Re: [PATCH v10 1/3] ACPI/IORT: Add msi address regions reservation helper

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Nov 29, 2017 at 02:14:47PM +0000, Shameer Kolothum wrote:
> On some platforms msi parent address regions have to be excluded from
> normal IOVA allocation in that they are detected and decoded in a HW
> specific way by system components and so they cannot be considered normal
> IOVA address space.
> 
> Add a helper function that retrieves ITS address regions - the msi
> parent - through IORT device <-> ITS mappings and reserves it so that
> these regions will not be translated by IOMMU and will be excluded from
> IOVA allocations. The function checks for the smmu model number and
> only applies the msi reservation if the platform requires it.
> 
> Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@xxxxxxxxxx>
> ---
>  drivers/acpi/arm64/iort.c        | 133 ++++++++++++++++++++++++++++++++++++++-
>  drivers/irqchip/irq-gic-v3-its.c |   3 +-
>  include/linux/acpi_iort.h        |   7 ++-
>  3 files changed, 138 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
> index 95255ec..1c5fc36 100644
> --- a/drivers/acpi/arm64/iort.c
> +++ b/drivers/acpi/arm64/iort.c
> @@ -39,6 +39,7 @@
>  struct iort_its_msi_chip {
>  	struct list_head	list;
>  	struct fwnode_handle	*fw_node;
> +	phys_addr_t		base_addr;
>  	u32			translation_id;
>  };
>  
> @@ -161,14 +162,16 @@ typedef acpi_status (*iort_find_node_callback)
>  static DEFINE_SPINLOCK(iort_msi_chip_lock);
>  
>  /**
> - * iort_register_domain_token() - register domain token and related ITS ID
> - * to the list from where we can get it back later on.
> + * iort_register_domain_token() - register domain token along with related
> + * ITS ID and base address to the list from where we can get it back later on.
>   * @trans_id: ITS ID.
> + * @base: ITS base address.
>   * @fw_node: Domain token.
>   *
>   * Returns: 0 on success, -ENOMEM if no memory when allocating list element
>   */
> -int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
> +int iort_register_domain_token(int trans_id, phys_addr_t base,
> +			       struct fwnode_handle *fw_node)
>  {
>  	struct iort_its_msi_chip *its_msi_chip;
>  
> @@ -178,6 +181,7 @@ int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
>  
>  	its_msi_chip->fw_node = fw_node;
>  	its_msi_chip->translation_id = trans_id;
> +	its_msi_chip->base_addr = base;
>  
>  	spin_lock(&iort_msi_chip_lock);
>  	list_add(&its_msi_chip->list, &iort_msi_chip_list);
> @@ -581,6 +585,24 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
>  	return -ENODEV;
>  }
>  
> +static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base)
> +{
> +	struct iort_its_msi_chip *its_msi_chip;
> +	bool match = false;
> +
> +	spin_lock(&iort_msi_chip_lock);
> +	list_for_each_entry(its_msi_chip, &iort_msi_chip_list, list) {
> +		if (its_msi_chip->translation_id == its_id) {
> +			*base = its_msi_chip->base_addr;
> +			match = true;
> +			break;
> +		}
> +	}
> +	spin_unlock(&iort_msi_chip_lock);
> +
> +	return match ? 0 : -ENODEV;

Nit: if you need to return an int, use it as the "match" variable,
there is no point in using a bool.

int ret = -ENODEV;

if (its_msi_chip->translation_id == its_id) {
	...
	ret = 0;
	break;
}

return ret;

> +}
> +
>  /**
>   * iort_dev_find_its_id() - Find the ITS identifier for a device
>   * @dev: The device.
> @@ -740,6 +762,38 @@ static int __maybe_unused __get_pci_rid(struct pci_dev *pdev, u16 alias,
>  	return 0;
>  }
>  
> +static bool __maybe_unused iort_hw_msi_resv_enable(struct device *dev,
> +					struct acpi_iort_node *node)
> +{
> +	struct iort_fwnode *curr;
> +	struct acpi_iort_node *iommu = NULL;
> +	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
> +
> +	if (WARN_ON(!fwspec || !fwspec->iommu_fwnode))

Remove WARN_ON() here, it seems excessive.

> +		return false;
> +
> +	spin_lock(&iort_fwnode_lock);
> +	list_for_each_entry(curr, &iort_fwnode_list, list) {
> +		if (curr->fwnode == fwspec->iommu_fwnode) {
> +			iommu = curr->iort_node;
> +			break;
> +		}
> +	}
> +	spin_unlock(&iort_fwnode_lock);

iort_get_iort_node() ?

> +	if (iommu && (iommu->type == ACPI_IORT_NODE_SMMU_V3)) {
> +		struct acpi_iort_smmu_v3 *smmu;
> +
> +		smmu = (struct acpi_iort_smmu_v3 *)iommu->node_data;
> +		if (smmu->model == ACPI_IORT_SMMU_V3_HISILICON_HI161X) {
> +			dev_notice(dev, "Enabling HiSilicon erratum 161010801\n");
> +			return true;
> +		}
> +	}
> +
> +	return false;
> +}
> +
>  static int arm_smmu_iort_xlate(struct device *dev, u32 streamid,
>  			       struct fwnode_handle *fwnode,
>  			       const struct iommu_ops *ops)
> @@ -782,6 +836,77 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
>  
>  	return err;
>  }
> +
> +/**
> + * iort_iommu_msi_get_resv_regions - Reserved region driver helper
> + * @dev: Device from iommu_get_resv_regions()
> + * @head: Reserved region list from iommu_get_resv_regions()
> + *
> + * Returns: Number of msi reserved regions on success (0 if platform
> + *          doesn't require the reservation or no associated msi regions),
> + *          appropriate error value otherwise. The ITS interrupt translation
> + *          space (ITS_base + 0x010000) associated with the device are the
> + *          msi reserved regions.
> + */
> +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
> +{
> +	struct acpi_iort_its_group *its;
> +	struct acpi_iort_node *node, *its_node = NULL;
> +	int i, resv = 0;
> +
> +	node = iort_find_dev_node(dev);
> +	if (!node)
> +		return -ENODEV;

You may not need node, see below.

