Merge branch 'iommu/guest-msi' of... (93fa6cf6) · Commits · EulixOS / Software / Kernel

Documentation/ABI/testing/sysfs-kernel-iommu_groups

+12 −0

Original line number	Diff line number	Diff line
		@@ -12,3 +12,15 @@ Description: /sys/kernel/iommu_groups/ contains a number of sub-
		file if the IOMMU driver has chosen to register a more
		common name for the group.
		Users:

		What: /sys/kernel/iommu_groups/reserved_regions
		Date: January 2017
		KernelVersion: v4.11
		Contact: Eric Auger <eric.auger@redhat.com>
		Description: /sys/kernel/iommu_groups/reserved_regions list IOVA
		regions that are reserved. Not necessarily all
		reserved regions are listed. This is typically used to
		output direct-mapped, MSI, non mappable regions. Each
		region is described on a single line: the 1st field is
		the base IOVA, the second is the end IOVA and the third
		field describes the type of the region.

drivers/iommu/amd_iommu.c

+35 −19

Original line number	Diff line number	Diff line
		@@ -3161,9 +3161,10 @@ static bool amd_iommu_capable(enum iommu_cap cap)
		return false;
		}

		static void amd_iommu_get_dm_regions(struct device *dev,
		static void amd_iommu_get_resv_regions(struct device *dev,
		struct list_head *head)
		{
		struct iommu_resv_region *region;
		struct unity_map_entry *entry;
		int devid;

		@@ -3172,41 +3173,56 @@ static void amd_iommu_get_dm_regions(struct device *dev,
		return;

		list_for_each_entry(entry, &amd_iommu_unity_map, list) {
		struct iommu_dm_region *region;
		size_t length;
		int prot = 0;

		if (devid < entry->devid_start \|\| devid > entry->devid_end)
		continue;

		region = kzalloc(sizeof(*region), GFP_KERNEL);
		length = entry->address_end - entry->address_start;
		if (entry->prot & IOMMU_PROT_IR)
		prot \|= IOMMU_READ;
		if (entry->prot & IOMMU_PROT_IW)
		prot \|= IOMMU_WRITE;

		region = iommu_alloc_resv_region(entry->address_start,
		length, prot,
		IOMMU_RESV_DIRECT);
		if (!region) {
		pr_err("Out of memory allocating dm-regions for %s\n",
		dev_name(dev));
		return;
		}
		list_add_tail(&region->list, head);
		}

		region->start = entry->address_start;
		region->length = entry->address_end - entry->address_start;
		if (entry->prot & IOMMU_PROT_IR)
		region->prot \|= IOMMU_READ;
		if (entry->prot & IOMMU_PROT_IW)
		region->prot \|= IOMMU_WRITE;
		region = iommu_alloc_resv_region(MSI_RANGE_START,
		MSI_RANGE_END - MSI_RANGE_START + 1,
		0, IOMMU_RESV_RESERVED);
		if (!region)
		return;
		list_add_tail(&region->list, head);

		region = iommu_alloc_resv_region(HT_RANGE_START,
		HT_RANGE_END - HT_RANGE_START + 1,
		0, IOMMU_RESV_RESERVED);
		if (!region)
		return;
		list_add_tail(&region->list, head);
		}
		}

		static void amd_iommu_put_dm_regions(struct device *dev,
		static void amd_iommu_put_resv_regions(struct device *dev,
		struct list_head *head)
		{
		struct iommu_dm_region entry, next;
		struct iommu_resv_region entry, next;

