24 files changed, 2361 insertions, 1075 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 019f380fd76..1ea0d1234f4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -41,7 +41,7 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config HAVE_HW_BRANCH_TRACER
 	bool
 
-config HAVE_FTRACE_SYSCALLS
+config HAVE_SYSCALL_TRACEPOINTS
 	bool
 
 config TRACER_MAX_TRACE
@@ -60,9 +60,14 @@ config EVENT_TRACING
 	bool
 
 config CONTEXT_SWITCH_TRACER
-	select MARKERS
 	bool
 
+config RING_BUFFER_ALLOW_SWAP
+	bool
+	help
+	 Allow the use of ring_buffer_swap_cpu.
+	 Adds a very slight overhead to tracing when enabled.
+
 # All tracer options should select GENERIC_TRACER. For those options that are
 # enabled by all tracers (context switch and event tracer) they select TRACING.
 # This allows those options to appear when no other tracer is selected. But the
@@ -147,6 +152,7 @@ config IRQSOFF_TRACER
 	select TRACE_IRQFLAGS
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in irqs-off critical
 	  sections, with microsecond accuracy.
@@ -168,6 +174,7 @@ config PREEMPT_TRACER
 	depends on PREEMPT
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in preemption off critical
 	  sections, with microsecond accuracy.
@@ -211,7 +218,7 @@ config ENABLE_DEFAULT_TRACERS
 
 config FTRACE_SYSCALLS
 	bool "Trace syscalls"
-	depends on HAVE_FTRACE_SYSCALLS
+	depends on HAVE_SYSCALL_TRACEPOINTS
 	select GENERIC_TRACER
 	select KALLSYMS
 	help
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7a34cb563fe..3eb159c277c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -65,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
 						  0, pc);
 		if (!event)
@@ -96,7 +98,7 @@ record_it:
 		memcpy((void *) t + sizeof(*t), data, len);
 
 		if (blk_tracer)
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 	}
 }
 
@@ -179,6 +181,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	struct blk_io_trace *t;
 	unsigned long flags = 0;
 	unsigned long *sequence;
@@ -204,8 +207,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
 						  0, pc);
 		if (!event)
@@ -252,7 +256,7 @@ record_it:
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
 		if (blk_tracer) {
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 			return;
 		}
 	}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 25edd5cc593..8c804e24f96 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1016,71 +1016,35 @@ static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ftrace_addr;
-	unsigned long ip, fl;
+	unsigned long flag = 0UL;
 
 	ftrace_addr = (unsigned long)FTRACE_ADDR;
 
-	ip = rec->ip;
-
 	/*
-	 * If this record is not to be traced and
-	 * it is not enabled then do nothing.
+	 * If this record is not to be traced or we want to disable it,
+	 * then disable it.
 	 *
-	 * If this record is not to be traced and
-	 * it is enabled then disable it.
+	 * If we want to enable it and filtering is off, then enable it.
 	 *
+	 * If we want to enable it and filtering is on, enable it only if
+	 * it's filtered
 	 */
-	if (rec->flags & FTRACE_FL_NOTRACE) {
-		if (rec->flags & FTRACE_FL_ENABLED)
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		else
-			return 0;
-
-	} else if (ftrace_filtered && enable) {
-		/*
-		 * Filtering is on:
-		 */
-
-		fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED);
-
-		/* Record is filtered and enabled, do nothing */
-		if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED))
-			return 0;
-
-		/* Record is not filtered or enabled, do nothing */
-		if (!fl)
-			return 0;
-
-		/* Record is not filtered but enabled, disable it */
-		if (fl == FTRACE_FL_ENABLED)
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		else
-		/* Otherwise record is filtered but not enabled, enable it */
-			rec->flags |= FTRACE_FL_ENABLED;
-	} else {
-		/* Disable or not filtered */
-
-		if (enable) {
-			/* if record is enabled, do nothing */
-			if (rec->flags & FTRACE_FL_ENABLED)
-				return 0;
-
-			rec->flags |= FTRACE_FL_ENABLED;
-
-		} else {
+	if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) {
+		if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER))
+			flag = FTRACE_FL_ENABLED;
+	}
 
