Merge remote-tracking branch 'iommu/tracking-qcomlt-iommu' into integration-linux-qcomlt

5 files changed, 226 insertions, 14 deletions

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
index 8a6ffce12af5..7c71a6ed465a 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -17,10 +17,19 @@ conditions.
                         "arm,mmu-401"
                         "arm,mmu-500"
                         "cavium,smmu-v2"
+                        "qcom,<soc>-smmu-v2", "qcom,smmu-v2"
 
                   depending on the particular implementation and/or the
                   version of the architecture implemented.
 
+                  A number of Qcom SoCs use qcom,smmu-v2 version of the IP.
+                  "qcom,<soc>-smmu-v2" represents a soc specific compatible
+                  string that should be present along with the "qcom,smmu-v2"
+                  to facilitate SoC specific clocks/power connections and to
+                  address specific bug fixes.
+                  An example string would be -
+                  "qcom,msm8996-smmu-v2", "qcom,smmu-v2".
+
 - reg           : Base address and size of the SMMU.
 
 - #global-interrupts : The number of global interrupts exposed by the
@@ -71,6 +80,22 @@ conditions.
                   or using stream matching with #iommu-cells = <2>, and
                   may be ignored if present in such cases.
 
+- clock-names:    List of the names of clocks input to the device. The
+                  required list depends on particular implementation and
+                  is as follows:
+                  - for "qcom,smmu-v2":
+                    - "bus": clock required for downstream bus access and
+                             for the smmu ptw,
+                    - "iface": clock required to access smmu's registers
+                               through the TCU's programming interface.
+                  - unspecified for other implementations.
+
+- clocks:         Specifiers for all clocks listed in the clock-names property,
+                  as per generic clock bindings.
+
+- power-domains:  Specifiers for power domains required to be powered on for
+                  the SMMU to operate, as per generic power domain bindings.
+
 ** Deprecated properties:
 
 - mmu-masters (deprecated in favour of the generic "iommus" binding) :
@@ -137,3 +162,20 @@ conditions.
                 iommu-map = <0 &smmu3 0 0x400>;
                 ...
         };
+
+	/* Qcom's arm,smmu-v2 implementation */
+	smmu4: iommu {
+		compatible = "qcom,msm8996-smmu-v2", "qcom,smmu-v2";
+		reg = <0xd00000 0x10000>;
+
+		#global-interrupts = <1>;
+		interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
+		#iommu-cells = <1>;
+		power-domains = <&mmcc MDSS_GDSC>;
+
+		clocks = <&mmcc SMMU_MDP_AXI_CLK>,
+			 <&mmcc SMMU_MDP_AHB_CLK>;
+		clock-names = "bus", "iface";
+	};
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 35b2e50f17fb..3be829780fad 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -39,25 +39,25 @@
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
-	asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
+	asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr));
 }
 
 #define __raw_writew __raw_writew
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
-	asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
+	asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr));
 }
 
 #define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
-	asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
+	asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr));
 }
 
 #define __raw_writeq __raw_writeq
 static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 {
-	asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
+	asm volatile("str %0, [%1]" : : "r" (val), "r" (addr));
 }
 
 #define __raw_readb __raw_readb
diff --git a/drivers/base/core.c b/drivers/base/core.c
index df3e1a44707a..135acf0cee96 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -517,6 +517,16 @@ void device_links_driver_cleanup(struct device *dev)
 
 		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE);
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
+
+		/*
+		 * autoremove the links between this @dev and its consumer
+		 * devices that are not active, i.e. where the link state
+		 * has moved to DL_STATE_SUPPLIER_UNBIND.
+		 */
+		if (link->status == DL_STATE_SUPPLIER_UNBIND &&
+		    link->flags & DL_FLAG_AUTOREMOVE_S)
+			kref_put(&link->kref, __device_link_del);
+
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index f7a96bcf94a6..23c01304e57a 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -48,6 +48,7 @@
 #include <linux/of_iommu.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
@@ -118,6 +119,7 @@ enum arm_smmu_implementation {
 	GENERIC_SMMU,
 	ARM_MMU500,
 	CAVIUM_SMMUV2,
+	QCOM_SMMUV2,
 };
 
 struct arm_smmu_s2cr {
@@ -205,6 +207,8 @@ struct arm_smmu_device {
 	u32				num_global_irqs;
 	u32				num_context_irqs;
 	unsigned int			*irqs;
+	struct clk_bulk_data		*clks;
+	int				num_clks;
 
 	u32				cavium_id_base; /* Specific to Cavium */
 
@@ -265,6 +269,20 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
 	{ 0, NULL},
 };
 
+static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
+{
+	if (pm_runtime_enabled(smmu->dev))
+		return pm_runtime_get_sync(smmu->dev);
+
+	return 0;
+}
+
+static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
+{
+	if (pm_runtime_enabled(smmu->dev))
+		pm_runtime_put(smmu->dev);
+}
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
@@ -910,11 +928,15 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	int irq;
+	int ret, irq;
 
 	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
 		return;
 
