Merge branch 'msm-fixes' of https://gitlab.freedesktop.org/drm/msm.git

16 files changed, 116 insertions, 15 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index c17e9777beae..0259e60b8011 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -25,6 +25,8 @@
 
 extern bool hang_debug;
 
+#define A3XX_VBIF_XIN_HALT_CTRL0_MASK	GENMASK(5, 0)
+
 static void a3xx_dump(struct msm_gpu *gpu);
 static bool a3xx_idle(struct msm_gpu *gpu);
 
@@ -496,6 +498,38 @@ static u64 a3xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
 	return busy_cycles;
 }
 
+static int a3xx_vbif_halt(struct msm_gpu *gpu)
+{
+	u32 ack;
+	int ret;
+
+	gpu_write(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL0,
+		  A3XX_VBIF_XIN_HALT_CTRL0_MASK);
+	ret = spin_until(((ack = gpu_read(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL1)) &
+			  A3XX_VBIF_XIN_HALT_CTRL0_MASK) ==
+			 A3XX_VBIF_XIN_HALT_CTRL0_MASK);
+	gpu_write(gpu, REG_A3XX_VBIF_XIN_HALT_CTRL0, 0);
+
+	if (ret)
+		return -EBUSY;
+
+	return 0;
+}
+
+static int a3xx_pm_suspend(struct msm_gpu *gpu)
+{
+	int ret;
+
+	if (!a3xx_idle(gpu))
+		return -EBUSY;
+
+	ret = a3xx_vbif_halt(gpu);
+	if (ret)
+		return ret;
+
+	return msm_gpu_pm_suspend(gpu);
+}
+
 static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	ring->memptrs->rptr = gpu_read(gpu, REG_AXXX_CP_RB_RPTR);
@@ -581,7 +615,7 @@ const struct adreno_gpu_funcs a3xx_gpu_funcs = {
 		.get_param = adreno_get_param,
 		.set_param = adreno_set_param,
 		.hw_init = a3xx_hw_init,
-		.pm_suspend = msm_gpu_pm_suspend,
+		.pm_suspend = a3xx_pm_suspend,
 		.pm_resume = msm_gpu_pm_resume,
 		.recover = a3xx_recover,
 		.submit = a3xx_submit,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 2c0bbac43c52..f1df2514c613 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1275,6 +1275,11 @@ static irqreturn_t a5xx_irq(struct msm_gpu *gpu)
 		status & ~A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR);
 
 	if (priv->disable_err_irq) {
+		/* Turn off interrupts to avoid interrupt storm */
+		gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK,
+			       A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS |
+			       A5XX_RBBM_INT_0_MASK_CP_SW);
+
 		status &= A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS |
 			  A5XX_RBBM_INT_0_MASK_CP_SW;
 	}
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 2e5d7b53a0c3..a2f6918c4f7f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -642,7 +642,7 @@ static void a6xx_rpmh_stop(struct a6xx_gmu *gmu)
 	int ret;
 	u32 val;
 
-	if (test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status))
+	if (!test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status))
 		return;
 
 	if (adreno_is_a840(adreno_gpu))
@@ -1465,6 +1465,9 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 	/* Stop the interrupts and mask the hardware */
 	a6xx_gmu_irq_disable(gmu);
 
+	/* Halt the gmu cm3 core */
+	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
+
 	/* Tell RPMh to power off the GPU */
 	a6xx_rpmh_stop(gmu);
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 8b3bb2fd433b..e293b4ca808a 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1911,8 +1911,11 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
 
 	gpu_write(gpu, REG_A6XX_RBBM_INT_CLEAR_CMD, status);
 