-			/* if record is not enabled, do nothing */
-			if (!(rec->flags & FTRACE_FL_ENABLED))
-				return 0;
+	/* If the state of this record hasn't changed, then do nothing */
+	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
+		return 0;
 
-			rec->flags &= ~FTRACE_FL_ENABLED;
-		}
+	if (flag) {
+		rec->flags |= FTRACE_FL_ENABLED;
+		return ftrace_make_call(rec, ftrace_addr);
 	}
 
-	if (rec->flags & FTRACE_FL_ENABLED)
-		return ftrace_make_call(rec, ftrace_addr);
-	else
-		return ftrace_make_nop(NULL, rec, ftrace_addr);
+	rec->flags &= ~FTRACE_FL_ENABLED;
+	return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
 static void ftrace_replace_code(int enable)
@@ -1375,7 +1339,6 @@ struct ftrace_iterator {
 	unsigned		flags;
 	unsigned char		buffer[FTRACE_BUFF_MAX+1];
 	unsigned		buffer_idx;
-	unsigned		filtered;
 };
 
 static void *
@@ -1438,18 +1401,13 @@ static int t_hash_show(struct seq_file *m, void *v)
 {
 	struct ftrace_func_probe *rec;
 	struct hlist_node *hnd = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	rec = hlist_entry(hnd, struct ftrace_func_probe, node);
 
 	if (rec->ops->print)
 		return rec->ops->print(m, rec->ip, rec->ops, rec->data);
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-	seq_printf(m, "%s:", str);
-
-	kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str);
-	seq_printf(m, "%s", str);
+	seq_printf(m, "%pf:%pf", (void *)rec->ip, (void *)rec->ops->func);
 
 	if (rec->data)
 		seq_printf(m, ":%p", rec->data);
@@ -1547,7 +1505,6 @@ static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
 	struct dyn_ftrace *rec = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_show(m, v);
@@ -1560,9 +1517,7 @@ static int t_show(struct seq_file *m, void *v)
 	if (!rec)
 		return 0;
 
-	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-
-	seq_printf(m, "%s\n", str);
+	seq_printf(m, "%pf\n", (void *)rec->ip);
 
 	return 0;
 }
@@ -1601,17 +1556,6 @@ ftrace_avail_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-int ftrace_avail_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *m = (struct seq_file *)file->private_data;
-	struct ftrace_iterator *iter = m->private;
-
-	seq_release(inode, file);
-	kfree(iter);
-
-	return 0;
-}
-
 static int
 ftrace_failures_open(struct inode *inode, struct file *file)
 {
@@ -2317,7 +2261,6 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	}
 
 	if (isspace(ch)) {
-		iter->filtered++;
 		iter->buffer[iter->buffer_idx] = 0;
 		ret = ftrace_process_regex(iter->buffer,
 					   iter->buffer_idx, enable);
@@ -2448,7 +2391,6 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 		iter = file->private_data;
 
 	if (iter->buffer_idx) {
-		iter->filtered++;
 		iter->buffer[iter->buffer_idx] = 0;
 		ftrace_match_records(iter->buffer, iter->buffer_idx, enable);
 	}
@@ -2479,14 +2421,14 @@ static const struct file_operations ftrace_avail_fops = {
 	.open = ftrace_avail_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = ftrace_avail_release,
+	.release = seq_release_private,
 };
 
 static const struct file_operations ftrace_failures_fops = {
 	.open = ftrace_failures_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = ftrace_avail_release,
+	.release = seq_release_private,
 };
 
 static const struct file_operations ftrace_filter_fops = {
@@ -2548,7 +2490,6 @@ static void g_stop(struct seq_file *m, void *p)
 static int g_show(struct seq_file *m, void *v)
 {
 	unsigned long *ptr = v;
-	char str[KSYM_SYMBOL_LEN];
 
 	if (!ptr)
 		return 0;
@@ -2558,9 +2499,7 @@ static int g_show(struct seq_file *m, void *v)
 		return 0;
 	}
 
