Merge tag 'drm-msm-next-2020-12-07' of https://gitlab.freedesktop.org/drm/msm into drm-next

* Shutdown hook for GPU (to ensure GPU is idle before iommu goes away)
* GPU cooling device support
* DSI 7nm and 10nm phy/pll updates
* Additional sm8150/sm8250 DPU support (merge_3d and DSPP color
  processing)
* Various DP fixes
* A whole bunch of W=1 fixes from Lee Jones
* GEM locking re-work (no more trylock_recursive in shrinker!)
* LLCC (system cache) support
* Various other fixes/cleanups

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGt0G=H3_RbF_GAQv838z5uujSmFd+7fYhL6Yg=23LwZ=g@mail.gmail.com

76 files changed, 2057 insertions, 1114 deletions

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index e5816b498494..dabb4a1ccdcf 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -4,8 +4,8 @@ config DRM_MSM
 	tristate "MSM DRM"
 	depends on DRM
 	depends on ARCH_QCOM || SOC_IMX5 || (ARM && COMPILE_TEST)
+	depends on IOMMU_SUPPORT
 	depends on OF && COMMON_CLK
-	depends on MMU
 	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	select IOMMU_IO_PGTABLE
 	select QCOM_MDT_LOADER if ARCH_QCOM
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 340682cd0f32..3cc906121fb3 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -67,6 +67,7 @@ msm-y := \
 	disp/dpu1/dpu_hw_pingpong.o \
 	disp/dpu1/dpu_hw_sspp.o \
 	disp/dpu1/dpu_hw_dspp.o \
+	disp/dpu1/dpu_hw_merge3d.o \
 	disp/dpu1/dpu_hw_top.o \
 	disp/dpu1/dpu_hw_util.o \
 	disp/dpu1/dpu_hw_vbif.o \
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index f29c77d9cd42..93da6683a866 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -519,6 +519,8 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	struct msm_gpu *gpu;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct platform_device *pdev = priv->gpu_pdev;
+	struct icc_path *ocmem_icc_path;
+	struct icc_path *icc_path;
 	int ret;
 
 	if (!pdev) {
@@ -566,13 +568,28 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
+	ret = IS_ERR(icc_path);
+	if (ret)
+		goto fail;
+
+	ocmem_icc_path = devm_of_icc_get(&pdev->dev, "ocmem");
+	ret = IS_ERR(ocmem_icc_path);
+	if (ret) {
+		/* allow -ENODATA, ocmem icc is optional */
+		if (ret != -ENODATA)
+			goto fail;
+		ocmem_icc_path = NULL;
+	}
+
+
 	/*
 	 * Set the ICC path to maximum speed for now by multiplying the fastest
 	 * frequency by the bus width (8). We'll want to scale this later on to
 	 * improve battery life.
 	 */
-	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
-	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
 
 	return gpu;
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 2b93b33b05e4..c0be3a0f36b2 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -648,6 +648,8 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 	struct msm_gpu *gpu;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct platform_device *pdev = priv->gpu_pdev;
+	struct icc_path *ocmem_icc_path;
+	struct icc_path *icc_path;
 	int ret;
 
 	if (!pdev) {
@@ -694,13 +696,27 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
+	ret = IS_ERR(icc_path);
+	if (ret)
+		goto fail;
+
+	ocmem_icc_path = devm_of_icc_get(&pdev->dev, "ocmem");
+	ret = IS_ERR(ocmem_icc_path);
+	if (ret) {
+		/* allow -ENODATA, ocmem icc is optional */
+		if (ret != -ENODATA)
+			goto fail;
+		ocmem_icc_path = NULL;
+	}
+
 	/*
 	 * Set the ICC path to maximum speed for now by multiplying the fastest
 	 * frequency by the bus width (8). We'll want to scale this later on to
 	 * improve battery life.
 	 */
-	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
-	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
 
 	return gpu;
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index d6804a802355..a5af223eaf50 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -36,7 +36,7 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		OUT_RING(ring, upper_32_bits(shadowptr(a5xx_gpu, ring)));
 	}
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock_irqsave(&ring->preempt_lock, flags);
 
 	/* Copy the shadow to the actual register */
 	ring->cur = ring->next;
@@ -44,7 +44,7 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	/* Make sure to wrap wptr if we need to */
 	wptr = get_wptr(ring);
 
