin_unlock(&trace_buf_lock);
@@ -1389,8 +1517,10 @@ int trace_array_vprintk(struct trace_array *tr,
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = '\0';
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(buffer, irq_flags, 6, pc);
+	}
 
  out_unlock:
 	arch_spin_unlock(&trace_buf_lock);
@@ -1427,7 +1557,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+		unsigned long *lost_events)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1438,7 +1569,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
-		event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+					 lost_events);
 
 	ftrace_enable_cpu();
 
@@ -1446,10 +1578,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+		  unsigned long *missing_events, u64 *ent_ts)
 {
 	struct ring_buffer *buffer = iter->tr->buffer;
 	struct trace_entry *ent, *next = NULL;
+	unsigned long lost_events = 0, next_lost = 0;
 	int cpu_file = iter->cpu_file;
 	u64 next_ts = 0, ts;
 	int next_cpu = -1;
@@ -1462,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (cpu_file > TRACE_PIPE_ALL_CPU) {
 		if (ring_buffer_empty_cpu(buffer, cpu_file))
 			return NULL;
-		ent = peek_next_entry(iter, cpu_file, ent_ts);
+		ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
 		if (ent_cpu)
 			*ent_cpu = cpu_file;
 
@@ -1474,7 +1608,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 		if (ring_buffer_empty_cpu(buffer, cpu))
 			continue;
 
-		ent = peek_next_entry(iter, cpu, &ts);
+		ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
 		/*
 		 * Pick the entry with the smallest timestamp:
@@ -1483,6 +1617,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 			next = ent;
 			next_cpu = cpu;
 			next_ts = ts;
+			next_lost = lost_events;
 		}
 	}
 
@@ -1492,6 +1627,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 	if (ent_ts)
 		*ent_ts = next_ts;
 
+	if (missing_events)
+		*missing_events = next_lost;
+
 	return next;
 }
 
@@ -1499,13 +1637,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, ent_ts);
+	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-	iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+	iter->ent = __find_next_entry(iter, &iter->cpu,
+				      &iter->lost_events, &iter->ts);
 
 	if (iter->ent)
 		trace_iterator_increment(iter);
@@ -1517,7 +1656,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
-	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+			    &iter->lost_events);
 	ftrace_enable_cpu();
 }
 
@@ -1580,12 +1720,6 @@ static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 }
 
 /*
- * No necessary locking here. The worst thing which can
- * happen is loosing events consumed at the same time
- * by a trace_pipe reader.
- * Other than that, we don't risk to crash the ring buffer
- * because it serializes the readers.
- *
  * The current tracer is copied to avoid a global locking
  * all around.
  */
@@ -1623,6 +1757,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 		ftrace_enable_cpu();
 
+		iter->leftover = 0;
 		for (p = iter; p && l < *pos; p = s_next(m, p, &l))
 			;
 
@@ -1640,12 +1775,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	}
 
 	trace_event_read_lock();
+	trace_access_lock(cpu_file);
 	return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
+	struct trace_iterator *iter = m->private;
+
 	atomic_dec(&trace_record_cmdline_disabled);
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
 
@@ -1669,7 +1808,7 @@ static void print_func_help_header(struct seq_file *m)
 }
 
 
-static void
+void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
 	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1797,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 	}
 
 	if (event)
-		return event->trace(iter, sym_flags);
+		return event->funcs->trace(iter, sym_flags, event);
 
 	if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
 		goto partial;
@@ -1823,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
 	event = ftrace_find_event(entry->type);
 	if (event)
-		return event->raw(iter, 0);
+		return event->funcs->raw(iter, 0, event);
 
 	if (!trace_seq_printf(s, "%d ?\n", entry->type))
 		goto partial;
@@ -1850,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
 	event = ftrace_find_event(entry->type);
 	if (event) {
-		enum print_line_t ret = event->hex(iter, 0);
+		enum print_line_t ret = event->funcs->hex(iter, 0, event);
 		if (ret != TRACE_TYPE_HANDLED)
 			return ret;
 	}
@@ -1875,10 +2014,11 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 	}
 
 	event = ftrace_find_event(entry->type);
-	return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+	return event ? event->funcs->binary(iter, 0, event) :
+		TRACE_TYPE_HANDLED;
 }
 
