drm/i915/perf: Replace gt->perf.lock with stream->lock for file ops

With multi-gt, user can access multiple OA buffers concurrently. Use
stream->lock instead of gt->perf.lock to serialize file operations.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-9-umesh.nerlige.ramappa@intel.com

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 83c5dc0..9a00398 100644 (file)
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3231,6 +3231,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
        stream->poll_check_timer.function = oa_poll_check_timer_cb;
        init_waitqueue_head(&stream->poll_wq);
        spin_lock_init(&stream->oa_buffer.ptr_lock);
+       mutex_init(&stream->lock);
 
        return 0;
 
@@ -3294,7 +3295,6 @@ static ssize_t i915_perf_read(struct file *file,
                              loff_t *ppos)
 {
        struct i915_perf_stream *stream = file->private_data;
-       struct intel_gt *gt = stream->engine->gt;
        size_t offset = 0;
        int ret;
 
@@ -3318,14 +3318,14 @@ static ssize_t i915_perf_read(struct file *file,
                        if (ret)
                                return ret;
 
-                       mutex_lock(&gt->perf.lock);
+                       mutex_lock(&stream->lock);
                        ret = stream->ops->read(stream, buf, count, &offset);
-                       mutex_unlock(&gt->perf.lock);
+                       mutex_unlock(&stream->lock);
                } while (!offset && !ret);
        } else {
-               mutex_lock(&gt->perf.lock);
+               mutex_lock(&stream->lock);
                ret = stream->ops->read(stream, buf, count, &offset);
-               mutex_unlock(&gt->perf.lock);
+               mutex_unlock(&stream->lock);
        }
 
        /* We allow the poll checking to sometimes report false positive EPOLLIN
@@ -3372,9 +3372,6 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
  * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that
  * will be woken for new stream data.
  *
- * Note: The &gt->perf.lock mutex has been taken to serialize
- * with any non-file-operation driver hooks.
- *
  * Returns: any poll events that are ready without sleeping
  */
 static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
@@ -3413,12 +3410,11 @@ static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
 static __poll_t i915_perf_poll(struct file *file, poll_table *wait)
 {
        struct i915_perf_stream *stream = file->private_data;
-       struct intel_gt *gt = stream->engine->gt;
        __poll_t ret;
 
-       mutex_lock(&gt->perf.lock);
+       mutex_lock(&stream->lock);
        ret = i915_perf_poll_locked(stream, file, wait);
-       mutex_unlock(&gt->perf.lock);
+       mutex_unlock(&stream->lock);
 
        return ret;
 }
@@ -3517,9 +3513,6 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
  * @cmd: the ioctl request
  * @arg: the ioctl data
  *
- * Note: The &gt->perf.lock mutex has been taken to serialize
- * with any non-file-operation driver hooks.
- *
  * Returns: zero on success or a negative error code. Returns -EINVAL for
  * an unknown ioctl request.
  */
@@ -3557,12 +3550,11 @@ static long i915_perf_ioctl(struct file *file,
                            unsigned long arg)
 {
        struct i915_perf_stream *stream = file->private_data;
-       struct intel_gt *gt = stream->engine->gt;
        long ret;
 
-       mutex_lock(&gt->perf.lock);
+       mutex_lock(&stream->lock);
        ret = i915_perf_ioctl_locked(stream, cmd, arg);
-       mutex_unlock(&gt->perf.lock);
+       mutex_unlock(&stream->lock);
 
        return ret;
 }
@@ -3608,6 +3600,11 @@ static int i915_perf_release(struct inode *inode, struct file *file)
        struct i915_perf *perf = stream->perf;
        struct intel_gt *gt = stream->engine->gt;
 
+       /*
+        * Within this call, we know that the fd is being closed and we have no
+        * other user of stream->lock. Use the perf lock to destroy the stream
+        * here.
+        */
        mutex_lock(&gt->perf.lock);
        i915_perf_destroy_locked(stream);
        mutex_unlock(&gt->perf.lock);

diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index e888bfa..dc9bfd8 100644 (file)
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -146,6 +146,11 @@ struct i915_perf_stream {
         */
        struct intel_engine_cs *engine;
 
+       /*
+        * Lock associated with operations on stream
+        */
+       struct mutex lock;
+
        /**
         * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
         * properties given when opening a stream, representing the contents