diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index ec1b5e32b9725bc1104d10e5d7a32af7b211b50a..5124e7431fe31550fafa835a09be725270aa3316 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -154,7 +154,6 @@ config IOMMU_DMA select DMA_OPS_HELPERS select IOMMU_API select IOMMU_IOVA - select IRQ_MSI_IOMMU select NEED_SG_DMA_LENGTH select NEED_SG_DMA_FLAGS if SWIOTLB diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 2a9fa0c8cc00feb20bc9d520406fe286ad36e318..94263ed2c5644b18ff112bcb0bce831c70c1ab42 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -24,6 +24,7 @@ #include <linux/memremap.h> #include <linux/mm.h> #include <linux/mutex.h> +#include <linux/msi.h> #include <linux/of_iommu.h> #include <linux/pci.h> #include <linux/scatterlist.h> @@ -102,6 +103,9 @@ static int __init iommu_dma_forcedac_setup(char *str) } early_param("iommu.forcedac", iommu_dma_forcedac_setup); +static int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr); + /* Number of entries per flush queue */ #define IOVA_DEFAULT_FQ_SIZE 256 #define IOVA_SINGLE_FQ_SIZE 32768 @@ -398,6 +402,7 @@ int iommu_get_dma_cookie(struct iommu_domain *domain) return -ENOMEM; mutex_init(&domain->iova_cookie->mutex); + iommu_domain_set_sw_msi(domain, iommu_dma_sw_msi); return 0; } @@ -429,6 +434,7 @@ int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) cookie->msi_iova = base; domain->iova_cookie = cookie; + iommu_domain_set_sw_msi(domain, iommu_dma_sw_msi); return 0; } EXPORT_SYMBOL(iommu_get_msi_cookie); @@ -443,6 +449,11 @@ void iommu_put_dma_cookie(struct iommu_domain *domain) struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iommu_dma_msi_page *msi, *tmp; +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) + if (domain->sw_msi != iommu_dma_sw_msi) + return; +#endif + if (!cookie) return; @@ -1800,60 +1811,26 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, return NULL; } -/** - * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain - * @desc: MSI descriptor, will store the MSI page - * @msi_addr: MSI target address to be mapped - * - * Return: 0 on success or negative error code if the mapping failed. - */ -int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) +static int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr) { struct device *dev = msi_desc_to_dev(desc); - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - struct iommu_dma_msi_page *msi_page; - static DEFINE_MUTEX(msi_prepare_lock); /* see below */ + const struct iommu_dma_msi_page *msi_page; - if (!domain || !domain->iova_cookie) { - desc->iommu_cookie = NULL; + if (!domain->iova_cookie) { + msi_desc_set_iommu_msi_iova(desc, 0, 0); return 0; } - /* - * In fact the whole prepare operation should already be serialised by - * irq_domain_mutex further up the callchain, but that's pretty subtle - * on its own, so consider this locking as failsafe documentation... - */ - mutex_lock(&msi_prepare_lock); + iommu_group_mutex_assert(dev); msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain); - mutex_unlock(&msi_prepare_lock); - - msi_desc_set_iommu_cookie(desc, msi_page); - if (!msi_page) return -ENOMEM; - return 0; -} - -/** - * iommu_dma_compose_msi_msg() - Apply translation to an MSI message - * @desc: MSI descriptor prepared by iommu_dma_prepare_msi() - * @msg: MSI message containing target physical address - */ -void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg) -{ - struct device *dev = msi_desc_to_dev(desc); - const struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - const struct iommu_dma_msi_page *msi_page; - - msi_page = msi_desc_get_iommu_cookie(desc); - if (!domain || !domain->iova_cookie || WARN_ON(!msi_page)) - return; - - msg->address_hi = upper_32_bits(msi_page->iova); - msg->address_lo &= cookie_msi_granule(domain->iova_cookie) - 1; - msg->address_lo += lower_32_bits(msi_page->iova); + msi_desc_set_iommu_msi_iova( + desc, msi_page->iova, + ilog2(cookie_msi_granule(domain->iova_cookie))); + return 0; } static int iommu_dma_init(void) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 60aed01e54f27cec3ed8b2ac79bcbfd4eb06e63f..c3194ef81142111e2f418bf6d268e62d4c52159b 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3596,3 +3596,32 @@ int iommu_replace_group_handle(struct iommu_group *group, return ret; } EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL"); + +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) +/** + * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain + * @desc: MSI descriptor, will store the MSI page + * @msi_addr: MSI target address to be mapped + * + * The implementation of sw_msi() should take msi_addr and map it to + * an IOVA in the domain and call msi_desc_set_iommu_msi_iova() with the + * mapping information. + * + * Return: 0 on success or negative error code if the mapping failed. + */ +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) +{ + struct device *dev = msi_desc_to_dev(desc); + struct iommu_group *group = dev->iommu_group; + int ret = 0; + + if (!group) + return 0; + + mutex_lock(&group->mutex); + if (group->domain && group->domain->sw_msi) + ret = group->domain->sw_msi(group->domain, desc, msi_addr); + mutex_unlock(&group->mutex); + return ret; +} +#endif /* CONFIG_IRQ_MSI_IOMMU */ diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index dfd0898fb6c157312c0406c883c60b8dae7ba117..6dccbf7217f5d3d7a126fc1075848b69e76e8e06 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -5,6 +5,7 @@ #include <linux/iommufd.h> #include <linux/slab.h> #include <uapi/linux/iommufd.h> +#include <linux/msi.h> #include "../iommu-priv.h" #include "io_pagetable.h" @@ -293,36 +294,151 @@ u32 iommufd_device_to_id(struct iommufd_device *idev) } EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, "IOMMUFD"); +/* + * Get a iommufd_sw_msi_map for the msi physical address requested by the irq + * layer. The mapping to IOVA is global to the iommufd file descriptor, every + * domain that is attached to a device using the same MSI parameters will use + * the same IOVA. + */ +static __maybe_unused struct iommufd_sw_msi_map * +iommufd_sw_msi_get_map(struct iommufd_ctx *ictx, phys_addr_t msi_addr, + phys_addr_t sw_msi_start) +{ + struct iommufd_sw_msi_map *cur; + unsigned int max_pgoff = 0; + + lockdep_assert_held(&ictx->sw_msi_lock); + + list_for_each_entry(cur, &ictx->sw_msi_list, sw_msi_item) { + if (cur->sw_msi_start != sw_msi_start) + continue; + max_pgoff = max(max_pgoff, cur->pgoff + 1); + if (cur->msi_addr == msi_addr) + return cur; + } + + if (ictx->sw_msi_id >= + BITS_PER_BYTE * sizeof_field(struct iommufd_sw_msi_maps, bitmap)) + return ERR_PTR(-EOVERFLOW); + + cur = kzalloc(sizeof(*cur), GFP_KERNEL); + if (!cur) + cur = ERR_PTR(-ENOMEM); + cur->sw_msi_start = sw_msi_start; + cur->msi_addr = msi_addr; + cur->pgoff = max_pgoff; + cur->id = ictx->sw_msi_id++; + list_add_tail(&cur->sw_msi_item, &ictx->sw_msi_list); + return cur; +} + +static int iommufd_sw_msi_install(struct iommufd_ctx *ictx, + struct iommufd_hwpt_paging *hwpt_paging, + struct iommufd_sw_msi_map *msi_map) +{ + unsigned long iova; + + lockdep_assert_held(&ictx->sw_msi_lock); + + iova = msi_map->sw_msi_start + msi_map->pgoff * PAGE_SIZE; + if (!test_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap)) { + int rc; + + rc = iommu_map(hwpt_paging->common.domain, iova, + msi_map->msi_addr, PAGE_SIZE, + IOMMU_WRITE | IOMMU_READ | IOMMU_MMIO, + GFP_KERNEL_ACCOUNT); + if (rc) + return rc; + __set_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap); + } + return 0; +} + +/* + * Called by the irq code if the platform translates the MSI address through the + * IOMMU. msi_addr is the physical address of the MSI page. iommufd will + * allocate a fd global iova for the physical page that is the same on all + * domains and devices. + */ +#ifdef CONFIG_IRQ_MSI_IOMMU +int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr) +{ + struct device *dev = msi_desc_to_dev(desc); + struct iommufd_hwpt_paging *hwpt_paging; + struct iommu_attach_handle *raw_handle; + struct iommufd_attach_handle *handle; + struct iommufd_sw_msi_map *msi_map; + struct iommufd_ctx *ictx; + unsigned long iova; + int rc; + + /* + * It is safe to call iommu_attach_handle_get() here because the iommu + * core code invokes this under the group mutex which also prevents any + * change of the attach handle for the duration of this function. + */ + iommu_group_mutex_assert(dev); + + raw_handle = + iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0); + if (IS_ERR(raw_handle)) + return 0; + hwpt_paging = find_hwpt_paging(domain->iommufd_hwpt); + + handle = to_iommufd_handle(raw_handle); + /* No IOMMU_RESV_SW_MSI means no change to the msi_msg */ + if (handle->idev->igroup->sw_msi_start == PHYS_ADDR_MAX) + return 0; + + ictx = handle->idev->ictx; + guard(mutex)(&ictx->sw_msi_lock); + /* + * The input msi_addr is the exact byte offset of the MSI doorbell, we + * assume the caller has checked that it is contained with a MMIO region + * that is secure to map at PAGE_SIZE. + */ + msi_map = iommufd_sw_msi_get_map(handle->idev->ictx, + msi_addr & PAGE_MASK, + handle->idev->igroup->sw_msi_start); + if (IS_ERR(msi_map)) + return PTR_ERR(msi_map); + + rc = iommufd_sw_msi_install(ictx, hwpt_paging, msi_map); + if (rc) + return rc; + __set_bit(msi_map->id, handle->idev->igroup->required_sw_msi.bitmap); + + iova = msi_map->sw_msi_start + msi_map->pgoff * PAGE_SIZE; + msi_desc_set_iommu_msi_iova(desc, iova, PAGE_SHIFT); + return 0; +} +#endif + static int iommufd_group_setup_msi(struct iommufd_group *igroup, struct iommufd_hwpt_paging *hwpt_paging) { - phys_addr_t sw_msi_start = igroup->sw_msi_start; - int rc; + struct iommufd_ctx *ictx = igroup->ictx; + struct iommufd_sw_msi_map *cur; + + if (igroup->sw_msi_start == PHYS_ADDR_MAX) + return 0; /* - * If the IOMMU driver gives a IOMMU_RESV_SW_MSI then it is asking us to - * call iommu_get_msi_cookie() on its behalf. This is necessary to setup - * the MSI window so iommu_dma_prepare_msi() can install pages into our - * domain after request_irq(). If it is not done interrupts will not - * work on this domain. - * - * FIXME: This is conceptually broken for iommufd since we want to allow - * userspace to change the domains, eg switch from an identity IOAS to a - * DMA IOAS. There is currently no way to create a MSI window that - * matches what the IRQ layer actually expects in a newly created - * domain. + * Install all the MSI pages the device has been using into the domain */ - if (sw_msi_start != PHYS_ADDR_MAX && !hwpt_paging->msi_cookie) { - rc = iommu_get_msi_cookie(hwpt_paging->common.domain, - sw_msi_start); + guard(mutex)(&ictx->sw_msi_lock); + list_for_each_entry(cur, &ictx->sw_msi_list, sw_msi_item) { + int rc; + + if (cur->sw_msi_start != igroup->sw_msi_start || + !test_bit(cur->id, igroup->required_sw_msi.bitmap)) + continue; + + rc = iommufd_sw_msi_install(ictx, hwpt_paging, cur); if (rc) return rc; - - /* - * iommu_get_msi_cookie() can only be called once per domain, - * it returns -EBUSY on later calls. - */ - hwpt_paging->msi_cookie = true; } return 0; } @@ -352,6 +468,111 @@ iommufd_device_attach_reserved_iova(struct iommufd_device *idev, return 0; } +/* The device attach/detach/replace helpers for attach_handle */ + +static int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt, + struct iommufd_device *idev) +{ + struct iommufd_attach_handle *handle; + int rc; + + lockdep_assert_held(&idev->igroup->lock); + + handle = kzalloc(sizeof(*handle), GFP_KERNEL); + if (!handle) + return -ENOMEM; + + if (hwpt->fault) { + rc = iommufd_fault_iopf_enable(idev); + if (rc) + goto out_free_handle; + } + + handle->idev = idev; + rc = iommu_attach_group_handle(hwpt->domain, idev->igroup->group, + &handle->handle); + if (rc) + goto out_disable_iopf; + + return 0; + +out_disable_iopf: + if (hwpt->fault) + iommufd_fault_iopf_disable(idev); +out_free_handle: + kfree(handle); + return rc; +} + +static struct iommufd_attach_handle * +iommufd_device_get_attach_handle(struct iommufd_device *idev) +{ + struct iommu_attach_handle *handle; + + lockdep_assert_held(&idev->igroup->lock); + + handle = + iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0); + if (IS_ERR(handle)) + return NULL; + return to_iommufd_handle(handle); +} + +static void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt, + struct iommufd_device *idev) +{ + struct iommufd_attach_handle *handle; + + handle = iommufd_device_get_attach_handle(idev); + iommu_detach_group_handle(hwpt->domain, idev->igroup->group); + if (hwpt->fault) { + iommufd_auto_response_faults(hwpt, handle); + iommufd_fault_iopf_disable(idev); + } + kfree(handle); +} + +static