Adding upstream version 6.8.9.upstream/6.8.9

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 91 insertions, 58 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index e5916c1067..c003f97018 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -684,7 +684,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
-	u32 regbit;
+	u32 hbb;
 	int ret;
 
 	gpu_write(gpu, REG_A5XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x00000003);
@@ -820,18 +820,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F);
 
-	/* Set the highest bank bit */
-	if (adreno_is_a540(adreno_gpu) || adreno_is_a530(adreno_gpu))
-		regbit = 2;
-	else
-		regbit = 1;
+	BUG_ON(adreno_gpu->ubwc_config.highest_bank_bit < 13);
+	hbb = adreno_gpu->ubwc_config.highest_bank_bit - 13;
 
-	gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, regbit << 7);
-	gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, regbit << 1);
+	gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, hbb << 7);
+	gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, hbb << 1);
 
 	if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu) ||
 	    adreno_is_a540(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, regbit);
+		gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, hbb);
 
 	/* Disable All flat shading optimization (ALLFLATOPTDIS) */
 	gpu_rmw(gpu, REG_A5XX_VPC_DBG_ECO_CNTL, 0, (1 << 10));
@@ -1785,5 +1782,11 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
 	/* Set up the preemption specific bits and pieces for each ringbuffer */
 	a5xx_preempt_init(gpu);
 
+	/* Set the highest bank bit */
+	if (adreno_is_a540(adreno_gpu) || adreno_is_a530(adreno_gpu))
+		adreno_gpu->ubwc_config.highest_bank_bit = 15;
+	else
+		adreno_gpu->ubwc_config.highest_bank_bit = 14;
+
 	return gpu;
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index edc1eeef84..792a4c60a2 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1270,81 +1270,95 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_CP_PROTECT(count_max - 1), regs[i]);
 }
 
-static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
+static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 {
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	/* Unknown, introduced with A650 family, related to UBWC mode/ver 4 */
-	u32 rgb565_predicator = 0;
+	gpu->ubwc_config.rgb565_predicator = 0;
 	/* Unknown, introduced with A650 family */
-	u32 uavflagprd_inv = 0;
+	gpu->ubwc_config.uavflagprd_inv = 0;
 	/* Whether the minimum access length is 64 bits */
-	u32 min_acc_len = 0;
+	gpu->ubwc_config.min_acc_len = 0;
 	/* Entirely magic, per-GPU-gen value */
-	u32 ubwc_mode = 0;
+	gpu->ubwc_config.ubwc_mode = 0;
 	/*
 	 * The Highest Bank Bit value represents the bit of the highest DDR bank.
-	 * We then subtract 13 from it (13 is the minimum value allowed by hw) and
-	 * write the lowest two bits of the remaining value as hbb_lo and the
-	 * one above it as hbb_hi to the hardware. This should ideally use DRAM
-	 * type detection.
+	 * This should ideally use DRAM type detection.
 	 */
-	u32 hbb_hi = 0;
-	u32 hbb_lo = 2;
-	/* Unknown, introduced with A640/680 */
-	u32 amsbc = 0;
+	gpu->ubwc_config.highest_bank_bit = 15;
 
-	if (adreno_is_a610(adreno_gpu)) {
-		/* HBB = 14 */
-		hbb_lo = 1;
-		min_acc_len = 1;
-		ubwc_mode = 1;
+	if (adreno_is_a610(gpu)) {
+		gpu->ubwc_config.highest_bank_bit = 13;
+		gpu->ubwc_config.min_acc_len = 1;
+		gpu->ubwc_config.ubwc_mode = 1;
 	}
 
-	/* a618 is using the hw default values */
-	if (adreno_is_a618(adreno_gpu))
-		return;
+	if (adreno_is_a618(gpu))
+		gpu->ubwc_config.highest_bank_bit = 14;
 
-	if (adreno_is_a619_holi(adreno_gpu))
-		hbb_lo = 0;
+	if (adreno_is_a619(gpu))
+		/* TODO: Should be 14 but causes corruption at e.g. 1920x1200 on DP */
+		gpu->ubwc_config.highest_bank_bit = 13;
+
+	if (adreno_is_a619_holi(gpu))
+		gpu->ubwc_config.highest_bank_bit = 13;
 
-	if (adreno_is_a640_family(adreno_gpu))
-		amsbc = 1;
+	if (adreno_is_a640_family(gpu))
+		gpu->ubwc_config.amsbc = 1;
 
-	if (adreno_is_a650(adreno_gpu) ||
-	    adreno_is_a660(adreno_gpu) ||
-	    adreno_is_a690(adreno_gpu) ||
-	    adreno_is_a730(adreno_gpu) ||
-	    adreno_is_a740_family(adreno_gpu)) {
+	if (adreno_is_a650(gpu) ||
+	    adreno_is_a660(gpu) ||
+	    adreno_is_a690(gpu) ||
+	    adreno_is_a730(gpu) ||
+	    adreno_is_a740_family(gpu)) {
 		/* TODO: get ddr type from bootloader and use 2 for LPDDR4 */
-		hbb_lo = 3;
-		amsbc = 1;
-		rgb565_predicator = 1;
-		uavflagprd_inv = 2;
+		gpu->ubwc_config.highest_bank_bit = 16;
+		gpu->ubwc_config.amsbc = 1;
+		gpu->ubwc_config.rgb565_predicator = 1;
+		gpu->ubwc_config.uavflagprd_inv = 2;
 	}
 
