Merge branch 'drm-kms-locking' of git://people.freedesktop.org/~danvet/drm-intel into drm-next

The aim of this locking rework is that ioctls which a compositor should be
might call for every frame (set_cursor, page_flip, addfb, rmfb and
getfb/create_handle) should not be able to block on kms background
activities like output detection. And since each EDID read takes about
25ms (in the best case), that always means we'll drop at least one frame.

The solution is to add per-crtc locking for these ioctls, and restrict
background activities to only use the global lock. Change-the-world type
of events (modeset, dpms, ...) need to grab all locks.

Two tricky parts arose in the conversion:
- A lot of current code assumes that a kms fb object can't disappear while
  holding the global lock, since the current code serializes fb
  destruction with it. Hence proper lifetime management using the already
  created refcounting for fbs need to be instantiated for all ioctls and
  interfaces/users.

- The rmfb ioctl removes the to-be-deleted fb from all active users. But
  unconditionally taking the global kms lock to do so introduces an
  unacceptable potential stall point. And obviously changing the userspace
  abi isn't on the table, either. Hence this conversion opportunistically
  checks whether the rmfb ioctl holds the very last reference, which
  guarantees that the fb isn't in active use on any crtc or plane (thanks
  to the conversion to the new lifetime rules using proper refcounting).
  Only if this is not the case will the code go through the slowpath and
  grab all modeset locks. Sane compositors will never hit this path and so
  avoid the stall, but userspace relying on these semantics will also not
  break.

All these cases are exercised by the newly added subtests for the i-g-t
kms_flip, tested on a machine where a full detect cycle takes around 100
ms.  It works, and no frames are dropped any more with these patches
applied.  kms_flip also contains a special case to exercise the
above-describe rmfb slowpath.

* 'drm-kms-locking' of git://people.freedesktop.org/~danvet/drm-intel: (335 commits)
  drm/fb_helper: check whether fbcon is bound
  drm/doc: updates for new framebuffer lifetime rules
  drm: don't hold crtc mutexes for connector ->detect callbacks
  drm: only grab the crtc lock for pageflips
  drm: optimize drm_framebuffer_remove
  drm/vmwgfx: add proper framebuffer refcounting
  drm/i915: dump refcount into framebuffer debugfs file
  drm: refcounting for crtc framebuffers
  drm: refcounting for sprite framebuffers
  drm: fb refcounting for dirtyfb_ioctl
  drm: don't take modeset locks in getfb ioctl
  drm: push modeset_lock_all into ->fb_create driver callbacks
  drm: nest modeset locks within fpriv->fbs_lock
  drm: reference framebuffers which are on the idr
  drm: revamp framebuffer cleanup interfaces
  drm: create drm_framebuffer_lookup
  drm: revamp locking around fb creation/destruction
  drm: only take the crtc lock for ->cursor_move
  drm: only take the crtc lock for ->cursor_set
  drm: add per-crtc locks
  ...

9 files changed, 112 insertions, 34 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 9d3118384858..a1d585c351d6 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -196,6 +196,9 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a
 	atomic_inc(&entry_count);
 	spin_unlock_irqrestore(&async_lock, flags);
 
+	/* mark that this task has queued an async job, used by module init */
+	current->flags |= PF_USED_ASYNC;
+
 	/* schedule for execution */
 	queue_work(system_unbound_wq, &entry->work);
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 40414e9143db..d596e5355f15 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -272,6 +272,8 @@ static int audit_log_config_change(char *function_name, int new, int old,
 	int rc = 0;
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+	if (unlikely(!ab))
+		return rc;
 	audit_log_format(ab, "%s=%d old=%d auid=%u ses=%u", function_name, new,
 			 old, from_kuid(&init_user_ns, loginuid), sessionid);
 	if (sid) {
@@ -619,6 +621,8 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type,
 	}
 
 	*ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
+	if (unlikely(!*ab))
+		return rc;
 	audit_log_format(*ab, "pid=%d uid=%u auid=%u ses=%u",
 			 task_tgid_vnr(current),
 			 from_kuid(&init_user_ns, current_uid()),
@@ -1097,6 +1101,23 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 	}
 }
 
+/*
+ * Wait for auditd to drain the queue a little
+ */
+static void wait_for_auditd(unsigned long sleep_time)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	set_current_state(TASK_INTERRUPTIBLE);
+	add_wait_queue(&audit_backlog_wait, &wait);
+
+	if (audit_backlog_limit &&
+	    skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
+		schedule_timeout(sleep_time);
+
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&audit_backlog_wait, &wait);
+}
+
 /* Obtain an audit buffer.  This routine does locking to obtain the
  * audit buffer, but then no locking is required for calls to
  * audit_log_*format.  If the tsk is a task that is currently in a
@@ -1142,20 +1163,13 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 	while (audit_backlog_limit
 	       && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
-		if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time
-		    && time_before(jiffies, timeout_start + audit_backlog_wait_time)) {
+		if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) {
+			unsigned long sleep_time;
 