-	kallsyms_lookup(*ptr, NULL, NULL, NULL, str);
-
-	seq_printf(m, "%s\n", str);
+	seq_printf(m, "%pf\n", v);
 
 	return 0;
 }
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 1edaa9516e8..81b1645c854 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -183,11 +183,9 @@ static void kmemtrace_stop_probes(void)
 
 static int kmem_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	kmemtrace_array = tr;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	kmemtrace_start_probes();
 
@@ -239,12 +237,52 @@ struct kmemtrace_user_event_alloc {
 };
 
 static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter,
-			   struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
 {
-	struct kmemtrace_user_event_alloc *ev_alloc;
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
+	    "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+	    entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
+	    (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
+	    (unsigned long)entry->gfp_flags, entry->node);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
+			       entry->type_id, (void *)entry->call_site,
+			       (unsigned long)entry->ptr);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
 	struct kmemtrace_user_event *ev;
+	struct kmemtrace_user_event_alloc *ev_alloc;
+
+	trace_assign_type(entry, iter->ent);
 
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
@@ -271,12 +309,14 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter,
 }
 
 static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter,
-			  struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
 {
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
 	struct kmemtrace_user_event *ev;
 
+	trace_assign_type(entry, iter->ent);
+
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -294,12 +334,14 @@ kmemtrace_print_free_user(struct trace_iterator *iter,
 
 /* The two other following provide a more minimalistic output */
 static enum print_line_t
-kmemtrace_print_alloc_compress(struct trace_iterator *iter,
-					struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_alloc_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Alloc entry */
 	ret = trace_seq_printf(s, "  +      ");
 	if (!ret)
@@ -345,29 +387,24 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Node */
-	ret = trace_seq_printf(s, "%4d   ", entry->node);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	/* Node and call site*/
+	ret = trace_seq_printf(s, "%4d   %pf\n", entry->node,
+						 (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
 static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter,
-			      struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_free_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Free entry */
 	ret = trace_seq_printf(s, "  -      ");
 	if (!ret)
@@ -401,19 +438,11 @@ kmemtrace_print_free_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Skip node */
-	ret = trace_seq_printf(s, "       ");
+	/* Skip node and print call site*/
+	ret = trace_seq_printf(s, "       %pf\n", (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -421,32 +450,31 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 {
 	struct trace_entry *entry = iter->ent;
 
-	switch (entry->type) {
-	case TRACE_KMEM_ALLOC: {
-		struct kmemtrace_alloc_entry *field;
-
-		trace_assign_type(field, entry);
-		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-			return kmemtrace_print_alloc_compress(iter, field);
-		else
-			return kmemtrace_print_alloc_user(iter, field);
-	}
-
-	case TRACE_KMEM_FREE: {
-		struct kmemtrace_free_entry *field;
-
-		trace_assign_type(field, entry);
-		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-			return kmemtrace_print_free_compress(iter, field);
-		else
-			return kmemtrace_print_free_user(iter, field);
-	}
+	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+		return TRACE_TYPE_UNHANDLED;
 
+	switch (entry->type) {
+	case TRACE_KMEM_ALLOC:
+		return kmemtrace_print_alloc_compress(iter);
+	case TRACE_KMEM_FREE:
+		return kmemtrace_print_free_compress(iter);
 	default:
 		return TRACE_TYPE_UNHANDLED;
 	}
 }
 