> +	if (!iort_hw_msi_resv_enable(dev, node))

node is passed but effectively not used by the function.

> +		return 0;
> +
> +	/*
> +	 * Current logic to reserve ITS regions relies on HW topologies
> +	 * where a given PCI or named component maps its IDs to only one
> +	 * ITS group; if a PCI or named component can map its IDs to
> +	 * different ITS groups through IORT mappings this function has
> +	 * to be reworked to ensure we reserve regions for all ITS groups
> +	 * a given PCI or named component may map IDs to.
> +	 */
> +	if (dev_is_pci(dev)) {
> +		u32 rid;
> +
> +		pci_for_each_dma_alias(to_pci_dev(dev), __get_pci_rid, &rid);
> +		its_node = iort_node_map_id(node, rid, NULL, IORT_MSI_TYPE);
> +	} else {
> +		for (i = 0; i < node->mapping_count; i++) {
> +			its_node = iort_node_map_platform_id(node, NULL,
> +							 IORT_MSI_TYPE, i);
> +			if (its_node)
> +				break;
> +		}
> +	}

Ok. So, how about doing:

for (i = 0; i < dev->iommu_fwspec->num_ids; i++) {
	its_node = iort_node_map_id(iommu_iort_node, dev->iommu_fwspec->ids[i],
				    NULL, IORT_MSI_TYPE);
	if (its_node)
		break;
}

which removes the need for dev_is_pci() check and simplifies a bit, is
there any issue with that ?

iommu_iort_node can be returned by iort_hw_msi_resv_enable(), that
you can rename accordingly.

Lorenzo

> +
> +	if (!its_node)
> +		return 0;
> +
> +	/* Move to ITS specific data */
> +	its = (struct acpi_iort_its_group *)its_node->node_data;
> +
> +	for (i = 0; i < its->its_count; i++) {
> +		phys_addr_t base;
> +
> +		if (!iort_find_its_base(its->identifiers[i], &base)) {
> +			int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
> +			struct iommu_resv_region *region;
> +
> +			region = iommu_alloc_resv_region(base + SZ_64K, SZ_64K,
> +							 prot, IOMMU_RESV_MSI);
> +			if (region) {
> +				list_add_tail(&region->list, head);
> +				resv++;
> +			}
> +		}
> +	}
> +
> +	return (resv == its->its_count) ? resv : -ENODEV;
> +}
>  #else
>  static inline const struct iommu_ops *iort_fwspec_iommu_ops(
>  				struct iommu_fwspec *fwspec)
> @@ -789,6 +914,8 @@ static inline const struct iommu_ops *iort_fwspec_iommu_ops(
>  static inline int iort_add_device_replay(const struct iommu_ops *ops,
>  					 struct device *dev)
>  { return 0; }
> +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
> +{ return -ENODEV; }
>  #endif
>  
>  static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,
> diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
> index 4039e64..d4cff12 100644
> --- a/drivers/irqchip/irq-gic-v3-its.c
> +++ b/drivers/irqchip/irq-gic-v3-its.c
> @@ -3450,7 +3450,8 @@ static int __init gic_acpi_parse_madt_its(struct acpi_subtable_header *header,
>  		return -ENOMEM;
>  	}
>  
> -	err = iort_register_domain_token(its_entry->translation_id, dom_handle);
> +	err = iort_register_domain_token(its_entry->translation_id, res.start,
> +					 dom_handle);
>  	if (err) {
>  		pr_err("ITS@%pa: Unable to register GICv3 ITS domain token (ITS ID %d) to IORT\n",
>  		       &res.start, its_entry->translation_id);
> diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
> index 2f7a292..38cd77b 100644
> --- a/include/linux/acpi_iort.h
> +++ b/include/linux/acpi_iort.h
> @@ -26,7 +26,8 @@
>  #define IORT_IRQ_MASK(irq)		(irq & 0xffffffffULL)
>  #define IORT_IRQ_TRIGGER_MASK(irq)	((irq >> 32) & 0xffffffffULL)
>  
> -int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node);
> +int iort_register_domain_token(int trans_id, phys_addr_t base,
> +			       struct fwnode_handle *fw_node);
>  void iort_deregister_domain_token(int trans_id);
>  struct fwnode_handle *iort_find_domain_token(int trans_id);
>  #ifdef CONFIG_ACPI_IORT
> @@ -38,6 +39,7 @@
>  /* IOMMU interface */
>  void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
>  const struct iommu_ops *iort_iommu_configure(struct device *dev);
> +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
>  #else
>  static inline void acpi_iort_init(void) { }
>  static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
> @@ -52,6 +54,9 @@ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
>  static inline const struct iommu_ops *iort_iommu_configure(
>  				      struct device *dev)
>  { return NULL; }
> +static inline
> +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
> +{ return 0; }
>  #endif
>  
>  #endif /* __ACPI_IORT_H__ */
> -- 
> 1.9.1
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [Linux IBM ACPI]     [Linux Power Management]     [Linux Kernel]     [Linux Laptop]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux