15 files changed, 220 insertions, 83 deletions

diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index c438f545a321..be775f7e81e0 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -255,7 +255,14 @@ extern void kdb_ps1(const struct task_struct *p);
 extern void kdb_print_nameval(const char *name, unsigned long val);
 extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
 extern void kdb_meminfo_proc_show(void);
+#ifdef CONFIG_KALLSYMS
 extern const char *kdb_walk_kallsyms(loff_t *pos);
+#else /* ! CONFIG_KALLSYMS */
+static inline const char *kdb_walk_kallsyms(loff_t *pos)
+{
+	return NULL;
+}
+#endif /* ! CONFIG_KALLSYMS */
 extern char *kdb_getstr(char *, size_t, char *);
 
 /* Defines for kdb_symbol_print */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 45344d5c53dd..6b2485dcb050 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -82,8 +82,8 @@ static char *kdb_name_table[100];	/* arbitrary size */
 int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
 {
 	int ret = 0;
-	unsigned long symbolsize;
-	unsigned long offset;
+	unsigned long symbolsize = 0;
+	unsigned long offset = 0;
 #define knt1_size 128		/* must be >= kallsyms table size */
 	char *knt1 = NULL;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 671ed56e0a49..03120229db28 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1386,8 +1386,7 @@ static int wait_task_stopped(struct wait_opts *wo,
 	if (!unlikely(wo->wo_flags & WNOWAIT))
 		*p_code = 0;
 
-	/* don't need the RCU readlock here as we're holding a spinlock */
-	uid = __task_cred(p)->uid;
+	uid = task_uid(p);
 unlock_sig:
 	spin_unlock_irq(&p->sighand->siglock);
 	if (!exit_code)
@@ -1460,7 +1459,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	}
 	if (!unlikely(wo->wo_flags & WNOWAIT))
 		p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
-	uid = __task_cred(p)->uid;
+	uid = task_uid(p);
 	spin_unlock_irq(&p->sighand->siglock);
 
 	pid = task_pid_vnr(p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 98b450876f93..b7e9d60a675d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -300,7 +300,7 @@ out:
 #ifdef CONFIG_MMU
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	struct vm_area_struct *mpnt, *tmp, **pprev;
+	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
 	int retval;
 	unsigned long charge;
@@ -328,6 +328,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	if (retval)
 		goto out;
 
+	prev = NULL;
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
 		struct file *file;
 
@@ -359,7 +360,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
 		tmp->vm_mm = mm;
-		tmp->vm_next = NULL;
+		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
@@ -392,6 +393,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		 */
 		*pprev = tmp;
 		pprev = &tmp->vm_next;
+		tmp->vm_prev = prev;
+		prev = tmp;
 
 		__vma_link_rb(mm, tmp, rb_link, rb_parent);
 		rb_link = &tmp->vm_rb.rb_right;
@@ -752,13 +755,13 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	struct fs_struct *fs = current->fs;
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
-		write_lock(&fs->lock);
+		spin_lock(&fs->lock);
 		if (fs->in_exec) {
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 			return -EAGAIN;
 		}
 		fs->users++;
-		write_unlock(&fs->lock);
+		spin_unlock(&fs->lock);
 		return 0;
 	}
 	tsk->fs = copy_fs_struct(fs);
@@ -1676,13 +1679,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 
 		if (new_fs) {
 			fs = current->fs;
-			write_lock(&fs->lock);
+			spin_lock(&fs->lock);
 			current->fs = new_fs;
 			if (--fs->users)
 				new_fs = NULL;
 			else
 				new_fs = fs;
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 		}
 
 		if (new_mm) {
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 4502604ecadf..6b5580c57644 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -503,6 +503,15 @@ unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf,
 }
 EXPORT_SYMBOL(__kfifo_out_r);
 
+void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize)
+{
+	unsigned int n;
+
+	n = __kfifo_peek_n(fifo, recsize);
+	fifo->out += n + recsize;
+}
+EXPORT_SYMBOL(__kfifo_skip_r);
+
 int __kfifo_from_user_r(struct __kfifo *fifo, const void __user *from,
 	unsigned long len, unsigned int *copied, size_t recsize)
 {
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 6e9b19667a8d..9cd0591c96a2 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -153,7 +153,9 @@ static int ____call_usermodehelper(void *data)
 			goto fail;
 	}
 
-	retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp);
+	retval = kernel_execve(sub_info->path,
+			       (const char *const *)sub_info->argv,
+			       (const char *const *)sub_info->envp);
 
 	/* Exec failed? */
 fail:
diff --git a/kernel/sched.c b/kernel/sched.c
index 41541d79e3c8..09b574e7f4df 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3865,8 +3865,16 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 		/*
 		 * Owner changed, break to re-assess state.
 		 */
-		if (lock->owner != owner)
+		if (lock->owner != owner) {
+			/*
+			 * If the lock has switched to a different owner,
+			 * we likely have heavy contention. Return 0 to quit
+			 * optimistic spinning and not contend further:
+			 */
+			if (lock->owner)
+				return 0;
 			break;
+		}
 