+static struct trace_event kmem_trace_alloc = {
+	.type			= TRACE_KMEM_ALLOC,
+	.trace			= kmemtrace_print_alloc,
+	.binary			= kmemtrace_print_alloc_user,
+};
+
+static struct trace_event kmem_trace_free = {
+	.type			= TRACE_KMEM_FREE,
+	.trace			= kmemtrace_print_free,
+	.binary			= kmemtrace_print_free_user,
+};
+
 static struct tracer kmem_tracer __read_mostly = {
 	.name			= "kmemtrace",
 	.init			= kmem_trace_init,
@@ -463,6 +491,21 @@ void kmemtrace_init(void)
 
 static int __init init_kmem_tracer(void)
 {
-	return register_tracer(&kmem_tracer);
+	if (!register_ftrace_event(&kmem_trace_alloc)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_ftrace_event(&kmem_trace_free)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_tracer(&kmem_tracer)) {
+		pr_warning("Warning: could not register the kmem tracer\n");
+		return 1;
+	}
+
+	return 0;
 }
 device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a330513d96c..454e74e718c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -218,17 +218,12 @@ enum {
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
-	return event->type_len == RINGBUF_TYPE_PADDING
-			&& event->time_delta == 0;
-}
-
-static inline int rb_discarded_event(struct ring_buffer_event *event)
-{
-	return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
+	return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
 }
 
 static void rb_event_set_padding(struct ring_buffer_event *event)
 {
+	/* padding has a NULL time_delta */
 	event->type_len = RINGBUF_TYPE_PADDING;
 	event->time_delta = 0;
 }
@@ -322,6 +317,14 @@ struct buffer_data_page {
 	unsigned char	 data[];	/* data of buffer page */
 };
 
+/*
+ * Note, the buffer_page list must be first. The buffer pages
+ * are allocated in cache lines, which means that each buffer
+ * page will be at the beginning of a cache line, and thus
+ * the least significant bits will be zero. We use this to
+ * add flags in the list struct pointers, to make the ring buffer
+ * lockless.
+ */
 struct buffer_page {
 	struct list_head list;		/* list of buffer pages */
 	local_t		 write;		/* index for next write */
@@ -330,6 +333,21 @@ struct buffer_page {
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
+/*
+ * The buffer page counters, write and entries, must be reset
+ * atomically when crossing page boundaries. To synchronize this
+ * update, two counters are inserted into the number. One is
+ * the actual counter for the write position or count on the page.
+ *
+ * The other is a counter of updaters. Before an update happens
+ * the update partition of the counter is incremented. This will
+ * allow the updater to update the counter atomically.
+ *
+ * The counter is 20 bits, and the state data is 12.
+ */
+#define RB_WRITE_MASK		0xfffff
+#define RB_WRITE_INTCNT		(1 << 20)
+
 static void rb_init_page(struct buffer_data_page *bpage)
 {
 	local_set(&bpage->commit, 0);
@@ -403,21 +421,20 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 struct ring_buffer_per_cpu {
 	int				cpu;
 	struct ring_buffer		*buffer;
-	spinlock_t			reader_lock; /* serialize readers */
+	spinlock_t			reader_lock;	/* serialize readers */
 	raw_spinlock_t			lock;
 	struct lock_class_key		lock_key;
-	struct list_head		pages;
+	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
-	unsigned long			nmi_dropped;
-	unsigned long			commit_overrun;
-	unsigned long			overrun;
-	unsigned long			read;
+	local_t				commit_overrun;
+	local_t				overrun;
 	local_t				entries;
 	local_t				committing;
 	local_t				commits;
+	unsigned long			read;
 	u64				write_stamp;
 	u64				read_stamp;
 	atomic_t			record_disabled;
@@ -450,14 +467,19 @@ struct ring_buffer_iter {
 };
 
 /* buffer may be either ring_buffer or ring_buffer_per_cpu */
-#define RB_WARN_ON(buffer, cond)				\
-	({							\
-		int _____ret = unlikely(cond);			\
-		if (_____ret) {					\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-		}						\
-		_____ret;					\
+#define RB_WARN_ON(b, cond)						\
+	({								\
+		int _____ret = unlikely(cond);				\
+		if (_____ret) {						\
+			if (__same_type(*(b), struct ring_buffer_per_cpu)) { \
+				struct ring_buffer_per_cpu *__b =	\
+					(void *)b;			\
+				atomic_inc(&__b->buffer->record_disabled); \
+			} else						\
+				atomic_inc(&b->record_disabled);	\
+			WARN_ON(1);					\
+		}							\
+		_____ret;						\
 	})
 
