From: Jason Gunthorpe jgg@nvidia.com

All the iommu cases simply want to override the MSI page's address with the IOVA that was mapped through the iommu. This doesn't need a cookie pointer, we just need to store the IOVA and its page size in the msi_desc.

Instead provide msi_desc_set_iommu_msi_iova() which allows the IOMMU side to specify the IOVA that the MSI page is placed during iommu_dma_prepare(). This is stored in the msi_desc and then iommu_dma_compose_msi_msg() is a simple inline that sets address_hi/lo.

The next patch will correct the naming.

This is done because we cannot correctly lock access to group->domain in the atomic context that iommu_dma_compose_msi_msg() is called under. Today the locking miss is tolerable because dma_iommu.c operates under an assumption that the domain does not change while a driver is probed.

However iommufd now permits the domain to change while the driver is probed and VFIO userspace can create races with IRQ changes calling iommu_dma_prepare/compose_msi_msg() and changing/freeing the iommu_domain.

Removing the pointer, and critically, the call to iommu_get_domain_for_dev() during compose resolves this race.

Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 6 ------ include/linux/msi.h | 45 +++++++++++++++++++++++---------------- drivers/iommu/dma-iommu.c | 30 +++++--------------------- 3 files changed, 32 insertions(+), 49 deletions(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 318d27841130..3a4215966c1b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1513,7 +1513,6 @@ static inline void iommu_debugfs_setup(void) {} 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 */

@@ -1529,11 +1528,6 @@ static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_a { 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 b10093c4d00e..d442b4a69d56 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -184,7 +184,8 @@ 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_page_shift : 6; #endif #ifdef CONFIG_SYSFS struct device_attribute *sysfs_attrs; @@ -285,28 +286,36 @@ 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) -{ - return desc->iommu_cookie; -} - -static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, - const void *iommu_cookie) +static inline void msi_desc_set_iommu_msi_iova(struct msi_desc *desc, + u64 msi_iova, + unsigned int page_shift) { - 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 >> page_shift; + desc->iommu_msi_page_shift = page_shift; +#endif }

-static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, - const void *iommu_cookie) +/** + * 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 + */ +static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, + struct msi_msg *msg) { -} +#ifdef CONFIG_IRQ_MSI_IOMMU + if (desc->iommu_msi_page_shift) { + u64 msi_iova = desc->iommu_msi_iova + << desc->iommu_msi_page_shift; + + msg->address_hi = upper_32_bits(msi_iova); + msg->address_lo = lower_32_bits(msi_iova) | + (msg->address_lo & + ((1 << desc->iommu_msi_page_shift) - 1)); + } #endif +}

int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid, struct msi_desc *init_desc); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 2a9fa0c8cc00..bf91e014d179 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1815,7 +1815,7 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) static DEFINE_MUTEX(msi_prepare_lock); /* see below */

if (!domain || !domain->iova_cookie) { - desc->iommu_cookie = NULL; + msi_desc_set_iommu_msi_iova(desc, 0, 0); return 0; }

@@ -1827,33 +1827,13 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) mutex_lock(&msi_prepare_lock); 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)

From: Jason Gunthorpe jgg@nvidia.com

SW_MSI supports IOMMU to translate an MSI message before the MSI message is delivered to the interrupt controller. On such systems the iommu_domain must have a translation for the MSI message for interrupts to work.

The IRQ subsystem will call into IOMMU to request that a physical page be setup to receive MSI message, and the IOMMU then sets an IOVA that maps to that physical page. Ultimately the IOVA is programmed into the device via the msi_msg.

Generalize this to allow the iommu_domain owner to provide its own implementation of this mapping. Add a function pointer to struct iommu_domain to allow the domain owner to provide an implementation.

Have dma-iommu supply its implementation for IOMMU_DOMAIN_DMA types during the iommu_get_dma_cookie() path. For IOMMU_DOMAIN_UNMANAGED types used by VFIO (and iommufd for now), have the same iommu_dma_sw_msi set as well in the iommu_get_msi_cookie() path.