-			/* Wait for auditd to drain the queue a little */
-			DECLARE_WAITQUEUE(wait, current);
-			set_current_state(TASK_INTERRUPTIBLE);
-			add_wait_queue(&audit_backlog_wait, &wait);
-
-			if (audit_backlog_limit &&
-			    skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
-				schedule_timeout(timeout_start + audit_backlog_wait_time - jiffies);
-
-			__set_current_state(TASK_RUNNING);
-			remove_wait_queue(&audit_backlog_wait, &wait);
+			sleep_time = timeout_start + audit_backlog_wait_time -
+					jiffies;
+			if ((long)sleep_time > 0)
+				wait_for_auditd(sleep_time);
 			continue;
 		}
 		if (audit_rate_check() && printk_ratelimit())
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e81175ef25f8..642a89c4f3d6 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -449,11 +449,26 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	return 0;
 }
 
+static void audit_log_remove_rule(struct audit_krule *rule)
+{
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+	if (unlikely(!ab))
+		return;
+	audit_log_format(ab, "op=");
+	audit_log_string(ab, "remove rule");
+	audit_log_format(ab, " dir=");
+	audit_log_untrustedstring(ab, rule->tree->pathname);
+	audit_log_key(ab, rule->filterkey);
+	audit_log_format(ab, " list=%d res=1", rule->listnr);
+	audit_log_end(ab);
+}
+
 static void kill_rules(struct audit_tree *tree)
 {
 	struct audit_krule *rule, *next;
 	struct audit_entry *entry;
-	struct audit_buffer *ab;
 
 	list_for_each_entry_safe(rule, next, &tree->rules, rlist) {
 		entry = container_of(rule, struct audit_entry, rule);
@@ -461,14 +476,7 @@ static void kill_rules(struct audit_tree *tree)
 		list_del_init(&rule->rlist);
 		if (rule->tree) {
 			/* not a half-baked one */
-			ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
-			audit_log_format(ab, "op=");
-			audit_log_string(ab, "remove rule");
-			audit_log_format(ab, " dir=");
-			audit_log_untrustedstring(ab, rule->tree->pathname);
-			audit_log_key(ab, rule->filterkey);
-			audit_log_format(ab, " list=%d res=1", rule->listnr);
-			audit_log_end(ab);
+			audit_log_remove_rule(rule);
 			rule->tree = NULL;
 			list_del_rcu(&entry->list);
 			list_del(&entry->rule.list);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 4a599f699adc..22831c4d369c 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -240,6 +240,8 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc
 	if (audit_enabled) {
 		struct audit_buffer *ab;
 		ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
+		if (unlikely(!ab))
+			return;
 		audit_log_format(ab, "auid=%u ses=%u op=",
 				 from_kuid(&init_user_ns, audit_get_loginuid(current)),
 				 audit_get_sessionid(current));
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 7f19f23d38a3..f9fc54bbe06f 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1144,7 +1144,6 @@ static void audit_log_rule_change(kuid_t loginuid, u32 sessionid, u32 sid,
  * audit_receive_filter - apply all rules to the specified message type
  * @type: audit message type
  * @pid: target pid for netlink audit messages
- * @uid: target uid for netlink audit messages
  * @seq: netlink audit message sequence (serial) number
  * @data: payload data
  * @datasz: size of payload data
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index e37e6a12c5e3..a371f857a0a9 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1464,14 +1464,14 @@ static void show_special(struct audit_context *context, int *call_panic)
 			audit_log_end(ab);
 			ab = audit_log_start(context, GFP_KERNEL,
 					     AUDIT_IPC_SET_PERM);
+			if (unlikely(!ab))
+				return;
 			audit_log_format(ab,
 				"qbytes=%lx ouid=%u ogid=%u mode=%#ho",
 				context->ipc.qbytes,
 				context->ipc.perm_uid,
 				context->ipc.perm_gid,
 				context->ipc.perm_mode);
-			if (!ab)
-				return;
 		}
 		break; }
 	case AUDIT_MQ_OPEN: {
@@ -2675,7 +2675,7 @@ void __audit_mmap_fd(int fd, int flags)
 	context->type = AUDIT_MMAP;
 }
 