 /* Up this if you want to test the TIME_EXTENTS and normalization */
@@ -489,6 +511,390 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
+/*
+ * Making the ring buffer lockless makes things tricky.
+ * Although writes only happen on the CPU that they are on,
+ * and they only need to worry about interrupts. Reads can
+ * happen on any CPU.
+ *
+ * The reader page is always off the ring buffer, but when the
+ * reader finishes with a page, it needs to swap its page with
+ * a new one from the buffer. The reader needs to take from
+ * the head (writes go to the tail). But if a writer is in overwrite
+ * mode and wraps, it must push the head page forward.
+ *
+ * Here lies the problem.
+ *
+ * The reader must be careful to replace only the head page, and
+ * not another one. As described at the top of the file in the
+ * ASCII art, the reader sets its old page to point to the next
+ * page after head. It then sets the page after head to point to
+ * the old reader page. But if the writer moves the head page
+ * during this operation, the reader could end up with the tail.
+ *
+ * We use cmpxchg to help prevent this race. We also do something
+ * special with the page before head. We set the LSB to 1.
+ *
+ * When the writer must push the page forward, it will clear the
+ * bit that points to the head page, move the head, and then set
+ * the bit that points to the new head page.
+ *
+ * We also don't want an interrupt coming in and moving the head
+ * page on another writer. Thus we use the second LSB to catch
+ * that too. Thus:
+ *
+ * head->list->prev->next        bit 1          bit 0
+ *                              -------        -------
+ * Normal page                     0              0
+ * Points to head page             0              1
+ * New head page                   1              0
+ *
+ * Note we can not trust the prev pointer of the head page, because:
+ *
+ * +----+       +-----+        +-----+
+ * |    |------>|  T  |---X--->|  N  |
+ * |    |<------|     |        |     |
+ * +----+       +-----+        +-----+
+ *   ^                           ^ |
+ *   |          +-----+          | |
+ *   +----------|  R  |----------+ |
+ *              |     |<-----------+
+ *              +-----+
+ *
+ * Key:  ---X-->  HEAD flag set in pointer
+ *         T      Tail page
+ *         R      Reader page
+ *         N      Next page
+ *
+ * (see __rb_reserve_next() to see where this happens)
+ *
+ *  What the above shows is that the reader just swapped out
+ *  the reader page with a page in the buffer, but before it
+ *  could make the new header point back to the new page added
+ *  it was preempted by a writer. The writer moved forward onto
+ *  the new page added by the reader and is about to move forward
+ *  again.
+ *
+ *  You can see, it is legitimate for the previous pointer of
+ *  the head (or any page) not to point back to itself. But only
+ *  temporarially.
+ */
+
+#define RB_PAGE_NORMAL		0UL
+#define RB_PAGE_HEAD		1UL
+#define RB_PAGE_UPDATE		2UL
+
+
+#define RB_FLAG_MASK		3UL
+
+/* PAGE_MOVED is not part of the mask */
+#define RB_PAGE_MOVED		4UL
+
+/*
+ * rb_list_head - remove any bit
+ */
+static struct list_head *rb_list_head(struct list_head *list)
+{
+	unsigned long val = (unsigned long)list;
+
+	return (struct list_head *)(val & ~RB_FLAG_MASK);
+}
+
+/*
+ * rb_is_head_page - test if the give page is the head page
+ *
+ * Because the reader may move the head_page pointer, we can
+ * not trust what the head page is (it may be pointing to
+ * the reader page). But if the next page is a header page,
+ * its flags will be non zero.
+ */
+static int inline
+rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		struct buffer_page *page, struct list_head *list)
+{
+	unsigned long val;
+
