drm/msm: gpu: Add A5XX target support

Add support for the A5XX family of Adreno GPUs.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>

8 files changed, 945 insertions, 9 deletions

diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 90f66c408120..3c9f0ccc8abb 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -6,6 +6,7 @@ msm-y := \
 	adreno/adreno_gpu.o \
 	adreno/a3xx_gpu.o \
 	adreno/a4xx_gpu.o \
+	adreno/a5xx_gpu.o \
 	hdmi/hdmi.o \
 	hdmi/hdmi_audio.o \
 	hdmi/hdmi_bridge.o \
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
new file mode 100644
index 000000000000..bf0a93038554
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -0,0 +1,830 @@
+/* Copyright (c) 2016 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include "msm_gem.h"
+#include "a5xx_gpu.h"
+
+extern bool hang_debug;
+static void a5xx_dump(struct msm_gpu *gpu);
+
+static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
+	struct msm_file_private *ctx)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct msm_ringbuffer *ring = gpu->rb;
+	unsigned int i, ibs = 0;
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		switch (submit->cmd[i].type) {
+		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
+			break;
+		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
+			if (priv->lastctx == ctx)
+				break;
+		case MSM_SUBMIT_CMD_BUF:
+			OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
+			OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
+			OUT_RING(ring, upper_32_bits(submit->cmd[i].iova));
+			OUT_RING(ring, submit->cmd[i].size);
+			ibs++;
+			break;
+		}
+	}
+
+	OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1);
+	OUT_RING(ring, submit->fence->seqno);
+
+	OUT_PKT7(ring, CP_EVENT_WRITE, 4);
+	OUT_RING(ring, CACHE_FLUSH_TS | (1 << 31));
+	OUT_RING(ring, lower_32_bits(rbmemptr(adreno_gpu, fence)));
+	OUT_RING(ring, upper_32_bits(rbmemptr(adreno_gpu, fence)));
+	OUT_RING(ring, submit->fence->seqno);
+
+	gpu->funcs->flush(gpu);
+}
+
+struct a5xx_hwcg {
+	u32 offset;
+	u32 value;
+};
+
+static const struct a5xx_hwcg a530_hwcg[] = {
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP1, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP2, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP3, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP1, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP2, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP3, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP1, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP2, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP3, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP1, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP2, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP3, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP1, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP2, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP3, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP1, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP2, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP3, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP0, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP1, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP2, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP3, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP1, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP2, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP3, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP1, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP2, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP3, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP0, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP1, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP2, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP3, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP1, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP2, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP3, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP1, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP2, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP3, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP0, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP1, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP2, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP3, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_HYST_UCHE, 0x00444444},
