From 68cbbc3a9d1fc231810b2490bca73b3b444ef542 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 26 Mar 2015 16:42:09 +1100 Subject: drivers/vfio: Support EEH error injection The patch adds one more EEH sub-command (VFIO_EEH_PE_INJECT_ERR) to inject the specified EEH error, which is represented by (struct vfio_eeh_pe_err), to the indicated PE for testing purpose. Signed-off-by: Gavin Shan Reviewed-by: David Gibson Acked-by: Alex Williamson Signed-off-by: Michael Ellerman --- include/uapi/linux/vfio.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index b57b750c222f..e4fa1995f613 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -470,12 +470,23 @@ struct vfio_iommu_spapr_tce_info { * - unfreeze IO/DMA for frozen PE; * - read PE state; * - reset PE; - * - configure PE. + * - configure PE; + * - inject EEH error. */ +struct vfio_eeh_pe_err { + __u32 type; + __u32 func; + __u64 addr; + __u64 mask; +}; + struct vfio_eeh_pe_op { __u32 argsz; __u32 flags; __u32 op; + union { + struct vfio_eeh_pe_err err; + }; }; #define VFIO_EEH_PE_DISABLE 0 /* Disable EEH functionality */ @@ -492,6 +503,7 @@ struct vfio_eeh_pe_op { #define VFIO_EEH_PE_RESET_HOT 6 /* Assert hot reset */ #define VFIO_EEH_PE_RESET_FUNDAMENTAL 7 /* Assert fundamental reset */ #define VFIO_EEH_PE_CONFIGURE 8 /* PE configuration */ +#define VFIO_EEH_PE_INJECT_ERR 9 /* Inject EEH error */ #define VFIO_EEH_PE_OP _IO(VFIO_TYPE, VFIO_BASE + 21) -- cgit v1.2.3 From 2157e7b82f3b81f57bd80cd67cef09ef26e5f74c Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Fri, 5 Jun 2015 16:35:25 +1000 Subject: vfio: powerpc/spapr: Register memory and define IOMMU v2 The existing implementation accounts the whole DMA window in the locked_vm counter. This is going to be worse with multiple containers and huge DMA windows. Also, real-time accounting would requite additional tracking of accounted pages due to the page size difference - IOMMU uses 4K pages and system uses 4K or 64K pages. Another issue is that actual pages pinning/unpinning happens on every DMA map/unmap request. This does not affect the performance much now as we spend way too much time now on switching context between guest/userspace/host but this will start to matter when we add in-kernel DMA map/unmap acceleration. This introduces a new IOMMU type for SPAPR - VFIO_SPAPR_TCE_v2_IOMMU. New IOMMU deprecates VFIO_IOMMU_ENABLE/VFIO_IOMMU_DISABLE and introduces 2 new ioctls to register/unregister DMA memory - VFIO_IOMMU_SPAPR_REGISTER_MEMORY and VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY - which receive user space address and size of a memory region which needs to be pinned/unpinned and counted in locked_vm. New IOMMU splits physical pages pinning and TCE table update into 2 different operations. It requires: 1) guest pages to be registered first 2) consequent map/unmap requests to work only with pre-registered memory. For the default single window case this means that the entire guest (instead of 2GB) needs to be pinned before using VFIO. When a huge DMA window is added, no additional pinning will be required, otherwise it would be guest RAM + 2GB. The new memory registration ioctls are not supported by VFIO_SPAPR_TCE_IOMMU. Dynamic DMA window and in-kernel acceleration will require memory to be preregistered in order to work. The accounting is done per the user process. This advertises v2 SPAPR TCE IOMMU and restricts what the userspace can do with v1 or v2 IOMMUs. In order to support memory pre-registration, we need a way to track the use of every registered memory region and only allow unregistration if a region is not in use anymore. So we need a way to tell from what region the just cleared TCE was from. This adds a userspace view of the TCE table into iommu_table struct. It contains userspace address, one per TCE entry. The table is only allocated when the ownership over an IOMMU group is taken which means it is only used from outside of the powernv code (such as VFIO). As v2 IOMMU supports IODA2 and pre-IODA2 IOMMUs (which do not support DDW API), this creates a default DMA window for IODA2 for consistency. Signed-off-by: Alexey Kardashevskiy [aw: for the vfio related