-	if (priv->disable_err_irq)
+	if (priv->disable_err_irq) {
+		/* Turn off interrupts to avoid interrupt storm */
+		gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS);
 		status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS;
+	}
 
 	if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT)
 		a6xx_fault_detect_irq(gpu);
@@ -2770,8 +2773,9 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 
 	adreno_gpu->ubwc_config = qcom_ubwc_config_get_data();
 	if (IS_ERR(adreno_gpu->ubwc_config)) {
+		ret = PTR_ERR(adreno_gpu->ubwc_config);
 		a6xx_destroy(&(a6xx_gpu->base.base));
-		return ERR_CAST(adreno_gpu->ubwc_config);
+		return ERR_PTR(ret);
 	}
 
 	/* Set up the preemption specific bits and pieces for each ringbuffer */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 166365359fa6..3ea8ff8c7404 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -1244,9 +1244,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1],
 		&a6xx_state->gmu_registers[1], true);
 
-	if (adreno_is_a621(adreno_gpu) || adreno_is_a623(adreno_gpu))
+	if (adreno_is_a621(adreno_gpu))
 		_a6xx_get_gmu_registers(gpu, a6xx_state, &a621_gpucc_reg,
 			&a6xx_state->gmu_registers[2], false);
+	else if (adreno_is_a623(adreno_gpu) || adreno_is_a663(adreno_gpu))
+		_a6xx_get_gmu_registers(gpu, a6xx_state, &a623_gpucc_reg,
+			&a6xx_state->gmu_registers[2], false);
 	else
 		_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gpucc_reg,
 			&a6xx_state->gmu_registers[2], false);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index b49d8427b59e..0a13a65f89ac 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -378,6 +378,17 @@ static const u32 a6xx_gmu_gpucc_registers[] = {
 
 static const u32 a621_gmu_gpucc_registers[] = {
 	/* GPU CC */
+	0x24000, 0x2400e, 0x24400, 0x2440e, 0x24800, 0x24805, 0x24c00, 0x24cff,
+	0x25800, 0x25804, 0x25c00, 0x25c04, 0x26000, 0x26004, 0x26400, 0x26405,
+	0x26414, 0x2641d, 0x2642a, 0x26430, 0x26432, 0x26432, 0x26441, 0x26455,
+	0x26466, 0x26468, 0x26478, 0x2647a, 0x26489, 0x2648a, 0x2649c, 0x2649e,
+	0x264a0, 0x264a3, 0x264b3, 0x264b5, 0x264c5, 0x264c7, 0x264d6, 0x264d8,
+	0x264e8, 0x264e9, 0x264f9, 0x264fc, 0x2650b, 0x2650c, 0x2651c, 0x2651e,
+	0x26540, 0x26570, 0x26600, 0x26616, 0x26620, 0x2662d,
+};
+
+static const u32 a623_gmu_gpucc_registers[] = {
+	/* GPU CC */
 	0x24000, 0x2400e, 0x24400, 0x2440e, 0x25800, 0x25804, 0x25c00, 0x25c04,
 	0x26000, 0x26004, 0x26400, 0x26405, 0x26414, 0x2641d, 0x2642a, 0x26430,
 	0x26432, 0x26432, 0x26441, 0x26455, 0x26466, 0x26468, 0x26478, 0x2647a,
@@ -402,6 +413,7 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = {
 
 static const struct a6xx_registers a6xx_gpucc_reg = REGS(a6xx_gmu_gpucc_registers, 0, 0);
 static const struct a6xx_registers a621_gpucc_reg = REGS(a621_gmu_gpucc_registers, 0, 0);
+static const struct a6xx_registers a623_gpucc_reg = REGS(a623_gmu_gpucc_registers, 0, 0);
 
 static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu);
 static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
index 9e44fd1ae634..0f6fd35bd587 100644
--- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
@@ -1211,8 +1211,11 @@ irqreturn_t a8xx_irq(struct msm_gpu *gpu)
 
 	gpu_write(gpu, REG_A8XX_RBBM_INT_CLEAR_CMD, status);
 