		list_for_each_entry_safe(entry, next, head, list)
		kfree(entry);
		}

		static void amd_iommu_apply_dm_region(struct device *dev,
		static void amd_iommu_apply_resv_region(struct device *dev,
		struct iommu_domain *domain,
		struct iommu_dm_region *region)
		struct iommu_resv_region *region)
		{
		struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
		unsigned long start, end;
		@@ -3230,9 +3246,9 @@ static const struct iommu_ops amd_iommu_ops = {
		.add_device = amd_iommu_add_device,
		.remove_device = amd_iommu_remove_device,
		.device_group = amd_iommu_device_group,
		.get_dm_regions = amd_iommu_get_dm_regions,
		.put_dm_regions = amd_iommu_put_dm_regions,
		.apply_dm_region = amd_iommu_apply_dm_region,
		.get_resv_regions = amd_iommu_get_resv_regions,
		.put_resv_regions = amd_iommu_put_resv_regions,
		.apply_resv_region = amd_iommu_apply_resv_region,
		.pgsize_bitmap = AMD_IOMMU_PGSIZES,
		};

drivers/iommu/arm-smmu-v3.c

+28 −2

Original line number	Diff line number	Diff line
		@@ -412,6 +412,9 @@
		/* High-level queue structures */
		#define ARM_SMMU_POLL_TIMEOUT_US 100

		#define MSI_IOVA_BASE 0x8000000
		#define MSI_IOVA_LENGTH 0x100000

		static bool disable_bypass;
		module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
		MODULE_PARM_DESC(disable_bypass,
		@@ -1372,8 +1375,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
		switch (cap) {
		case IOMMU_CAP_CACHE_COHERENCY:
		return true;
		case IOMMU_CAP_INTR_REMAP:
		return true; /* MSIs are just memory writes */
		case IOMMU_CAP_NOEXEC:
		return true;
		default:
		@@ -1883,6 +1884,29 @@ static int arm_smmu_of_xlate(struct device dev, struct of_phandle_args args)
		return iommu_fwspec_add_ids(dev, args->args, 1);
		}

		static void arm_smmu_get_resv_regions(struct device *dev,
		struct list_head *head)
		{
		struct iommu_resv_region *region;
		int prot = IOMMU_WRITE \| IOMMU_NOEXEC \| IOMMU_MMIO;

		region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
		prot, IOMMU_RESV_MSI);
		if (!region)
		return;

		list_add_tail(&region->list, head);
		}

		static void arm_smmu_put_resv_regions(struct device *dev,
		struct list_head *head)
		{
		struct iommu_resv_region entry, next;

		list_for_each_entry_safe(entry, next, head, list)
		kfree(entry);
		}

		static struct iommu_ops arm_smmu_ops = {
		.capable = arm_smmu_capable,
		.domain_alloc = arm_smmu_domain_alloc,
		@@ -1898,6 +1922,8 @@ static struct iommu_ops arm_smmu_ops = {
		.domain_get_attr = arm_smmu_domain_get_attr,
		.domain_set_attr = arm_smmu_domain_set_attr,
		.of_xlate = arm_smmu_of_xlate,
		.get_resv_regions = arm_smmu_get_resv_regions,
		.put_resv_regions = arm_smmu_put_resv_regions,
		.pgsize_bitmap = -1UL, /* Restricted during device attach */
		};

drivers/iommu/arm-smmu.c

+28 −2

Original line number	Diff line number	Diff line
		@@ -281,6 +281,9 @@ enum arm_smmu_s2cr_privcfg {

		#define FSYNR0_WNR (1 << 4)

		#define MSI_IOVA_BASE 0x8000000
		#define MSI_IOVA_LENGTH 0x100000

		static int force_stage;
		module_param(force_stage, int, S_IRUGO);
		MODULE_PARM_DESC(force_stage,
		@@ -1371,8 +1374,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
		* requests.
		*/
		return true;
		case IOMMU_CAP_INTR_REMAP:
		return true; /* MSIs are just memory writes */
		case IOMMU_CAP_NOEXEC:
		return true;
		default:
		@@ -1549,6 +1550,29 @@ static int arm_smmu_of_xlate(struct device dev, struct of_phandle_args args)
		return iommu_fwspec_add_ids(dev, &fwid, 1);
		}