changes] Acked-by: Alex Williamson Reviewed-by: David Gibson Signed-off-by: Michael Ellerman --- Documentation/vfio.txt | 31 ++- arch/powerpc/include/asm/iommu.h | 6 + drivers/vfio/vfio_iommu_spapr_tce.c | 501 ++++++++++++++++++++++++++++++------ include/uapi/linux/vfio.h | 27 ++ 4 files changed, 482 insertions(+), 83 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt index 4c746a7e717a..dcc37e109c68 100644 --- a/Documentation/vfio.txt +++ b/Documentation/vfio.txt @@ -289,10 +289,12 @@ PPC64 sPAPR implementation note This implementation has some specifics: -1) Only one IOMMU group per container is supported as an IOMMU group -represents the minimal entity which isolation can be guaranteed for and -groups are allocated statically, one per a Partitionable Endpoint (PE) +1) On older systems (POWER7 with P5IOC2/IODA1) only one IOMMU group per +container is supported as an IOMMU table is allocated at the boot time, +one table per a IOMMU group which is a Partitionable Endpoint (PE) (PE is often a PCI domain but not always). +Newer systems (POWER8 with IODA2) have improved hardware design which allows +to remove this limitation and have multiple IOMMU groups per a VFIO container. 2) The hardware supports so called DMA windows - the PCI address range within which DMA transfer is allowed, any attempt to access address space @@ -439,6 +441,29 @@ The code flow from the example above should be slightly changed: .... +5) There is v2 of SPAPR TCE IOMMU. It deprecates VFIO_IOMMU_ENABLE/ +VFIO_IOMMU_DISABLE and implements 2 new ioctls: +VFIO_IOMMU_SPAPR_REGISTER_MEMORY and VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY +(which are unsupported in v1 IOMMU). + +PPC64 paravirtualized guests generate a lot of map/unmap requests, +and the handling of those includes pinning/unpinning pages and updating +mm::locked_vm counter to make sure we do not exceed the rlimit. +The v2 IOMMU splits accounting and pinning into separate operations: + +- VFIO_IOMMU_SPAPR_REGISTER_MEMORY/VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY ioctls +receive a user space address and size of the block to be pinned. +Bisecting is not supported and VFIO_IOMMU_UNREGISTER_MEMORY is expected to +be called with the exact address and size used for registering +the memory block. The userspace is not expected to call these often. +The ranges are stored in a linked list in a VFIO container. + +- VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA ioctls only update the actual +IOMMU table and do not do pinning; instead these check that the userspace +address is from pre-registered range. + +This separation helps in optimizing DMA for guests. + ------------------------------------------------------------------------------- [1] VFIO was originally an acronym for "Virtual Function I/O" in its diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 9d3749287689..f9957eb4c659 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -112,9 +112,15 @@ struct iommu_table { unsigned long *it_map; /* A simple allocation bitmap for now */ unsigned long it_page_shift;/* table iommu page size */ struct list_head it_group_list;/* List of iommu_table_group_link */ + unsigned long *it_userspace; /* userspace view of the table */ struct iommu_table_ops *it_ops; }; +#define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ + ((tbl)->it_userspace ? \ + &((tbl)->it_userspace[(entry) - (tbl)->it_offset]) : \ + NULL) + /* Pure 2^n version of get_order */ static inline __attribute_const__ int get_iommu_order(unsigned long size, struct iommu_table *tbl) diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 203caacf2242..91a32239bd0a 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -19,8 +19,10 @@ #include #include #include +#include #include #include +#include #define DRIVER_VERSION "0.1" #define DRIVER_AUTHOR "aik@ozlabs.ru" @@ -81,6 +83,11 @@ static void decrement_locked_vm(long npages) * into DMA'ble space using the IOMMU */ +struct tce_iommu_group { + struct list_head next; + struct iommu_group *grp; +}; + /* * The container descriptor supports only a single group per container. * Required by the API as the container is not supplied with