kernel/locking: Add context to ww_mutex_trylock()

i915 will soon gain an eviction path that trylock a whole lot of locks
for eviction, getting dmesg failures like below:

  BUG: MAX_LOCK_DEPTH too low!
  turning off the locking correctness validator.
  depth: 48  max: 48!
  48 locks held by i915_selftest/5776:
   #0: ffff888101a79240 (&dev->mutex){....}-{3:3}, at: __driver_attach+0x88/0x160
   #1: ffffc900009778c0 (reservation_ww_class_acquire){+.+.}-{0:0}, at: i915_vma_pin.constprop.63+0x39/0x1b0 [i915]
   #2: ffff88800cf74de8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_vma_pin.constprop.63+0x5f/0x1b0 [i915]
   #3: ffff88810c7f9e38 (&vm->mutex/1){+.+.}-{3:3}, at: i915_vma_pin_ww+0x1c4/0x9d0 [i915]
   #4: ffff88810bad5768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915]
   #5: ffff88810bad60e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915]
  ...
   #46: ffff88811964d768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915]
   #47: ffff88811964e0e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915]
  INFO: lockdep is turned off.

Fixing eviction to nest into ww_class_acquire is a high priority, but
it requires a rework of the entire driver, which can only be done one
step at a time.

As an intermediate solution, add an acquire context to
ww_mutex_trylock, which allows us to do proper nesting annotations on
the trylocks, making the above lockdep splat disappear.

This is also useful in regulator_lock_nested, which may avoid dropping
regulator_nesting_mutex in the uncontended path, so use it there.

TTM may be another user for this, where we could lock a buffer in a
fastpath with list locks held, without dropping all locks we hold.

[peterz: rework actual ww_mutex_trylock() implementations]
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/YUBGPdDDjKlxAuXJ@hirez.programming.kicks-ass.net

1 files changed, 65 insertions, 21 deletions

diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 3e82f449b4ff..d63ac411f367 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -16,6 +16,15 @@
 static DEFINE_WD_CLASS(ww_class);
 struct workqueue_struct *wq;
 
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+#define ww_acquire_init_noinject(a, b) do { \
+		ww_acquire_init((a), (b)); \
+		(a)->deadlock_inject_countdown = ~0U; \
+	} while (0)
+#else
+#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b))
+#endif
+
 struct test_mutex {
 	struct work_struct work;
 	struct ww_mutex mutex;
@@ -36,7 +45,7 @@ static void test_mutex_work(struct work_struct *work)
 	wait_for_completion(&mtx->go);
 
 	if (mtx->flags & TEST_MTX_TRY) {
-		while (!ww_mutex_trylock(&mtx->mutex))
+		while (!ww_mutex_trylock(&mtx->mutex, NULL))
 			cond_resched();
 	} else {
 		ww_mutex_lock(&mtx->mutex, NULL);
@@ -109,19 +118,38 @@ static int test_mutex(void)
 	return 0;
 }
 
-static int test_aa(void)
+static int test_aa(bool trylock)
 {
 	struct ww_mutex mutex;
 	struct ww_acquire_ctx ctx;
 	int ret;
+	const char *from = trylock ? "trylock" : "lock";
 
 	ww_mutex_init(&mutex, &ww_class);
 	ww_acquire_init(&ctx, &ww_class);
 
-	ww_mutex_lock(&mutex, &ctx);
+	if (!trylock) {
+		ret = ww_mutex_lock(&mutex, &ctx);
+		if (ret) {
+			pr_err("%s: initial lock failed!\n", __func__);
+			goto out;
+		}
+	} else {
+		if (!ww_mutex_trylock(&mutex, &ctx)) {
+			pr_err("%s: initial trylock failed!\n", __func__);
+			goto out;
+		}
+	}
 
-	if (ww_mutex_trylock(&mutex))  {
-		pr_err("%s: trylocked itself!\n", __func__);
+	if (ww_mutex_trylock(&mutex, NULL))  {
+		pr_err("%s: trylocked itself without context from %s!\n", __func__, from);
+		ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (ww_mutex_trylock(&mutex, &ctx))  {
+		pr_err("%s: trylocked itself with context from %s!\n", __func__, from);
 		ww_mutex_unlock(&mutex);
 		ret = -EINVAL;
 		goto out;
@@ -129,17 +157,17 @@ static int test_aa(void)
 
 	ret = ww_mutex_lock(&mutex, &ctx);
 	if (ret != -EALREADY) {
-		pr_err("%s: missed deadlock for recursing, ret=%d\n",
-		       __func__, ret);
+		pr_err("%s: missed deadlock for recursing, ret=%d from %s\n",
+		       __func__, ret, from);
 		if (!ret)
 			ww_mutex_unlock(&mutex);
 		ret = -EINVAL;
 		goto out;
 	}
 