int iommufd_hwpt_replace_device(struct iommufd_device *idev, + struct iommufd_hw_pagetable *hwpt, + struct iommufd_hw_pagetable *old) +{ + struct iommufd_attach_handle *handle, *old_handle = + iommufd_device_get_attach_handle(idev); + int rc; + + handle = kzalloc(sizeof(*handle), GFP_KERNEL); + if (!handle) + return -ENOMEM; + + if (hwpt->fault && !old->fault) { + rc = iommufd_fault_iopf_enable(idev); + if (rc) + goto out_free_handle; + } + + handle->idev = idev; + rc = iommu_replace_group_handle(idev->igroup->group, hwpt->domain, + &handle->handle); + if (rc) + goto out_disable_iopf; + + if (old->fault) { + iommufd_auto_response_faults(hwpt, old_handle); + if (!hwpt->fault) + iommufd_fault_iopf_disable(idev); + } + kfree(old_handle); + + return 0; + +out_disable_iopf: + if (hwpt->fault && !old->fault) + iommufd_fault_iopf_disable(idev); +out_free_handle: + kfree(handle); + return rc; +} + int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt, struct iommufd_device *idev) { diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index d9a937450e552693905018dddf446cb325311f62..c48d72c9668ca370223ae64a39630161ad43d3b8 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -17,7 +17,7 @@ #include "../iommu-priv.h" #include "iommufd_private.h" -static int iommufd_fault_iopf_enable(struct iommufd_device *idev) +int iommufd_fault_iopf_enable(struct iommufd_device *idev) { struct device *dev = idev->dev; int ret; @@ -50,7 +50,7 @@ static int iommufd_fault_iopf_enable(struct iommufd_device *idev) return ret; } -static void iommufd_fault_iopf_disable(struct iommufd_device *idev) +void iommufd_fault_iopf_disable(struct iommufd_device *idev) { mutex_lock(&idev->iopf_lock); if (!WARN_ON(idev->iopf_enabled == 0)) { @@ -60,46 +60,8 @@ static void iommufd_fault_iopf_disable(struct iommufd_device *idev) mutex_unlock(&idev->iopf_lock); } -static int __fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev) -{ - struct iommufd_attach_handle *handle; - int ret; - - handle = kzalloc(sizeof(*handle), GFP_KERNEL); - if (!handle) - return -ENOMEM; - - handle->idev = idev; - ret = iommu_attach_group_handle(hwpt->domain, idev->igroup->group, - &handle->handle); - if (ret) - kfree(handle); - - return ret; -} - -int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev) -{ - int ret; - - if (!hwpt->fault) - return -EINVAL; - - ret = iommufd_fault_iopf_enable(idev); - if (ret) - return ret; - - ret = __fault_domain_attach_dev(hwpt, idev); - if (ret) - iommufd_fault_iopf_disable(idev); - - return ret; -} - -static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt, - struct iommufd_attach_handle *handle) +void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt, + struct iommufd_attach_handle *handle) { struct iommufd_fault *fault = hwpt->fault; struct iopf_group *group, *next; @@ -135,88 +97,6 @@ static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt, mutex_unlock(&fault->mutex); } -static struct iommufd_attach_handle * -iommufd_device_get_attach_handle(struct iommufd_device *idev) -{ - struct iommu_attach_handle *handle; - - handle = iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0); - if (IS_ERR(handle)) - return NULL; - - return to_iommufd_handle(handle); -} - -void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev) -{ - struct iommufd_attach_handle *handle; - - handle = iommufd_device_get_attach_handle(idev); - iommu_detach_group_handle(hwpt->domain, idev->igroup->group); - iommufd_auto_response_faults(hwpt, handle); - iommufd_fault_iopf_disable(idev); - kfree(handle); -} - -static int __fault_domain_replace_dev(struct iommufd_device *idev, - struct iommufd_hw_pagetable *hwpt, - struct iommufd_hw_pagetable *old) -{ - struct iommufd_attach_handle *handle, *curr = NULL; - int ret; - - if (old->fault) - curr = iommufd_device_get_attach_handle(idev); - - if (hwpt->fault) { - handle = kzalloc(sizeof(*handle), GFP_KERNEL); - if (!handle) - return -ENOMEM; - - handle->idev = idev; - ret = iommu_replace_group_handle(idev->igroup->group, - hwpt->domain, &handle->handle); - } else { - ret = iommu_replace_group_handle(idev->igroup->group, - hwpt->domain, NULL); - } - - if (!ret && curr) { - iommufd_auto_response_faults(old, curr); - kfree(curr); - } - - return ret; -} - -int iommufd_fault_domain_replace_dev(struct iommufd_device *idev, - struct iommufd_hw_pagetable *hwpt, - struct iommufd_hw_pagetable *old) -{ - bool iopf_off = !hwpt->fault && old->fault; - bool iopf_on = hwpt->fault && !old->fault; - int ret; - - if (iopf_on) { - ret = iommufd_fault_iopf_enable(idev); - if (ret) - return ret; - } - - ret = __fault_domain_replace_dev(idev, hwpt, old); - if (ret) { - if (iopf_on) - iommufd_fault_iopf_disable(idev); - return ret; - } - - if (iopf_off) - iommufd_fault_iopf_disable(idev); - - return 0; -} - void iommufd_fault_destroy(struct iommufd_object *obj) { struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj); @@ -449,7 +329,7 @@ int iommufd_fault_iopf_handler(struct iopf_group *group) struct iommufd_hw_pagetable *hwpt; struct iommufd_fault *fault; - hwpt = group->attach_handle->domain->fault_data; + hwpt = group->attach_handle->domain->iommufd_hwpt; fault = hwpt->fault; spin_lock(&fault->lock); diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 598be26a14e28e93fe86934e16c341dc48d60793..7de6e914232e71d8297aed8575bb0261249b5d28 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -156,6 +156,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, goto out_abort; } } + iommu_domain_set_sw_msi(hwpt->domain, iommufd_sw_msi); /* * Set the coherency mode before we do iopt_table_add_domain() as some @@ -251,6 +252,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, goto out_abort; } hwpt->domain->owner = ops; + iommu_domain_set_sw_msi(hwpt->domain, iommufd_sw_msi); if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { rc = -EINVAL; @@ -307,6 +309,7 @@ iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags, goto out_abort; } hwpt->domain->owner = viommu->iommu_dev->ops; + iommu_domain_set_sw_msi(hwpt->domain, iommufd_sw_msi); if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { rc = -EINVAL; @@ -406,10 +409,10 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) } hwpt->fault = fault; hwpt->domain->iopf_handler = iommufd_fault_iopf_handler; - hwpt->domain->fault_data = hwpt; refcount_inc(&fault->obj.users); iommufd_put_object(ucmd->ictx, &fault->obj); } + hwpt->domain->iommufd_hwpt = hwpt; cmd->out_hwpt_id = hwpt->obj.id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 0b1bafc7fd99400547983368d027cdeb5e4ca242..246297452a44ee14aea01add7c2f3a04ea49b935 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -19,6 +19,22 @@ struct iommu_group; struct iommu_option; struct iommufd_device; +struct iommufd_sw_msi_map { + struct list_head sw_msi_item; + phys_addr_t sw_msi_start; + phys_addr_t msi_addr; + unsigned int pgoff; + unsigned int id; +}; + +/* Bitmap of struct iommufd_sw_msi_map::id */ +struct iommufd_sw_msi_maps { + DECLARE_BITMAP(bitmap, 64); +}; + +int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr); + struct iommufd_ctx { struct file *file; struct xarray objects; @@ -26,6 +42,10 @@ struct iommufd_ctx { wait_queue_head_t destroy_wait; struct rw_semaphore ioas_creation_lock; + struct mutex sw_msi_lock; + struct list_head sw_msi_list; + unsigned int sw_msi_id; + u8 account_mode; /* Compatibility with VFIO no iommu */ u8 no_iommu_mode; @@ -283,10 +303,10 @@ struct iommufd_hwpt_paging { struct iommufd_ioas *ioas; bool auto_domain : 1; bool enforce_cache_coherency : 1; - bool msi_cookie : 1; bool nest_parent : 1; /* Head at iommufd_ioas::hwpt_list */ struct list_head hwpt_item; + struct iommufd_sw_msi_maps present_sw_msi; }; struct iommufd_hwpt_nested { @@ -383,6 +403,7 @@ struct iommufd_group { struct iommu_group *group; struct iommufd_hw_pagetable *hwpt; struct list_head device_list; + struct iommufd_sw_msi_maps required_sw_msi; phys_addr_t sw_msi_start; }; @@ -496,43 +517,10 @@ int iommufd_fault_alloc(struct iommufd_ucmd *ucmd); void iommufd_fault_destroy(struct iommufd_object *obj); int iommufd_fault_iopf_handler(struct iopf_group *group); -int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev); -void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev); -int iommufd_fault_domain_replace_dev(struct iommufd_device *idev, - struct iommufd_hw_pagetable *hwpt, - struct iommufd_hw_pagetable *old); - -static inline int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev) -{ - if (hwpt->fault) - return iommufd_fault_domain_attach_dev(hwpt, idev); - - return iommu_attach_group(hwpt->domain, idev->igroup->group); -} - -static inline void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt, - struct iommufd_device *idev) -{ - if (hwpt->fault) { - iommufd_fault_domain_detach_dev(hwpt, idev); - return; - } - - iommu_detach_group(hwpt->domain, idev->igroup->group); -} - -static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev, - struct iommufd_hw_pagetable *hwpt, - struct iommufd_hw_pagetable *old) -{ - if (old->fault || hwpt->fault) - return iommufd_fault_domain_replace_dev(idev, hwpt, old); - - return iommu_group_replace_domain(idev->igroup->group, hwpt->domain); -} +int iommufd_fault_iopf_enable(struct iommufd_device *idev); +void iommufd_fault_iopf_disable(struct iommufd_device *idev); +void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt, + struct iommufd_attach_handle *handle); static inline struct iommufd_viommu * iommufd_get_viommu(struct iommufd_ucmd *ucmd, u32 id) diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index ccf616462a1cb9d87c94b018a48435ac32c9ed3f..b6fa9fd11bc18e8f0d1a6b58b8ce00b784aac066 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -227,6 +227,8 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp) xa_init(&ictx->groups); ictx->file = filp; init_waitqueue_head(&ictx->destroy_wait); + mutex_init(&ictx->sw_msi_lock); + INIT_LIST_HEAD(&ictx->sw_msi_list); filp->private_data = ictx; return 0; } @@ -234,6 +236,8 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp) static int iommufd_fops_release(struct inode *inode, struct file *filp) { struct iommufd_ctx *ictx = filp->private_data; + struct iommufd_sw_msi_map *next; + struct iommufd_sw_msi_map *cur; struct iommufd_object *obj; /* @@ -262,6 +266,11 @@ static int iommufd_fops_release(struct inode *inode, struct file *filp) break; } WARN_ON(!xa_empty(&ictx->groups)); + + mutex_destroy(&ictx->sw_msi_lock); + list_for_each_entry_safe(cur, next, &ictx->sw_msi_list, sw_msi_item) + kfree(cur); + kfree(ictx); return 0; } diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 9e9eb865b3801686a41c5a36cf3497390905fa6b..cec05e443083b8982b3e72f4212d808a22883914 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -28,6 +28,7 @@ config ARM_GIC_V2M select ARM_GIC select IRQ_MSI_LIB select PCI_MSI + select IRQ_MSI_IOMMU config GIC_NON_BANKED bool @@ -38,12 +39,14 @@ config ARM_GIC_V3 select PARTITION_PERCPU select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP select HAVE_ARM_SMCCC_DISCOVERY + select IRQ_MSI_IOMMU config ARM_GIC_V3_ITS bool select GENERIC_MSI_IRQ select IRQ_MSI_LIB default ARM_GIC_V3 + select IRQ_MSI_IOMMU config ARM_GIC_V3_ITS_FSL_MC bool @@ -424,6 +427,7 @@ config LS_EXTIRQ config LS_SCFG_MSI def_bool y if SOC_LS1021A || ARCH_LAYERSCAPE + select IRQ_MSI_IOMMU depends on PCI_MSI config PARTITION_PERCPU diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 1e3476c335ca842e6005b8ad2a1f6688ef4a9f8e..c6989486186667356362d9dd321e728bf978acfc 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -87,9 +87,6 @@ static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct v2m_data *v2m = irq_data_get_irq_chip_data(data); phys_addr_t addr = gicv2m_get_msi_addr(v2m, data->hwirq); - msg->address_hi = upper_32_bits(addr); - msg->address_lo = lower_32_bits(addr); - if (v2m->flags & GICV2M_GRAVITON_ADDRESS_ONLY) msg->data = 0; else @@ -97,7 +94,7 @@ static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) if (v2m->flags & GICV2M_NEEDS_SPI_OFFSET) msg->data -= v2m->spi_offset; - iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), msg); + msi_msg_set_addr(irq_data_get_msi_desc(data), msg, addr); } static struct irq_chip gicv2m_irq_chip = { diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index f30ed281882ff80a43eb9e57aa37e0b2507fb0eb..0115ad6c82593de511c285d99437996919bfa308 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1811,17 +1811,10 @@ static u64 its_irq_get_msi_base(struct its_device *its_dev) static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); - struct