+	{REG_A5XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB1, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB2, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB3, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB0, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB1, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB2, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB3, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU0, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU1, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU2, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU3, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RAC, 0x05522222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RAC, 0x00505555},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU0, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU1, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU2, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU3, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RAC, 0x07444044},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_0, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_1, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_2, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_3, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RAC, 0x00010011},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
+	{REG_A5XX_RBBM_CLOCK_MODE_GPC, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
+	{REG_A5XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
+	{REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}
+};
+
+static const struct {
+	int (*test)(struct adreno_gpu *gpu);
+	const struct a5xx_hwcg *regs;
+	unsigned int count;
+} a5xx_hwcg_regs[] = {
+	{ adreno_is_a530, a530_hwcg, ARRAY_SIZE(a530_hwcg), },
+};
+
+static void _a5xx_enable_hwcg(struct msm_gpu *gpu,
+		const struct a5xx_hwcg *regs, unsigned int count)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++)
+		gpu_write(gpu, regs[i].offset, regs[i].value);
+
+	gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xAAA8AA00);
+	gpu_write(gpu, REG_A5XX_RBBM_ISDB_CNT, 0x182);
+}
+
+static void a5xx_enable_hwcg(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(a5xx_hwcg_regs); i++) {
+		if (a5xx_hwcg_regs[i].test(adreno_gpu)) {
+			_a5xx_enable_hwcg(gpu, a5xx_hwcg_regs[i].regs,
+				a5xx_hwcg_regs[i].count);
+			return;
+		}
+	}
+}
+
+static int a5xx_me_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct msm_ringbuffer *ring = gpu->rb;
+
+	OUT_PKT7(ring, CP_ME_INIT, 8);
+
+	OUT_RING(ring, 0x0000002F);
+
+	/* Enable multiple hardware contexts */
+	OUT_RING(ring, 0x00000003);
+
+	/* Enable error detection */
+	OUT_RING(ring, 0x20000000);
+
+	/* Don't enable header dump */
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+
+	/* Specify workarounds for various microcode issues */
+	if (adreno_is_a530(adreno_gpu)) {
+		/* Workaround for token end syncs
+		 * Force a WFI after every direct-render 3D mode draw and every
+		 * 2D mode 3 draw
+		 */
+		OUT_RING(ring, 0x0000000B);
+	} else {
+		/* No workarounds enabled */
+		OUT_RING(ring, 0x00000000);
+	}
+
+	OUT_RING(ring, 0x00000000);
+	OUT_RING(ring, 0x00000000);
+
+	gpu->funcs->flush(gpu);
+
+	return gpu->funcs->idle(gpu) ? 0 : -EINVAL;
+}
+
+static struct drm_gem_object *a5xx_ucode_load_bo(struct msm_gpu *gpu,
+		const struct firmware *fw, u64 *iova)
+{
+	struct drm_device *drm = gpu->dev;
+	struct drm_gem_object *bo;
+	void *ptr;
+
+	mutex_lock(&drm->struct_mutex);
+	bo = msm_gem_new(drm, fw->size - 4, MSM_BO_UNCACHED);
+	mutex_unlock(&drm->struct_mutex);
+
+	if (IS_ERR(bo))
+		return bo;
+
+	ptr = msm_gem_get_vaddr(bo);
+	if (!ptr) {
+		drm_gem_object_unreference_unlocked(bo);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (iova) {
+		int ret = msm_gem_get_iova(bo, gpu->id, iova);
+
+		if (ret) {
+			drm_gem_object_unreference_unlocked(bo);
+			return ERR_PTR(ret);
+		}
+	}
+
+	memcpy(ptr, &fw->data[4], fw->size - 4);
+
+	msm_gem_put_vaddr(bo);
+	return bo;
+}
+
+static int a5xx_ucode_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+	int ret;
+
+	if (!a5xx_gpu->pm4_bo) {
+		a5xx_gpu->pm4_bo = a5xx_ucode_load_bo(gpu, adreno_gpu->pm4,
+			&a5xx_gpu->pm4_iova);
+
+		if (IS_ERR(a5xx_gpu->pm4_bo)) {
+			ret = PTR_ERR(a5xx_gpu->pm4_bo);
+			a5xx_gpu->pm4_bo = NULL;
+			dev_err(gpu->dev->dev, "could not allocate PM4: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	if (!a5xx_gpu->pfp_bo) {
+		a5xx_gpu->pfp_bo = a5xx_ucode_load_bo(gpu, adreno_gpu->pfp,
+			&a5xx_gpu->pfp_iova);
+
+		if (IS_ERR(a5xx_gpu->pfp_bo)) {
+			ret = PTR_ERR(a5xx_gpu->pfp_bo);
+			a5xx_gpu->pfp_bo = NULL;
+			dev_err(gpu->dev->dev, "could not allocate PFP: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO,
+		REG_A5XX_CP_ME_INSTR_BASE_HI, a5xx_gpu->pm4_iova);
+
+	gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO,
+		REG_A5XX_CP_PFP_INSTR_BASE_HI, a5xx_gpu->pfp_iova);