Hold the group mutex while in iommu_dma_prepare_msi() to ensure the domain doesn't change or become freed while running. Races with IRQ operations from VFIO and domain changes from iommufd are possible here.

Rreplace the msi_prepare_lock with a lockdep assertion for the group mutex as documentation. For the dma_iommu.c each iommu_domain unique to a group.

Signed-off-by: Jason Gunthorpe jgg@nvidia.com [nicolinc: move iommu_domain_set_sw_msi() from iommu_dma_init_domain() to iommu_dma_init_domain(); add in iommu_put_dma_cookie() an sw_msi test] Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 44 ++++++++++++++++++++++++++------------- drivers/iommu/dma-iommu.c | 33 +++++++++++++---------------- drivers/iommu/iommu.c | 29 ++++++++++++++++++++++++++ 3 files changed, 73 insertions(+), 33 deletions(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 3a4215966c1b..423fdfa6b3bb 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 */ @@ -216,6 +218,12 @@ struct iommu_domain { struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; int (*iopf_handler)(struct iopf_group *group); + +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) + int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr); +#endif + void *fault_data; union { struct { @@ -234,6 +242,16 @@ 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; @@ -1475,6 +1493,18 @@ 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 @@ -1508,26 +1538,12 @@ 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); - #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; -} #endif /* CONFIG_IOMMU_DMA */

/* diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index bf91e014d179..3b58244e6344 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 +449,9 @@ 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 (domain->sw_msi != iommu_dma_sw_msi) + return; + if (!cookie) return;

@@ -1800,33 +1809,19 @@ 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) { + 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); if (!msi_page) return -ENOMEM;

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 599030e1e890..fbbbcdba8a4f 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3587,3 +3587,32 @@ 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 */

A "fault_data" was added exclusively for the iommufd_fault_iopf_handler() used by IOPF/PRI use cases, along with the attach_handle. Now, the iommufd version of sw_msi function will resue the attach_handle and fault_data for a non-fault case.

Rename "fault_data" to "iommufd_hwpt" so as not to confine it to a "fault" case. Move it into a union to be the iommufd private pointer. A following patch will move the iova_cookie to the union for dma-iommu too, after the iommufd_sw_msi implementation is added.

Since we have two unions now, add some simple comments for readability.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 6 ++++-- drivers/iommu/iommufd/fault.c | 2 +- drivers/iommu/iommufd/hw_pagetable.c | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 423fdfa6b3bb..b6526d734f30 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -224,8 +224,10 @@ struct iommu_domain { phys_addr_t msi_addr); #endif

- void *fault_data; - union { + 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; diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index 1fe804e28a86..06aa83a75e94 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -431,7 +431,7 @@ 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;

mutex_lock(&fault->mutex); diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index ce03c3804651..f7c0d7b214b6 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -402,10 +402,10 @@ 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));

From: Jason Gunthorpe jgg@nvidia.com

iommufd has a model where the iommu_domain can be changed while the VFIO device is attached. In this case the MSI should continue to work. This corner case has not worked because the dma-iommu implementation of sw_msi is tied to a single domain.

Implement the sw_msi mapping directly and use a global per-fd table to associate assigned iova to the MSI pages. This allows the MSI pages to loaded into a domain before it is attached ensuring that MSI is not disrupted.

Signed-off-by: Jason Gunthorpe jgg@nvidia.com [nicolinc: set sw_msi pointer in nested hwpt allocators] Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 23 +++- drivers/iommu/iommufd/device.c | 158 ++++++++++++++++++++---- drivers/iommu/iommufd/hw_pagetable.c | 3 + drivers/iommu/iommufd/main.c | 9 ++ 4 files changed, 170 insertions(+), 23 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 063c0a42f54f..3e83bbb5912c 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; };

