Merge tag 'arm-drivers-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc

Pull ARM driver updates from Olof Johansson:

 - Reset controllers: Adding support for Microchip Sparx5 Switch.

 - Memory controllers: ARM Primecell PL35x SMC memory controller driver
   cleanups and improvements.

 - i.MX SoC drivers: Power domain support for i.MX8MM and i.MX8MN.

 - Rockchip: RK3568 power domains support + DT binding updates,
   cleanups.

 - Qualcomm SoC drivers: Amend socinfo with more SoC/PMIC details,
   including support for MSM8226, MDM9607, SM6125 and SC8180X.

 - ARM FFA driver: "Firmware Framework for ARMv8-A", defining management
   interfaces and communication (including bus model) between partitions
   both in Normal and Secure Worlds.

 - Tegra Memory controller changes, including major rework to deal with
   identity mappings at boot and integration with ARM SMMU pieces.

* tag 'arm-drivers-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (120 commits)
  firmware: turris-mox-rwtm: add marvell,armada-3700-rwtm-firmware compatible string
  firmware: turris-mox-rwtm: show message about HWRNG registration
  firmware: turris-mox-rwtm: fail probing when firmware does not support hwrng
  firmware: turris-mox-rwtm: report failures better
  firmware: turris-mox-rwtm: fix reply status decoding function
  soc: imx: gpcv2: add support for i.MX8MN power domains
  dt-bindings: add defines for i.MX8MN power domains
  firmware: tegra: bpmp: Fix Tegra234-only builds
  iommu/arm-smmu: Use Tegra implementation on Tegra186
  iommu/arm-smmu: tegra: Implement SID override programming
  iommu/arm-smmu: tegra: Detect number of instances at runtime
  dt-bindings: arm-smmu: Add Tegra186 compatible string
  firmware: qcom_scm: Add MDM9607 compatible
  soc: qcom: rpmpd: Add MDM9607 RPM Power Domains
  soc: renesas: Add support to read LSI DEVID register of RZ/G2{L,LC} SoC's
  soc: renesas: Add ARCH_R9A07G044 for the new RZ/G2L SoC's
  dt-bindings: soc: rockchip: drop unnecessary #phy-cells from grf.yaml
  memory: emif: remove unused frequency and voltage notifiers
  memory: fsl_ifc: fix leak of private memory on probe failure
  memory: fsl_ifc: fix leak of IO mapping on probe failure
  ...

2 files changed, 73 insertions, 20 deletions

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index 136872e77195..9f465e146799 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -211,7 +211,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
-	if (of_device_is_compatible(np, "nvidia,tegra194-smmu"))
+	if (of_device_is_compatible(np, "nvidia,tegra194-smmu") ||
+	    of_device_is_compatible(np, "nvidia,tegra186-smmu"))
 		return nvidia_smmu_impl_init(smmu);
 
 	smmu = qcom_smmu_impl_init(smmu);
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
index 29117444e5a0..01e9b50b10a1 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
@@ -7,6 +7,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#include <soc/tegra/mc.h>
+
 #include "arm-smmu.h"
 
 /*
@@ -15,18 +17,32 @@
  * interleaved IOVA accesses across them and translates accesses from
  * non-isochronous HW devices.
  * Third one is used for translating accesses from isochronous HW devices.
+ *
+ * In addition, the SMMU driver needs to coordinate with the memory controller
+ * driver to ensure that the right SID override is programmed for any given
+ * memory client. This is necessary to allow for use-case such as seamlessly
+ * handing over the display controller configuration from the firmware to the
+ * kernel.
+ *
  * This implementation supports programming of the two instances that must
- * be programmed identically.
- * The third instance usage is through standard arm-smmu driver itself and
- * is out of scope of this implementation.
+ * be programmed identically and takes care of invoking the memory controller
+ * driver for SID override programming after devices have been attached to an
+ * SMMU instance.
  */
-#define NUM_SMMU_INSTANCES 2
+#define MAX_SMMU_INSTANCES 2
 
 struct nvidia_smmu {
-	struct arm_smmu_device	smmu;
-	void __iomem		*bases[NUM_SMMU_INSTANCES];
+	struct arm_smmu_device smmu;
+	void __iomem *bases[MAX_SMMU_INSTANCES];
+	unsigned int num_instances;
+	struct tegra_mc *mc;
 };
 
+static inline struct nvidia_smmu *to_nvidia_smmu(struct arm_smmu_device *smmu)
+{
+	return container_of(smmu, struct nvidia_smmu, smmu);
+}
+
 static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
 					     unsigned int inst, int page)
 {
@@ -47,9 +63,10 @@ static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
 static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
 				  int page, int offset, u32 val)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int i;
 
