Merge tag 'drm-msm-next-2024-09-02' of https://gitlab.freedesktop.org/drm/msm into drm-next

Updates for v6.12

DPU:
- Fix implement DP/PHY mapping on SC8180X
- Enable writeback on SM8150, SC8180X, SM6125, SM6350

DP:
- Enable widebus on all relevant chipsets

DSI:
- Fix PHY programming on SM8350 / SM8450

HDMI:
- Add support for HDMI on MSM8998

MDP5:
- NULL string fix

GPU:
- A642L speedbin support
- A615 support
- A306 support
- A621 support
- Expand UBWC uapi
- A7xx GPU devcoredump fixes
- A5xx preemption fixes
- cleanups

Signed-off-by: Dave Airlie <[email protected]>
From: Rob Clark <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGudK7YMiKDhtvYgp=bY64OZZt0UQSkEkSxLo4rLmeVd9g@mail.gmail.com

Author: airlied

Documentation/devicetree/bindings/display/msm/hdmi.yaml

@@ -19,14 +19,15 @@ properties:
       - qcom,hdmi-tx-8974
       - qcom,hdmi-tx-8994
       - qcom,hdmi-tx-8996
+      - qcom,hdmi-tx-8998
 
   clocks:
     minItems: 1
-    maxItems: 5
+    maxItems: 8
 
   clock-names:
     minItems: 1
-    maxItems: 5
+    maxItems: 8
 
   reg:
     minItems: 1
@@ -142,6 +143,7 @@ allOf:
       properties:
         clocks:
           minItems: 5
+          maxItems: 5
         clock-names:
           items:
             - const: mdp_core
@@ -151,6 +153,28 @@ allOf:
             - const: extp
         hdmi-mux-supplies: false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,hdmi-tx-8998
+    then:
+      properties:
+        clocks:
+          minItems: 8
+          maxItems: 8
+        clock-names:
+          items:
+            - const: mdp_core
+            - const: iface
+            - const: core
+            - const: alt_iface
+            - const: extp
+            - const: bus
+            - const: mnoc
+            - const: iface_mmss
+
 additionalProperties: false
 
 examples:

Documentation/devicetree/bindings/phy/qcom,hdmi-phy-qmp.yaml

@@ -14,6 +14,7 @@ properties:
   compatible:
     enum:
       - qcom,hdmi-phy-8996
+      - qcom,hdmi-phy-8998
 
   reg:
     maxItems: 6

drivers/gpu/drm/msm/Makefile

@@ -37,6 +37,7 @@ msm-display-$(CONFIG_DRM_MSM_HDMI) += \
 	hdmi/hdmi_phy.o \
 	hdmi/hdmi_phy_8960.o \
 	hdmi/hdmi_phy_8996.o \
+	hdmi/hdmi_phy_8998.o \
 	hdmi/hdmi_phy_8x60.o \
 	hdmi/hdmi_phy_8x74.o \
 	hdmi/hdmi_pll_8960.o \

drivers/gpu/drm/msm/adreno/a3xx_catalog.c

@@ -41,6 +41,17 @@ static const struct adreno_info a3xx_gpus[] = {
 		.gmem  = SZ_128K,
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
+	}, {
+		.chip_ids = ADRENO_CHIP_IDS(0x03000620),
+		.family = ADRENO_3XX,
+		.revn = 308,
+		.fw = {
+			[ADRENO_FW_PM4] = "a300_pm4.fw",
+			[ADRENO_FW_PFP] = "a300_pfp.fw",
+		},
+		.gmem = SZ_128K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a3xx_gpu_init,
 	}, {
 		.chip_ids = ADRENO_CHIP_IDS(
 			0x03020000,

drivers/gpu/drm/msm/adreno/a3xx_gpu.c

@@ -145,6 +145,10 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x0003);
 		gpu_write(gpu, REG_A3XX_VBIF_OUT_RD_LIM_CONF0, 0x0000000a);
 		gpu_write(gpu, REG_A3XX_VBIF_OUT_WR_LIM_CONF0, 0x0000000a);
+	} else if (adreno_is_a306a(adreno_gpu)) {
+		gpu_write(gpu, REG_A3XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x0003);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_RD_LIM_CONF0, 0x00000010);
+		gpu_write(gpu, REG_A3XX_VBIF_OUT_WR_LIM_CONF0, 0x00000010);
 	} else if (adreno_is_a320(adreno_gpu)) {
 		/* Set up 16 deep read/write request queues: */
 		gpu_write(gpu, REG_A3XX_VBIF_IN_RD_LIM_CONF0, 0x10101010);
@@ -237,7 +241,9 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A3XX_UCHE_CACHE_MODE_CONTROL_REG, 0x00000001);
 
 	/* Enable Clock gating: */
-	if (adreno_is_a305b(adreno_gpu) || adreno_is_a306(adreno_gpu))
+	if (adreno_is_a305b(adreno_gpu) ||
+	    adreno_is_a306(adreno_gpu) ||
+	    adreno_is_a306a(adreno_gpu))
 		gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xaaaaaaaa);
 	else if (adreno_is_a320(adreno_gpu))
 		gpu_write(gpu, REG_A3XX_RBBM_CLOCK_CTL, 0xbfffffff);
@@ -334,8 +340,10 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_CP_PFP_UCODE_DATA, ptr[i]);
 
 	/* CP ROQ queue sizes (bytes) - RB:16, ST:16, IB1:32, IB2:64 */
-	if (adreno_is_a305(adreno_gpu) || adreno_is_a306(adreno_gpu) ||
-			adreno_is_a320(adreno_gpu)) {
+	if (adreno_is_a305(adreno_gpu) ||
+	    adreno_is_a306(adreno_gpu) ||
+	    adreno_is_a306a(adreno_gpu) ||
+	    adreno_is_a320(adreno_gpu)) {
 		gpu_write(gpu, REG_AXXX_CP_QUEUE_THRESHOLDS,
 				AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB1_START(2) |
 				AXXX_CP_QUEUE_THRESHOLDS_CSQ_IB2_START(6) |