the IOMMU group @@ -88,11 +95,84 @@ static void decrement_locked_vm(long npages) */ struct tce_container { struct mutex lock; - struct iommu_group *grp; bool enabled; + bool v2; unsigned long locked_pages; + struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES]; + struct list_head group_list; }; +static long tce_iommu_unregister_pages(struct tce_container *container, + __u64 vaddr, __u64 size) +{ + struct mm_iommu_table_group_mem_t *mem; + + if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK)) + return -EINVAL; + + mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT); + if (!mem) + return -ENOENT; + + return mm_iommu_put(mem); +} + +static long tce_iommu_register_pages(struct tce_container *container, + __u64 vaddr, __u64 size) +{ + long ret = 0; + struct mm_iommu_table_group_mem_t *mem = NULL; + unsigned long entries = size >> PAGE_SHIFT; + + if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) || + ((vaddr + size) < vaddr)) + return -EINVAL; + + ret = mm_iommu_get(vaddr, entries, &mem); + if (ret) + return ret; + + container->enabled = true; + + return 0; +} + +static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl) +{ + unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) * + tbl->it_size, PAGE_SIZE); + unsigned long *uas; + long ret; + + BUG_ON(tbl->it_userspace); + + ret = try_increment_locked_vm(cb >> PAGE_SHIFT); + if (ret) + return ret; + + uas = vzalloc(cb); + if (!uas) { + decrement_locked_vm(cb >> PAGE_SHIFT); + return -ENOMEM; + } + tbl->it_userspace = uas; + + return 0; +} + +static void tce_iommu_userspace_view_free(struct iommu_table *tbl) +{ + unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) * + tbl->it_size, PAGE_SIZE); + + if (!tbl->it_userspace) + return; + + vfree(tbl->it_userspace); + tbl->it_userspace = NULL; + decrement_locked_vm(cb >> PAGE_SHIFT); +} + static bool tce_page_is_contained(struct page *page, unsigned page_shift) { /* @@ -103,18 +183,18 @@ static bool tce_page_is_contained(struct page *page, unsigned page_shift) return (PAGE_SHIFT + compound_order(compound_head(page))) >= page_shift; } +static inline bool tce_groups_attached(struct tce_container *container) +{ + return !list_empty(&container->group_list); +} + static long tce_iommu_find_table(struct tce_container *container, phys_addr_t ioba, struct iommu_table **ptbl) { long i; - struct iommu_table_group *table_group; - - table_group = iommu_group_get_iommudata(container->grp); - if (!table_group) - return -1; for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { - struct iommu_table *tbl = table_group->tables[i]; + struct iommu_table *tbl = container->tables[i]; if (tbl) { unsigned long entry = ioba >> tbl->it_page_shift; @@ -136,9 +216,7 @@ static int tce_iommu_enable(struct tce_container *container) int ret = 0; unsigned long locked; struct iommu_table_group *table_group; - - if (!container->grp) - return -ENXIO; + struct tce_iommu_group *tcegrp; if (!current->mm) return -ESRCH; /* process exited */ @@ -175,7 +253,12 @@ static int tce_iommu_enable(struct tce_container *container) * as there is no way to know how much we should increment * the locked_vm counter. */ - table_group = iommu_group_get_iommudata(container->grp); + if (!tce_groups_attached(container)) + return -ENODEV; + + tcegrp = list_first_entry(&container->group_list, + struct tce_iommu_group, next); + table_group = iommu_group_get_iommudata(tcegrp->grp); if (!table_group) return -ENODEV; @@ -211,7 +294,7 @@ static void *tce_iommu_open(unsigned long arg) { struct tce_container *container; - if (arg != VFIO_SPAPR_TCE_IOMMU) { + if ((arg != VFIO_SPAPR_TCE_IOMMU) && (arg != VFIO_SPAPR_TCE_v2_IOMMU)) { pr_err("tce_vfio: Wrong IOMMU type\n"); return ERR_PTR(-EINVAL); } @@ -221,18 +304,45 @@ static void *tce_iommu_open(unsigned long arg) return ERR_PTR(-ENOMEM); mutex_init(&container->lock); + INIT_LIST_HEAD_RCU(&container->group_list); + + container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU; return container; } +static int tce_iommu_clear(struct tce_container *container, + struct iommu_table *tbl, + unsigned long entry, unsigned long pages); +static void tce_iommu_free_table(struct iommu_table *tbl); + static void tce_iommu_release(void *iommu_data) { struct tce_container *container = iommu_data; + struct iommu_table_group *table_group; + struct tce_iommu_group *tcegrp; + long i; - WARN_ON(container->grp); + while (tce_groups_attached(container)) { + tcegrp = list_first_entry(&container->group_list, + struct tce_iommu_group, next); + table_group = iommu_group_get_iommudata(tcegrp->grp); + tce_iommu_detach_group(iommu_data, tcegrp->grp); + } - if (container->grp) - tce_iommu_detach_group(iommu_data, container->grp); + /* + * If VFIO created a table, it was not disposed + * by tce_iommu_detach_group() so do it now. + */ + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + struct iommu_table *tbl = container->tables[i]; + + if (!tbl) + continue; + + tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size); + tce_iommu_free_table(tbl); + } tce_iommu_disable(container); mutex_destroy(&container->lock); @@ -249,6 +359,47 @@ static void tce_iommu_unuse_page(struct tce_container *container, put_page(page); } +static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size, + unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem) +{ + long ret = 0; + struct mm_iommu_table_group_mem_t *mem; + + mem = mm_iommu_lookup(tce, size); + if (!mem) + return -EINVAL; + + ret = mm_iommu_ua_to_hpa(mem, tce, phpa); + if (ret) + return -EINVAL; + + *pmem = mem; + + return 0; +} + +static void tce_iommu_unuse_page_v2(struct iommu_table *tbl, + unsigned long entry) +{ + struct mm_iommu_table_group_mem_t *mem = NULL; + int ret; + unsigned long hpa = 0; + unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + + if (!pua || !current || !current->mm) + return; + + ret = tce_iommu_prereg_ua_to_hpa(*pua, IOMMU_PAGE_SIZE(tbl), + &hpa, &mem); + if (ret) + pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n", + __func__, *pua, entry, ret); + if (mem) + mm_iommu_mapped_dec(mem); + + *pua = 0; +} + static int tce_iommu_clear(struct tce_container *container, struct iommu_table *tbl, unsigned long entry, unsigned long pages) @@ -267,6 +418,11 @@ static int tce_iommu_clear(struct tce_container *container, if (direction == DMA_NONE) continue; + if (container->v2) { + tce_iommu_unuse_page_v2(tbl, entry); + continue; + } + tce_iommu_unuse_page(container, oldhpa); } @@ -333,6 +489,64 @@ static long tce_iommu_build(struct tce_container *container, return ret; } +static long tce_iommu_build_v2(struct tce_container *container, + struct iommu_table *tbl, + unsigned long entry, unsigned long tce, unsigned long pages, + enum dma_data_direction direction) +{ + long i, ret = 0; + struct page *page; + unsigned long hpa; + enum dma_data_direction dirtmp; + + for (i = 0; i < pages; ++i) { + struct mm_iommu_table_group_mem_t *mem = NULL; + unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, + entry + i); + + ret = tce_iommu_prereg_ua_to_hpa(tce, IOMMU_PAGE_SIZE(tbl), + &hpa, &mem); + if (ret) + break; + + page = pfn_to_page(hpa >> PAGE_SHIFT); + if (!tce_page_is_contained(page, tbl->it_page_shift)) { + ret = -EPERM; + break; + } + + /* Preserve offset within IOMMU page */ + hpa |= tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK; + dirtmp = direction; + + /* The registered region is being unregistered */ + if (mm_iommu_mapped_inc(mem)) + break; + + ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp); + if (ret) { + /* dirtmp cannot be DMA_NONE here */ + tce_iommu_unuse_page_v2(tbl, entry + i); + pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n", + __func__, entry << tbl->it_page_shift, + tce, ret); + break; + } + + if (dirtmp != DMA_NONE) + tce_iommu_unuse_page_v2(tbl, entry + i); + + *pua = tce; + + tce += IOMMU_PAGE_SIZE(tbl); + } + + if (ret) + tce_iommu_clear(container, tbl, entry, i); + + return ret; +} + static long tce_iommu_create_table(struct tce_container *container, struct iommu_table_group *table_group, int num, @@ -358,6 +572,12 @@ static long tce_iommu_create_table(struct tce_container *container, WARN_ON(!ret && !