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 	/* Make sure everything is posted before making a decision */
 	mb();
@@ -426,7 +426,7 @@ static int a5xx_preempt_start(struct msm_gpu *gpu)
 static void a5xx_ucode_check_version(struct a5xx_gpu *a5xx_gpu,
 		struct drm_gem_object *obj)
 {
-	u32 *buf = msm_gem_get_vaddr_active(obj);
+	u32 *buf = msm_gem_get_vaddr(obj);
 
 	if (IS_ERR(buf))
 		return;
@@ -755,12 +755,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_CP_RB_CNTL,
 		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
 
-	/* Disable preemption if WHERE_AM_I isn't available */
-	if (!a5xx_gpu->has_whereami && gpu->nr_rings > 1) {
-		a5xx_preempt_fini(gpu);
-		gpu->nr_rings = 1;
-	} else {
-		/* Create a privileged buffer for the RPTR shadow */
+	/* Create a privileged buffer for the RPTR shadow */
+	if (a5xx_gpu->has_whereami) {
 		if (!a5xx_gpu->shadow_bo) {
 			a5xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
 				sizeof(u32) * gpu->nr_rings,
@@ -774,6 +770,10 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 		gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR,
 			REG_A5XX_CP_RB_RPTR_ADDR_HI, shadowptr(a5xx_gpu, gpu->rb[0]));
+	} else if (gpu->nr_rings > 1) {
+		/* Disable preemption if WHERE_AM_I isn't available */
+		a5xx_preempt_fini(gpu);
+		gpu->nr_rings = 1;
 	}
 
 	a5xx_preempt_hw_init(gpu);
@@ -1056,7 +1056,6 @@ static void a5xx_gpmu_err_irq(struct msm_gpu *gpu)
 static void a5xx_fault_detect_irq(struct msm_gpu *gpu)
 {
 	struct drm_device *dev = gpu->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 
 	DRM_DEV_ERROR(dev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n",
@@ -1072,7 +1071,7 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu)
 	/* Turn off the hangcheck timer to keep it from bothering us */
 	del_timer(&gpu->hangcheck_timer);
 
-	queue_work(priv->wq, &gpu->recover_work);
+	kthread_queue_work(gpu->worker, &gpu->recover_work);
 }
 
 #define RBBM_ERROR_MASK \
@@ -1207,7 +1206,9 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 static int a5xx_pm_suspend(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	u32 mask = 0xf;
+	int i, ret;
 
 	/* A510 has 3 XIN ports in VBIF */
 	if (adreno_is_a510(adreno_gpu))
@@ -1227,7 +1228,15 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x003C0000);
 	gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x00000000);
 
-	return msm_gpu_pm_suspend(gpu);
+	ret = msm_gpu_pm_suspend(gpu);
+	if (ret)
+		return ret;
+
+	if (a5xx_gpu->has_whereami)
+		for (i = 0; i < gpu->nr_rings; i++)
+			a5xx_gpu->shadow[i] = 0;
+
+	return 0;
 }
 
 static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index 7e04509c4e1f..42eaef7ad7c7 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -45,9 +45,9 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	if (!ring)
 		return;
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock_irqsave(&ring->preempt_lock, flags);
 	wptr = get_wptr(ring);
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 	gpu_write(gpu, REG_A5XX_CP_RB_WPTR, wptr);
 }
@@ -62,9 +62,9 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
 		bool empty;
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
-		spin_lock_irqsave(&ring->lock, flags);
+		spin_lock_irqsave(&ring->preempt_lock, flags);
 		empty = (get_wptr(ring) == ring->memptrs->rptr);
-		spin_unlock_irqrestore(&ring->lock, flags);
+		spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 		if (!empty)
 			return ring;
@@ -78,13 +78,12 @@ static void a5xx_preempt_timer(struct timer_list *t)
 	struct a5xx_gpu *a5xx_gpu = from_timer(a5xx_gpu, t, preempt_timer);
 	struct msm_gpu *gpu = &a5xx_gpu->base.base;
 	struct drm_device *dev = gpu->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 
 	if (!try_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED, PREEMPT_FAULTED))
 		return;
 
 	DRM_DEV_ERROR(dev->dev, "%s: preemption timed out\n", gpu->name);
-	queue_work(priv->wq, &gpu->recover_work);
+	kthread_queue_work(gpu->worker, &gpu->recover_work);
 }
 
 /* Try to trigger a preemption switch */
@@ -132,9 +131,9 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
 	}
 