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 38b31b652147..f75b3c23cd41 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 +294,149 @@ 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 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 iommu_attach_handle *raw_handle; + struct iommufd_hwpt_paging *hwpt_paging; + struct iommufd_attach_handle *handle; + struct iommufd_sw_msi_map *msi_map; + struct iommufd_ctx *ictx; + unsigned long iova; + int rc; + + raw_handle = + iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0); + if (!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 + +/* + * FIXME: when a domain is removed any ids that are not in the union of + * all still attached devices should be removed. + */ + 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; } diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index f7c0d7b214b6..538484eecb3b 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; @@ -303,6 +305,7 @@ 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; diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 97c5e3567d33..7cc9497b7193 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; }

Now, iommufd has its own iommufd_sw_msi using iommufd_hwpt, the iommufd owned domain's private pointer. Similarly, iova_cookie can be seen as a dma-iommu owned domain's private pointer. So, move iova_cookie into the union.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b6526d734f30..284c40fe0e12 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -216,7 +216,6 @@ struct iommu_domain { const struct iommu_ops *owner; /* Whose domain_alloc we came from */ unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ struct iommu_domain_geometry geometry; - struct iommu_dma_cookie *iova_cookie; int (*iopf_handler)(struct iopf_group *group);

#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) @@ -225,6 +224,7 @@ struct iommu_domain { #endif

union { /* Pointer usable by owner of the domain */ + struct iommu_dma_cookie *iova_cookie; /* dma-iommu */ struct iommufd_hw_pagetable *iommufd_hwpt; /* iommufd */ }; union { /* Fault handler */

For systems that require MSI pages to be mapped into the IOMMU translation the IOMMU driver provides an IOMMU_RESV_SW_MSI range, which is the default recommended IOVA window to place these mappings. However, there is nothing special about this address. And to support the RMR trick in VMM for nested translation, the VMM needs to know what sw_msi window the kernel is using. As there is no particular reason to force VMM to adopt the kernel default, provide a simple IOMMU_OPTION_SW_MSI_START/SIZE ioctl that the VMM can use to directly specify the sw_msi window that it wants to use, which replaces and disables the default IOMMU_RESV_SW_MSI from the driver to avoid having to build an API to discover the default IOMMU_RESV_SW_MSI.

Since iommufd now has its own sw_msi function, this is easy to implement.

To keep things simple, the parameters are global to the entire iommufd FD, and will directly replace the IOMMU_RESV_SW_MSI values. The VMM must set the values before creating any hwpt's to have any effect.

Suggested-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 4 +++ include/uapi/linux/iommufd.h | 18 ++++++++++++- drivers/iommu/iommufd/device.c | 4 +++ drivers/iommu/iommufd/io_pagetable.c | 4 ++- drivers/iommu/iommufd/ioas.c | 34 +++++++++++++++++++++++++ drivers/iommu/iommufd/main.c | 6 +++++ 6 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 3e83bbb5912c..9f071609f00b 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -45,6 +45,9 @@ struct iommufd_ctx { struct mutex sw_msi_lock; struct list_head sw_msi_list; unsigned int sw_msi_id; + /* User-programmed SW_MSI region, to override igroup->sw_msi_start */ + phys_addr_t sw_msi_start; + size_t sw_msi_size;

u8 account_mode; /* Compatibility with VFIO no iommu */ @@ -281,6 +284,7 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd); int iommufd_ioas_option(struct iommufd_ucmd *ucmd); int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx); +int iommufd_option_sw_msi(struct iommu_option *cmd, struct iommufd_ctx *ictx);

int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd); int iommufd_check_iova_range(struct io_pagetable *iopt, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 34810f6ae2b5..c864a201e502 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -294,7 +294,9 @@ struct iommu_ioas_unmap {

/** * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and - * ioctl(IOMMU_OPTION_HUGE_PAGES) + * ioctl(IOMMU_OPTION_HUGE_PAGES) and + * ioctl(IOMMU_OPTION_SW_MSI_START) and + * ioctl(IOMMU_OPTION_SW_MSI_SIZE) * @IOMMU_OPTION_RLIMIT_MODE: * Change how RLIMIT_MEMLOCK accounting works. The caller must have privilege * to invoke this. Value 0 (default) is user based accounting, 1 uses process @@ -304,10 +306,24 @@ struct iommu_ioas_unmap { * iommu mappings. Value 0 disables combining, everything is mapped to * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS * option, the object_id must be the IOAS ID. + * @IOMMU_OPTION_SW_MSI_START: + * Change the base address of the IOMMU mapping region for MSI doorbell(s). + * It must be set this before attaching a device to an IOAS/HWPT, otherwise + * this option will be not effective on that IOAS/HWPT. User can choose to + * let kernel pick a base address, by simply ignoring this option or setting + * a value 0 to IOMMU_OPTION_SW_MSI_SIZE. Global option, object_id must be 0 + * @IOMMU_OPTION_SW_MSI_SIZE: + * Change the size of the IOMMU mapping region for MSI doorbell(s). It must + * be set this before attaching a device to an IOAS/HWPT, otherwise it won't + * be effective on that IOAS/HWPT. The value is in MB, and the minimum value + * is 1 MB. A value 0 (default) will invalidate the MSI doorbell base address + * value set to IOMMU_OPTION_SW_MSI_START. Global option, object_id must be 0 */ enum iommufd_option { IOMMU_OPTION_RLIMIT_MODE = 0, IOMMU_OPTION_HUGE_PAGES = 1, + IOMMU_OPTION_SW_MSI_START = 2, + IOMMU_OPTION_SW_MSI_SIZE = 3, };

/** diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index f75b3c23cd41..093a3bd798db 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -445,10 +445,14 @@ static int iommufd_device_attach_reserved_iova(struct iommufd_device *idev, struct iommufd_hwpt_paging *hwpt_paging) { + struct iommufd_ctx *ictx = idev->ictx; int rc;

lockdep_assert_held(&idev->igroup->lock);

+ /* Override it with a user-programmed SW_MSI region */ + if (ictx->sw_msi_size && ictx->sw_msi_start != PHYS_ADDR_MAX) + idev->igroup->sw_msi_start = ictx->sw_msi_start; rc = iopt_table_enforce_dev_resv_regions(&hwpt_paging->ioas->iopt, idev->dev, &idev->igroup->sw_msi_start); diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 8a790e597e12..5d7f5ca1eecf 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -1446,7 +1446,9 @@ int iopt_table_enforce_dev_resv_regions(struct io_pagetable *iopt, if (sw_msi_start && resv->type == IOMMU_RESV_MSI) num_hw_msi++; if (sw_msi_start && resv->type == IOMMU_RESV_SW_MSI) { - *sw_msi_start = resv->start; + /* Bypass the driver-defined SW_MSI region, if preset */ + if (*sw_msi_start == PHYS_ADDR_MAX) + *sw_msi_start = resv->start; num_sw_msi++; }

diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c index 1542c5fd10a8..3f4e25b660f9 100644 --- a/drivers/iommu/iommufd/ioas.c +++ b/drivers/iommu/iommufd/ioas.c @@ -620,6 +620,40 @@ int iommufd_option_rlimit_mode(struct iommu_option *cmd, return -EOPNOTSUPP; }

+int iommufd_option_sw_msi(struct iommu_option *cmd, struct iommufd_ctx *ictx) +{ + if (cmd->object_id) + return -EOPNOTSUPP; + + if (cmd->op == IOMMU_OPTION_OP_GET) { + switch (cmd->option_id) { + case IOMMU_OPTION_SW_MSI_START: + cmd->val64 = (u64)ictx->sw_msi_start; + break; + case IOMMU_OPTION_SW_MSI_SIZE: + cmd->val64 = (u64)ictx->sw_msi_size; + break; + default: + return -EOPNOTSUPP; + } + return 0; + } + if (cmd->op == IOMMU_OPTION_OP_SET) { + switch (cmd->option_id) { + case IOMMU_OPTION_SW_MSI_START: + ictx->sw_msi_start = (phys_addr_t)cmd->val64; + break; + case IOMMU_OPTION_SW_MSI_SIZE: + ictx->sw_msi_size = (size_t)cmd->val64; + break; + default: + return -EOPNOTSUPP; + } + return 0; + } + return -EOPNOTSUPP; +} + static int iommufd_ioas_option_huge_pages(struct iommu_option *cmd, struct iommufd_ioas *ioas) { diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 7cc9497b7193..026297265c71 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -229,6 +229,8 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp) init_waitqueue_head(&ictx->destroy_wait); mutex_init(&ictx->sw_msi_lock); INIT_LIST_HEAD(&ictx->sw_msi_list); + ictx->sw_msi_start = PHYS_ADDR_MAX; + ictx->sw_msi_size = 0; filp->private_data = ictx; return 0; } @@ -287,6 +289,10 @@ static int iommufd_option(struct iommufd_ucmd *ucmd) case IOMMU_OPTION_RLIMIT_MODE: rc = iommufd_option_rlimit_mode(cmd, ucmd->ictx); break; + case IOMMU_OPTION_SW_MSI_START: + case IOMMU_OPTION_SW_MSI_SIZE: + rc = iommufd_option_sw_msi(cmd, ucmd->ictx); + break; case IOMMU_OPTION_HUGE_PAGES: rc = iommufd_ioas_option(ucmd); break;

