[PATCH v7 2/7] iommu/arm-smmu-qcom-tbu: Add Qualcomm TBU driver

[Konrad Dybcio]

On 3/29/24 22:06, Georgi Djakov wrote:
> Operating the TBUs (Translation Buffer Units) from Linux on Qualcomm
> platforms can help with debugging context faults. To help with that,
> the TBUs can run ATOS (Address Translation Operations) to manually
> trigger address translation of IOVA to physical address in hardware
> and provide more details when a context fault happens.
> 
> The driver will control the resources needed by the TBU to allow
> running the debug operations such as ATOS, check for outstanding
> transactions, do snapshot capture etc.
> 
> Signed-off-by: Georgi Djakov <quic_c_gdjako at quicinc.com>
> ---
>   drivers/iommu/Kconfig                         |   9 +
>   drivers/iommu/arm/arm-smmu/Makefile           |   1 +
>   .../iommu/arm/arm-smmu/arm-smmu-qcom-tbu.c    | 372 ++++++++++++++++++
>   drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h    |   2 +
>   drivers/iommu/arm/arm-smmu/arm-smmu.h         |   2 +
>   5 files changed, 386 insertions(+)
>   create mode 100644 drivers/iommu/arm/arm-smmu/arm-smmu-qcom-tbu.c
> 
> diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
> index 0af39bbbe3a3..b699e88f42c5 100644
> --- a/drivers/iommu/Kconfig
> +++ b/drivers/iommu/Kconfig
> @@ -374,6 +374,15 @@ 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_TBU
> +	bool "Qualcomm TBU driver"
> +	depends on ARM_SMMU_QCOM
> +	help
> +	  The SMMUs on Qualcomm platforms may include Translation Buffer
> +	  Units (TBUs) for each master. Enabling support for these units
> +	  allows to operate the TBUs and obtain additional information
> +	  when debugging memory management issues like context faults.
> +
>   config ARM_SMMU_QCOM_DEBUG
>   	bool "ARM SMMU QCOM implementation defined debug support"
>   	depends on ARM_SMMU_QCOM
> diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile
> index 2a5a95e8e3f9..c35ff78fcfd5 100644
> --- a/drivers/iommu/arm/arm-smmu/Makefile
> +++ b/drivers/iommu/arm/arm-smmu/Makefile
> @@ -3,4 +3,5 @@ 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_TBU) += arm-smmu-qcom-tbu.o
>   arm_smmu-$(CONFIG_ARM_SMMU_QCOM_DEBUG) += arm-smmu-qcom-debug.o
> diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-tbu.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-tbu.c
> new file mode 100644
> index 000000000000..e3202ed89566
> --- /dev/null
> +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-tbu.c
> @@ -0,0 +1,372 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
> + */
> +
> +#include <linux/interconnect.h>
> +#include <linux/iopoll.h>
> +#include <linux/list.h>
> +#include <linux/mod_devicetable.h>
> +#include <linux/mutex.h>
> +#include <linux/platform_device.h>
> +#include <linux/spinlock.h>
> +
> +#include "arm-smmu.h"
> +#include "arm-smmu-qcom.h"
> +
> +#define TBU_DBG_TIMEOUT_US		100
> +#define DEBUG_AXUSER_REG		0x30
> +#define DEBUG_AXUSER_CDMID		GENMASK_ULL(43, 36)
> +#define DEBUG_AXUSER_CDMID_VAL		0xff
> +#define DEBUG_PAR_REG			0x28
> +#define DEBUG_PAR_FAULT_VAL		BIT(0)
> +#define DEBUG_PAR_PA			GENMASK_ULL(47, 12)
> +#define DEBUG_SID_HALT_REG		0x0
> +#define DEBUG_SID_HALT_VAL		BIT(16)
> +#define DEBUG_SID_HALT_SID		GENMASK(9, 0)
> +#define DEBUG_SR_HALT_ACK_REG		0x20
> +#define DEBUG_SR_HALT_ACK_VAL		BIT(1)
> +#define DEBUG_SR_ECATS_RUNNING_VAL	BIT(0)
> +#define DEBUG_TXN_AXCACHE		GENMASK(5, 2)
> +#define DEBUG_TXN_AXPROT		GENMASK(8, 6)
> +#define DEBUG_TXN_AXPROT_PRIV		0x1
> +#define DEBUG_TXN_AXPROT_NSEC		0x2
> +#define DEBUG_TXN_TRIGG_REG		0x18
> +#define DEBUG_TXN_TRIGGER		BIT(0)
> +#define DEBUG_VA_ADDR_REG		0x8
> +
> +static LIST_HEAD(tbu_list);
> +static DEFINE_MUTEX(tbu_list_lock);
> +static DEFINE_SPINLOCK(atos_lock);
> +
> +struct qcom_tbu {
> +	struct device *dev;
> +	struct device_node *smmu_np;
> +	u32 sid_range[2];
> +	struct list_head list;
> +	struct clk *clk;
> +	struct icc_path	*path;
> +	void __iomem *base;
> +	spinlock_t halt_lock; /* multiple halt or resume can't execute concurrently */
> +	int halt_count;
> +};
> +
> +static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
> +{
> +	return container_of(smmu, struct qcom_smmu, smmu);
> +}
> +
> +static struct qcom_tbu *qcom_find_tbu(struct qcom_smmu *qsmmu, u32 sid)
> +{
> +	struct qcom_tbu *tbu;
> +	u32 start, end;
> +
> +	mutex_lock(&tbu_list_lock);

#include <linux/cleanup.h>

guard(mutex)(&tbu_list_lock);

and remove the unlocks

similarly for the spinlocks below

Konrad