 	/* Make sure the wptr doesn't update while we're in motion */
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock_irqsave(&ring->preempt_lock, flags);
 	a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring);
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 	/* Set the address of the incoming preemption record */
 	gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO,
@@ -162,7 +161,6 @@ void a5xx_preempt_irq(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	struct drm_device *dev = gpu->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 
 	if (!try_preempt_state(a5xx_gpu, PREEMPT_TRIGGERED, PREEMPT_PENDING))
 		return;
@@ -181,7 +179,7 @@ void a5xx_preempt_irq(struct msm_gpu *gpu)
 		set_preempt_state(a5xx_gpu, PREEMPT_FAULTED);
 		DRM_DEV_ERROR(dev->dev, "%s: Preemption failed to complete\n",
 			gpu->name);
-		queue_work(priv->wq, &gpu->recover_work);
+		kthread_queue_work(gpu->worker, &gpu->recover_work);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 491fee410daf..e6703ae98760 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -19,8 +19,6 @@ static void a6xx_gmu_fault(struct a6xx_gmu *gmu)
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	struct drm_device *dev = gpu->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 
 	/* FIXME: add a banner here */
 	gmu->hung = true;
@@ -29,7 +27,7 @@ static void a6xx_gmu_fault(struct a6xx_gmu *gmu)
 	del_timer(&gpu->hangcheck_timer);
 
 	/* Queue the GPU handler because we need to treat this as a recovery */
-	queue_work(priv->wq, &gpu->recover_work);
+	kthread_queue_work(gpu->worker, &gpu->recover_work);
 }
 
 static irqreturn_t a6xx_gmu_irq(int irq, void *data)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 948f3656c20c..130661898546 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -8,7 +8,9 @@
 #include "a6xx_gpu.h"
 #include "a6xx_gmu.xml.h"
 
+#include <linux/bitfield.h>
 #include <linux/devfreq.h>
+#include <linux/soc/qcom/llcc-qcom.h>
 
 #define GPU_PAS_ID 13
 
@@ -30,7 +32,7 @@ static inline bool _a6xx_check_idle(struct msm_gpu *gpu)
 		A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT);
 }
 
-bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+static bool a6xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	/* wait for CP to drain ringbuffer: */
 	if (!adreno_idle(gpu, ring))
@@ -65,7 +67,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 		OUT_RING(ring, upper_32_bits(shadowptr(a6xx_gpu, ring)));
 	}
 
-	spin_lock_irqsave(&ring->lock, flags);
+	spin_lock_irqsave(&ring->preempt_lock, flags);
 
 	/* Copy the shadow to the actual register */
 	ring->cur = ring->next;
@@ -73,7 +75,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	/* Make sure to wrap wptr if we need to */
 	wptr = get_wptr(ring);
 
-	spin_unlock_irqrestore(&ring->lock, flags);
+	spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 	/* Make sure everything is posted before making a decision */
 	mb();
@@ -522,7 +524,7 @@ static int a6xx_cp_init(struct msm_gpu *gpu)
 static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		struct drm_gem_object *obj)
 {
-	u32 *buf = msm_gem_get_vaddr_active(obj);
+	u32 *buf = msm_gem_get_vaddr(obj);
 
 	if (IS_ERR(buf))
 		return;
@@ -965,8 +967,6 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	struct drm_device *dev = gpu->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 
 	/*
@@ -989,7 +989,7 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu)
 	/* Turn off the hangcheck timer to keep it from bothering us */
 	del_timer(&gpu->hangcheck_timer);
 
-	queue_work(priv->wq, &gpu->recover_work);
+	kthread_queue_work(gpu->worker, &gpu->recover_work);
 }
 
 static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
@@ -1022,6 +1022,105 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
 	return IRQ_HANDLED;
 }
 
+static void a6xx_llc_rmw(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 mask, u32 or)
+{
+	return msm_rmw(a6xx_gpu->llc_mmio + (reg << 2), mask, or);
+}
+
+static void a6xx_llc_write(struct a6xx_gpu *a6xx_gpu, u32 reg, u32 value)
+{
+	return msm_writel(value, a6xx_gpu->llc_mmio + (reg << 2));
+}
+
+static void a6xx_llc_deactivate(struct a6xx_gpu *a6xx_gpu)
+{
+	llcc_slice_deactivate(a6xx_gpu->llc_slice);
+	llcc_slice_deactivate(a6xx_gpu->htw_llc_slice);
+}
+
+static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
+{
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	u32 cntl1_regval = 0;
+
+	if (IS_ERR(a6xx_gpu->llc_mmio))
+		return;
+
+	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+
+		gpu_scid &= 0x1f;
+		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
+			       (gpu_scid << 15) | (gpu_scid << 20);
+	}
+
+	/*
+	 * For targets with a MMU500, activate the slice but don't program the