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return;
+
 	/*
 	 * Disable the context bank and free the page tables before freeing
 	 * it.
@@ -929,6 +951,8 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 
 	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
 	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
+
+	arm_smmu_rpm_put(smmu);
 }
 
 static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
@@ -1210,10 +1234,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return -ENODEV;
 
 	smmu = fwspec_smmu(fwspec);
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
 	/* Ensure that the domain is finalised */
 	ret = arm_smmu_init_domain_context(domain, smmu);
 	if (ret < 0)
-		return ret;
+		goto rpm_put;
 
 	/*
 	 * Sanity check the domain. We don't support domains across
@@ -1223,33 +1252,50 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		dev_err(dev,
 			"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
 			dev_name(smmu_domain->smmu->dev), dev_name(smmu->dev));
-		return -EINVAL;
+		ret = -EINVAL;
+		goto rpm_put;
 	}
 
 	/* Looks ok, so add the device to the domain */
-	return arm_smmu_domain_add_master(smmu_domain, fwspec);
+	ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
+
+rpm_put:
+	arm_smmu_rpm_put(smmu);
+	return ret;
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 			phys_addr_t paddr, size_t size, int prot)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+	int ret;
 
 	if (!ops)
 		return -ENODEV;
 
-	return ops->map(ops, iova, paddr, size, prot);
+	arm_smmu_rpm_get(smmu);
+	ret = ops->map(ops, iova, paddr, size, prot);
+	arm_smmu_rpm_put(smmu);
+
+	return ret;
 }
 
 static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 			     size_t size)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+	size_t ret;
 
 	if (!ops)
 		return 0;
 
-	return ops->unmap(ops, iova, size);
+	arm_smmu_rpm_get(smmu);
+	ret = ops->unmap(ops, iova, size);
+	arm_smmu_rpm_put(smmu);
+
+	return ret;
 }
 
 static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
@@ -1404,14 +1450,32 @@ static int arm_smmu_add_device(struct device *dev)
 	while (i--)
 		cfg->smendx[i] = INVALID_SMENDX;
 
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		goto out_cfg_free;
+
 	ret = arm_smmu_master_alloc_smes(dev);
+	arm_smmu_rpm_put(smmu);
+
 	if (ret)
 		goto out_cfg_free;
 
 	iommu_device_link(&smmu->iommu, dev);
 
+	if (pm_runtime_enabled(smmu->dev) &&
+	    !device_link_add(dev, smmu->dev,
+			     DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_S)) {
+		dev_err(smmu->dev, "Unable to add link to the consumer %s\n",
+			dev_name(dev));
+		ret = -ENODEV;
+		goto out_unlink;
+	}
+
 	return 0;
 
+out_unlink:
+	iommu_device_unlink(&smmu->iommu, dev);
+	arm_smmu_master_free_smes(fwspec);
 out_cfg_free:
 	kfree(cfg);
 out_free:
@@ -1424,7 +1488,7 @@ static void arm_smmu_remove_device(struct device *dev)
 	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
 	struct arm_smmu_master_cfg *cfg;
 	struct arm_smmu_device *smmu;
-
+	int ret;
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return;
@@ -1432,8 +1496,15 @@ static void arm_smmu_remove_device(struct device *dev)
 	cfg  = fwspec->iommu_priv;
 	smmu = cfg->smmu;
 
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return;
+
 	iommu_device_unlink(&smmu->iommu, dev);
 	arm_smmu_master_free_smes(fwspec);
+
+	arm_smmu_rpm_put(smmu);
+
 	iommu_group_remove_device(dev);
 	kfree(fwspec->iommu_priv);
 	iommu_fwspec_free(dev);
@@ -1897,10 +1968,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 struct arm_smmu_match_data {
 	enum arm_smmu_arch_version version;
 	enum arm_smmu_implementation model;
+	const char * const *clks;
+	int num_clks;
 };
 
 #define ARM_SMMU_MATCH_DATA(name, ver, imp)	\
-static struct arm_smmu_match_data name = { .version = ver, .model = imp }
+static const struct arm_smmu_match_data name = { .version = ver, .model = imp }
 
 ARM_SMMU_MATCH_DATA(smmu_generic_v1, ARM_SMMU_V1, GENERIC_SMMU);
 ARM_SMMU_MATCH_DATA(smmu_generic_v2, ARM_SMMU_V2, GENERIC_SMMU);
@@ -1908,6 +1981,17 @@ ARM_SMMU_MATCH_DATA(arm_mmu401, ARM_SMMU_V1_64K, GENERIC_SMMU);
 ARM_SMMU_MATCH_DATA(arm_mmu500, ARM_SMMU_V2, ARM_MMU500);
 ARM_SMMU_MATCH_DATA(cavium_smmuv2, ARM_SMMU_V2, CAVIUM_SMMUV2);
 