+
+	return 0;
+}
+
+#define A5XX_INT_MASK (A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR | \
+	  A5XX_RBBM_INT_0_MASK_RBBM_TRANSFER_TIMEOUT | \
+	  A5XX_RBBM_INT_0_MASK_RBBM_ME_MS_TIMEOUT | \
+	  A5XX_RBBM_INT_0_MASK_RBBM_PFP_MS_TIMEOUT | \
+	  A5XX_RBBM_INT_0_MASK_RBBM_ETS_MS_TIMEOUT | \
+	  A5XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNC_OVERFLOW | \
+	  A5XX_RBBM_INT_0_MASK_CP_HW_ERROR | \
+	  A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \
+	  A5XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
+	  A5XX_RBBM_INT_0_MASK_GPMU_VOLTAGE_DROOP)
+
+static int a5xx_hw_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int ret;
+
+	gpu_write(gpu, REG_A5XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x00000003);
+
+	/* Make all blocks contribute to the GPU BUSY perf counter */
+	gpu_write(gpu, REG_A5XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xFFFFFFFF);
+
+	/* Enable RBBM error reporting bits */
+	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL0, 0x00000001);
+
+	if (adreno_gpu->quirks & ADRENO_QUIRK_FAULT_DETECT_MASK) {
+		/*
+		 * Mask out the activity signals from RB1-3 to avoid false
+		 * positives
+		 */
+
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL11,
+			0xF0000000);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL12,
+			0xFFFFFFFF);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL13,
+			0xFFFFFFFF);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL14,
+			0xFFFFFFFF);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL15,
+			0xFFFFFFFF);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL16,
+			0xFFFFFFFF);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL17,
+			0xFFFFFFFF);
+		gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_MASK_CNTL18,
+			0xFFFFFFFF);
+	}
+
+	/* Enable fault detection */
+	gpu_write(gpu, REG_A5XX_RBBM_INTERFACE_HANG_INT_CNTL,
+		(1 << 30) | 0xFFFF);
+
+	/* Turn on performance counters */
+	gpu_write(gpu, REG_A5XX_RBBM_PERFCTR_CNTL, 0x01);
+
+	/* Increase VFD cache access so LRZ and other data gets evicted less */
+	gpu_write(gpu, REG_A5XX_UCHE_CACHE_WAYS, 0x02);
+
+	/* Disable L2 bypass in the UCHE */
+	gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, 0xFFFF0000);
+	gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, 0x0001FFFF);
+	gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, 0xFFFF0000);
+	gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, 0x0001FFFF);
+
+	/* Set the GMEM VA range (0 to gpu->gmem) */
+	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000);
+	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MIN_HI, 0x00000000);
+	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_LO,
+		0x00100000 + adreno_gpu->gmem - 1);
+	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000);
+
+	gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
+	gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
+	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
+	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
+
+	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22));
+
+	if (adreno_gpu->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI)
+		gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8));
+
+	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0xc0200100);
+
+	/* Enable USE_RETENTION_FLOPS */
+	gpu_write(gpu, REG_A5XX_CP_CHICKEN_DBG, 0x02000000);
+
+	/* Enable ME/PFP split notification */
+	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF);
+
+	/* Enable HWCG */
+	a5xx_enable_hwcg(gpu);
+
+	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F);
+
+	/* Set the highest bank bit */
+	gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, 2 << 7);
+	gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, 2 << 1);
+
+	/* Protect registers from the CP */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT_CNTL, 0x00000007);
+
+	/* RBBM */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(0), ADRENO_PROTECT_RW(0x04, 4));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(1), ADRENO_PROTECT_RW(0x08, 8));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(2), ADRENO_PROTECT_RW(0x10, 16));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(3), ADRENO_PROTECT_RW(0x20, 32));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(4), ADRENO_PROTECT_RW(0x40, 64));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(5), ADRENO_PROTECT_RW(0x80, 64));
+
+	/* Content protect */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(6),
+		ADRENO_PROTECT_RW(REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO,
+			16));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(7),
+		ADRENO_PROTECT_RW(REG_A5XX_RBBM_SECVID_TRUST_CNTL, 2));