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

@@ -65,6 +65,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 
 static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	struct msm_ringbuffer *ring = submit->ring;
 	struct drm_gem_object *obj;
 	uint32_t *ptr, dwords;
@@ -109,6 +111,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
 		}
 	}
 
+	a5xx_gpu->last_seqno[ring->id] = submit->seqno;
 	a5xx_flush(gpu, ring, true);
 	a5xx_preempt_trigger(gpu);
 
@@ -150,9 +153,13 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1);
 	OUT_RING(ring, 1);
 
-	/* Enable local preemption for finegrain preemption */
+	/*
+	 * Disable local preemption by default because it requires
+	 * user-space to be aware of it and provide additional handling
+	 * to restore rendering state or do various flushes on switch.
+	 */
 	OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1);
-	OUT_RING(ring, 0x1);
+	OUT_RING(ring, 0x0);
 
 	/* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */
 	OUT_PKT7(ring, CP_YIELD_ENABLE, 1);
@@ -206,6 +213,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	/* Write the fence to the scratch register */
 	OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1);
 	OUT_RING(ring, submit->seqno);
+	a5xx_gpu->last_seqno[ring->id] = submit->seqno;
 
 	/*
 	 * Execute a CACHE_FLUSH_TS event. This will ensure that the
@@ -1793,5 +1801,9 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 	else
 		adreno_gpu->ubwc_config.highest_bank_bit = 14;
 
+	/* a5xx only supports UBWC 1.0, these are not configurable */
+	adreno_gpu->ubwc_config.macrotile_mode = 0;
+	adreno_gpu->ubwc_config.ubwc_swizzle = 0x7;
+
 	return gpu;
 }

drivers/gpu/drm/msm/adreno/a5xx_gpu.h

@@ -34,8 +34,10 @@ struct a5xx_gpu {
 	struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS];
 	struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
 	uint64_t preempt_iova[MSM_GPU_MAX_RINGS];
+	uint32_t last_seqno[MSM_GPU_MAX_RINGS];
 
 	atomic_t preempt_state;
+	spinlock_t preempt_start_lock;
 	struct timer_list preempt_timer;
 
 	struct drm_gem_object *shadow_bo;

drivers/gpu/drm/msm/adreno/a5xx_preempt.c

@@ -55,6 +55,8 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 /* Return the highest priority ringbuffer with something in it */
 static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
 	unsigned long flags;
 	int i;
 
@@ -64,6 +66,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
 
 		spin_lock_irqsave(&ring->preempt_lock, flags);
 		empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring));
+		if (!empty && ring == a5xx_gpu->cur_ring)
+			empty = ring->memptrs->fence == a5xx_gpu->last_seqno[i];
 		spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 		if (!empty)
@@ -97,12 +101,19 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
 	if (gpu->nr_rings == 1)
 		return;
 
+	/*
+	 * Serialize preemption start to ensure that we always make
+	 * decision on latest state. Otherwise we can get stuck in
+	 * lower priority or empty ring.
+	 */
+	spin_lock_irqsave(&a5xx_gpu->preempt_start_lock, flags);
+
 	/*
 	 * Try to start preemption by moving from NONE to START. If
 	 * unsuccessful, a preemption is already in flight
 	 */
 	if (!try_preempt_state(a5xx_gpu, PREEMPT_NONE, PREEMPT_START))
-		return;
+		goto out;
 
 	/* Get the next ring to preempt to */
 	ring = get_next_ring(gpu);
@@ -127,9 +138,11 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
 		set_preempt_state(a5xx_gpu, PREEMPT_ABORT);
 		update_wptr(gpu, a5xx_gpu->cur_ring);
 		set_preempt_state(a5xx_gpu, PREEMPT_NONE);
-		return;
+		goto out;
 	}
 
+	spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags);
+
 	/* Make sure the wptr doesn't update while we're in motion */
 	spin_lock_irqsave(&ring->preempt_lock, flags);
 	a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring);
@@ -152,6 +165,10 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
 
 	/* And actually start the preemption */
 	gpu_write(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL, 1);
+	return;
+
+out:
+	spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags);
 }
 
 void a5xx_preempt_irq(struct msm_gpu *gpu)
@@ -188,6 +205,12 @@ void a5xx_preempt_irq(struct msm_gpu *gpu)
 	update_wptr(gpu, a5xx_gpu->cur_ring);
 
 	set_preempt_state(a5xx_gpu, PREEMPT_NONE);
+
+	/*
+	 * Try to trigger preemption again in case there was a submit or
+	 * retire during ring switch
+	 */
+	a5xx_preempt_trigger(gpu);
 }
 
 void a5xx_preempt_hw_init(struct msm_gpu *gpu)
@@ -204,6 +227,8 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu)
 		return;
 
 	for (i = 0; i < gpu->nr_rings; i++) {
+		a5xx_gpu->preempt[i]->data = 0;
+		a5xx_gpu->preempt[i]->info = 0;
 		a5xx_gpu->preempt[i]->wptr = 0;
 		a5xx_gpu->preempt[i]->rptr = 0;
 		a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova;
@@ -298,5 +323,6 @@ void a5xx_preempt_init(struct msm_gpu *gpu)
 		}
 	}
 
+	spin_lock_init(&a5xx_gpu->preempt_start_lock);
 	timer_setup(&a5xx_gpu->preempt_timer, a5xx_preempt_timer, 0);
 }