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
 {
 	int cpu;
 
@@ -1913,6 +2053,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
 	enum print_line_t ret;
 
+	if (iter->lost_events)
+		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+				 iter->cpu, iter->lost_events);
+
 	if (iter->trace && iter->trace->print_line) {
 		ret = iter->trace->print_line(iter);
 		if (ret != TRACE_TYPE_UNHANDLED)
@@ -1941,6 +2085,23 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 	return print_trace_fmt(iter);
 }
 
+void trace_default_header(struct seq_file *m)
+{
+	struct trace_iterator *iter = m->private;
+
+	if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+		/* print nothing if the buffers are empty */
+		if (trace_empty(iter))
+			return;
+		print_trace_header(m, iter);
+		if (!(trace_flags & TRACE_ITER_VERBOSE))
+			print_lat_help_header(m);
+	} else {
+		if (!(trace_flags & TRACE_ITER_VERBOSE))
+			print_func_help_header(m);
+	}
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -1953,17 +2114,9 @@ static int s_show(struct seq_file *m, void *v)
 		}
 		if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
-		else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
-			/* print nothing if the buffers are empty */
-			if (trace_empty(iter))
-				return 0;
-			print_trace_header(m, iter);
-			if (!(trace_flags & TRACE_ITER_VERBOSE))
-				print_lat_help_header(m);
-		} else {
-			if (!(trace_flags & TRACE_ITER_VERBOSE))
-				print_func_help_header(m);
-		}
+		else
+			trace_default_header(m);
+
 	} else if (iter->leftover) {
 		/*
 		 * If we filled the seq_file buffer earlier, we
@@ -2049,15 +2202,20 @@ __tracing_open(struct inode *inode, struct file *file)
 
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
-
 			iter->buffer_iter[cpu] =
-				ring_buffer_read_start(iter->tr->buffer, cpu);
+				ring_buffer_read_prepare(iter->tr->buffer, cpu);
+		}
+		ring_buffer_read_prepare_sync();
+		for_each_tracing_cpu(cpu) {
+			ring_buffer_read_start(iter->buffer_iter[cpu]);
 			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
-				ring_buffer_read_start(iter->tr->buffer, cpu);
+			ring_buffer_read_prepare(iter->tr->buffer, cpu);
+		ring_buffer_read_prepare_sync();
+		ring_buffer_read_start(iter->buffer_iter[cpu]);
 		tracing_iter_reset(iter, cpu);
 	}
 
@@ -2836,22 +2994,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	mutex_lock(&trace_types_lock);
 
-	/* We only allow one reader per cpu */
-	if (cpu_file == TRACE_PIPE_ALL_CPU) {
-		if (!cpumask_empty(tracing_reader_cpumask)) {
-			ret = -EBUSY;
-			goto out;
-		}
-		cpumask_setall(tracing_reader_cpumask);
-	} else {
-		if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
-			cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
-		else {
-			ret = -EBUSY;
-			goto out;
-		}
-	}
-
 	/* create a buffer to store the information to pass to userspace */
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (!iter) {
@@ -2907,12 +3049,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
-		cpumask_clear(tracing_reader_cpumask);
-	else
-		cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
-
-
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
 