its_node *its; - u64 addr; - - its = its_dev->its; - addr = its->get_msi_base(its_dev); - - msg->address_lo = lower_32_bits(addr); - msg->address_hi = upper_32_bits(addr); - msg->data = its_get_event_id(d); - iommu_dma_compose_msi_msg(irq_data_get_msi_desc(d), msg); + msg->data = its_get_event_id(d); + msi_msg_set_addr(irq_data_get_msi_desc(d), msg, + its_dev->its->get_msi_base(its_dev)); } static int its_irq_set_irqchip_state(struct irq_data *d, diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c index 3e1d8a1cda5e642fa783f08042e61288cadb1f45..34e9ca77a8c368c84667bd3df0af7eb1a8e37a22 100644 --- a/drivers/irqchip/irq-gic-v3-mbi.c +++ b/drivers/irqchip/irq-gic-v3-mbi.c @@ -147,22 +147,18 @@ static const struct irq_domain_ops mbi_domain_ops = { static void mbi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { - msg[0].address_hi = upper_32_bits(mbi_phys_base + GICD_SETSPI_NSR); - msg[0].address_lo = lower_32_bits(mbi_phys_base + GICD_SETSPI_NSR); msg[0].data = data->parent_data->hwirq; - - iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), msg); + msi_msg_set_addr(irq_data_get_msi_desc(data), &msg[0], + mbi_phys_base + GICD_SETSPI_NSR); } static void mbi_compose_mbi_msg(struct irq_data *data, struct msi_msg *msg) { mbi_compose_msi_msg(data, msg); - msg[1].address_hi = upper_32_bits(mbi_phys_base + GICD_CLRSPI_NSR); - msg[1].address_lo = lower_32_bits(mbi_phys_base + GICD_CLRSPI_NSR); msg[1].data = data->parent_data->hwirq; - - iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), &msg[1]); + msi_msg_set_addr(irq_data_get_msi_desc(data), &msg[1], + mbi_phys_base + GICD_CLRSPI_NSR); } static bool mbi_init_dev_msi_info(struct device *dev, struct irq_domain *domain, diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c index c0e1aafe468c321f30b680f6556e1597f49077fc..3cb80796cc7ccaa5a940e11a39ae056f29a7e522 100644 --- a/drivers/irqchip/irq-ls-scfg-msi.c +++ b/drivers/irqchip/irq-ls-scfg-msi.c @@ -87,8 +87,6 @@ static void ls_scfg_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) { struct ls_scfg_msi *msi_data = irq_data_get_irq_chip_data(data); - msg->address_hi = upper_32_bits(msi_data->msiir_addr); - msg->address_lo = lower_32_bits(msi_data->msiir_addr); msg->data = data->hwirq; if (msi_affinity_flag) { @@ -98,7 +96,8 @@ static void ls_scfg_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) msg->data |= cpumask_first(mask); } - iommu_dma_compose_msi_msg(irq_data_get_msi_desc(data), msg); + msi_msg_set_addr(irq_data_get_msi_desc(data), msg, + msi_data->msiir_addr); } static int ls_scfg_msi_set_affinity(struct irq_data *irq_data, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 38c65e92ecd091975c42e630e7db50a4133166c4..e93d2e918599f837529e8864873835ff7dca2b22 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -44,6 +44,8 @@ struct iommu_dma_cookie; struct iommu_fault_param; struct iommufd_ctx; struct iommufd_viommu; +struct msi_desc; +struct msi_msg; #define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ #define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ @@ -216,8 +218,16 @@ struct iommu_domain { struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; int (*iopf_handler)(struct iopf_group *group); - void *fault_data; - union { + +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) + int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr); +#endif + + union { /* Pointer usable by owner of the domain */ + struct iommufd_hw_pagetable *iommufd_hwpt; /* iommufd */ + }; + union { /* Fault handler */ struct { iommu_fault_handler_t handler; void *handler_token; @@ -234,6 +244,16 @@ struct iommu_domain { }; }; +static inline void iommu_domain_set_sw_msi( + struct iommu_domain *domain, + int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr)) +{ +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) + domain->sw_msi = sw_msi; +#endif +} + static inline bool iommu_is_dma_domain(struct iommu_domain *domain) { return domain->type & __IOMMU_DOMAIN_DMA_API; @@ -1470,6 +1490,18 @@ static inline ioasid_t iommu_alloc_global_pasid(struct device *dev) static inline void iommu_free_global_pasid(ioasid_t pasid) {} #endif /* CONFIG_IOMMU_API */ +#ifdef CONFIG_IRQ_MSI_IOMMU +#ifdef