+
+	/* CP */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(8), ADRENO_PROTECT_RW(0x800, 64));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(9), ADRENO_PROTECT_RW(0x840, 8));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(10), ADRENO_PROTECT_RW(0x880, 32));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(11), ADRENO_PROTECT_RW(0xAA0, 1));
+
+	/* RB */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(12), ADRENO_PROTECT_RW(0xCC0, 1));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(13), ADRENO_PROTECT_RW(0xCF0, 2));
+
+	/* VPC */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(14), ADRENO_PROTECT_RW(0xE68, 8));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(15), ADRENO_PROTECT_RW(0xE70, 4));
+
+	/* UCHE */
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16));
+
+	if (adreno_is_a530(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_CP_PROTECT(17),
+			ADRENO_PROTECT_RW(0x10000, 0x8000));
+
+	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_CNTL, 0);
+	/*
+	 * Disable the trusted memory range - we don't actually supported secure
+	 * memory rendering at this point in time and we don't want to block off
+	 * part of the virtual memory space.
+	 */
+	gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO,
+		REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
+	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
+
+	ret = adreno_hw_init(gpu);
+	if (ret)
+		return ret;
+
+	ret = a5xx_ucode_init(gpu);
+	if (ret)
+		return ret;
+
+	/* Disable the interrupts through the initial bringup stage */
+	gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK);
+
+	/* Clear ME_HALT to start the micro engine */
+	gpu_write(gpu, REG_A5XX_CP_PFP_ME_CNTL, 0);
+	ret = a5xx_me_init(gpu);
+	if (ret)
+		return ret;
+
+	/* Put the GPU into insecure mode */
+	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+
+	/*
+	 * Send a pipeline event stat to get misbehaving counters to start
+	 * ticking correctly
+	 */
+	if (adreno_is_a530(adreno_gpu)) {
+		OUT_PKT7(gpu->rb, CP_EVENT_WRITE, 1);
+		OUT_RING(gpu->rb, 0x0F);
+
+		gpu->funcs->flush(gpu);
+		if (!gpu->funcs->idle(gpu))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void a5xx_recover(struct msm_gpu *gpu)
+{
+	int i;
+
+	adreno_dump_info(gpu);
+
+	for (i = 0; i < 8; i++) {
+		printk("CP_SCRATCH_REG%d: %u\n", i,
+			gpu_read(gpu, REG_A5XX_CP_SCRATCH_REG(i)));
+	}
+
+	if (hang_debug)
+		a5xx_dump(gpu);
+
+	gpu_write(gpu, REG_A5XX_RBBM_SW_RESET_CMD, 1);
+	gpu_read(gpu, REG_A5XX_RBBM_SW_RESET_CMD);
+	gpu_write(gpu, REG_A5XX_RBBM_SW_RESET_CMD, 0);
+	adreno_recover(gpu);
+}
+
+static void a5xx_destroy(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+
+	DBG("%s", gpu->name);
+
+	if (a5xx_gpu->pm4_bo) {
+		if (a5xx_gpu->pm4_iova)
+			msm_gem_put_iova(a5xx_gpu->pm4_bo, gpu->id);
+		drm_gem_object_unreference_unlocked(a5xx_gpu->pm4_bo);
+	}
+
+	if (a5xx_gpu->pfp_bo) {
+		if (a5xx_gpu->pfp_iova)
+			msm_gem_put_iova(a5xx_gpu->pfp_bo, gpu->id);
+		drm_gem_object_unreference_unlocked(a5xx_gpu->pfp_bo);
+	}
+
+	adreno_gpu_cleanup(adreno_gpu);
+	kfree(a5xx_gpu);
+}
+
+static inline bool _a5xx_check_idle(struct msm_gpu *gpu)
+{
+	if (gpu_read(gpu, REG_A5XX_RBBM_STATUS) & ~A5XX_RBBM_STATUS_HI_BUSY)
+		return false;
+
+	/*
+	 * Nearly every abnormality ends up pausing the GPU and triggering a
+	 * fault so we can safely just watch for this one interrupt to fire
+	 */
+	return !(gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS) &
+		A5XX_RBBM_INT_0_MASK_MISC_HANG_DETECT);
+}
+
+static bool a5xx_idle(struct msm_gpu *gpu)
+{
+	/* wait for CP to drain ringbuffer: */
+	if (!adreno_idle(gpu))
+		return false;
+
+	if (spin_until(_a5xx_check_idle(gpu))) {
+		DRM_ERROR("%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X\n",
+			gpu->name, __builtin_return_address(0),
+			gpu_read(gpu, REG_A5XX_RBBM_STATUS),
+			gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS));
+
+		return false;
+	}
+
+	return true;
+}
+
+static void a5xx_cp_err_irq(struct msm_gpu *gpu)
+{
+	u32 status = gpu_read(gpu, REG_A5XX_CP_INTERRUPT_STATUS);
+
+	if (status & A5XX_CP_INT_CP_OPCODE_ERROR) {
+		u32 val;
+
+		gpu_write(gpu, REG_A5XX_CP_PFP_STAT_ADDR, 0);
+
+		/*
+		 * REG_A5XX_CP_PFP_STAT_DATA is indexed, and we want index 1 so
+		 * read it twice
+		 */
+
+		gpu_read(gpu, REG_A5XX_CP_PFP_STAT_DATA);
+		val = gpu_read(gpu, REG_A5XX_CP_PFP_STAT_DATA);
+
+		dev_err_ratelimited(gpu->dev->dev, "CP | opcode error | possible opcode=0x%8.8X\n",
+			val);
+	}
+
+	if (status & A5XX_CP_INT_CP_HW_FAULT_ERROR)
+		dev_err_ratelimited(gpu->dev->dev, "CP | HW fault | status=0x%8.8X\n",
+			gpu_read(gpu, REG_A5XX_CP_HW_FAULT));
+
+	if (status & A5XX_CP_INT_CP_DMA_ERROR)