(*ptbl)->it_ops->free); WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size)); + if (!ret && container->v2) { + ret = tce_iommu_userspace_view_alloc(*ptbl); + if (ret) + (*ptbl)->it_ops->free(*ptbl); + } + if (ret) decrement_locked_vm(table_size >> PAGE_SHIFT); @@ -368,6 +588,7 @@ static void tce_iommu_free_table(struct iommu_table *tbl) { unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT; + tce_iommu_userspace_view_free(tbl); tbl->it_ops->free(tbl); decrement_locked_vm(pages); } @@ -383,6 +604,7 @@ static long tce_iommu_ioctl(void *iommu_data, case VFIO_CHECK_EXTENSION: switch (arg) { case VFIO_SPAPR_TCE_IOMMU: + case VFIO_SPAPR_TCE_v2_IOMMU: ret = 1; break; default: @@ -394,12 +616,15 @@ static long tce_iommu_ioctl(void *iommu_data, case VFIO_IOMMU_SPAPR_TCE_GET_INFO: { struct vfio_iommu_spapr_tce_info info; + struct tce_iommu_group *tcegrp; struct iommu_table_group *table_group; - if (WARN_ON(!container->grp)) + if (!tce_groups_attached(container)) return -ENXIO; - table_group = iommu_group_get_iommudata(container->grp); + tcegrp = list_first_entry(&container->group_list, + struct tce_iommu_group, next); + table_group = iommu_group_get_iommudata(tcegrp->grp); if (!table_group) return -ENXIO; @@ -468,11 +693,18 @@ static long tce_iommu_ioctl(void *iommu_data, if (ret) return ret; - ret = tce_iommu_build(container, tbl, - param.iova >> tbl->it_page_shift, - param.vaddr, - param.size >> tbl->it_page_shift, - direction); + if (container->v2) + ret = tce_iommu_build_v2(container, tbl, + param.iova >> tbl->it_page_shift, + param.vaddr, + param.size >> tbl->it_page_shift, + direction); + else + ret = tce_iommu_build(container, tbl, + param.iova >> tbl->it_page_shift, + param.vaddr, + param.size >> tbl->it_page_shift, + direction); iommu_flush_tce(tbl); @@ -518,7 +750,62 @@ static long tce_iommu_ioctl(void *iommu_data, return ret; } + case VFIO_IOMMU_SPAPR_REGISTER_MEMORY: { + struct vfio_iommu_spapr_register_memory param; + + if (!container->v2) + break; + + minsz = offsetofend(struct vfio_iommu_spapr_register_memory, + size); + + if (copy_from_user(¶m, (void __user *)arg, minsz)) + return -EFAULT; + + if (param.argsz < minsz) + return -EINVAL; + + /* No flag is supported now */ + if (param.flags) + return -EINVAL; + + mutex_lock(&container->lock); + ret = tce_iommu_register_pages(container, param.vaddr, + param.size); + mutex_unlock(&container->lock); + + return ret; + } + case VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY: { + struct vfio_iommu_spapr_register_memory param; + + if (!container->v2) + break; + + minsz = offsetofend(struct vfio_iommu_spapr_register_memory, + size); + + if (copy_from_user(¶m, (void __user *)arg, minsz)) + return -EFAULT; + + if (param.argsz < minsz) + return -EINVAL; + + /* No flag is supported now */ + if (param.flags) + return -EINVAL; + + mutex_lock(&container->lock); + ret = tce_iommu_unregister_pages(container, param.vaddr, + param.size); + mutex_unlock(&container->lock); + + return ret; + } case VFIO_IOMMU_ENABLE: + if (container->v2) + break; + mutex_lock(&container->lock); ret = tce_iommu_enable(container); mutex_unlock(&container->lock); @@ -526,16 +813,27 @@ static long tce_iommu_ioctl(void *iommu_data, case VFIO_IOMMU_DISABLE: + if (container->v2) + break; + mutex_lock(&container->lock); tce_iommu_disable(container); mutex_unlock(&container->lock); return 0; - case VFIO_EEH_PE_OP: - if (!container->grp) - return -ENODEV; - return vfio_spapr_iommu_eeh_ioctl(container->grp, - cmd, arg); + case VFIO_EEH_PE_OP: { + struct tce_iommu_group *tcegrp; + + ret = 0; + list_for_each_entry(tcegrp, &container->group_list, next) { + ret = vfio_spapr_iommu_eeh_ioctl(tcegrp->grp, + cmd, arg); + if (ret) + return ret; + } + return ret; + } + } return -ENOTTY; @@ -547,14 +845,17 @@ static void tce_iommu_release_ownership(struct tce_container *container, int i; for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { - struct iommu_table *tbl = table_group->tables[i]; + struct iommu_table *tbl = container->tables[i]; if (!tbl) continue; tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size); + tce_iommu_userspace_view_free(tbl); if (tbl->it_map) iommu_release_ownership(tbl); + + container->tables[i] = NULL; } } @@ -569,7 +870,10 @@ static int tce_iommu_take_ownership(struct tce_container *container, if (!tbl || !tbl->it_map) continue; - rc = iommu_take_ownership(tbl); + rc = tce_iommu_userspace_view_alloc(tbl); + if (!rc) + rc = iommu_take_ownership(tbl); + if (rc) { for (j = 0; j < i; ++j) iommu_release_ownership( @@ -579,6 +883,9 @@ static int tce_iommu_take_ownership(struct tce_container *container, } } + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) + container->tables[i] = table_group->tables[i]; + return 0; } @@ -592,18 +899,8 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container, return; } - for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { - /* Store table pointer as unset_window resets it */ - struct iommu_table *tbl = table_group->tables[i]; - - if (!tbl) - continue; - + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) table_group->ops->unset_window(table_group, i); - tce_iommu_clear(container, tbl, - tbl->it_offset, tbl->it_size); - tce_iommu_free_table(tbl); - } table_group->ops->release_ownership(table_group); } @@ -611,7 +908,7 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container, static long tce_iommu_take_ownership_ddw(struct tce_container *container, struct iommu_table_group *table_group) { - long ret; + long i, ret = 0; struct iommu_table *tbl = NULL; if (!table_group->ops->create_table || !table_group->ops->set_window || @@ -622,23 +919,45 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container, table_group->ops->take_ownership(table_group); - ret = tce_iommu_create_table(container, - table_group, - 0, /* window number */ - IOMMU_PAGE_SHIFT_4K, - table_group->tce32_size, - 1, /* default levels */ - &tbl); - if (!ret) { - ret = table_group->ops->set_window(table_group, 0, tbl); + /* + * If it the first group attached, check if there is + * a default DMA window and create one if none as + * the userspace expects it to exist. + */ + if (!tce_groups_attached(container) && !container->tables[0]) { + ret = tce_iommu_create_table(container, + table_group, + 0, /* window number */ + IOMMU_PAGE_SHIFT_4K, + table_group->tce32_size, + 1, /* default levels */ + &tbl); if (ret) - tce_iommu_free_table(tbl); + goto release_exit; else - table_group->tables[0] = tbl; + container->tables[0] = tbl; } - if (ret) - table_group->ops->release_ownership(table_group); + /* Set all windows to the new group */ + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + tbl = container->tables[i]; + + if (!tbl) + continue; + + /* Set the default window to a new group */ + ret = table_group->ops->set_window(table_group, i, tbl); + if (ret) + goto release_exit; + } + + return 0; + +release_exit: + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) + table_group->ops->unset_window(table_group, i); + + table_group->ops->release_ownership(table_group); return ret; } @@ -649,29 +968,44 @@ static int tce_iommu_attach_group(void *iommu_data, int ret; struct tce_container *container = iommu_data; struct iommu_table_group *table_group; + struct tce_iommu_group *tcegrp = NULL; mutex_lock(&container->lock); /* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n", iommu_group_id(iommu_group), iommu_group); */ - if (container->grp) { - pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n", - iommu_group_id(container->grp), - iommu_group_id(iommu_group)); + table_group = iommu_group_get_iommudata(iommu_group); + + if (tce_groups_attached(container) && (!table_group->ops || + !table_group->ops->take_ownership || + !table_group->ops->release_ownership)) { ret = -EBUSY; goto unlock_exit; } - if (container->enabled) { - pr_err("tce_vfio: attaching group #%u to enabled container\n", - iommu_group_id(iommu_group)); - ret = -EBUSY; - goto unlock_exit; + /* Check if new group has the same iommu_ops (i.e. compatible) */ + list_for_each_entry(tcegrp, &container->group_list, next) { + struct iommu_table_group *table_group_tmp; + + if (tcegrp->grp == iommu_group) { + pr_warn("tce_vfio: Group %d is already attached\n", + iommu_group_id(iommu_group)); + ret = -EBUSY; + goto unlock_exit; + } + table_group_tmp = iommu_group_get_iommudata(tcegrp->grp); + if (table_group_tmp->ops != table_group->ops) { + pr_warn("tce_vfio: Group %d is incompatible with group %d\n", + iommu_group_id(iommu_group), + iommu_group_id(tcegrp->grp)); + ret = -EPERM; + goto unlock_exit; + } } - table_group = iommu_group_get_iommudata(iommu_group); - if (!table_group) { - ret = -ENXIO; + tcegrp = kzalloc(sizeof(*tcegrp), GFP_KERNEL); + if (!tcegrp) { + ret = -ENOMEM; goto unlock_exit; } @@ -681,10 +1015,15 @@ static int tce_iommu_attach_group(void *iommu_data, else ret = tce_iommu_take_ownership_ddw(container, table_group); - if (!ret) - container->grp = iommu_group; + if (!ret) { + tcegrp->grp = iommu_group; + list_add(&tcegrp->next, &container->group_list); + } unlock_exit: + if (ret && tcegrp) + kfree(tcegrp); + mutex_unlock(&container->lock); return ret; @@ -695,24 +1034,26 @@ static void tce_iommu_detach_group(void *iommu_data, { struct tce_container *container = iommu_data; struct iommu_table_group *table_group; + bool found = false; + struct tce_iommu_group *tcegrp; mutex_lock(&container->lock); - if (iommu_group != container->grp) { - pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n", - iommu_group_id(iommu_group), - iommu_group_id(container->grp)); - goto unlock_exit; + + list_for_each_entry(tcegrp, &container->group_list, next) { + if (tcegrp->grp == iommu_group) { + found = true; + break; + } } - if (container->enabled) { - pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n", - iommu_group_id(container->grp)); - tce_iommu_disable(container); + if (!found) { + pr_warn("tce_vfio: detaching unattached group #%u\n", + iommu_group_id(iommu_group)); + goto unlock_exit; } - /* pr_debug("tce_vfio: detaching group #%u from iommu %p\n", - iommu_group_id(iommu_group), iommu_group); */ - container->grp = NULL; + list_del(&tcegrp->next); + kfree(tcegrp); table_group = iommu_group_get_iommudata(iommu_group); BUG_ON(!table_group); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index e4fa1995f613..fa84391a0d00 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -36,6 +36,8 @@ /* Two-stage IOMMU */ #define VFIO_TYPE1_NESTING_IOMMU 6 /* Implies v2 */ +#define VFIO_SPAPR_TCE_v2_IOMMU 7 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between @@ -507,6 +509,31 @@ struct vfio_eeh_pe_op { #define VFIO_EEH_PE_OP _IO(VFIO_TYPE, VFIO_BASE + 21) +/** + * VFIO_IOMMU_SPAPR_REGISTER_MEMORY - _IOW(VFIO_TYPE, VFIO_BASE + 17, struct vfio_iommu_spapr_register_memory) + * + * Registers user space memory where DMA is allowed. It pins + * user pages and does the locked memory accounting so + * subsequent VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA calls + * get faster. + */ +struct vfio_iommu_spapr_register_memory { + __u32 argsz; + __u32 flags; + __u64 vaddr; /* Process virtual address */ + __u64 size; /* Size of mapping (bytes) */ +}; +#define VFIO_IOMMU_SPAPR_REGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 17) + +/** + * VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY - _IOW(VFIO_TYPE, VFIO_BASE + 18, struct vfio_iommu_spapr_register_memory) + * + * Unregisters user space memory registered with + * VFIO_IOMMU_SPAPR_REGISTER_MEMORY. + * Uses vfio_iommu_spapr_register_memory for parameters. + */ +#define VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 18) + /* ***************************************************************** */ #endif /* _UAPIVFIO_H */ -- cgit v1.2.3 From e633bc86a922468a82300eef5b9802e17be5e23d Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Fri, 5 Jun 2015 16:35:26 +1000 Subject: vfio: powerpc/spapr: Support Dynamic DMA windows This adds create/remove window ioctls to create and remove DMA windows. sPAPR defines a Dynamic DMA windows capability which allows para-virtualized guests to create additional DMA windows on a PCI bus. The existing linux kernels use this new window to map the entire guest memory and switch to the direct DMA operations saving time on map/unmap requests which would normally happen in a big amounts. This adds 2 ioctl handlers - VFIO_IOMMU_SPAPR_TCE_CREATE and VFIO_IOMMU_SPAPR_TCE_REMOVE - to create and remove windows. Up to 2 windows are supported now by the hardware and by this driver. This changes VFIO_IOMMU_SPAPR_TCE_GET_INFO handler to return additional information such as a number of supported windows and maximum number