-static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
+static void audit_log_task(struct audit_buffer *ab)
 {
 	kuid_t auid, uid;
 	kgid_t gid;
@@ -2693,6 +2693,11 @@ static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
 	audit_log_task_context(ab);
 	audit_log_format(ab, " pid=%d comm=", current->pid);
 	audit_log_untrustedstring(ab, current->comm);
+}
+
+static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
+{
+	audit_log_task(ab);
 	audit_log_format(ab, " reason=");
 	audit_log_string(ab, reason);
 	audit_log_format(ab, " sig=%ld", signr);
@@ -2715,6 +2720,8 @@ void audit_core_dumps(long signr)
 		return;
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
+	if (unlikely(!ab))
+		return;
 	audit_log_abend(ab, "memory violation", signr);
 	audit_log_end(ab);
 }
@@ -2723,8 +2730,11 @@ void __audit_seccomp(unsigned long syscall, long signr, int code)
 {
 	struct audit_buffer *ab;
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
-	audit_log_abend(ab, "seccomp", signr);
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP);
+	if (unlikely(!ab))
+		return;
+	audit_log_task(ab);
+	audit_log_format(ab, " sig=%ld", signr);
 	audit_log_format(ab, " syscall=%ld", syscall);
 	audit_log_format(ab, " compat=%d", is_compat_task());
 	audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current));
diff --git a/kernel/module.c b/kernel/module.c
index 250092c1d57d..b10b048367e1 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3013,6 +3013,12 @@ static int do_init_module(struct module *mod)
 {
 	int ret = 0;
 
+	/*
+	 * We want to find out whether @mod uses async during init.  Clear
+	 * PF_USED_ASYNC.  async_schedule*() will set it.
+	 */
+	current->flags &= ~PF_USED_ASYNC;
+
 	blocking_notifier_call_chain(&module_notify_list,
 			MODULE_STATE_COMING, mod);
 
@@ -3058,8 +3064,25 @@ static int do_init_module(struct module *mod)
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_LIVE, mod);
 
-	/* We need to finish all async code before the module init sequence is done */
-	async_synchronize_full();
+	/*
+	 * We need to finish all async code before the module init sequence
+	 * is done.  This has potential to deadlock.  For example, a newly
+	 * detected block device can trigger request_module() of the
+	 * default iosched from async probing task.  Once userland helper
+	 * reaches here, async_synchronize_full() will wait on the async
+	 * task waiting on request_module() and deadlock.
+	 *
+	 * This deadlock is avoided by perfomring async_synchronize_full()
+	 * iff module init queued any async jobs.  This isn't a full
+	 * solution as it will deadlock the same if module loading from
+	 * async jobs nests more than once; however, due to the various
+	 * constraints, this hack seems to be the best option for now.
+	 * Please refer to the following thread for details.
+	 *
+	 * http://thread.gmane.org/gmane.linux.kernel/1420814
+	 */
+	if (current->flags & PF_USED_ASYNC)
+		async_synchronize_full();
 
 	mutex_lock(&module_mutex);
 	/* Drop initial reference. */
diff --git a/kernel/rwsem.c b/kernel/rwsem.c
index 6850f53e02d8..b3c6c3fcd847 100644
--- a/kernel/rwsem.c
+++ b/kernel/rwsem.c
@@ -116,6 +116,16 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 
 EXPORT_SYMBOL(down_read_nested);
 
+void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
+{
+	might_sleep();
+	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
+
+	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+}
+
+EXPORT_SYMBOL(_down_write_nest_lock);
+
 void down_write_nested(struct rw_semaphore *sem, int subclass)
 {
 	might_sleep();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e5125677efa0..3c13e46d7d24 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2899,6 +2899,8 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
 
+	buf[cnt] = 0;
+
 	trace_set_options(buf);
 
 	*ppos += cnt;
@@ -3452,7 +3454,7 @@ static int tracing_wait_pipe(struct file *filp)
 			return -EINTR;
 
 		/*
-		 * We block until we read something and tracing is enabled.
+		 * We block until we read something and tracing is disabled.
 		 * We still block if tracing is disabled, but we have never
 		 * read anything. This allows a user to cat this file, and
 		 * then enable tracing. But after we have read something,
@@ -3460,7 +3462,7 @@ static int tracing_wait_pipe(struct file *filp)
 		 *
 		 * iter->pos will be 0 if we haven't read anything.
 		 */
-		if (tracing_is_enabled() && iter->pos)
+		if (!tracing_is_enabled() && iter->pos)
 			break;
 	}
 
@@ -4815,10 +4817,17 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 		return ret;
 
 	if (buffer) {
-		if (val)
+		mutex_lock(&trace_types_lock);
+		if (val) {
 			ring_buffer_record_on(buffer);
-		else
+			if (current_trace->start)
+				current_trace->start(tr);
+		} else {
 			ring_buffer_record_off(buffer);
+			if (current_trace->stop)
+				current_trace->stop(tr);
+		}
+		mutex_unlock(&trace_types_lock);
 	}
 
 	(*ppos)++;