+		dev_err_ratelimited(gpu->dev->dev, "CP | DMA error\n");
+
+	if (status & A5XX_CP_INT_CP_REGISTER_PROTECTION_ERROR) {
+		u32 val = gpu_read(gpu, REG_A5XX_CP_PROTECT_STATUS);
+
+		dev_err_ratelimited(gpu->dev->dev,
+			"CP | protected mode error | %s | addr=0x%8.8X | status=0x%8.8X\n",
+			val & (1 << 24) ? "WRITE" : "READ",
+			(val & 0xFFFFF) >> 2, val);
+	}
+
+	if (status & A5XX_CP_INT_CP_AHB_ERROR) {
+		u32 status = gpu_read(gpu, REG_A5XX_CP_AHB_FAULT);
+		const char *access[16] = { "reserved", "reserved",
+			"timestamp lo", "timestamp hi", "pfp read", "pfp write",
+			"", "", "me read", "me write", "", "", "crashdump read",
+			"crashdump write" };
+
+		dev_err_ratelimited(gpu->dev->dev,
+			"CP | AHB error | addr=%X access=%s error=%d | status=0x%8.8X\n",
+			status & 0xFFFFF, access[(status >> 24) & 0xF],
+			(status & (1 << 31)), status);
+	}
+}
+
+static void a5xx_rbbm_err_irq(struct msm_gpu *gpu)
+{
+	u32 status = gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS);
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR) {
+		u32 val = gpu_read(gpu, REG_A5XX_RBBM_AHB_ERROR_STATUS);
+
+		dev_err_ratelimited(gpu->dev->dev,
+			"RBBM | AHB bus error | %s | addr=0x%X | ports=0x%X:0x%X\n",
+			val & (1 << 28) ? "WRITE" : "READ",
+			(val & 0xFFFFF) >> 2, (val >> 20) & 0x3,
+			(val >> 24) & 0xF);
+
+		/* Clear the error */
+		gpu_write(gpu, REG_A5XX_RBBM_AHB_CMD, (1 << 4));
+	}
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_TRANSFER_TIMEOUT)
+		dev_err_ratelimited(gpu->dev->dev, "RBBM | AHB transfer timeout\n");
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_ME_MS_TIMEOUT)
+		dev_err_ratelimited(gpu->dev->dev, "RBBM | ME master split | status=0x%X\n",
+			gpu_read(gpu, REG_A5XX_RBBM_AHB_ME_SPLIT_STATUS));
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_PFP_MS_TIMEOUT)
+		dev_err_ratelimited(gpu->dev->dev, "RBBM | PFP master split | status=0x%X\n",
+			gpu_read(gpu, REG_A5XX_RBBM_AHB_PFP_SPLIT_STATUS));
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_ETS_MS_TIMEOUT)
+		dev_err_ratelimited(gpu->dev->dev, "RBBM | ETS master split | status=0x%X\n",
+			gpu_read(gpu, REG_A5XX_RBBM_AHB_ETS_SPLIT_STATUS));
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNC_OVERFLOW)
+		dev_err_ratelimited(gpu->dev->dev, "RBBM | ATB ASYNC overflow\n");
+
+	if (status & A5XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW)
+		dev_err_ratelimited(gpu->dev->dev, "RBBM | ATB bus overflow\n");
+}
+
+static void a5xx_uche_err_irq(struct msm_gpu *gpu)
+{
+	uint64_t addr = (uint64_t) gpu_read(gpu, REG_A5XX_UCHE_TRAP_LOG_HI);
+
+	addr |= gpu_read(gpu, REG_A5XX_UCHE_TRAP_LOG_LO);
+
+	dev_err_ratelimited(gpu->dev->dev, "UCHE | Out of bounds access | addr=0x%llX\n",
+		addr);
+}
+
+static void a5xx_gpmu_err_irq(struct msm_gpu *gpu)
+{
+	dev_err_ratelimited(gpu->dev->dev, "GPMU | voltage droop\n");
+}
+
+#define RBBM_ERROR_MASK \
+	(A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR | \
+	A5XX_RBBM_INT_0_MASK_RBBM_TRANSFER_TIMEOUT | \
+	A5XX_RBBM_INT_0_MASK_RBBM_ME_MS_TIMEOUT | \
+	A5XX_RBBM_INT_0_MASK_RBBM_PFP_MS_TIMEOUT | \
+	A5XX_RBBM_INT_0_MASK_RBBM_ETS_MS_TIMEOUT | \
+	A5XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNC_OVERFLOW)
+
+static irqreturn_t a5xx_irq(struct msm_gpu *gpu)
+{
+	u32 status = gpu_read(gpu, REG_A5XX_RBBM_INT_0_STATUS);
+
+	gpu_write(gpu, REG_A5XX_RBBM_INT_CLEAR_CMD, status);
+
+	if (status & RBBM_ERROR_MASK)
+		a5xx_rbbm_err_irq(gpu);
+
+	if (status & A5XX_RBBM_INT_0_MASK_CP_HW_ERROR)
+		a5xx_cp_err_irq(gpu);
+
+	if (status & A5XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS)
+		a5xx_uche_err_irq(gpu);
+
+	if (status & A5XX_RBBM_INT_0_MASK_GPMU_VOLTAGE_DROOP)
+		a5xx_gpmu_err_irq(gpu);
+
+	if (status & A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS)
+		msm_gpu_retire(gpu);
+
+	return IRQ_HANDLED;
+}
+
+static const u32 a5xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A5XX_CP_RB_BASE),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE_HI, REG_A5XX_CP_RB_BASE_HI),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR, REG_A5XX_CP_RB_RPTR_ADDR),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR_ADDR_HI,
+		REG_A5XX_CP_RB_RPTR_ADDR_HI),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_RPTR, REG_A5XX_CP_RB_RPTR),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_WPTR, REG_A5XX_CP_RB_WPTR),
+	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A5XX_CP_RB_CNTL),
+};
+
+static const u32 a5xx_registers[] = {
+	0x0000, 0x0002, 0x0004, 0x0020, 0x0022, 0x0026, 0x0029, 0x002B,
+	0x002E, 0x0035, 0x0038, 0x0042, 0x0044, 0x0044, 0x0047, 0x0095,
+	0x0097, 0x00BB, 0x03A0, 0x0464, 0x0469, 0x046F, 0x04D2, 0x04D3,
+	0x04E0, 0x0533, 0x0540, 0x0555, 0xF400, 0xF400, 0xF800, 0xF807,