		static void arm_smmu_get_resv_regions(struct device *dev,
		struct list_head *head)
		{
		struct iommu_resv_region *region;
		int prot = IOMMU_WRITE \| IOMMU_NOEXEC \| IOMMU_MMIO;

		region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
		prot, IOMMU_RESV_MSI);
		if (!region)
		return;

		list_add_tail(&region->list, head);
		}

		static void arm_smmu_put_resv_regions(struct device *dev,
		struct list_head *head)
		{
		struct iommu_resv_region entry, next;

		list_for_each_entry_safe(entry, next, head, list)
		kfree(entry);
		}

		static struct iommu_ops arm_smmu_ops = {
		.capable = arm_smmu_capable,
		.domain_alloc = arm_smmu_domain_alloc,
		@@ -1564,6 +1588,8 @@ static struct iommu_ops arm_smmu_ops = {
		.domain_get_attr = arm_smmu_domain_get_attr,
		.domain_set_attr = arm_smmu_domain_set_attr,
		.of_xlate = arm_smmu_of_xlate,
		.get_resv_regions = arm_smmu_get_resv_regions,
		.put_resv_regions = arm_smmu_put_resv_regions,
		.pgsize_bitmap = -1UL, /* Restricted during device attach */
		};

drivers/iommu/dma-iommu.c

+96 −23

Original line number	Diff line number	Diff line
		@@ -37,15 +37,50 @@ struct iommu_dma_msi_page {
		phys_addr_t phys;
		};

		enum iommu_dma_cookie_type {
		IOMMU_DMA_IOVA_COOKIE,
		IOMMU_DMA_MSI_COOKIE,
		};

		struct iommu_dma_cookie {
		enum iommu_dma_cookie_type type;
		union {
		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
		struct iova_domain iovad;
		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
		dma_addr_t msi_iova;
		};
		struct list_head msi_page_list;
		spinlock_t msi_lock;
		};

		static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
		{
		if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
		return cookie->iovad.granule;
		return PAGE_SIZE;
		}

		static inline struct iova_domain cookie_iovad(struct iommu_domain domain)
		{
		return &((struct iommu_dma_cookie *)domain->iova_cookie)->iovad;
		struct iommu_dma_cookie *cookie = domain->iova_cookie;

		if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
		return &cookie->iovad;
		return NULL;
		}

		static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
		{
		struct iommu_dma_cookie *cookie;

		cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
		if (cookie) {
		spin_lock_init(&cookie->msi_lock);
		INIT_LIST_HEAD(&cookie->msi_page_list);
		cookie->type = type;
		}
		return cookie;
		}

		int iommu_dma_init(void)
		@@ -61,26 +96,54 @@ int iommu_dma_init(void)
		* callback when domain->type == IOMMU_DOMAIN_DMA.
		*/
		int iommu_get_dma_cookie(struct iommu_domain *domain)
		{
		if (domain->iova_cookie)
		return -EEXIST;

		domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
		if (!domain->iova_cookie)
		return -ENOMEM;

		return 0;
		}
		EXPORT_SYMBOL(iommu_get_dma_cookie);

		/**
		* iommu_get_msi_cookie - Acquire just MSI remapping resources
		* @domain: IOMMU domain to prepare
		* @base: Start address of IOVA region for MSI mappings
		*
		* Users who manage their own IOVA allocation and do not want DMA API support,
		* but would still like to take advantage of automatic MSI remapping, can use
		* this to initialise their own domain appropriately. Users should reserve a
		* contiguous IOVA region, starting at @base, large enough to accommodate the
		* number of PAGE_SIZE mappings necessary to cover every MSI doorbell address
		* used by the devices attached to @domain.
		*/
		int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
		{
		struct iommu_dma_cookie *cookie;

		if (domain->type != IOMMU_DOMAIN_UNMANAGED)
		return -EINVAL;

		if (domain->iova_cookie)
		return -EEXIST;

		cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
		cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
		if (!cookie)
		return -ENOMEM;

		spin_lock_init(&cookie->msi_lock);
		INIT_LIST_HEAD(&cookie->msi_page_list);
		cookie->msi_iova = base;
		domain->iova_cookie = cookie;
		return 0;
		}
		EXPORT_SYMBOL(iommu_get_dma_cookie);
		EXPORT_SYMBOL(iommu_get_msi_cookie);