-	if (adreno_is_7c3(adreno_gpu)) {
-		hbb_lo = 1;
-		amsbc = 1;
-		rgb565_predicator = 1;
-		uavflagprd_inv = 2;
+	if (adreno_is_7c3(gpu)) {
+		gpu->ubwc_config.highest_bank_bit = 14;
+		gpu->ubwc_config.amsbc = 1;
+		gpu->ubwc_config.rgb565_predicator = 1;
+		gpu->ubwc_config.uavflagprd_inv = 2;
 	}
+}
+
+static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	/*
+	 * We subtract 13 from the highest bank bit (13 is the minimum value
+	 * allowed by hw) and write the lowest two bits of the remaining value
+	 * as hbb_lo and the one above it as hbb_hi to the hardware.
+	 */
+	BUG_ON(adreno_gpu->ubwc_config.highest_bank_bit < 13);
+	u32 hbb = adreno_gpu->ubwc_config.highest_bank_bit - 13;
+	u32 hbb_hi = hbb >> 2;
+	u32 hbb_lo = hbb & 3;
 
 	gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL,
-		  rgb565_predicator << 11 | hbb_hi << 10 | amsbc << 4 |
-		  min_acc_len << 3 | hbb_lo << 1 | ubwc_mode);
+		  adreno_gpu->ubwc_config.rgb565_predicator << 11 |
+		  hbb_hi << 10 | adreno_gpu->ubwc_config.amsbc << 4 |
+		  adreno_gpu->ubwc_config.min_acc_len << 3 |
+		  hbb_lo << 1 | adreno_gpu->ubwc_config.ubwc_mode);
 
 	gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, hbb_hi << 4 |
-		  min_acc_len << 3 | hbb_lo << 1 | ubwc_mode);
+		  adreno_gpu->ubwc_config.min_acc_len << 3 |
+		  hbb_lo << 1 | adreno_gpu->ubwc_config.ubwc_mode);
 
 	gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, hbb_hi << 10 |
-		  uavflagprd_inv << 4 | min_acc_len << 3 |
-		  hbb_lo << 1 | ubwc_mode);
+		  adreno_gpu->ubwc_config.uavflagprd_inv << 4 |
+		  adreno_gpu->ubwc_config.min_acc_len << 3 |
+		  hbb_lo << 1 | adreno_gpu->ubwc_config.ubwc_mode);
 
 	if (adreno_is_a7xx(adreno_gpu))
 		gpu_write(gpu, REG_A7XX_GRAS_NC_MODE_CNTL,
 			  FIELD_PREP(GENMASK(8, 5), hbb_lo));
 
-	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, min_acc_len << 23 | hbb_lo << 21);
+	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL,
+		  adreno_gpu->ubwc_config.min_acc_len << 23 | hbb_lo << 21);
 }
 
 static int a6xx_cp_init(struct msm_gpu *gpu)
@@ -1780,7 +1794,7 @@ static int hw_init(struct msm_gpu *gpu)
 	else
 		gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x1fffff);
 
-	gpu_write(gpu, REG_A6XX_UCHE_CLIENT_PF, 1);
+	gpu_write(gpu, REG_A6XX_UCHE_CLIENT_PF, BIT(7) | 0x1);
 
 	/* Set weights for bicubic filtering */
 	if (adreno_is_a650_family(adreno_gpu)) {
@@ -2911,5 +2925,7 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 		msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu,
 				a6xx_fault_handler);
 
+	a6xx_calc_ubwc_config(adreno_gpu);
+
 	return gpu;
 }
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 3ee14646ab..2ce7d7b169 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -841,7 +841,8 @@ static void suspend_scheduler(struct msm_gpu *gpu)
 	 */
 	for (i = 0; i < gpu->nr_rings; i++) {
 		struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched;
-		kthread_park(sched->thread);
+
+		drm_sched_wqueue_stop(sched);
 	}
 }
 
@@ -851,7 +852,8 @@ static void resume_scheduler(struct msm_gpu *gpu)
 
 	for (i = 0; i < gpu->nr_rings; i++) {
 		struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched;
-		kthread_unpark(sched->thread);
+
+		drm_sched_wqueue_start(sched);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 3fe9fd240c..074fb49870 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -373,6 +373,9 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 			return -EINVAL;
 		*value = ctx->aspace->va_size;
 		return 0;
+	case MSM_PARAM_HIGHEST_BANK_BIT:
+		*value = adreno_gpu->ubwc_config.highest_bank_bit;
+		return 0;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 80b3f63121..bc14df96fe 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -165,6 +165,15 @@ struct adreno_gpu {
 	/* firmware: */
 	const struct firmware *fw[ADRENO_FW_MAX];
 
+	struct {
+		u32 rgb565_predicator;
+		u32 uavflagprd_inv;
+		u32 min_acc_len;
+		u32 ubwc_mode;
+		u32 highest_bank_bit;
+		u32 amsbc;
+	} ubwc_config;
+
 	/*
 	 * Register offsets are different between some GPUs.
 	 * GPU specific offsets will be exported by GPU specific