-	for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+	for (i = 0; i < nvidia->num_instances; i++) {
 		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
 
 		writel_relaxed(val, reg);
@@ -67,9 +84,10 @@ static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
 static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
 				    int page, int offset, u64 val)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int i;
 
-	for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+	for (i = 0; i < nvidia->num_instances; i++) {
 		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
 
 		writeq_relaxed(val, reg);
@@ -79,6 +97,7 @@ static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
 static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 				 int sync, int status)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int delay;
 
 	arm_smmu_writel(smmu, page, sync, 0);
@@ -90,7 +109,7 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 			u32 val = 0;
 			unsigned int i;
 
-			for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+			for (i = 0; i < nvidia->num_instances; i++) {
 				void __iomem *reg;
 
 				reg = nvidia_smmu_page(smmu, i, page) + status;
@@ -112,9 +131,10 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 
 static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int i;
 
-	for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+	for (i = 0; i < nvidia->num_instances; i++) {
 		u32 val;
 		void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
 				    ARM_SMMU_GR0_sGFSR;
@@ -157,8 +177,9 @@ static irqreturn_t nvidia_smmu_global_fault(int irq, void *dev)
 	unsigned int inst;
 	irqreturn_t ret = IRQ_NONE;
 	struct arm_smmu_device *smmu = dev;
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 
-	for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+	for (inst = 0; inst < nvidia->num_instances; inst++) {
 		irqreturn_t irq_ret;
 
 		irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
@@ -202,11 +223,13 @@ static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev)
 	struct arm_smmu_device *smmu;
 	struct iommu_domain *domain = dev;
 	struct arm_smmu_domain *smmu_domain;
+	struct nvidia_smmu *nvidia;
 
 	smmu_domain = container_of(domain, struct arm_smmu_domain, domain);
 	smmu = smmu_domain->smmu;
+	nvidia = to_nvidia_smmu(smmu);
 
-	for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+	for (inst = 0; inst < nvidia->num_instances; inst++) {
 		irqreturn_t irq_ret;
 
 		/*
@@ -224,6 +247,17 @@ static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev)
 	return ret;
 }
 
+static void nvidia_smmu_probe_finalize(struct arm_smmu_device *smmu, struct device *dev)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	int err;
+
+	err = tegra_mc_probe_device(nvidia->mc, dev);
+	if (err < 0)
+		dev_err(smmu->dev, "memory controller probe failed for %s: %d\n",
+			dev_name(dev), err);
+}
+
 static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.read_reg = nvidia_smmu_read_reg,
 	.write_reg = nvidia_smmu_write_reg,
@@ -233,6 +267,11 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.tlb_sync = nvidia_smmu_tlb_sync,
 	.global_fault = nvidia_smmu_global_fault,
 	.context_fault = nvidia_smmu_context_fault,
+	.probe_finalize = nvidia_smmu_probe_finalize,
+};
+
+static const struct arm_smmu_impl nvidia_smmu_single_impl = {
+	.probe_finalize = nvidia_smmu_probe_finalize,
 };
 
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
@@ -241,23 +280,36 @@ struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
 	struct device *dev = smmu->dev;
 	struct nvidia_smmu *nvidia_smmu;
 	struct platform_device *pdev = to_platform_device(dev);
+	unsigned int i;
 
 	nvidia_smmu = devm_krealloc(dev, smmu, sizeof(*nvidia_smmu), GFP_KERNEL);
 	if (!nvidia_smmu)
 		return ERR_PTR(-ENOMEM);
 
+	nvidia_smmu->mc = devm_tegra_memory_controller_get(dev);
+	if (IS_ERR(nvidia_smmu->mc))
+		return ERR_CAST(nvidia_smmu->mc);
+
 	/* Instance 0 is ioremapped by arm-smmu.c. */
 	nvidia_smmu->bases[0] = smmu->base;
+	nvidia_smmu->num_instances++;
+
+	for (i = 1; i < MAX_SMMU_INSTANCES; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			break;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!res)
-		return ERR_PTR(-ENODEV);
+		nvidia_smmu->bases[i] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[i]))
+			return ERR_CAST(nvidia_smmu->bases[i]);
 
-	nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res);
-	if (IS_ERR(nvidia_smmu->bases[1]))
-		return ERR_CAST(nvidia_smmu->bases[1]);
+		nvidia_smmu->num_instances++;
+	}
 
-	nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+	if (nvidia_smmu->num_instances == 1)
+		nvidia_smmu->smmu.impl = &nvidia_smmu_single_impl;
+	else
+		nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
 
 	return &nvidia_smmu->smmu;
 }