Merge remote-tracking branch 'torvalds/master' into perf/core

To get closer to upstream and check if we need to sync more UAPI
headers, pick up fixes for libbpf that prevent perf's container tests
from completing successfuly, etc.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

7 files changed, 64 insertions, 8 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 1671db47aa57..e9c55d1d6c04 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -59,6 +59,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
 		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
 			if (priv->lastctx == ctx)
 				break;
+			/* fall-thru */
 		case MSM_SUBMIT_CMD_BUF:
 			/* copy commands into RB: */
 			obj = submit->bos[submit->cmd[i].idx].obj;
@@ -149,6 +150,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
 			if (priv->lastctx == ctx)
 				break;
+			/* fall-thru */
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index be39cf01e51e..dc8ec2c94301 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -115,6 +115,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
 			if (priv->lastctx == ctx)
 				break;
+			/* fall-thru */
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
 			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 9acbbc0f3232..048c8be426f3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -428,6 +428,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 			/* ignore if there has not been a ctx switch: */
 			if (priv->lastctx == ctx)
 				break;
+			/* fall-thru */
 		case MSM_SUBMIT_CMD_BUF:
 			OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ?
 				CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index ff14555372d0..78d5fa230c16 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -439,6 +439,18 @@ static void mdp5_crtc_atomic_disable(struct drm_crtc *crtc,
 	mdp5_crtc->enabled = false;
 }
 
+static void mdp5_crtc_vblank_on(struct drm_crtc *crtc)
+{
+	struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc->state);
+	struct mdp5_interface *intf = mdp5_cstate->pipeline.intf;
+	u32 count;
+
+	count = intf->mode == MDP5_INTF_DSI_MODE_COMMAND ? 0 : 0xffffffff;
+	drm_crtc_set_max_vblank_count(crtc, count);
+
+	drm_crtc_vblank_on(crtc);
+}
+
 static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc,
 				    struct drm_crtc_state *old_state)
 {
@@ -475,7 +487,7 @@ static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc,
 	}
 
 	/* Restore vblank irq handling after power is enabled */
-	drm_crtc_vblank_on(crtc);
+	mdp5_crtc_vblank_on(crtc);
 
 	mdp5_crtc_mode_set_nofb(crtc);
 
@@ -1028,6 +1040,8 @@ static void mdp5_crtc_reset(struct drm_crtc *crtc)
 		mdp5_crtc_destroy_state(crtc, crtc->state);
 
 	__drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base);
+
+	drm_crtc_vblank_reset(crtc);
 }
 
 static const struct drm_crtc_funcs mdp5_crtc_funcs = {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 4a60f5fca6b0..fec6ef1ae3b9 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -740,7 +740,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	dev->driver->get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos;
 	dev->driver->get_scanout_position = mdp5_get_scanoutpos;
 	dev->driver->get_vblank_counter = mdp5_get_vblank_counter;
-	dev->max_vblank_count = 0xffffffff;
+	dev->max_vblank_count = 0; /* max_vblank_count is set on each CRTC */
 	dev->vblank_disable_immediate = true;
 
 	return kms;
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index c226156f2dea..c356f5ccf253 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1279,7 +1279,8 @@ static int add_gpu_components(struct device *dev,
 	if (!np)
 		return 0;
 
-	drm_of_component_match_add(dev, matchptr, compare_of, np);
+	if (of_device_is_available(np))
+		drm_of_component_match_add(dev, matchptr, compare_of, np);
 
 	of_node_put(np);
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index c2114c748c2f..8cf6362e64bf 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -32,6 +32,46 @@ static bool use_pages(struct drm_gem_object *obj)
 	return !msm_obj->vram_node;
 }
 
+/*
+ * Cache sync.. this is a bit over-complicated, to fit dma-mapping
+ * API.  Really GPU cache is out of scope here (handled on cmdstream)
+ * and all we need to do is invalidate newly allocated pages before
+ * mapping to CPU as uncached/writecombine.
+ *
+ * On top of this, we have the added headache, that depending on
+ * display generation, the display's iommu may be wired up to either
+ * the toplevel drm device (mdss), or to the mdp sub-node, meaning
+ * that here we either have dma-direct or iommu ops.
+ *
+ * Let this be a cautionary tail of abstraction gone wrong.
+ */
+
+static void sync_for_device(struct msm_gem_object *msm_obj)
+{
+	struct device *dev = msm_obj->base.dev->dev;
+
+	if (get_dma_ops(dev)) {
+		dma_sync_sg_for_device(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	} else {
+		dma_map_sg(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	}
+}
+
+static void sync_for_cpu(struct msm_gem_object *msm_obj)
+{
+	struct device *dev = msm_obj->base.dev->dev;
+
+	if (get_dma_ops(dev)) {
+		dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	} else {
+		dma_unmap_sg(dev, msm_obj->sgt->sgl,
+			msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+	}
+}
+
 /* allocate pages from VRAM carveout, used when no IOMMU: */
 static struct page **get_pages_vram(struct drm_gem_object *obj, int npages)
 {
@@ -97,8 +137,7 @@ static struct page **get_pages(struct drm_gem_object *obj)
 		 * because display controller, GPU, etc. are not coherent:
 		 */
 		if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
-			dma_sync_sg_for_device(dev->dev, msm_obj->sgt->sgl,
-					msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+			sync_for_device(msm_obj);
 	}
 
 	return msm_obj->pages;
@@ -127,9 +166,7 @@ static void put_pages(struct drm_gem_object *obj)
 			 * GPU, etc. are not coherent:
 			 */
 			if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
-				dma_sync_sg_for_cpu(obj->dev->dev, msm_obj->sgt->sgl,
-					     msm_obj->sgt->nents,
-					     DMA_BIDIRECTIONAL);
+				sync_for_cpu(msm_obj);
 
 			sg_free_table(msm_obj->sgt);
 			kfree(msm_obj->sgt);