Also add fail_nth coverage too.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- tools/testing/selftests/iommu/iommufd.c | 53 +++++++++++++++++++ .../selftests/iommu/iommufd_fail_nth.c | 14 +++++ 2 files changed, 67 insertions(+)

diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index a1b2b657999d..87b5b5ac927a 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -334,6 +334,59 @@ TEST_F(change_process, basic) ASSERT_EQ(child, waitpid(child, NULL, 0)); }

+FIXTURE(iommufd_sw_msi) +{ + int fd; + uint32_t ioas_id; +}; + +FIXTURE_SETUP(iommufd_sw_msi) +{ + self->fd = open("/dev/iommu", O_RDWR); + ASSERT_NE(-1, self->fd); + + test_ioctl_ioas_alloc(&self->ioas_id); +} + +FIXTURE_TEARDOWN(iommufd_sw_msi) +{ + teardown_iommufd(self->fd, _metadata); +} + +TEST_F(iommufd_sw_msi, basic) +{ + struct iommu_option cmd = { + .size = sizeof(cmd), + .op = IOMMU_OPTION_OP_SET, + }; + /* Negative case: assign an object_id to this global option */ + cmd.object_id = self->ioas_id; + cmd.option_id = IOMMU_OPTION_SW_MSI_START; + cmd.val64 = 0xffffffff; + EXPECT_ERRNO(EOPNOTSUPP, ioctl(self->fd, IOMMU_OPTION, &cmd)); + cmd.option_id = IOMMU_OPTION_SW_MSI_SIZE; + cmd.val64 = 2; + EXPECT_ERRNO(EOPNOTSUPP, ioctl(self->fd, IOMMU_OPTION, &cmd)); + + cmd.object_id = 0; + cmd.option_id = IOMMU_OPTION_SW_MSI_START; + cmd.val64 = 0xffffffff; + ASSERT_EQ(0, ioctl(self->fd, IOMMU_OPTION, &cmd)); + cmd.option_id = IOMMU_OPTION_SW_MSI_SIZE; + cmd.val64 = 2; + ASSERT_EQ(0, ioctl(self->fd, IOMMU_OPTION, &cmd)); + + /* Read them back to verify */ + cmd.op = IOMMU_OPTION_OP_GET; + cmd.object_id = 0; + cmd.option_id = IOMMU_OPTION_SW_MSI_START; + ASSERT_EQ(0, ioctl(self->fd, IOMMU_OPTION, &cmd)); + ASSERT_EQ(cmd.val64, 0xffffffff); + cmd.option_id = IOMMU_OPTION_SW_MSI_SIZE; + ASSERT_EQ(0, ioctl(self->fd, IOMMU_OPTION, &cmd)); + ASSERT_EQ(cmd.val64, 2); +} + FIXTURE(iommufd_ioas) { int fd; diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index 64b1f8e1b0cf..6d7b1417ce45 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -615,6 +615,10 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) /* device.c */ TEST_FAIL_NTH(basic_fail_nth, device) { + struct iommu_option cmd = { + .size = sizeof(cmd), + .op = IOMMU_OPTION_OP_SET, + }; struct iommu_hwpt_selftest data = { .iotlb = IOMMU_TEST_IOTLB_DEFAULT, }; @@ -634,6 +638,16 @@ TEST_FAIL_NTH(basic_fail_nth, device) if (self->fd == -1) return -1;

