BACKPORT: FROMGIT: binder: switch alloc->mutex to spinlock_t

The alloc->mutex is a highly contended lock that causes performance
issues on Android devices. When a low-priority task is given this lock
and it sleeps, it becomes difficult for the task to wake up and complete
its work. This delays other tasks that are also waiting on the mutex.

The problem gets worse when there is memory pressure in the system,
because this increases the contention on the alloc->mutex while the
shrinker reclaims binder pages.

Switching to a spinlock helps to keep the waiters running and avoids the
overhead of waking up tasks. This significantly improves the transaction
latency when the problematic scenario occurs.

The performance impact of this patchset was measured by stress-testing
the binder alloc contention. In this test, several clients of different
priorities send thousands of transactions of different sizes to a single
server. In parallel, pages get reclaimed using the shinker's debugfs.

The test was run on a Pixel 8, Pixel 6 and qemu machine. The results
were similar on all three devices:

after:
  | sched  | prio | average | max       | min     |
  |--------+------+---------+-----------+---------|
  | fifo   |   99 | 0.135ms |   1.197ms | 0.022ms |
  | fifo   |   01 | 0.136ms |   5.232ms | 0.018ms |
  | other  |  -20 | 0.180ms |   7.403ms | 0.019ms |
  | other  |   19 | 0.241ms |  58.094ms | 0.018ms |

before:
  | sched  | prio | average | max       | min     |
  |--------+------+---------+-----------+---------|
  | fifo   |   99 | 0.350ms | 248.730ms | 0.020ms |
  | fifo   |   01 | 0.357ms | 248.817ms | 0.024ms |
  | other  |  -20 | 0.399ms | 249.906ms | 0.020ms |
  | other  |   19 | 0.477ms | 297.756ms | 0.022ms |

The key metrics above are the average and max latencies (wall time).
These improvements should roughly translate to p95-p99 latencies on real
workloads. The response time is up to 200x faster in these scenarios and
there is no penalty in the regular path.

Note that it is only possible to convert this lock after a series of
changes made by previous patches. These mainly include refactoring the
sections that might_sleep() and changing the locking order with the
mmap_lock amongst others.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231201172212.1813387-29-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Bug: 254650075
(cherry picked from commit 7710e2cca32e7f3958480e8bd44f50e29d0c2509
 https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 char-misc-next)
Change-Id: I67121be071d5f072ac0e5eb719c95c0f1dee5eb5
[cmllamas: fixed conflicts due to missing e66b77e50522]
Signed-off-by: Carlos Llamas <cmllamas@google.com>

2 files changed, 28 insertions, 27 deletions

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 73a187cab701..352d875c3910 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -170,9 +170,9 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 {
 	struct binder_buffer *buffer;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return buffer;
 }
 
@@ -615,10 +615,10 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	if (!next)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async);
 	if (IS_ERR(buffer)) {
-		mutex_unlock(&alloc->mutex);
+		spin_unlock(&alloc->lock);
 		goto out;
 	}
 
@@ -626,7 +626,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	buffer->offsets_size = offsets_size;
 	buffer->extra_buffers_size = extra_buffers_size;
 	buffer->pid = current->tgid;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 
 	ret = binder_install_buffer_pages(alloc, buffer, size);
 	if (ret) {
@@ -807,17 +807,17 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	 * We could eliminate the call to binder_alloc_clear_buf()
 	 * from binder_alloc_deferred_release() by moving this to
 	 * binder_free_buf_locked(). However, that could
-	 * increase contention for the alloc mutex if clear_on_free
-	 * is used frequently for large buffers. The mutex is not
+	 * increase contention for the alloc->lock if clear_on_free
+	 * is used frequently for large buffers. This lock is not
 	 * needed for correctness here.
 	 */
 	if (buffer->clear_on_free) {
 		binder_alloc_clear_buf(alloc, buffer);
 		buffer->clear_on_free = false;
 	}
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	binder_free_buf_locked(alloc, buffer);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 }
 