+	0x0800, 0x081A, 0x081F, 0x0841, 0x0860, 0x0860, 0x0880, 0x08A0,
+	0x0B00, 0x0B12, 0x0B15, 0x0B28, 0x0B78, 0x0B7F, 0x0BB0, 0x0BBD,
+	0x0BC0, 0x0BC6, 0x0BD0, 0x0C53, 0x0C60, 0x0C61, 0x0C80, 0x0C82,
+	0x0C84, 0x0C85, 0x0C90, 0x0C98, 0x0CA0, 0x0CA0, 0x0CB0, 0x0CB2,
+	0x2180, 0x2185, 0x2580, 0x2585, 0x0CC1, 0x0CC1, 0x0CC4, 0x0CC7,
+	0x0CCC, 0x0CCC, 0x0CD0, 0x0CD8, 0x0CE0, 0x0CE5, 0x0CE8, 0x0CE8,
+	0x0CEC, 0x0CF1, 0x0CFB, 0x0D0E, 0x2100, 0x211E, 0x2140, 0x2145,
+	0x2500, 0x251E, 0x2540, 0x2545, 0x0D10, 0x0D17, 0x0D20, 0x0D23,
+	0x0D30, 0x0D30, 0x20C0, 0x20C0, 0x24C0, 0x24C0, 0x0E40, 0x0E43,
+	0x0E4A, 0x0E4A, 0x0E50, 0x0E57, 0x0E60, 0x0E7C, 0x0E80, 0x0E8E,
+	0x0E90, 0x0E96, 0x0EA0, 0x0EA8, 0x0EB0, 0x0EB2, 0xE140, 0xE147,
+	0xE150, 0xE187, 0xE1A0, 0xE1A9, 0xE1B0, 0xE1B6, 0xE1C0, 0xE1C7,
+	0xE1D0, 0xE1D1, 0xE200, 0xE201, 0xE210, 0xE21C, 0xE240, 0xE268,
+	0xE000, 0xE006, 0xE010, 0xE09A, 0xE0A0, 0xE0A4, 0xE0AA, 0xE0EB,
+	0xE100, 0xE105, 0xE380, 0xE38F, 0xE3B0, 0xE3B0, 0xE400, 0xE405,
+	0xE408, 0xE4E9, 0xE4F0, 0xE4F0, 0xE280, 0xE280, 0xE282, 0xE2A3,
+	0xE2A5, 0xE2C2, 0xE940, 0xE947, 0xE950, 0xE987, 0xE9A0, 0xE9A9,
+	0xE9B0, 0xE9B6, 0xE9C0, 0xE9C7, 0xE9D0, 0xE9D1, 0xEA00, 0xEA01,
+	0xEA10, 0xEA1C, 0xEA40, 0xEA68, 0xE800, 0xE806, 0xE810, 0xE89A,
+	0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB, 0xE900, 0xE905, 0xEB80, 0xEB8F,
+	0xEBB0, 0xEBB0, 0xEC00, 0xEC05, 0xEC08, 0xECE9, 0xECF0, 0xECF0,
+	0xEA80, 0xEA80, 0xEA82, 0xEAA3, 0xEAA5, 0xEAC2, 0xA800, 0xA8FF,
+	0xAC60, 0xAC60, 0xB000, 0xB97F, 0xB9A0, 0xB9BF,
+	~0
+};
+
+static void a5xx_dump(struct msm_gpu *gpu)
+{
+	dev_info(gpu->dev->dev, "status:   %08x\n",
+		gpu_read(gpu, REG_A5XX_RBBM_STATUS));
+	adreno_dump(gpu);
+}
+
+static int a5xx_pm_resume(struct msm_gpu *gpu)
+{
+	return msm_gpu_pm_resume(gpu);
+}
+
+static int a5xx_pm_suspend(struct msm_gpu *gpu)
+{
+	return msm_gpu_pm_suspend(gpu);
+}
+
+static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
+{
+	*value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO,
+		REG_A5XX_RBBM_PERFCTR_CP_0_HI);
+
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
+{
+	gpu->funcs->pm_resume(gpu);
+
+	seq_printf(m, "status:   %08x\n",
+			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
+	gpu->funcs->pm_suspend(gpu);
+
+	adreno_show(gpu, m);
+}
+#endif
+
+static const struct adreno_gpu_funcs funcs = {
+	.base = {
+		.get_param = adreno_get_param,
+		.hw_init = a5xx_hw_init,
+		.pm_suspend = a5xx_pm_suspend,
+		.pm_resume = a5xx_pm_resume,
+		.recover = a5xx_recover,
+		.last_fence = adreno_last_fence,
+		.submit = a5xx_submit,
+		.flush = adreno_flush,
+		.idle = a5xx_idle,
+		.irq = a5xx_irq,
+		.destroy = a5xx_destroy,
+		.show = a5xx_show,
+	},
+	.get_timestamp = a5xx_get_timestamp,
+};
+
+struct msm_gpu *a5xx_gpu_init(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct platform_device *pdev = priv->gpu_pdev;
+	struct a5xx_gpu *a5xx_gpu = NULL;
+	struct adreno_gpu *adreno_gpu;
+	struct msm_gpu *gpu;
+	int ret;
+
+	if (!pdev) {
+		dev_err(dev->dev, "No A5XX device is defined\n");
+		return ERR_PTR(-ENXIO);
+	}
+
+	a5xx_gpu = kzalloc(sizeof(*a5xx_gpu), GFP_KERNEL);
+	if (!a5xx_gpu)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu = &a5xx_gpu->base;
+	gpu = &adreno_gpu->base;
+
+	a5xx_gpu->pdev = pdev;
+	adreno_gpu->registers = a5xx_registers;
+	adreno_gpu->reg_offsets = a5xx_register_offsets;
+
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs);
+	if (ret) {
+		a5xx_destroy(&(a5xx_gpu->base.base));
+		return ERR_PTR(ret);
+	}
+
+	return gpu;
+}
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
new file mode 100644
index 000000000000..39a07f400b35
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
@@ -0,0 +1,37 @@
+/* Copyright (c) 2016 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef __A5XX_GPU_H__
+#define __A5XX_GPU_H__
+
+#include "adreno_gpu.h"
+
+/* Bringing over the hack from the previous targets */
+#undef ROP_COPY
+#undef ROP_XOR
+
+#include "a5xx.xml.h"
+
+struct a5xx_gpu {
+	struct adreno_gpu base;
+	struct platform_device *pdev;
+
+	struct drm_gem_object *pm4_bo;
+	uint64_t pm4_iova;
+
+	struct drm_gem_object *pfp_bo;
+	uint64_t pfp_iova;
+};
+
+#define to_a5xx_gpu(x) container_of(x, struct a5xx_gpu, base)
+
+#endif /* __A5XX_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 1fa1fdda9ee2..985d95fbb726 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -74,6 +74,14 @@ static const struct adreno_info gpulist[] = {
 		.pfpfw = "a420_pfp.fw",
 		.gmem  = (SZ_1M + SZ_512K),
 		.init  = a4xx_gpu_init,
+	}, {
+		.rev = ADRENO_REV(5, 3, 0, ANY_ID),
+		.revn = 530,
+		.name = "A530",
+		.pm4fw = "a530_pm4.fw",
+		.pfpfw = "a530_pfp.fw",
+		.gmem = SZ_1M,
+		.init = a5xx_gpu_init,
 	},
 };
 
