[PATCH v3 07/10] drm/msm/a6xx: Mostly implement A7xx gpu_state

[Konrad Dybcio <konrad.dybcio@linaro.org>]

Provide the necessary alternations to mostly support state dumping on
A7xx. Newer GPUs will probably require more changes here. Crashdumper
and debugbus remain untested.

Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8550-QRD
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> # sm8450
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 52 +++++++++++++++++++++++-
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h | 61 ++++++++++++++++++++++++++++-
 2 files changed, 110 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 4e5d650578c6..18be2d3bde09 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -948,6 +948,18 @@ static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu)
 	return gpu_read(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2) >> 14;
 }
 
+static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu)
+{
+	/*
+	 * The value at CP_ROQ_THRESHOLDS_2[20:31] is in 4dword units.
+	 * That register however is not directly accessible from APSS on A7xx.
+	 * Program the SQE_UCODE_DBG_ADDR with offset=0x70d3 and read the value.
+	 */
+	gpu_write(gpu, REG_A6XX_CP_SQE_UCODE_DBG_ADDR, 0x70d3);
+
+	return 4 * (gpu_read(gpu, REG_A6XX_CP_SQE_UCODE_DBG_DATA) >> 20);
+}
+
 /* Read a block of data from an indexed register pair */
 static void a6xx_get_indexed_regs(struct msm_gpu *gpu,
 		struct a6xx_gpu_state *a6xx_state,
@@ -1019,8 +1031,40 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu,
 
 	/* Restore the size in the hardware */
 	gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size);
+}
+
+static void a7xx_get_indexed_registers(struct msm_gpu *gpu,
+		struct a6xx_gpu_state *a6xx_state)
+{
+	int i, indexed_count, mempool_count;
+
+	indexed_count = ARRAY_SIZE(a7xx_indexed_reglist);
+	mempool_count = ARRAY_SIZE(a7xx_cp_bv_mempool_indexed);
 
-	a6xx_state->nr_indexed_regs = count;
+	a6xx_state->indexed_regs = state_kcalloc(a6xx_state,
+					indexed_count + mempool_count,
+					sizeof(*a6xx_state->indexed_regs));
+	if (!a6xx_state->indexed_regs)
+		return;
+
+	a6xx_state->nr_indexed_regs = indexed_count + mempool_count;
+
+	/* First read the common regs */
+	for (i = 0; i < indexed_count; i++)
+		a6xx_get_indexed_regs(gpu, a6xx_state, &a7xx_indexed_reglist[i],
+			&a6xx_state->indexed_regs[i]);
+
+	gpu_rmw(gpu, REG_A6XX_CP_CHICKEN_DBG, 0, BIT(2));
+	gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, 0, BIT(2));
+
+	/* Get the contents of the CP_BV mempool */
+	for (i = 0; i < mempool_count; i++)
+		a6xx_get_indexed_regs(gpu, a6xx_state, a7xx_cp_bv_mempool_indexed,
+			&a6xx_state->indexed_regs[indexed_count - 1 + i]);
+
+	gpu_rmw(gpu, REG_A6XX_CP_CHICKEN_DBG, BIT(2), 0);
+	gpu_rmw(gpu, REG_A7XX_CP_BV_CHICKEN_DBG, BIT(2), 0);
+	return;
 }
 
 struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
@@ -1056,6 +1100,12 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		return &a6xx_state->base;
 
 	/* Get the banks of indexed registers */
+	if (adreno_is_a7xx(adreno_gpu)) {
+		a7xx_get_indexed_registers(gpu, a6xx_state);
+		/* Further codeflow is untested on A7xx. */
+		return &a6xx_state->base;
+	}
+
 	a6xx_get_indexed_registers(gpu, a6xx_state);
 
 	/*
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index e788ed72eb0d..8d7e6f26480a 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -338,6 +338,28 @@ static const struct a6xx_registers a6xx_vbif_reglist =
 static const struct a6xx_registers a6xx_gbif_reglist =
 			REGS(a6xx_gbif_registers, 0, 0);
 
+static const u32 a7xx_ahb_registers[] = {
+	/* RBBM_STATUS */
+	0x210, 0x210,
+	/* RBBM_STATUS2-3 */
+	0x212, 0x213,
+};
+
+static const u32 a7xx_gbif_registers[] = {
+	0x3c00, 0x3c0b,
+	0x3c40, 0x3c42,
+	0x3c45, 0x3c47,
+	0x3c49, 0x3c4a,
+	0x3cc0, 0x3cd1,
+};
+
+static const struct a6xx_registers a7xx_ahb_reglist[] = {
+	REGS(a7xx_ahb_registers, 0, 0),
+};
+
+static const struct a6xx_registers a7xx_gbif_reglist =
+	REGS(a7xx_gbif_registers, 0, 0);
+
 static const u32 a6xx_gmu_gx_registers[] = {
 	/* GMU GX */
 	0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b,
@@ -384,14 +406,17 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = {
 };
 
 static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu);
+static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu);
 
-static struct a6xx_indexed_registers {
+struct a6xx_indexed_registers {
 	const char *name;
 	u32 addr;
 	u32 data;
 	u32 count;
 	u32 (*count_fn)(struct msm_gpu *gpu);
-} a6xx_indexed_reglist[] = {
+};
+
+static struct a6xx_indexed_registers a6xx_indexed_reglist[] = {
 	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
 		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
@@ -402,11 +427,43 @@ static struct a6xx_indexed_registers {
 		REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size},
 };
 
+static struct a6xx_indexed_registers a7xx_indexed_reglist[] = {
+	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
+		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
+	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
+		REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL },
+	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL },
+	{ "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR,
+		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL },
+	{ "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+		REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL },
+	{ "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
+		REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL },
+	{ "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR,
+		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL },
+	{ "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
+		REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL },
+	{ "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
+		REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL },
+	{ "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
+		REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL },
+	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+		REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size },
+};
+
 static struct a6xx_indexed_registers a6xx_cp_mempool_indexed = {
 	"CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
 		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL,
 };
 
+static struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = {
+	{ "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL },
+	{ "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR,
+		REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL },
+};
+
 #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count }
 
 static const struct a6xx_debugbus_block {

-- 
2.42.0