CONFIG_IOMMU_API +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); +#else +static inline int iommu_dma_prepare_msi(struct msi_desc *desc, + phys_addr_t msi_addr) +{ + return 0; +} +#endif /* CONFIG_IOMMU_API */ +#endif /* CONFIG_IRQ_MSI_IOMMU */ + #if IS_ENABLED(CONFIG_LOCKDEP) && IS_ENABLED(CONFIG_IOMMU_API) void iommu_group_mutex_assert(struct device *dev); #else @@ -1503,32 +1535,12 @@ static inline void iommu_debugfs_setup(void) {} #endif #ifdef CONFIG_IOMMU_DMA -#include <linux/msi.h> - int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); - -int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); -void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); - #else /* CONFIG_IOMMU_DMA */ - -struct msi_desc; -struct msi_msg; - static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) { return -ENODEV; } - -static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) -{ - return 0; -} - -static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg) -{ -} - #endif /* CONFIG_IOMMU_DMA */ /* diff --git a/include/linux/msi.h b/include/linux/msi.h index 9abef442c1463b56b9c276e874cf9e2b859a53e0..93467efbc3ea915bf23c5cfe7971a8d1ee2c42b4 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -166,6 +166,10 @@ struct msi_desc_data { * @dev: Pointer to the device which uses this descriptor * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor + * @iommu_msi_iova: Optional shifted IOVA from the IOMMU to override the msi_addr. + * Only used if iommu_msi_shift != 0 + * @iommu_msi_shift: Indicates how many bits of the original address should be + * preserved when using iommu_msi_iova. * @sysfs_attr: Pointer to sysfs device attribute * * @write_msi_msg: Callback that may be called when the MSI message @@ -184,7 +188,8 @@ struct msi_desc { struct msi_msg msg; struct irq_affinity_desc *affinity; #ifdef CONFIG_IRQ_MSI_IOMMU - const void *iommu_cookie; + u64 iommu_msi_iova : 58; + u64 iommu_msi_shift : 6; #endif #ifdef CONFIG_SYSFS struct device_attribute *sysfs_attrs; @@ -285,28 +290,42 @@ struct msi_desc *msi_next_desc(struct device *dev, unsigned int domid, #define msi_desc_to_dev(desc) ((desc)->dev) -#ifdef CONFIG_IRQ_MSI_IOMMU -static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) +static inline void msi_desc_set_iommu_msi_iova(struct msi_desc *desc, u64 msi_iova, + unsigned int msi_shift) { - return desc->iommu_cookie; -} - -static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, - const void *iommu_cookie) -{ - desc->iommu_cookie = iommu_cookie; -} -#else -static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) -{ - return NULL; +#ifdef CONFIG_IRQ_MSI_IOMMU + desc->iommu_msi_iova = msi_iova >> msi_shift; + desc->iommu_msi_shift = msi_shift; +#endif } -static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, - const void *iommu_cookie) +/** + * msi_msg_set_addr() - Set MSI address in an MSI message + * + * @desc: MSI descriptor that may carry an IOVA base address for MSI via @iommu_msi_iova/shift + * @msg: Target MSI message to set its address_hi and address_lo + * @msi_addr: Physical address to set the MSI message + * + * Notes: + * - Override @msi_addr using the IOVA base address in the @desc if @iommu_msi_shift is set + * - Otherwise, simply set @msi_addr to @msg + */ +static inline void msi_msg_set_addr(struct msi_desc *desc, struct msi_msg *msg, + phys_addr_t msi_addr) { -} +#ifdef CONFIG_IRQ_MSI_IOMMU + if (desc->iommu_msi_shift) { + u64 msi_iova = desc->iommu_msi_iova << desc->iommu_msi_shift; + + msg->address_hi = upper_32_bits(msi_iova); + msg->address_lo = lower_32_bits(msi_iova) | + (msi_addr & ((1 << desc->iommu_msi_shift) - 1)); + return; + } #endif + msg->address_hi = upper_32_bits(msi_addr); + msg->address_lo = lower_32_bits(msi_addr); +} int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid, struct msi_desc *init_desc); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 875f25ed6f710aa002b7af7870cdc32fa06dd92b..e126e6ce510e4d67168b11ef2f6d75e17cd5a1f9 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -96,6 +96,7 @@ config GENERIC_MSI_IRQ bool select IRQ_DOMAIN_HIERARCHY +# irqchip drivers should select this if they call iommu_dma_prepare_msi() config IRQ_MSI_IOMMU bool