@@ -3074,6 +3210,7 @@ waitagain:
 	iter->pos = -1;
 
 	trace_event_read_lock();
+	trace_access_lock(iter->cpu_file);
 	while (find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
 		int len = iter->seq.len;
@@ -3090,6 +3227,7 @@ waitagain:
 		if (iter->seq.len >= cnt)
 			break;
 	}
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 
 	/* Now copy what we have to the user */
@@ -3172,12 +3310,12 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 					size_t len,
 					unsigned int flags)
 {
-	struct page *pages[PIPE_BUFFERS];
-	struct partial_page partial[PIPE_BUFFERS];
+	struct page *pages_def[PIPE_DEF_BUFFERS];
+	struct partial_page partial_def[PIPE_DEF_BUFFERS];
 	struct trace_iterator *iter = filp->private_data;
 	struct splice_pipe_desc spd = {
-		.pages		= pages,
-		.partial	= partial,
+		.pages		= pages_def,
+		.partial	= partial_def,
 		.nr_pages	= 0, /* This gets updated below. */
 		.flags		= flags,
 		.ops		= &tracing_pipe_buf_ops,
@@ -3188,6 +3326,9 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	size_t rem;
 	unsigned int i;
 
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
 	if (unlikely(old_tracer != current_trace && current_trace)) {
@@ -3215,40 +3356,44 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	}
 
 	trace_event_read_lock();
+	trace_access_lock(iter->cpu_file);
 
 	/* Fill as many pages as possible. */
-	for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
-		pages[i] = alloc_page(GFP_KERNEL);
-		if (!pages[i])
+	for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+		spd.pages[i] = alloc_page(GFP_KERNEL);
+		if (!spd.pages[i])
 			break;
 
 		rem = tracing_fill_pipe_page(rem, iter);
 
 		/* Copy the data into the page, so we can start over. */
 		ret = trace_seq_to_buffer(&iter->seq,
-					  page_address(pages[i]),
+					  page_address(spd.pages[i]),
 					  iter->seq.len);
 		if (ret < 0) {
-			__free_page(pages[i]);
+			__free_page(spd.pages[i]);
 			break;
 		}
-		partial[i].offset = 0;
-		partial[i].len = iter->seq.len;
+		spd.partial[i].offset = 0;
+		spd.partial[i].len = iter->seq.len;
 
 		trace_seq_init(&iter->seq);
 	}
 
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 	mutex_unlock(&iter->mutex);
 
 	spd.nr_pages = i;
 
-	return splice_to_pipe(pipe, &spd);
+	ret = splice_to_pipe(pipe, &spd);
+out:
+	splice_shrink_spd(pipe, &spd);
+	return ret;
 
 out_err:
 	mutex_unlock(&iter->mutex);
-
-	return ret;
+	goto out;
 }
 
 static ssize_t
@@ -3521,7 +3666,6 @@ 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;
 
@@ -3539,18 +3683,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
 
+	trace_access_lock(info->cpu);
 	ret = ring_buffer_read_page(info->tr->buffer,
 				    &info->spare,
 				    count,
 				    info->cpu, 0);
+	trace_access_unlock(info->cpu);
 	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)
@@ -3645,11 +3786,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			    unsigned int flags)
 {
 	struct ftrace_buffer_info *info = file->private_data;
-	struct partial_page partial[PIPE_BUFFERS];
-	struct page *pages[PIPE_BUFFERS];
+	struct partial_page partial_def[PIPE_DEF_BUFFERS];
+	struct page *pages_def[PIPE_DEF_BUFFERS];
 	struct splice_pipe_desc spd = {
-		.pages		= pages,
-		.partial	= partial,
+		.pages		= pages_def,
+		.partial	= partial_def,
 		.flags		= flags,
 		.ops		= &buffer_pipe_buf_ops,
 		.spd_release	= buffer_spd_release,
@@ -3658,21 +3799,28 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	int entries, size, i;
 	size_t ret;
 
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
 	if (*ppos & (PAGE_SIZE - 1)) {
 		WARN_ONCE(1, "Ftrace: previous read must page-align\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (len & (PAGE_SIZE - 1)) {
 		WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
-		if (len < PAGE_SIZE)
-			return -EINVAL;
+		if (len < PAGE_SIZE) {
+			ret = -EINVAL;
+			goto out;
+		}
 		len &= PAGE_MASK;
 	}
 