 		/*
 		 * Is that owner really running on that cpu?
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 806d1b227a21..ab661ebc4895 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3752,6 +3752,8 @@ static void task_fork_fair(struct task_struct *p)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 
+	update_rq_clock(rq);
+
 	if (unlikely(task_cpu(p) != this_cpu))
 		__set_task_cpu(p, this_cpu);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3632ce87674f..19cccc3c3028 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3846,6 +3846,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 			rpos = reader->read;
 			pos += size;
 
+			if (rpos >= commit)
+				break;
+
 			event = rb_reader_event(cpu_buffer);
 			size = rb_event_length(event);
 		} while (len > size);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ba14a22be4cc..9ec59f541156 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3463,6 +3463,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
 	char *buf;
+	size_t written;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -3484,11 +3485,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	} else
 		buf[cnt] = '\0';
 
-	cnt = mark_printk("%s", buf);
+	written = mark_printk("%s", buf);
 	kfree(buf);
-	*fpos += cnt;
+	*fpos += written;
 
-	return cnt;
+	/* don't tell userspace we wrote more - it might confuse them */
+	if (written > cnt)
+		written = cnt;
+
+	return written;
 }
 
 static int tracing_clock_show(struct seq_file *m, void *v)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 09b4fa6e4d3b..4c758f146328 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -598,88 +598,165 @@ out:
 	return ret;
 }
 
-static void print_event_fields(struct trace_seq *s, struct list_head *head)
+enum {
+	FORMAT_HEADER		= 1,
+	FORMAT_PRINTFMT		= 2,
+};
+
+static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	struct ftrace_event_call *call = m->private;
 	struct ftrace_event_field *field;
+	struct list_head *head;
 
-	list_for_each_entry_reverse(field, head, link) {
-		/*
-		 * Smartly shows the array type(except dynamic array).
-		 * Normal:
-		 *	field:TYPE VAR
-		 * If TYPE := TYPE[LEN], it is shown:
-		 *	field:TYPE VAR[LEN]
-		 */
-		const char *array_descriptor = strchr(field->type, '[');
+	(*pos)++;
 
-		if (!strncmp(field->type, "__data_loc", 10))
-			array_descriptor = NULL;
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		head = &ftrace_common_fields;
 
-		if (!array_descriptor) {
-			trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					field->type, field->name, field->offset,
-					field->size, !!field->is_signed);
-		} else {
-			trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
-					"\tsize:%u;\tsigned:%d;\n",
-					(int)(array_descriptor - field->type),
-					field->type, field->name,
-					array_descriptor, field->offset,
-					field->size, !!field->is_signed);
-		}
+		if (unlikely(list_empty(head)))
+			return NULL;
+
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		return field;
+
+	case FORMAT_PRINTFMT:
+		/* all done */
+		return NULL;
+	}
+
+	head = trace_get_fields(call);
+
+	/*
+	 * To separate common fields from event fields, the
+	 * LSB is set on the first event field. Clear it in case.
+	 */
+	v = (void *)((unsigned long)v & ~1L);
+
+	field = v;
+	/*
+	 * If this is a common field, and at the end of the list, then
+	 * continue with main list.
+	 */
+	if (field->link.prev == &ftrace_common_fields) {
+		if (unlikely(list_empty(head)))
+			return NULL;
+		field = list_entry(head->prev, struct ftrace_event_field, link);
+		/* Set the LSB to notify f_show to print an extra newline */
+		field = (struct ftrace_event_field *)
+			((unsigned long)field | 1);
+		return field;
 	}
+
+	/* If we are done tell f_show to print the format */
+	if (field->link.prev == head)
+		return (void *)FORMAT_PRINTFMT;
+
+	field = list_entry(field->link.prev, struct ftrace_event_field, link);
+
+	return field;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-		  loff_t *ppos)
+static void *f_start(struct seq_file *m, loff_t *pos)
 {
-	struct ftrace_event_call *call = filp->private_data;
-	struct list_head *head;
-	struct trace_seq *s;
-	char *buf;
-	int r;
+	loff_t l = 0;
+	void *p;
 
-	if (*ppos)
+	/* Start by showing the header */
+	if (!*pos)
+		return (void *)FORMAT_HEADER;
+
+	p = (void *)FORMAT_HEADER;
+	do {
+		p = f_next(m, p, &l);
+	} while (p && l < *pos);
+
+	return p;
+}
+
+static int f_show(struct seq_file *m, void *v)
+{
+	struct ftrace_event_call *call = m->private;
+	struct ftrace_event_field *field;
+	const char *array_descriptor;
+
+	switch ((unsigned long)v) {
+	case FORMAT_HEADER:
+		seq_printf(m, "name: %s\n", call->name);
+		seq_printf(m, "ID: %d\n", call->event.type);
+		seq_printf(m, "format:\n");
 		return 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
+	case FORMAT_PRINTFMT:
+		seq_printf(m, "\nprint fmt: %s\n",
+			   call->print_fmt);
+		return 0;
+	}
 