-	if (priv->disable_err_irq)
+	if (priv->disable_err_irq) {
+		/* Turn off interrupts to avoid interrupt storm */
+		gpu_write(gpu, REG_A8XX_RBBM_INT_0_MASK, A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS);
 		status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS;
+	}
 
 	if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT)
 		a8xx_fault_detect_irq(gpu);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 13cc658065c5..2ff255d7795e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -34,7 +34,7 @@ enum dpu_perf_mode {
 /**
  * dpu_core_perf_adjusted_mode_clk - Adjust given mode clock rate according to
  *   the perf clock factor.
- * @crtc_clk_rate - Unadjusted mode clock rate
+ * @mode_clk_rate: unadjusted mode clock rate
  * @perf_cfg: performance configuration
  */
 u64 dpu_core_perf_adjusted_mode_clk(u64 mode_clk_rate,
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index 6bb021820d7c..5b4954e7cb74 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -332,8 +332,10 @@ int msm_dp_panel_get_modes(struct msm_dp_panel *msm_dp_panel,
 		return -EINVAL;
 	}
 
-	if (msm_dp_panel->drm_edid)
+	if (msm_dp_panel->drm_edid) {
+		drm_edid_connector_update(connector, msm_dp_panel->drm_edid);
 		return drm_edid_connector_add_modes(connector);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 982abaaac00d..5e1b313f04c0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -670,12 +670,24 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 {
+	long rounded_byte_clk_rate;
+
 	if (!msm_host->mode) {
 		pr_err("%s: mode not set\n", __func__);
 		return -EINVAL;
 	}
 
 	dsi_calc_pclk(msm_host, is_bonded_dsi);
+
+	rounded_byte_clk_rate = clk_round_rate(msm_host->byte_clk,
+					       msm_host->byte_clk_rate);
+	if (rounded_byte_clk_rate < 0) {
+		pr_err("%s: failed to round byte clock rate, %ld\n",
+		       __func__, rounded_byte_clk_rate);
+		return rounded_byte_clk_rate;
+	}
+
+	msm_host->byte_clk_rate = rounded_byte_clk_rate;
 	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index 21a59d66e8dc..f5d3e806f8fd 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -111,6 +111,7 @@ struct msm_dsi_phy {
 	struct msm_dsi_dphy_timing timing;
 	const struct msm_dsi_phy_cfg *cfg;
 	void *tuning_cfg;
+	void *pll_data;
 
 	enum msm_dsi_phy_usecase usecase;
 	bool regulator_ldo_mode;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 984a66085dfb..5d805a797abd 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -426,8 +426,11 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll)
 	u32 data;
 
 	spin_lock_irqsave(&pll->pll_enable_lock, flags);
-	pll->pll_enable_cnt++;
-	WARN_ON(pll->pll_enable_cnt == INT_MAX);
+	if (pll->pll_enable_cnt++) {
+		spin_unlock_irqrestore(&pll->pll_enable_lock, flags);
+		WARN_ON(pll->pll_enable_cnt == INT_MAX);
+		return;
+	}
 
 	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0);
 	data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB;
@@ -873,6 +876,7 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy)
 	spin_lock_init(&pll_7nm->pll_enable_lock);
 
 	pll_7nm->phy = phy;
+	phy->pll_data = pll_7nm;
 
 	ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws);
 	if (ret) {
@@ -961,8 +965,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	u32 const delay_us = 5;
 	u32 const timeout_us = 1000;
 	struct msm_dsi_dphy_timing *timing = &phy->timing;
+	struct dsi_pll_7nm *pll = phy->pll_data;
 	void __iomem *base = phy->base;
 	bool less_than_1500_mhz;
+	unsigned long flags;
 	u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0;
 	u32 glbl_pemph_ctrl_0;
 	u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0;
@@ -1084,10 +1090,13 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 		glbl_rescode_bot_ctrl = 0x3c;
 	}
 
+	spin_lock_irqsave(&pll->pll_enable_lock, flags);
+	pll->pll_enable_cnt = 1;
 	/* de-assert digital and pll power down */
 	data = DSI_7nm_PHY_CMN_CTRL_0_DIGTOP_PWRDN_B |
 	       DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB;
 	writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0);
+	spin_unlock_irqrestore(&pll->pll_enable_lock, flags);
 