@@ -83,6 +91,8 @@ MODULE_FIRMWARE("a330_pm4.fw");
 MODULE_FIRMWARE("a330_pfp.fw");
 MODULE_FIRMWARE("a420_pm4.fw");
 MODULE_FIRMWARE("a420_pfp.fw");
+MODULE_FIRMWARE("a530_fm4.fw");
+MODULE_FIRMWARE("a530_pfp.fw");
 
 static inline bool _rev_match(uint8_t entry, uint8_t id)
 {
@@ -170,12 +180,20 @@ static void set_gpu_pdev(struct drm_device *dev,
 	priv->gpu_pdev = pdev;
 }
 
+static const struct {
+	const char *str;
+	uint32_t flag;
+} quirks[] = {
+	{ "qcom,gpu-quirk-two-pass-use-wfi", ADRENO_QUIRK_TWO_PASS_USE_WFI },
+	{ "qcom,gpu-quirk-fault-detect-mask", ADRENO_QUIRK_FAULT_DETECT_MASK },
+};
+
 static int adreno_bind(struct device *dev, struct device *master, void *data)
 {
 	static struct adreno_platform_config config = {};
 	struct device_node *child, *node = dev->of_node;
 	u32 val;
-	int ret;
+	int ret, i;
 
 	ret = of_property_read_u32(node, "qcom,chipid", &val);
 	if (ret) {
@@ -209,6 +227,10 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 		return -ENXIO;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(quirks); i++)
+		if (of_property_read_bool(node, quirks[i].str))
+			config.quirks |= quirks[i].flag;
+
 	dev->platform_data = &config;
 	set_gpu_pdev(dev_get_drvdata(master), to_platform_device(dev));
 	return 0;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index c3a4c53eb8b3..a18126150e11 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -22,7 +22,7 @@
 #include "msm_mmu.h"
 
 #define RB_SIZE    SZ_32K
-#define RB_BLKSIZE 16
+#define RB_BLKSIZE 32
 
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 {
@@ -54,9 +54,6 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 	}
 }
 
-#define rbmemptr(adreno_gpu, member)  \
-	((adreno_gpu)->memptrs_iova + offsetof(struct adreno_rbmemptrs, member))
-
 int adreno_hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -349,6 +346,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	adreno_gpu->gmem = adreno_gpu->info->gmem;
 	adreno_gpu->revn = adreno_gpu->info->revn;
 	adreno_gpu->rev = config->rev;
+	adreno_gpu->quirks = config->quirks;
 
 	gpu->fast_rate = config->fast_rate;
 	gpu->slow_rate = config->slow_rate;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 9f21ca010525..0d1f4e757f59 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -48,6 +48,11 @@ enum adreno_regs {
 	REG_ADRENO_REGISTER_MAX,
 };
 
+enum adreno_quirks {
+	ADRENO_QUIRK_TWO_PASS_USE_WFI = 1,
+	ADRENO_QUIRK_FAULT_DETECT_MASK = 2,
+};
+
 struct adreno_rev {
 	uint8_t  core;
 	uint8_t  major;
@@ -74,6 +79,9 @@ struct adreno_info {
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);
 
+#define rbmemptr(adreno_gpu, member)  \
+	((adreno_gpu)->memptrs_iova + offsetof(struct adreno_rbmemptrs, member))
+
 struct adreno_rbmemptrs {
 	volatile uint32_t rptr;
 	volatile uint32_t wptr;
@@ -107,6 +115,8 @@ struct adreno_gpu {
 	 * code (a3xx_gpu.c) and stored in this common location.
 	 */
 	const unsigned int *reg_offsets;
+
+	uint32_t quirks;
 };
 #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)
 