-	trace_seq_init(s);
+	/*
+	 * To separate common fields from event fields, the
+	 * LSB is set on the first event field. Clear it and
+	 * print a newline if it is set.
+	 */
+	if ((unsigned long)v & 1) {
+		seq_putc(m, '\n');
+		v = (void *)((unsigned long)v & ~1L);
+	}
 
-	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->event.type);
-	trace_seq_printf(s, "format:\n");
+	field = v;
 
-	/* print common fields */
-	print_event_fields(s, &ftrace_common_fields);
+	/*
+	 * Smartly shows the array type(except dynamic array).
+	 * Normal:
+	 *	field:TYPE VAR
+	 * If TYPE := TYPE[LEN], it is shown:
+	 *	field:TYPE VAR[LEN]
+	 */
+	array_descriptor = strchr(field->type, '[');
 
-	trace_seq_putc(s, '\n');
+	if (!strncmp(field->type, "__data_loc", 10))
+		array_descriptor = NULL;
 
-	/* print event specific fields */
-	head = trace_get_fields(call);
-	print_event_fields(s, head);
+	if (!array_descriptor)
+		seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   field->type, field->name, field->offset,
+			   field->size, !!field->is_signed);
+	else
+		seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+			   (int)(array_descriptor - field->type),
+			   field->type, field->name,
+			   array_descriptor, field->offset,
+			   field->size, !!field->is_signed);
 
-	r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
+	return 0;
+}
 
-	if (!r) {
-		/*
-		 * ug!  The format output is bigger than a PAGE!!
-		 */
-		buf = "FORMAT TOO BIG\n";
-		r = simple_read_from_buffer(ubuf, cnt, ppos,
-					      buf, strlen(buf));
-		goto out;
-	}
+static void f_stop(struct seq_file *m, void *p)
+{
+}
 
-	r = simple_read_from_buffer(ubuf, cnt, ppos,
-				    s->buffer, s->len);
- out:
-	kfree(s);
-	return r;
+static const struct seq_operations trace_format_seq_ops = {
+	.start		= f_start,
+	.next		= f_next,
+	.stop		= f_stop,
+	.show		= f_show,
+};
+
+static int trace_format_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_event_call *call = inode->i_private;
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, &trace_format_seq_ops);
+	if (ret < 0)
+		return ret;
+
+	m = file->private_data;
+	m->private = call;
+
+	return 0;
 }
 
 static ssize_t
@@ -877,8 +954,10 @@ static const struct file_operations ftrace_enable_fops = {
 };
 
 static const struct file_operations ftrace_event_format_fops = {
-	.open = tracing_open_generic,
-	.read = event_format_read,
+	.open = trace_format_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
 };
 
 static const struct file_operations ftrace_event_id_fops = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6bff23625781..6f233698518e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * if the output fails.
 			 */
 			data->ent = *curr;
-			data->ret = *next;
+			/*
+			 * If the next event is not a return type, then
+			 * we only care about what type it is. Otherwise we can
+			 * safely copy the entire event.
+			 */
+			if (next->ent.type == TRACE_GRAPH_RET)
+				data->ret = *next;
+			else
+				data->ret.ent.type = next->ent.type;
 		}
 	}
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 056468eae7cf..a6b7e0e0f3eb 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -249,7 +249,7 @@ static int trace_lookup_stack(struct seq_file *m, long i)
 {
 	unsigned long addr = stack_dump_trace[i];
 
-	return seq_printf(m, "%pF\n", (void *)addr);
+	return seq_printf(m, "%pS\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 613bc1f04610..0d53c8e853b1 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -206,6 +206,9 @@ void watchdog_overflow_callback(struct perf_event *event, int nmi,
 		 struct perf_sample_data *data,
 		 struct pt_regs *regs)
 {
+	/* Ensure the watchdog never gets throttled */
+	event->hw.interrupts = 0;
+
 	if (__get_cpu_var(watchdog_nmi_touch) == true) {
 		__get_cpu_var(watchdog_nmi_touch) = false;
 		return;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2994a0e3a61c..8bd600c020e5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -35,6 +35,9 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
 #include "workqueue_sched.h"
 
 enum {
@@ -1790,7 +1793,13 @@ static void process_one_work(struct worker *worker, struct work_struct *work)
 	work_clear_pending(work);
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
+	trace_workqueue_execute_start(work);
 	f(work);
+	/*
+	 * While we must be careful to not use "work" after this, the trace
+	 * point will only record its address.
+	 */
+	trace_workqueue_execute_end(work);
 	lock_map_release(&lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);