+	ww_mutex_unlock(&mutex);
 	ret = 0;
 out:
-	ww_mutex_unlock(&mutex);
 	ww_acquire_fini(&ctx);
 	return ret;
 }
@@ -150,7 +178,7 @@ struct test_abba {
 	struct ww_mutex b_mutex;
 	struct completion a_ready;
 	struct completion b_ready;
-	bool resolve;
+	bool resolve, trylock;
 	int result;
 };
 
@@ -160,8 +188,13 @@ static void test_abba_work(struct work_struct *work)
 	struct ww_acquire_ctx ctx;
 	int err;
 
-	ww_acquire_init(&ctx, &ww_class);
-	ww_mutex_lock(&abba->b_mutex, &ctx);
+	ww_acquire_init_noinject(&ctx, &ww_class);
+	if (!abba->trylock)
+		ww_mutex_lock(&abba->b_mutex, &ctx);
+	else
+		WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx));
+
+	WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx);
 
 	complete(&abba->b_ready);
 	wait_for_completion(&abba->a_ready);
@@ -181,7 +214,7 @@ static void test_abba_work(struct work_struct *work)
 	abba->result = err;
 }
 
-static int test_abba(bool resolve)
+static int test_abba(bool trylock, bool resolve)
 {
 	struct test_abba abba;
 	struct ww_acquire_ctx ctx;
@@ -192,12 +225,18 @@ static int test_abba(bool resolve)
 	INIT_WORK_ONSTACK(&abba.work, test_abba_work);
 	init_completion(&abba.a_ready);
 	init_completion(&abba.b_ready);
+	abba.trylock = trylock;
 	abba.resolve = resolve;
 
 	schedule_work(&abba.work);
 
-	ww_acquire_init(&ctx, &ww_class);
-	ww_mutex_lock(&abba.a_mutex, &ctx);
+	ww_acquire_init_noinject(&ctx, &ww_class);
+	if (!trylock)
+		ww_mutex_lock(&abba.a_mutex, &ctx);
+	else
+		WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx));
+
+	WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx);
 
 	complete(&abba.a_ready);
 	wait_for_completion(&abba.b_ready);
@@ -249,7 +288,7 @@ static void test_cycle_work(struct work_struct *work)
 	struct ww_acquire_ctx ctx;
 	int err, erra = 0;
 
-	ww_acquire_init(&ctx, &ww_class);
+	ww_acquire_init_noinject(&ctx, &ww_class);
 	ww_mutex_lock(&cycle->a_mutex, &ctx);
 
 	complete(cycle->a_signal);
@@ -581,7 +620,9 @@ static int stress(int nlocks, int nthreads, unsigned int flags)
 static int __init test_ww_mutex_init(void)
 {
 	int ncpus = num_online_cpus();
-	int ret;
+	int ret, i;
+
+	printk(KERN_INFO "Beginning ww mutex selftests\n");
 
 	wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0);
 	if (!wq)
@@ -591,17 +632,19 @@ static int __init test_ww_mutex_init(void)
 	if (ret)
 		return ret;
 
-	ret = test_aa();
+	ret = test_aa(false);
 	if (ret)
 		return ret;
 
-	ret = test_abba(false);
+	ret = test_aa(true);
 	if (ret)
 		return ret;
 
-	ret = test_abba(true);
-	if (ret)
-		return ret;
+	for (i = 0; i < 4; i++) {
+		ret = test_abba(i & 1, i & 2);
+		if (ret)
+			return ret;
+	}
 
 	ret = test_cycle(ncpus);
 	if (ret)
@@ -619,6 +662,7 @@ static int __init test_ww_mutex_init(void)
 	if (ret)
 		return ret;
 
+	printk(KERN_INFO "All ww mutex selftests passed\n");
 	return 0;
 }