		/**
		* iommu_put_dma_cookie - Release a domain's DMA mapping resources
		* @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
		* @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
		* iommu_get_msi_cookie()
		*
		* IOMMU drivers should normally call this from their domain_free callback.
		*/
		@@ -92,7 +155,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
		if (!cookie)
		return;

		if (cookie->iovad.granule)
		if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
		put_iova_domain(&cookie->iovad);

		list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
		@@ -137,11 +200,12 @@ static void iova_reserve_pci_windows(struct pci_dev *dev,
		int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
		u64 size, struct device *dev)
		{
		struct iova_domain *iovad = cookie_iovad(domain);
		struct iommu_dma_cookie *cookie = domain->iova_cookie;
		struct iova_domain *iovad = &cookie->iovad;
		unsigned long order, base_pfn, end_pfn;

		if (!iovad)
		return -ENODEV;
		if (!cookie \|\| cookie->type != IOMMU_DMA_IOVA_COOKIE)
		return -EINVAL;

		/* Use the smallest supported page size for IOVA granularity */
		order = __ffs(domain->pgsize_bitmap);
		@@ -662,11 +726,12 @@ static struct iommu_dma_msi_page iommu_dma_get_msi_page(struct device dev,
		{
		struct iommu_dma_cookie *cookie = domain->iova_cookie;
		struct iommu_dma_msi_page *msi_page;
		struct iova_domain *iovad = &cookie->iovad;
		struct iova_domain *iovad = cookie_iovad(domain);
		struct iova *iova;
		int prot = IOMMU_WRITE \| IOMMU_NOEXEC \| IOMMU_MMIO;
		size_t size = cookie_msi_granule(cookie);

		msi_addr &= ~(phys_addr_t)iova_mask(iovad);
		msi_addr &= ~(phys_addr_t)(size - 1);
		list_for_each_entry(msi_page, &cookie->msi_page_list, list)
		if (msi_page->phys == msi_addr)
		return msi_page;
		@@ -675,13 +740,18 @@ static struct iommu_dma_msi_page iommu_dma_get_msi_page(struct device dev,
		if (!msi_page)
		return NULL;

		iova = __alloc_iova(domain, iovad->granule, dma_get_mask(dev));
		msi_page->phys = msi_addr;
		if (iovad) {
		iova = __alloc_iova(domain, size, dma_get_mask(dev));
		if (!iova)
		goto out_free_page;

		msi_page->phys = msi_addr;
		msi_page->iova = iova_dma_addr(iovad, iova);
		if (iommu_map(domain, msi_page->iova, msi_addr, iovad->granule, prot))
		} else {
		msi_page->iova = cookie->msi_iova;
		cookie->msi_iova += size;
		}

		if (iommu_map(domain, msi_page->iova, msi_addr, size, prot))
		goto out_free_iova;

		INIT_LIST_HEAD(&msi_page->list);
		@@ -689,7 +759,10 @@ static struct iommu_dma_msi_page iommu_dma_get_msi_page(struct device dev,
		return msi_page;

		out_free_iova:
		if (iovad)
		__free_iova(iovad, iova);
		else
		cookie->msi_iova -= size;
		out_free_page:
		kfree(msi_page);
		return NULL;
		@@ -730,7 +803,7 @@ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
		msg->data = ~0U;
		} else {
		msg->address_hi = upper_32_bits(msi_page->iova);
		msg->address_lo &= iova_mask(&cookie->iovad);
		msg->address_lo &= cookie_msi_granule(cookie) - 1;
		msg->address_lo += lower_32_bits(msi_page->iova);
		}
		}