drm/msm/adreno: Add fenced regwrite support

There are some special registers which are accessible even when GX power
domain is collapsed during an IFPC sleep. Accessing these registers
wakes up GPU from power collapse and allow programming these registers
without additional handshake with GMU. This patch adds support for this
special register write sequence.

Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/673368/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>

Author: akhilpo-qcom

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

@@ -16,6 +16,84 @@
 
 #define GPU_PAS_ID 13
 
+static bool fence_status_check(struct msm_gpu *gpu, u32 offset, u32 value, u32 status, u32 mask)
+{
+	/* Success if !writedropped0/1 */
+	if (!(status & mask))
+		return true;
+
+	udelay(10);
+
+	/* Try to update fenced register again */
+	gpu_write(gpu, offset, value);
+
+	/* We can't do a posted write here because the power domain could be
+	 * in collapse state. So use the heaviest barrier instead
+	 */
+	mb();
+	return false;
+}
+
+static int fenced_write(struct a6xx_gpu *a6xx_gpu, u32 offset, u32 value, u32 mask)
+{
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	u32 status;
+
+	gpu_write(gpu, offset, value);
+
+	/* Nothing else to be done in the case of no-GMU */
+	if (adreno_has_gmu_wrapper(adreno_gpu))
+		return 0;
+
+	/* We can't do a posted write here because the power domain could be
+	 * in collapse state. So use the heaviest barrier instead
+	 */
+	mb();
+
+	if (!gmu_poll_timeout(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS, status,
+			fence_status_check(gpu, offset, value, status, mask), 0, 1000))
+		return 0;
+
+	/* Try again for another 1ms before failing */
+	gpu_write(gpu, offset, value);
+	mb();
+
+	if (!gmu_poll_timeout(gmu, REG_A6XX_GMU_AHB_FENCE_STATUS, status,
+			fence_status_check(gpu, offset, value, status, mask), 0, 1000)) {
+		/*
+		 * The 'delay' warning is here because the pause to print this
+		 * warning will allow gpu to move to power collapse which
+		 * defeats the purpose of continuous polling for 2 ms
+		 */
+		dev_err_ratelimited(gmu->dev, "delay in fenced register write (0x%x)\n",
+				offset);
+		return 0;
+	}
+
+	dev_err_ratelimited(gmu->dev, "fenced register write (0x%x) fail\n",
+			offset);
+
+	return -ETIMEDOUT;
+}
+
+int a6xx_fenced_write(struct a6xx_gpu *a6xx_gpu, u32 offset, u64 value, u32 mask, bool is_64b)
+{
+	int ret;
+
+	ret = fenced_write(a6xx_gpu, offset, lower_32_bits(value), mask);
+	if (ret)
+		return ret;
+
+	if (!is_64b)
+		return 0;
+
+	ret = fenced_write(a6xx_gpu, offset + 1, upper_32_bits(value), mask);
+
+	return ret;
+}
+
 static inline bool _a6xx_check_idle(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -86,7 +164,7 @@ static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	/* Update HW if this is the current ring and we are not in preempt*/
 	if (!a6xx_in_preempt(a6xx_gpu)) {
 		if (a6xx_gpu->cur_ring == ring)
-			gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr);
+			a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_RB_WPTR, wptr, BIT(0), false);
 		else
 			ring->restore_wptr = true;
 	} else {

drivers/gpu/drm/msm/adreno/a6xx_gpu.h

@@ -295,5 +295,6 @@ int a6xx_gpu_state_put(struct msm_gpu_state *state);
 
 void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off);
 void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert);
+int a6xx_fenced_write(struct a6xx_gpu *gpu, u32 offset, u64 value, u32 mask, bool is_64b);
 
 #endif /* __A6XX_GPU_H__ */

drivers/gpu/drm/msm/adreno/a6xx_preempt.c

@@ -41,7 +41,7 @@ static inline void set_preempt_state(struct a6xx_gpu *gpu,
 }
 
 /* Write the most recent wptr for the given ring into the hardware */
-static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+static inline void update_wptr(struct a6xx_gpu *a6xx_gpu, struct msm_ringbuffer *ring)
 {
 	unsigned long flags;
 	uint32_t wptr;
@@ -51,7 +51,7 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	if (ring->restore_wptr) {
 		wptr = get_wptr(ring);
 
-		gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr);
+		a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_RB_WPTR, wptr, BIT(0), false);
 
 		ring->restore_wptr = false;
 	}
@@ -172,7 +172,7 @@ void a6xx_preempt_irq(struct msm_gpu *gpu)
 
 	set_preempt_state(a6xx_gpu, PREEMPT_FINISH);
 
-	update_wptr(gpu, a6xx_gpu->cur_ring);
+	update_wptr(a6xx_gpu, a6xx_gpu->cur_ring);
 
 	set_preempt_state(a6xx_gpu, PREEMPT_NONE);
 
@@ -268,7 +268,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu)
 	 */
 	if (!ring || (a6xx_gpu->cur_ring == ring)) {
 		set_preempt_state(a6xx_gpu, PREEMPT_FINISH);
-		update_wptr(gpu, a6xx_gpu->cur_ring);
+		update_wptr(a6xx_gpu, a6xx_gpu->cur_ring);
 		set_preempt_state(a6xx_gpu, PREEMPT_NONE);
 		spin_unlock_irqrestore(&a6xx_gpu->eval_lock, flags);
 		return;
@@ -302,13 +302,13 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu)
 
 	spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
-	gpu_write64(gpu,
-		REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO,
-		a6xx_gpu->preempt_smmu_iova[ring->id]);
+	a6xx_fenced_write(a6xx_gpu,
+		REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO, a6xx_gpu->preempt_smmu_iova[ring->id],
+		BIT(1), true);
 
-	gpu_write64(gpu,
+	a6xx_fenced_write(a6xx_gpu,
 		REG_A6XX_CP_CONTEXT_SWITCH_PRIV_NON_SECURE_RESTORE_ADDR,
-		a6xx_gpu->preempt_iova[ring->id]);
+		a6xx_gpu->preempt_iova[ring->id], BIT(1), true);
 
 	a6xx_gpu->next_ring = ring;
 
@@ -328,7 +328,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu)
 	set_preempt_state(a6xx_gpu, PREEMPT_TRIGGERED);
 
 	/* Trigger the preemption */
-	gpu_write(gpu, REG_A6XX_CP_CONTEXT_SWITCH_CNTL, cntl);
+	a6xx_fenced_write(a6xx_gpu, REG_A6XX_CP_CONTEXT_SWITCH_CNTL, cntl, BIT(1), false);
 }
 
 static int preempt_init_ring(struct a6xx_gpu *a6xx_gpu,