+ cmd.option_id = IOMMU_OPTION_SW_MSI_START; + cmd.val64 = 0x8000000; + if (ioctl(self->fd, IOMMU_OPTION, &cmd)) + return -1; + + cmd.option_id = IOMMU_OPTION_SW_MSI_SIZE; + cmd.val64 = 2; + if (ioctl(self->fd, IOMMU_OPTION, &cmd)) + return -1; + if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) return -1;

As the bridge between iommufd core and vfio core, add a set of msi_iova helpers to call the new msi_iova helpers from the iommufd_device level.

The next patch will use this bridging helpers in vfio-pci code.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/vfio.h | 25 +++++++++++++++++++++++++ drivers/vfio/iommufd.c | 27 +++++++++++++++++++++++++++ 2 files changed, 52 insertions(+)

diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 000a6cab2d31..f38a1e910a2f 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -133,6 +133,12 @@ struct vfio_device_ops {

#if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_ctx *vfio_iommufd_device_ictx(struct vfio_device *vdev); +int vfio_iommufd_device_set_num_msi_iovas(struct vfio_device *vdev, + unsigned int num); +int vfio_iommufd_device_set_msi_iova(struct vfio_device *vdev, + unsigned int index, dma_addr_t iova); +void vfio_iommufd_device_unset_msi_iova(struct vfio_device *vdev, + unsigned int index); int vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx); int vfio_iommufd_physical_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx, u32 *out_device_id); @@ -151,6 +157,25 @@ vfio_iommufd_device_ictx(struct vfio_device *vdev) return NULL; }

+static inline int +vfio_iommufd_device_set_num_msi_iovas(struct vfio_device *vdev, + unsigned int num) +{ + return -EOPNOTSUPP; +} + +static inline int vfio_iommufd_device_set_msi_iova(struct vfio_device *vdev, + unsigned int index, + dma_addr_t iova) +{ + return -EOPNOTSUPP; +} + +static inline void vfio_iommufd_device_unset_msi_iova(struct vfio_device *vdev, + unsigned int index) +{ +} + static inline int vfio_iommufd_get_dev_id(struct vfio_device *vdev, struct iommufd_ctx *ictx) { diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c index 516294fd901b..805efdbccc97 100644 --- a/drivers/vfio/iommufd.c +++ b/drivers/vfio/iommufd.c @@ -69,6 +69,33 @@ struct iommufd_ctx *vfio_iommufd_device_ictx(struct vfio_device *vdev) } EXPORT_SYMBOL_GPL(vfio_iommufd_device_ictx);

+int vfio_iommufd_device_set_num_msi_iovas(struct vfio_device *vdev, + unsigned int num) +{ + if (!vdev->iommufd_device) + return -ENODEV; + return iommufd_device_set_num_msi_iovas(vdev->iommufd_device, num); +} +EXPORT_SYMBOL_GPL(vfio_iommufd_device_set_num_msi_iovas); + +int vfio_iommufd_device_set_msi_iova(struct vfio_device *vdev, + unsigned int index, dma_addr_t iova) +{ + if (!vdev->iommufd_device) + return -ENODEV; + return iommufd_device_set_msi_iova(vdev->iommufd_device, index, iova); +} +EXPORT_SYMBOL_GPL(vfio_iommufd_device_set_msi_iova); + +void vfio_iommufd_device_unset_msi_iova(struct vfio_device *vdev, + unsigned int index) +{ + if (!vdev->iommufd_device) + return; + iommufd_device_unset_msi_iova(vdev->iommufd_device, index); +} +EXPORT_SYMBOL_GPL(vfio_iommufd_device_unset_msi_iova); + static int vfio_iommufd_device_id(struct vfio_device *vdev) { if (vdev->iommufd_device)