+static const char * const qcom_smmuv2_clks[] = {
+	"bus", "iface",
+};
+
+static const struct arm_smmu_match_data qcom_smmuv2 = {
+	.version = ARM_SMMU_V2,
+	.model = QCOM_SMMUV2,
+	.clks = qcom_smmuv2_clks,
+	.num_clks = ARRAY_SIZE(qcom_smmuv2_clks),
+};
+
 static const struct of_device_id arm_smmu_of_match[] = {
 	{ .compatible = "arm,smmu-v1", .data = &smmu_generic_v1 },
 	{ .compatible = "arm,smmu-v2", .data = &smmu_generic_v2 },
@@ -1915,10 +1999,28 @@ static const struct of_device_id arm_smmu_of_match[] = {
 	{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
 	{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
 	{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+	{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 
+static void arm_smmu_fill_clk_data(struct arm_smmu_device *smmu,
+				   const char * const *clks)
+{
+	int i;
+
+	if (smmu->num_clks < 1)
+		return;
+
+	smmu->clks = devm_kcalloc(smmu->dev, smmu->num_clks,
+				  sizeof(*smmu->clks), GFP_KERNEL);
+	if (!smmu->clks)
+		return;
+
+	for (i = 0; i < smmu->num_clks; i++)
+		smmu->clks[i].id = clks[i];
+}
+
 #ifdef CONFIG_ACPI
 static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu)
 {
@@ -2001,6 +2103,9 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
 	data = of_device_get_match_data(dev);
 	smmu->version = data->version;
 	smmu->model = data->model;
+	smmu->num_clks = data->num_clks;
+
+	arm_smmu_fill_clk_data(smmu, data->clks);
 
 	parse_driver_options(smmu);
 
@@ -2099,6 +2204,29 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		smmu->irqs[i] = irq;
 	}
 
+	platform_set_drvdata(pdev, smmu);
+
+	err = devm_clk_bulk_get(smmu->dev, smmu->num_clks, smmu->clks);
+	if (err)
+		return err;
+
+	err = clk_bulk_prepare(smmu->num_clks, smmu->clks);
+	if (err)
+		return err;
+
+	/*
+	 * We want to avoid touching dev->power.lock in fastpaths unless
+	 * it's really going to do something useful - pm_runtime_enabled()
+	 * can serve as an ideal proxy for that decision. So, conditionally
+	 * enable pm_runtime.
+	 */
+	if (dev->pm_domain)
+		pm_runtime_enable(dev);
+
+	err = arm_smmu_rpm_get(smmu);
+	if (err < 0)
+		return err;
+
 	err = arm_smmu_device_cfg_probe(smmu);
 	if (err)
 		return err;
@@ -2140,10 +2268,11 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	platform_set_drvdata(pdev, smmu);
 	arm_smmu_device_reset(smmu);
 	arm_smmu_test_smr_masks(smmu);
 
+	arm_smmu_rpm_put(smmu);
+
 	/*
 	 * For ACPI and generic DT bindings, an SMMU will be probed before
 	 * any device which might need it, so we want the bus ops in place
@@ -2179,8 +2308,16 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
 		dev_err(&pdev->dev, "removing device with active domains!\n");
 
+	arm_smmu_rpm_get(smmu);
 	/* Turn the thing off */
 	writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+	arm_smmu_rpm_put(smmu);
+
+	if (pm_runtime_enabled(smmu->dev))
+		pm_runtime_disable(smmu->dev);
+
+	clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+
 	return 0;
 }
 
@@ -2197,7 +2334,27 @@ static int __maybe_unused arm_smmu_pm_resume(struct device *dev)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(arm_smmu_pm_ops, NULL, arm_smmu_pm_resume);
+static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
+{
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+	return clk_bulk_enable(smmu->num_clks, smmu->clks);
+}
+
+static int __maybe_unused arm_smmu_runtime_suspend(struct device *dev)
+{
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+	clk_bulk_disable(smmu->num_clks, smmu->clks);
+
+	return 0;
+}
+
+static const struct dev_pm_ops arm_smmu_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(NULL, arm_smmu_pm_resume)
+	SET_RUNTIME_PM_OPS(arm_smmu_runtime_suspend,
+			   arm_smmu_runtime_resume, NULL)
+};
 
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
@@ -2217,6 +2374,7 @@ IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400");
 IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401");
 IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500");
 IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2");
+IOMMU_OF_DECLARE(qcom_smmuv2, "qcom,smmu-v2");
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..b24c5f804b8d 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -787,11 +787,13 @@ enum device_link_state {
  * AUTOREMOVE: Remove this link automatically on consumer driver unbind.
  * PM_RUNTIME: If set, the runtime PM framework will use this link.
  * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation.
+ * AUTOREMOVE_S: Remove this link automatically on supplier driver unbind.
  */
 #define DL_FLAG_STATELESS	BIT(0)
 #define DL_FLAG_AUTOREMOVE	BIT(1)
 #define DL_FLAG_PM_RUNTIME	BIT(2)
 #define DL_FLAG_RPM_ACTIVE	BIT(3)
+#define DL_FLAG_AUTOREMOVE_S	BIT(4)
 
 /**
  * struct device_link - Device link representation.