Merge tag 'drm-msm-fixes-2021-02-25' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

- pll fixes
- shutdown hook fix
- runtime resume fix
- clear_oob fix
- kms locking fix
- display aux retry fix

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvmiMKRms_NVavD=NA_jbuexZUcqqL35ke7umqpp-TxMw@mail.gmail.com

12 files changed, 119 insertions, 60 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index 5ccc9da455a1..c35b06b46fcc 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -304,7 +304,7 @@ int a5xx_power_init(struct msm_gpu *gpu)
 	/* Set up the limits management */
 	if (adreno_is_a530(adreno_gpu))
 		a530_lm_setup(gpu);
-	else
+	else if (adreno_is_a540(adreno_gpu))
 		a540_lm_setup(gpu);
 
 	/* Set up SP/TP power collpase */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 71c917f909af..91cf46f84025 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -339,7 +339,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 	else
 		bit = a6xx_gmu_oob_bits[state].ack_new;
 
-	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit);
+	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit);
 }
 
 /* Enable CPU control of SPTP power power collapse */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index ba8e9d3cf0fe..690409ca8a18 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -522,28 +522,73 @@ static int a6xx_cp_init(struct msm_gpu *gpu)
 	return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
 }
 
-static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
+/*
+ * Check that the microcode version is new enough to include several key
+ * security fixes. Return true if the ucode is safe.
+ */
+static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
 		struct drm_gem_object *obj)
 {
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
 	u32 *buf = msm_gem_get_vaddr(obj);
+	bool ret = false;
 
 	if (IS_ERR(buf))
-		return;
+		return false;
 
 	/*
-	 * If the lowest nibble is 0xa that is an indication that this microcode
-	 * has been patched. The actual version is in dword [3] but we only care
-	 * about the patchlevel which is the lowest nibble of dword [3]
-	 *
-	 * Otherwise check that the firmware is greater than or equal to 1.90
-	 * which was the first version that had this fix built in
+	 * Targets up to a640 (a618, a630 and a640) need to check for a
+	 * microcode version that is patched to support the whereami opcode or
+	 * one that is new enough to include it by default.
 	 */
-	if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1)
-		a6xx_gpu->has_whereami = true;
-	else if ((buf[0] & 0xfff) > 0x190)
-		a6xx_gpu->has_whereami = true;
+	if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
+		adreno_is_a640(adreno_gpu)) {
+		/*
+		 * If the lowest nibble is 0xa that is an indication that this
+		 * microcode has been patched. The actual version is in dword
+		 * [3] but we only care about the patchlevel which is the lowest
+		 * nibble of dword [3]
+		 *
+		 * Otherwise check that the firmware is greater than or equal
+		 * to 1.90 which was the first version that had this fix built
+		 * in
+		 */
+		if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) ||
+			(buf[0] & 0xfff) >= 0x190) {
+			a6xx_gpu->has_whereami = true;
+			ret = true;
+			goto out;
+		}
+
+		DRM_DEV_ERROR(&gpu->pdev->dev,
+			"a630 SQE ucode is too old. Have version %x need at least %x\n",
+			buf[0] & 0xfff, 0x190);
+	}  else {
+		/*
+		 * a650 tier targets don't need whereami but still need to be
+		 * equal to or newer than 1.95 for other security fixes
+		 */
+		if (adreno_is_a650(adreno_gpu)) {
+			if ((buf[0] & 0xfff) >= 0x195) {
+				ret = true;
+				goto out;
+			}
+
+			DRM_DEV_ERROR(&gpu->pdev->dev,
+				"a650 SQE ucode is too old. Have version %x need at least %x\n",
+				buf[0] & 0xfff, 0x195);
+		}
 
+		/*
+		 * When a660 is added those targets should return true here
+		 * since those have all the critical security fixes built in
+		 * from the start
+		 */
+	}
+out:
 	msm_gem_put_vaddr(obj);
+	return ret;
 }
 
 static int a6xx_ucode_init(struct msm_gpu *gpu)
@@ -566,7 +611,13 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
 		}
 
 		msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw");
-		a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo);
+		if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) {
+			msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
+			drm_gem_object_put(a6xx_gpu->sqe_bo);
+
+			a6xx_gpu->sqe_bo = NULL;
+			return -EPERM;
+		}
 	}
 