 	/* Assert PLL core reset */
 	writel(0x00, base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL);
@@ -1200,7 +1209,9 @@ static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable)
 
 static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 {
+	struct dsi_pll_7nm *pll = phy->pll_data;
 	void __iomem *base = phy->base;
+	unsigned long flags;
 	u32 data;
 
 	DBG("");
@@ -1227,8 +1238,11 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 	writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0);
 	writel(0, base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0);
 
+	spin_lock_irqsave(&pll->pll_enable_lock, flags);
+	pll->pll_enable_cnt = 0;
 	/* Turn off all PHY blocks */
 	writel(0x00, base + REG_DSI_7nm_PHY_CMN_CTRL_0);
+	spin_unlock_irqrestore(&pll->pll_enable_lock, flags);
 
 	/* make sure phy is turned off */
 	wmb();
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 18ed00e5f143..03c057856065 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -505,6 +505,8 @@ static void recover_worker(struct kthread_work *work)
 		 */
 		if (!vm->managed)
 			msm_gem_vm_unusable(submit->vm);
+
+		put_task_struct(task);
 	}
 
 	noreclaim_flag = memalloc_noreclaim_save();
@@ -552,11 +554,13 @@ static void recover_worker(struct kthread_work *work)
 		msm_update_fence(ring->fctx, fence);
 	}
 
-	/* retire completed submits, plus the one that hung: */
-	retire_submits(gpu);
+	priv->disable_err_irq = false;
 
 	gpu->funcs->recover(gpu);
 
+	/* retire completed submits, plus the one that hung: */
+	retire_submits(gpu);
+
 	/*
 	 * Replay all remaining submits starting with highest priority
 	 * ring
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 0d14c31bd4e4..af2b0edc4d58 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -108,9 +108,9 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->memptrs_iova = memptrs_iova;
 
 	ret = drm_sched_init(&ring->sched, &args);
-	if (ret) {
+	if (ret)
 		goto fail;
-	}
+	ring->sched_initialized = true;
 
 	INIT_LIST_HEAD(&ring->submits);
 	spin_lock_init(&ring->submit_lock);
@@ -132,7 +132,8 @@ void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 	if (IS_ERR_OR_NULL(ring))
 		return;
 
-	drm_sched_fini(&ring->sched);
+	if (ring->sched_initialized)
+		drm_sched_fini(&ring->sched);
 
 	msm_fence_context_free(ring->fctx);
 
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
index 28ca8c9f7463..3631ec283c6e 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
@@ -56,6 +56,7 @@ struct msm_ringbuffer {
 	 * The job scheduler for this ring.
 	 */
 	struct drm_gpu_scheduler sched;
+	bool sched_initialized;
 
 	/*
 	 * List of in-flight submits on this ring.  Protected by submit_lock.
diff --git a/drivers/gpu/drm/msm/registers/adreno/a3xx.xml b/drivers/gpu/drm/msm/registers/adreno/a3xx.xml
index 09c9606fc3e1..21b00a17ef3e 100644
--- a/drivers/gpu/drm/msm/registers/adreno/a3xx.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/a3xx.xml
@@ -1495,6 +1495,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 	<reg32 offset="0x3058" name="VBIF_OUT_AXI_AMEMTYPE_CONF0"/>
 	<reg32 offset="0x305e" name="VBIF_OUT_AXI_AOOO_EN"/>
 	<reg32 offset="0x305f" name="VBIF_OUT_AXI_AOOO"/>
+	<reg32 offset="0x3080" name="VBIF_XIN_HALT_CTRL0"/>
+	<reg32 offset="0x3081" name="VBIF_XIN_HALT_CTRL1"/>
 
 	<bitset name="a3xx_vbif_perf_cnt" inline="yes">
 		<bitfield name="CNT0" pos="0" type="boolean"/>