@@ -117,6 +127,7 @@ struct adreno_platform_config {
 #ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING
 	struct msm_bus_scale_pdata *bus_scale_table;
 #endif
+	uint32_t quirks;
 };
 
 #define ADRENO_IDLE_TIMEOUT msecs_to_jiffies(1000)
@@ -180,6 +191,11 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu)
        return gpu->revn == 430;
 }
 
+static inline int adreno_is_a530(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 530;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
 int adreno_hw_init(struct msm_gpu *gpu);
 uint32_t adreno_last_fence(struct msm_gpu *gpu);
@@ -299,6 +315,7 @@ static inline void adreno_gpu_write(struct adreno_gpu *gpu,
 
 struct msm_gpu *a3xx_gpu_init(struct drm_device *dev);
 struct msm_gpu *a4xx_gpu_init(struct drm_device *dev);
+struct msm_gpu *a5xx_gpu_init(struct drm_device *dev);
 
 static inline void adreno_gpu_write64(struct adreno_gpu *gpu,
 		enum adreno_regs lo, enum adreno_regs hi, u64 data)
@@ -307,4 +324,28 @@ static inline void adreno_gpu_write64(struct adreno_gpu *gpu,
 	adreno_gpu_write(gpu, hi, upper_32_bits(data));
 }
 
+/*
+ * Given a register and a count, return a value to program into
+ * REG_CP_PROTECT_REG(n) - this will block both reads and writes for _len
+ * registers starting at _reg.
+ *
+ * The register base needs to be a multiple of the length. If it is not, the
+ * hardware will quietly mask off the bits for you and shift the size. For
+ * example, if you intend the protection to start at 0x07 for a length of 4
+ * (0x07-0x0A) the hardware will actually protect (0x04-0x07) which might
+ * expose registers you intended to protect!
+ */
+#define ADRENO_PROTECT_RW(_reg, _len) \
+	((1 << 30) | (1 << 29) | \
+	((ilog2((_len)) & 0x1F) << 24) | (((_reg) << 2) & 0xFFFFF))
+
+/*
+ * Same as above, but allow reads over the range. For areas of mixed use (such
+ * as performance counters) this allows us to protect a much larger range with a
+ * single register
+ */
+#define ADRENO_PROTECT_RDONLY(_reg, _len) \
+	((1 << 29) \
+	((ilog2((_len)) & 0x1F) << 24) | (((_reg) << 2) & 0xFFFFF))
+
 #endif /* __ADRENO_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 3d6e3b7a13e2..b28527a65d09 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -96,6 +96,10 @@ static int enable_clk(struct msm_gpu *gpu)
 	if (gpu->grp_clks[0] && gpu->fast_rate)
 		clk_set_rate(gpu->grp_clks[0], gpu->fast_rate);
 
+	/* Set the RBBM timer rate to 19.2Mhz */
+	if (gpu->grp_clks[2])
+		clk_set_rate(gpu->grp_clks[2], 19200000);
+
 	for (i = ARRAY_SIZE(gpu->grp_clks) - 1; i >= 0; i--)
 		if (gpu->grp_clks[i])
 			clk_prepare(gpu->grp_clks[i]);
@@ -122,6 +126,9 @@ static int disable_clk(struct msm_gpu *gpu)
 	if (gpu->grp_clks[0] && gpu->slow_rate)
 		clk_set_rate(gpu->grp_clks[0], gpu->slow_rate);
 
+	if (gpu->grp_clks[2])
+		clk_set_rate(gpu->grp_clks[2], 0);
+
 	return 0;
 }
 
@@ -553,8 +560,8 @@ static irqreturn_t irq_handler(int irq, void *data)
 }
 
 static const char *clk_names[] = {
-		"core_clk", "iface_clk", "mem_clk", "mem_iface_clk",
-		"alt_mem_iface_clk",
+		"core_clk", "iface_clk", "rbbmtimer_clk", "mem_clk",
+		"mem_iface_clk", "alt_mem_iface_clk",
 };
 
 int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
@@ -647,7 +654,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	iommu = iommu_domain_alloc(&platform_bus_type);
 	if (iommu) {
 		/* TODO 32b vs 64b address space.. */
-		iommu->geometry.aperture_start = 0x1000;
+		iommu->geometry.aperture_start = SZ_16M;
 		iommu->geometry.aperture_end = 0xffffffff;
 
 		dev_info(drm->dev, "%s: using IOMMU\n", name);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 10252d07bb14..c4c39d3272c7 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -103,7 +103,7 @@ struct msm_gpu {
 
 	/* Power Control: */
 	struct regulator *gpu_reg, *gpu_cx;
-	struct clk *ebi1_clk, *grp_clks[5];
+	struct clk *ebi1_clk, *grp_clks[6];
 	uint32_t fast_rate, slow_rate, bus_freq;
 
 #ifdef DOWNSTREAM_CONFIG_MSM_BUS_SCALING