+	trace_access_lock(info->cpu);
 	entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 
-	for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
 		struct page *page;
 		int r;
 
@@ -3717,6 +3865,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 	}
 
+	trace_access_unlock(info->cpu);
 	spd.nr_pages = i;
 
 	/* did we read anything? */
@@ -3726,11 +3875,12 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		else
 			ret = 0;
 		/* TODO: block */
-		return ret;
+		goto out;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
-
+	splice_shrink_spd(pipe, &spd);
+out:
 	return ret;
 }
 
@@ -4153,6 +4303,8 @@ static __init int tracer_init_debugfs(void)
 	struct dentry *d_tracer;
 	int cpu;
 
+	trace_access_lock_init();
+
 	d_tracer = tracing_init_dentry();
 
 	trace_create_file("tracing_enabled", 0644, d_tracer,
@@ -4176,10 +4328,10 @@ static __init int tracer_init_debugfs(void)
 #ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_file("tracing_max_latency", 0644, d_tracer,
 			&tracing_max_latency, &tracing_max_lat_fops);
+#endif
 
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
-#endif
 
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
@@ -4219,7 +4371,7 @@ static int trace_panic_handler(struct notifier_block *this,
 			       unsigned long event, void *unused)
 {
 	if (ftrace_dump_on_oops)
-		ftrace_dump();
+		ftrace_dump(ftrace_dump_on_oops);
 	return NOTIFY_OK;
 }
 
@@ -4236,7 +4388,7 @@ static int trace_die_handler(struct notifier_block *self,
 	switch (val) {
 	case DIE_OOPS:
 		if (ftrace_dump_on_oops)
-			ftrace_dump();
+			ftrace_dump(ftrace_dump_on_oops);
 		break;
 	default:
 		break;
@@ -4277,7 +4429,8 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_init(s);
 }
 
-static void __ftrace_dump(bool disable_tracing)
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 {
 	static arch_spinlock_t ftrace_dump_lock =
 		(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -4310,12 +4463,25 @@ static void __ftrace_dump(bool disable_tracing)
 	/* don't look at user memory in panic mode */
 	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-	printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
 	/* Simulate the iterator */
 	iter.tr = &global_trace;
 	iter.trace = current_trace;
-	iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+	switch (oops_dump_mode) {
+	case DUMP_ALL:
+		iter.cpu_file = TRACE_PIPE_ALL_CPU;
+		break;
+	case DUMP_ORIG:
+		iter.cpu_file = raw_smp_processor_id();
+		break;
+	case DUMP_NONE:
+		goto out_enable;
+	default:
+		printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+		iter.cpu_file = TRACE_PIPE_ALL_CPU;
+	}
+
+	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
 	/*
 	 * We need to stop all tracing on all CPUS to read the
@@ -4354,6 +4520,7 @@ static void __ftrace_dump(bool disable_tracing)
 	else
 		printk(KERN_TRACE "---------------------------------\n");
 
+ out_enable:
 	/* Re-enable tracing if requested */
 	if (!disable_tracing) {
 		trace_flags |= old_userobj;
@@ -4370,9 +4537,9 @@ static void __ftrace_dump(bool disable_tracing)
 }
 
 /* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-	__ftrace_dump(true);
+	__ftrace_dump(true, oops_dump_mode);
 }
 
 __init static int tracer_alloc_buffers(void)
@@ -4387,9 +4554,6 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
-	if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
-		goto out_free_tracing_cpumask;
-
 	/* To save memory, keep the ring buffer size to its minimum */
 	if (ring_buffer_expanded)
 		ring_buf_size = trace_buf_size;
@@ -4447,8 +4611,6 @@ __init static int tracer_alloc_buffers(void)
 	return 0;
 
 out_free_cpumask:
-	free_cpumask_var(tracing_reader_cpumask);
-out_free_tracing_cpumask:
 	free_cpumask_var(tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);