 	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,
@@ -1350,35 +1401,20 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
 		u32 revn)
 {
 	struct opp_table *opp_table;
-	struct nvmem_cell *cell;
 	u32 supp_hw = UINT_MAX;
-	void *buf;
-
-	cell = nvmem_cell_get(dev, "speed_bin");
-	/*
-	 * -ENOENT means that the platform doesn't support speedbin which is
-	 * fine
-	 */
-	if (PTR_ERR(cell) == -ENOENT)
-		return 0;
-	else if (IS_ERR(cell)) {
-		DRM_DEV_ERROR(dev,
-				"failed to read speed-bin. Some OPPs may not be supported by hardware");
-		goto done;
-	}
+	u16 speedbin;
+	int ret;
 
-	buf = nvmem_cell_read(cell, NULL);
-	if (IS_ERR(buf)) {
-		nvmem_cell_put(cell);
+	ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
+	if (ret) {
 		DRM_DEV_ERROR(dev,
-				"failed to read speed-bin. Some OPPs may not be supported by hardware");
+			      "failed to read speed-bin (%d). Some OPPs may not be supported by hardware",
+			      ret);
 		goto done;
 	}
+	speedbin = le16_to_cpu(speedbin);
 
-	supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf));
-
-	kfree(buf);
-	nvmem_cell_put(cell);
+	supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
 
 done:
 	opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 5a8e3e1fc48c..85f2c3564c96 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -43,6 +43,8 @@
 #define DPU_DEBUGFS_DIR "msm_dpu"
 #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
 
+#define MIN_IB_BW	400000000ULL /* Min ib vote 400MB */
+
 static int dpu_kms_hw_init(struct msm_kms *kms);
 static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
 
@@ -931,6 +933,9 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		DPU_DEBUG("REG_DMA is not defined");
 	}
 
+	if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
+		dpu_kms_parse_data_bus_icc_path(dpu_kms);
+
 	pm_runtime_get_sync(&dpu_kms->pdev->dev);
 
 	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
@@ -1032,9 +1037,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	dpu_vbif_init_memtypes(dpu_kms);
 
-	if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
-		dpu_kms_parse_data_bus_icc_path(dpu_kms);
-
 	pm_runtime_put_sync(&dpu_kms->pdev->dev);
 
 	return 0;
@@ -1191,10 +1193,10 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev)
 
 	ddev = dpu_kms->dev;
 
+	WARN_ON(!(dpu_kms->num_paths));
 	/* Min vote of BW is required before turning on AXI clk */
 	for (i = 0; i < dpu_kms->num_paths; i++)
-		icc_set_bw(dpu_kms->path[i], 0,
-			dpu_kms->catalog->perf.min_dram_ib);
+		icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW));
 
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (rc) {
diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index 1c6e1d2b947c..7c22bfe0fc7d 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -32,6 +32,8 @@ struct dp_aux_private {
 	struct drm_dp_aux dp_aux;
 };
 
+#define MAX_AUX_RETRIES			5
+
 static const char *dp_aux_get_error(u32 aux_error)
 {
 	switch (aux_error) {
@@ -377,6 +379,11 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 	ret = dp_aux_cmd_fifo_tx(aux, msg);
 
 	if (ret < 0) {
+		if (aux->native) {
+			aux->retry_cnt++;
+			if (!(aux->retry_cnt % MAX_AUX_RETRIES))
+				dp_catalog_aux_update_cfg(aux->catalog);
+		}
 		usleep_range(400, 500); /* at least 400us to next try */
 		goto unlock_exit;
 	}
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
index a45fe95aff49..3dc65877fa10 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c
@@ -163,7 +163,7 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev,
 		break;
 	case MSM_DSI_PHY_7NM:
 	case MSM_DSI_PHY_7NM_V4_1:
-		pll = msm_dsi_pll_7nm_init(pdev, id);
+		pll = msm_dsi_pll_7nm_init(pdev, type, id);
 		break;
 	default:
 		pll = ERR_PTR(-ENXIO);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
index 3405982a092c..bbecb1de5678 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h
@@ -117,10 +117,12 @@ msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 }
 #endif
 #ifdef CONFIG_DRM_MSM_DSI_7NM_PHY
-struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id);
+struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev,
+					enum msm_dsi_phy_type type, int id);
 #else
 static inline struct msm_dsi_pll *
-msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
+msm_dsi_pll_7nm_init(struct platform_device *pdev,
+					enum msm_dsi_phy_type type, int id)
 {
 	return ERR_PTR(-ENODEV);
 }
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
index 93bf142e4a4e..e29b3bfd63d1 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c
@@ -325,7 +325,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll)
 	pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high);
-	pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40);
+	pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, reg->pll_lockdet_rate);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06);
 	pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */
 	pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters);
@@ -509,6 +509,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw,
 {
 	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll);
+	struct dsi_pll_config *config = &pll_7nm->pll_configuration;
 	void __iomem *base = pll_7nm->mmio;
 	u64 ref_clk = pll_7nm->vco_ref_clk_rate;
 	u64 vco_rate = 0x0;
@@ -529,9 +530,8 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw,
 	/*
 	 * TODO:
 	 *	1. Assumes prescaler is disabled
-	 *	2. Multiplier is 2^18. it should be 2^(num_of_frac_bits)
 	 */
-	multiplier = 1 << 18;
+	multiplier = 1 << config->frac_bits;
 	pll_freq = dec * (ref_clk * 2);
 	tmp64 = (ref_clk * 2 * frac);
 	pll_freq += div_u64(tmp64, multiplier);
@@ -852,7 +852,8 @@ err_base_clk_hw:
 	return ret;
 }
 
-struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
+struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev,
+					enum msm_dsi_phy_type type, int id)
 {
 	struct dsi_pll_7nm *pll_7nm;
 	struct msm_dsi_pll *pll;
@@ -885,7 +886,7 @@ struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
 	pll = &pll_7nm->base;
 	pll->min_rate = 1000000000UL;
 	pll->max_rate = 3500000000UL;
-	if (pll->type == MSM_DSI_PHY_7NM_V4_1) {
+	if (type == MSM_DSI_PHY_7NM_V4_1) {
 		pll->min_rate = 600000000UL;
 		pll->max_rate = (unsigned long)5000000000ULL;
 		/* workaround for max rate overflowing on 32-bit builds: */
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 6a326761dc4a..edcaccaa27e6 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -57,10 +57,13 @@ static void vblank_put(struct msm_kms *kms, unsigned crtc_mask)
 
 static void lock_crtcs(struct msm_kms *kms, unsigned int crtc_mask)
 {
+	int crtc_index;
 	struct drm_crtc *crtc;
 
-	for_each_crtc_mask(kms->dev, crtc, crtc_mask)
-		mutex_lock(&kms->commit_lock[drm_crtc_index(crtc)]);
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		crtc_index = drm_crtc_index(crtc);
+		mutex_lock_nested(&kms->commit_lock[crtc_index], crtc_index);
+	}
 }
 
 static void unlock_crtcs(struct msm_kms *kms, unsigned int crtc_mask)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 94525ac76d4e..a5c6b8c23336 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1072,6 +1072,10 @@ static int __maybe_unused msm_pm_resume(struct device *dev)
 static int __maybe_unused msm_pm_prepare(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return 0;
 
 	return drm_mode_config_helper_suspend(ddev);
 }
@@ -1079,6 +1083,10 @@ static int __maybe_unused msm_pm_prepare(struct device *dev)
 static void __maybe_unused msm_pm_complete(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return;
 
 	drm_mode_config_helper_resume(ddev);
 }
@@ -1311,6 +1319,10 @@ static int msm_pdev_remove(struct platform_device *pdev)
 static void msm_pdev_shutdown(struct platform_device *pdev)
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct msm_drm_private *priv = drm ? drm->dev_private : NULL;
+
+	if (!priv || !priv->kms)
+		return;
 
 	drm_atomic_helper_shutdown(drm);
 }
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index ad2703698b05..cd59a5918038 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -45,7 +45,7 @@ int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
 	int ret;
 
 	if (fence > fctx->last_fence) {
-		DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n",
+		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
 				fctx->name, fence, fctx->last_fence);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 4735251a394d..d8151a89e163 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -157,7 +157,6 @@ struct msm_kms {
 	 * from the crtc's pending_timer close to end of the frame:
 	 */
 	struct mutex commit_lock[MAX_CRTCS];
-	struct lock_class_key commit_lock_keys[MAX_CRTCS];
 	unsigned pending_crtc_mask;
 	struct msm_pending_timer pending_timers[MAX_CRTCS];
 };
@@ -167,11 +166,8 @@ static inline int msm_kms_init(struct msm_kms *kms,
 {
 	unsigned i, ret;
 
-	for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) {
-		lockdep_register_key(&kms->commit_lock_keys[i]);
-		__mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]",
-			     &kms->commit_lock_keys[i]);
-	}
+	for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++)
+		mutex_init(&kms->commit_lock[i]);
 
 	kms->funcs = funcs;