+	val = (unsigned long)list->next;
+
+	if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
+		return RB_PAGE_MOVED;
+
+	return val & RB_FLAG_MASK;
+}
+
+/*
+ * rb_is_reader_page
+ *
+ * The unique thing about the reader page, is that, if the
+ * writer is ever on it, the previous pointer never points
+ * back to the reader page.
+ */
+static int rb_is_reader_page(struct buffer_page *page)
+{
+	struct list_head *list = page->list.prev;
+
+	return rb_list_head(list->next) != &page->list;
+}
+
+/*
+ * rb_set_list_to_head - set a list_head to be pointing to head.
+ */
+static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
+				struct list_head *list)
+{
+	unsigned long *ptr;
+
+	ptr = (unsigned long *)&list->next;
+	*ptr |= RB_PAGE_HEAD;
+	*ptr &= ~RB_PAGE_UPDATE;
+}
+
+/*
+ * rb_head_page_activate - sets up head page
+ */
+static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+
+	head = cpu_buffer->head_page;
+	if (!head)
+		return;
+
+	/*
+	 * Set the previous list pointer to have the HEAD flag.
+	 */
+	rb_set_list_to_head(cpu_buffer, head->list.prev);
+}
+
+static void rb_list_head_clear(struct list_head *list)
+{
+	unsigned long *ptr = (unsigned long *)&list->next;
+
+	*ptr &= ~RB_FLAG_MASK;
+}
+
+/*
+ * rb_head_page_dactivate - clears head page ptr (for free list)
+ */
+static void
+rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct list_head *hd;
+
+	/* Go through the whole list and clear any pointers found. */
+	rb_list_head_clear(cpu_buffer->pages);
+
+	list_for_each(hd, cpu_buffer->pages)
+		rb_list_head_clear(hd);
+}
+
+static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
+			    struct buffer_page *head,
+			    struct buffer_page *prev,
+			    int old_flag, int new_flag)
+{
+	struct list_head *list;
+	unsigned long val = (unsigned long)&head->list;
+	unsigned long ret;
+
+	list = &prev->list;
+
+	val &= ~RB_FLAG_MASK;
+
+	ret = (unsigned long)cmpxchg(&list->next,
+				     val | old_flag, val | new_flag);
+
+	/* check if the reader took the page */
+	if ((ret & ~RB_FLAG_MASK) != val)
+		return RB_PAGE_MOVED;
+
+	return ret & RB_FLAG_MASK;
+}
+
+static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_UPDATE);
+}
+
+static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
+				 struct buffer_page *head,
+				 struct buffer_page *prev,
+				 int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_HEAD);
+}
+
+static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_NORMAL);
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page **bpage)
+{
+	struct list_head *p = rb_list_head((*bpage)->list.next);
+
+	*bpage = list_entry(p, struct buffer_page, list);
+}
+
+static struct buffer_page *
+rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+	struct buffer_page *page;
+	struct list_head *list;
+	int i;
+
+	if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
+		return NULL;
+
+	/* sanity check */
+	list = cpu_buffer->pages;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
+		return NULL;
+
+	page = head = cpu_buffer->head_page;
+	/*
+	 * It is possible that the writer moves the header behind
+	 * where we started, and we miss in one loop.
+	 * A second loop should grab the header, but we'll do
+	 * three loops just because I'm paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		do {
+			if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
+				cpu_buffer->head_page = page;
+				return page;
+			}
+			rb_inc_page(cpu_buffer, &page);
+		} while (page != head);
+	}
+
+	RB_WARN_ON(cpu_buffer, 1);
+
+	return NULL;
+}
+
+static int rb_head_page_replace(struct buffer_page *old,
+				struct buffer_page *new)
+{
+	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
+	unsigned long val;
+	unsigned long ret;
+
+	val = *ptr & ~RB_FLAG_MASK;
+	val |= RB_PAGE_HEAD;
+
+	ret = cmpxchg(ptr, val