 /**
@@ -907,7 +907,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 	struct binder_buffer *buffer;
 
 	buffers = 0;
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	BUG_ON(alloc->vma);
 
 	while ((n = rb_first(&alloc->allocated_buffers))) {
@@ -957,7 +957,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		}
 		kfree(alloc->pages);
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	if (alloc->vma_vm_mm)
 		mmdrop(alloc->vma_vm_mm);
 
@@ -980,7 +980,7 @@ void binder_alloc_print_allocated(struct seq_file *m,
 	struct binder_buffer *buffer;
 	struct rb_node *n;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
@@ -990,7 +990,7 @@ void binder_alloc_print_allocated(struct seq_file *m,
 			   buffer->extra_buffers_size,
 			   buffer->transaction ? "active" : "delivered");
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 }
 
 /**
@@ -1007,7 +1007,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 	int lru = 0;
 	int free = 0;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	/*
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
@@ -1023,7 +1023,7 @@ void binder_alloc_print_pages(struct seq_file *m,
 				lru++;
 		}
 	}
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
 }
@@ -1039,10 +1039,10 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
 	struct rb_node *n;
 	int count = 0;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
 		count++;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return count;
 }
 
@@ -1087,8 +1087,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		goto err_mmget;
 	if (!mmap_read_trylock(mm))
 		goto err_mmap_read_lock_failed;
-	if (!mutex_trylock(&alloc->mutex))
-		goto err_get_alloc_mutex_failed;
+	if (!spin_trylock(&alloc->lock))
+		goto err_get_alloc_lock_failed;
 	if (!page->page_ptr)
 		goto err_page_already_freed;
 
@@ -1107,7 +1107,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 	trace_binder_unmap_kernel_end(alloc, index);
 
 	list_lru_isolate(lru, item);
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	spin_unlock(lock);
 
 	if (vma) {
@@ -1127,8 +1127,8 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 err_invalid_vma:
 err_page_already_freed:
-	mutex_unlock(&alloc->mutex);
-err_get_alloc_mutex_failed:
+	spin_unlock(&alloc->lock);
+err_get_alloc_lock_failed:
 	mmap_read_unlock(mm);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
@@ -1165,7 +1165,7 @@ static struct shrinker binder_shrinker = {
 void binder_alloc_init(struct binder_alloc *alloc)
 {
 	alloc->pid = current->group_leader->pid;
-	mutex_init(&alloc->mutex);
+	spin_lock_init(&alloc->lock);
 	INIT_LIST_HEAD(&alloc->buffers);
 }
 
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index 10852e2d6947..93537957f4cc 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -9,7 +9,7 @@
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <linux/mm.h>
-#include <linux/rtmutex.h>
+#include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/list_lru.h>
@@ -72,6 +72,7 @@ struct binder_lru_page {
 
 /**
  * struct binder_alloc - per-binder proc state for binder allocator
+ * @lock:               protects binder_alloc fields
  * @vma:                vm_area_struct passed to mmap_handler
  *                      (invarient after mmap)
  * @tsk:                tid for task that called init for this proc
@@ -97,7 +98,7 @@ struct binder_lru_page {
  * struct binder_buffer objects used to track the user buffers
  */
 struct binder_alloc {
-	struct mutex mutex;
+	spinlock_t lock;
 	struct vm_area_struct *vma;
 	struct mm_struct *vma_vm_mm;
 	unsigned long buffer;
@@ -155,9 +156,9 @@ binder_alloc_get_free_async_space(struct binder_alloc *alloc)
 {
 	size_t free_async_space;
 
-	mutex_lock(&alloc->mutex);
+	spin_lock(&alloc->lock);
 	free_async_space = alloc->free_async_space;
-	mutex_unlock(&alloc->mutex);
+	spin_unlock(&alloc->lock);
 	return free_async_space;
 }