Arm SMMU updates for 5.20

- Add even more Qualcomm device-tree compatible strings
 
 - Support dumping of IMP DEF Qualcomm registers on TLB sync timeout
 
 - Fix reference count leak on device tree node in Qualcomm driver
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAmLXDEoQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNKc/B/950/2gtJLqPnxUlR0Jy2KzilNBuJagOIqy
 JveuwkW8MuMYIyNd8fpxMSTfQntXYsl+SGWtlh6yk7Xl5zZqki7YSu1VtRZJBiPk
 LSsD0hLa2Ev4qsEbD2Nbesx6VugXfOQ5bZdnA5WhxFwJoPp7/bTsBnBeEkr36d04
 Jpjv2svbi2heaU7VqOLQoAzuD45FjDgAjFAPJblC+3dYNHi8KTGtkSEzc9hzFtCZ
 1XiqNmV91PtESOuBiB8UIzNXpV5H8avnCSbST2VUvm3oHOGXpjh01l+8jlo0S9by
 1JF5j6w99/vDRPs7JK+M3tmpuuMktav8GyMNP/2iFVhRwbAMI99O
 =I3nv
 -----END PGP SIGNATURE-----

Merge tag 'arm-smmu-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

Arm SMMU updates for 5.20

- Add even more Qualcomm device-tree compatible strings

- Support dumping of IMP DEF Qualcomm registers on TLB sync timeout

- Fix reference count leak on device tree node in Qualcomm driver

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -42,6 +42,7 @@ properties:
               - qcom,sdx55-smmu-500
               - qcom,sdx65-smmu-500
               - qcom,sm6350-smmu-500
+              - qcom,sm6375-smmu-500
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
               - qcom,sm8350-smmu-500

drivers/iommu/Kconfig

@@ -363,6 +363,16 @@ config ARM_SMMU_QCOM
 	  When running on a Qualcomm platform that has the custom variant
 	  of the ARM SMMU, this needs to be built into the SMMU driver.
 
+config ARM_SMMU_QCOM_DEBUG
+	bool "ARM SMMU QCOM implementation defined debug support"
+	depends on ARM_SMMU_QCOM
+	help
+	  Support for implementation specific debug features in ARM SMMU
+	  hardware found in QTI platforms.
+
+	  Say Y here to enable debug for issues such as TLB sync timeouts
+	  which requires implementation defined register dumps.
+
 config ARM_SMMU_V3
 	tristate "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
 	depends on ARM64

drivers/iommu/arm/arm-smmu/Makefile

@@ -3,3 +3,4 @@ obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o
 obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
 arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o
 arm_smmu-$(CONFIG_ARM_SMMU_QCOM) += arm-smmu-qcom.o
+arm_smmu-$(CONFIG_ARM_SMMU_QCOM_DEBUG) += arm-smmu-qcom-debug.o

drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c

@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/of_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/ratelimit.h>
+
+#include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
+
+enum qcom_smmu_impl_reg_offset {
+	QCOM_SMMU_TBU_PWR_STATUS,
+	QCOM_SMMU_STATS_SYNC_INV_TBU_ACK,
+	QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR,
+};
+
+struct qcom_smmu_config {
+	const u32 *reg_offset;
+};
+
+void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu)
+{
+	int ret;
+	u32 tbu_pwr_status, sync_inv_ack, sync_inv_progress;
+	struct qcom_smmu *qsmmu = container_of(smmu, struct qcom_smmu, smmu);
+	const struct qcom_smmu_config *cfg;
+	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	if (__ratelimit(&rs)) {
+		dev_err(smmu->dev, "TLB sync timed out -- SMMU may be deadlocked\n");
+
+		cfg = qsmmu->cfg;
+		if (!cfg)
+			return;
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_TBU_PWR_STATUS],
+					&tbu_pwr_status);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TBU power status: %d\n", ret);
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_STATS_SYNC_INV_TBU_ACK],
+					&sync_inv_ack);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TBU sync/inv ack status: %d\n", ret);
+
+		ret = qcom_scm_io_readl(smmu->ioaddr + cfg->reg_offset[QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR],
+					&sync_inv_progress);
+		if (ret)
+			dev_err(smmu->dev,
+				"Failed to read TCU syn/inv progress: %d\n", ret);
+
+		dev_err(smmu->dev,
+			"TBU: power_status %#x sync_inv_ack %#x sync_inv_progress %#x\n",
+			tbu_pwr_status, sync_inv_ack, sync_inv_progress);
+	}
+}
+
+/* Implementation Defined Register Space 0 register offsets */
+static const u32 qcom_smmu_impl0_reg_offset[] = {
+	[QCOM_SMMU_TBU_PWR_STATUS]		= 0x2204,
+	[QCOM_SMMU_STATS_SYNC_INV_TBU_ACK]	= 0x25dc,
+	[QCOM_SMMU_MMU2QSS_AND_SAFE_WAIT_CNTR]	= 0x2670,
+};
+
+static const struct qcom_smmu_config qcm2290_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc7180_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc7280_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc8180x_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sc8280xp_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm6125_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm6350_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8150_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8250_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8350_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct qcom_smmu_config sm8450_smmu_cfg = {
+	.reg_offset = qcom_smmu_impl0_reg_offset,
+};
+
+static const struct of_device_id __maybe_unused qcom_smmu_impl_debug_match[] = {
+	{ .compatible = "qcom,msm8998-smmu-v2" },
+	{ .compatible = "qcom,qcm2290-smmu-500", .data = &qcm2290_smmu_cfg },
+	{ .compatible = "qcom,sc7180-smmu-500", .data = &sc7180_smmu_cfg },
+	{ .compatible = "qcom,sc7280-smmu-500", .data = &sc7280_smmu_cfg},
+	{ .compatible = "qcom,sc8180x-smmu-500", .data = &sc8180x_smmu_cfg },
+	{ .compatible = "qcom,sc8280xp-smmu-500", .data = &sc8280xp_smmu_cfg },
+	{ .compatible = "qcom,sdm630-smmu-v2" },
+	{ .compatible = "qcom,sdm845-smmu-500" },
+	{ .compatible = "qcom,sm6125-smmu-500", .data = &sm6125_smmu_cfg},
+	{ .compatible = "qcom,sm6350-smmu-500", .data = &sm6350_smmu_cfg},
+	{ .compatible = "qcom,sm8150-smmu-500", .data = &sm8150_smmu_cfg },
+	{ .compatible = "qcom,sm8250-smmu-500", .data = &sm8250_smmu_cfg },
+	{ .compatible = "qcom,sm8350-smmu-500", .data = &sm8350_smmu_cfg },
+	{ .compatible = "qcom,sm8450-smmu-500", .data = &sm8450_smmu_cfg },
+	{ }
+};
+
+const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu)
+{
+	const struct of_device_id *match;
+	const struct device_node *np = smmu->dev->of_node;
+
+	match = of_match_node(qcom_smmu_impl_debug_match, np);
+	if (!match)
+		return NULL;
+
+	return match->data;
+}

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -5,23 +5,40 @@
 
 #include <linux/acpi.h>
 #include <linux/adreno-smmu-priv.h>
+#include <linux/delay.h>
 #include <linux/of_device.h>
 #include <linux/qcom_scm.h>
 
 #include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
 
-struct qcom_smmu {
-	struct arm_smmu_device smmu;
-	bool bypass_quirk;
-	u8 bypass_cbndx;
-	u32 stall_enabled;
-};
+#define QCOM_DUMMY_VAL	-1
 
 static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
 {
 	return container_of(smmu, struct qcom_smmu, smmu);
 }
 
+static void qcom_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+				int sync, int status)
+{
+	unsigned int spin_cnt, delay;
+	u32 reg;
+
+	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			reg = arm_smmu_readl(smmu, page, status);
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+			cpu_relax();
+		}
+		udelay(delay);
+	}
+
+	qcom_smmu_tlb_sync_debug(smmu);
+}
+
 static void qcom_adreno_smmu_write_sctlr(struct arm_smmu_device *smmu, int idx,
 		u32 reg)
 {
@@ -233,6 +250,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,sc7280-mdss" },
 	{ .compatible = "qcom,sc7280-mss-pil" },
 	{ .compatible = "qcom,sc8180x-mdss" },
+	{ .compatible = "qcom,sm8250-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
 	{ }
@@ -374,6 +392,7 @@ static const struct arm_smmu_impl qcom_smmu_impl = {
 	.def_domain_type = qcom_smmu_def_domain_type,
 	.reset = qcom_smmu500_reset,
 	.write_s2cr = qcom_smmu_write_s2cr,
+	.tlb_sync = qcom_smmu_tlb_sync,
 };
 
 static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
@@ -382,6 +401,7 @@ static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
 	.reset = qcom_smmu500_reset,
 	.alloc_context_bank = qcom_adreno_smmu_alloc_context_bank,
 	.write_sctlr = qcom_adreno_smmu_write_sctlr,
+	.tlb_sync = qcom_smmu_tlb_sync,
 };
 
 static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
@@ -398,6 +418,7 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 		return ERR_PTR(-ENOMEM);
 
 	qsmmu->smmu.impl = impl;
+	qsmmu->cfg = qcom_smmu_impl_data(smmu);
 
 	return &qsmmu->smmu;
 }
@@ -413,6 +434,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm6125-smmu-500" },
 	{ .compatible = "qcom,sm6350-smmu-500" },
+	{ .compatible = "qcom,sm6375-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
 	{ .compatible = "qcom,sm8350-smmu-500" },

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _ARM_SMMU_QCOM_H
+#define _ARM_SMMU_QCOM_H
+
+struct qcom_smmu {
+	struct arm_smmu_device smmu;
+	const struct qcom_smmu_config *cfg;
+	bool bypass_quirk;
+	u8 bypass_cbndx;
+	u32 stall_enabled;
+};
+
+#ifdef CONFIG_ARM_SMMU_QCOM_DEBUG
+void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu);
+const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu);
+#else
+static inline void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu) { }
+static inline const void *qcom_smmu_impl_data(struct arm_smmu_device *smmu)
+{
+	return NULL;
+}
+#endif
+
+#endif /* _ARM_SMMU_QCOM_H */

drivers/iommu/arm/arm-smmu/arm-smmu.c

@@ -2074,7 +2074,6 @@ err_reset_platform_ops: __maybe_unused;
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	struct resource *res;
-	resource_size_t ioaddr;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	int num_irqs, i, err;
@@ -2098,7 +2097,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	smmu->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
-	ioaddr = res->start;
+	smmu->ioaddr = res->start;
+
 	/*
 	 * The resource size should effectively match the value of SMMU_TOP;
 	 * stash that temporarily until we know PAGESIZE to validate it with.
@@ -2178,7 +2178,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	}
 
 	err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
-				     "smmu.%pa", &ioaddr);
+				     "smmu.%pa", &smmu->ioaddr);
 	if (err) {
 		dev_err(dev, "Failed to register iommu in sysfs\n");
 		return err;

drivers/iommu/arm/arm-smmu/arm-smmu.h

@@ -278,6 +278,7 @@ struct arm_smmu_device {
 	struct device			*dev;
 
 	void __iomem			*base;
+	phys_addr_t			ioaddr;
 	unsigned int			numpage;
 	unsigned int			pgshift;
 

drivers/iommu/arm/arm-smmu/qcom_iommu.c

@@ -750,9 +750,12 @@ static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu)
 {
 	struct device_node *child;
 
-	for_each_child_of_node(qcom_iommu->dev->of_node, child)
-		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec"))
+	for_each_child_of_node(qcom_iommu->dev->of_node, child) {
+		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec")) {
+			of_node_put(child);
 			return true;
+		}
+	}
 
 	return false;
 }