drm/i915/gvt: Use vgpu_lock to protect per vgpu access

The patch set splits out 2 small locks from the original big gvt lock:
  - vgpu_lock protects per-vGPU data and logic, especially the vGPU
    trap emulation path.
  - sched_lock protects gvt scheudler structure, context schedule logic
    and vGPU's schedule data.

Use vgpu_lock to replace the gvt big lock. By doing this, the
mmio read/write trap path, vgpu virtual event emulation and other
vgpu related process, would be protected under per vgpu_lock.

v9:
  - Change commit author since the patches are improved a lot compared
    with original version.
    Original author: Pei Zhang <pei.zhang@intel.com>
  - Rebase to latest gvt-staging.
v8:
  - Correct coding and comment style.
  - Rebase to latest gvt-staging.
v7:
  - Remove gtt_lock since already proteced by gvt_lock and vgpu_lock.
  - Fix a typo in intel_gvt_deactivate_vgpu, unlock the wrong lock.
v6:
  - Rebase to latest gvt-staging.
v5:
  - Rebase to latest gvt-staging.
  - intel_vgpu_page_track_handler should use vgpu_lock.
v4:
  - Rebase to latest gvt-staging.
  - Protect vgpu->active access with vgpu_lock.
  - Do not wait gpu idle in vgpu_lock.
v3: update to latest code base
v2: add gvt->lock in function gvt_check_vblank_emulation

Performance comparison on Kabylake platform.
  - Configuration:
    Host: Ubuntu 16.04.
    Guest 1 & 2: Ubuntu 16.04.

glmark2 score comparison:
  - Configuration:
    Host: glxgears.
    Guests: glmark2.
+--------------------------------+-----------------+
| Setup                          | glmark2 score   |
+--------------------------------+-----------------+
| unified lock, iommu=on         | 58~62 (avg. 60) |
+--------------------------------+-----------------+
| unified lock, iommu=igfx_off   | 57~61 (avg. 59) |
+--------------------------------+-----------------+
| per-logic lock, iommu=on       | 60~68 (avg. 64) |
+--------------------------------+-----------------+
| per-logic lock, iommu=igfx_off | 61~67 (avg. 64) |
+--------------------------------+-----------------+

lock_stat comparison:
  - Configuration:
    Stop lock stat immediately after boot up.
    Boot 2 VM Guests.
    Run glmark2 in guests.
    Start perf lock_stat for 20 seconds and stop again.
  - Legend: c - contentions; w - waittime-avg
+------------+-----------------+-----------+---------------+------------+
|            | gvt_lock        |sched_lock | vgpu_lock     | gtt_lock   |
+ lock type; +-----------------+-----------+---------------+------------+
| iommu set  | c     | w       | c  | w    | c    | w      | c   | w    |
+------------+-------+---------+----+------+------+--------+-----+------+
| unified;   | 20697 | 839     |N/A | N/A  | N/A  | N/A    | N/A | N/A  |
| on         |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| unified;   | 21838 | 658.15  |N/A | N/A  | N/A  | N/A    | N/A | N/A  |
| igfx_off   |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| per-logic; | 1553  | 1599.96 |9458|429.97| 5846 | 274.33 | 0   | 0.00 |
| on         |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| per-logic; | 1911  | 1678.32 |8335|445.16| 5451 | 244.80 | 0   | 0.00 |
| igfx_off   |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+

Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

1 files changed, 19 insertions, 16 deletions

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8180e8d1e2..8e4a63c5b7d1 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -337,26 +337,28 @@ void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt)
 	struct intel_gvt_irq *irq = &gvt->irq;
 	struct intel_vgpu *vgpu;
 	int pipe, id;
+	int found = false;
 
-	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
-		return;
-
+	mutex_lock(&gvt->lock);
 	for_each_active_vgpu(gvt, vgpu, id) {
 		for (pipe = 0; pipe < I915_MAX_PIPES; pipe++) {
-			if (pipe_is_enabled(vgpu, pipe))
-				goto out;
+			if (pipe_is_enabled(vgpu, pipe)) {
+				found = true;
+				break;
+			}
 		}
+		if (found)
+			break;
 	}
 
 	/* all the pipes are disabled */
-	hrtimer_cancel(&irq->vblank_timer.timer);
-	return;
-
-out:
-	hrtimer_start(&irq->vblank_timer.timer,
-		ktime_add_ns(ktime_get(), irq->vblank_timer.period),
-		HRTIMER_MODE_ABS);
-
+	if (!found)
+		hrtimer_cancel(&irq->vblank_timer.timer);
+	else
+		hrtimer_start(&irq->vblank_timer.timer,
+			ktime_add_ns(ktime_get(), irq->vblank_timer.period),
+			HRTIMER_MODE_ABS);
+	mutex_unlock(&gvt->lock);
 }
 
 static void emulate_vblank_on_pipe(struct intel_vgpu *vgpu, int pipe)
@@ -393,8 +395,10 @@ static void emulate_vblank(struct intel_vgpu *vgpu)
 {
 	int pipe;
 
+	mutex_lock(&vgpu->vgpu_lock);
 	for_each_pipe(vgpu->gvt->dev_priv, pipe)
 		emulate_vblank_on_pipe(vgpu, pipe);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -409,11 +413,10 @@ void intel_gvt_emulate_vblank(struct intel_gvt *gvt)
 	struct intel_vgpu *vgpu;
 	int id;
 
-	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
-		return;
-
+	mutex_lock(&gvt->lock);
 	for_each_active_vgpu(gvt, vgpu, id)
 		emulate_vblank(vgpu);
+	mutex_unlock(&gvt->lock);
 }
 
 /**