levels of TCE tables. DDW is added as a capability, not as a SPAPR TCE IOMMU v2 unique feature as we still want to support v2 on platforms which cannot do DDW for the sake of TCE acceleration in KVM (coming soon). Signed-off-by: Alexey Kardashevskiy [aw: for the vfio related changes] Acked-by: Alex Williamson Reviewed-by: David Gibson Signed-off-by: Michael Ellerman --- Documentation/vfio.txt | 19 ++++ arch/powerpc/include/asm/iommu.h | 2 +- drivers/vfio/vfio_iommu_spapr_tce.c | 196 +++++++++++++++++++++++++++++++++++- include/uapi/linux/vfio.h | 61 ++++++++++- 4 files changed, 273 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt index dcc37e109c68..1dd3fddfd3a1 100644 --- a/Documentation/vfio.txt +++ b/Documentation/vfio.txt @@ -464,6 +464,25 @@ address is from pre-registered range. This separation helps in optimizing DMA for guests. +6) sPAPR specification allows guests to have an additional DMA window(s) on +a PCI bus with a variable page size. Two ioctls have been added to support +this: VFIO_IOMMU_SPAPR_TCE_CREATE and VFIO_IOMMU_SPAPR_TCE_REMOVE. +The platform has to support the functionality or error will be returned to +the userspace. The existing hardware supports up to 2 DMA windows, one is +2GB long, uses 4K pages and called "default 32bit window"; the other can +be as big as entire RAM, use different page size, it is optional - guests +create those in run-time if the guest driver supports 64bit DMA. + +VFIO_IOMMU_SPAPR_TCE_CREATE receives a page shift, a DMA window size and +a number of TCE table levels (if a TCE table is going to be big enough and +the kernel may not be able to allocate enough of physically contiguous memory). +It creates a new window in the available slot and returns the bus address where +the new window starts. Due to hardware limitation, the user space cannot choose +the location of DMA windows. + +VFIO_IOMMU_SPAPR_TCE_REMOVE receives the bus start address of the window +and removes it. + ------------------------------------------------------------------------------- [1] VFIO was originally an acronym for "Virtual Function I/O" in its diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f9957eb4c659..ca18cff90900 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -149,7 +149,7 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); */ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, int nid); -#define IOMMU_TABLE_GROUP_MAX_TABLES 1 +#define IOMMU_TABLE_GROUP_MAX_TABLES 2 struct iommu_table_group; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 91a32239bd0a..0582b72ef377 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -211,6 +211,18 @@ static long tce_iommu_find_table(struct tce_container *container, return -1; } +static int tce_iommu_find_free_table(struct tce_container *container) +{ + int i; + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + if (!container->tables[i]) + return i; + } + + return -ENOSPC; +} + static int tce_iommu_enable(struct tce_container *container) { int ret = 0; @@ -593,11 +605,115 @@ static void tce_iommu_free_table(struct iommu_table *tbl) decrement_locked_vm(pages); } +static long tce_iommu_create_window(struct tce_container *container, + __u32 page_shift, __u64 window_size, __u32 levels, + __u64 *start_addr) +{ + struct tce_iommu_group *tcegrp; + struct iommu_table_group *table_group; + struct iommu_table *tbl = NULL; + long ret, num; + + num = tce_iommu_find_free_table(container); + if (num < 0) + return num; + + /* Get the first group for ops::create_table */ + tcegrp = list_first_entry(&container->group_list, + struct tce_iommu_group, next); + table_group = iommu_group_get_iommudata(tcegrp->grp); + if (!table_group) + return -EFAULT; + + if (!(table_group->pgsizes & (1ULL << page_shift))) + return -EINVAL; + + if (!table_group->ops->set_window || !table_group->ops->unset_window || + !table_group->ops->get_table_size || + !table_group->ops->create_table) + return -EPERM; + + /* Create TCE table */ + ret = tce_iommu_create_table(container, table_group, num, + page_shift, window_size, levels, &tbl); + if (ret) + return ret; + + BUG_ON(!tbl->it_ops->free); + + /* + * Program the table to every group. + * Groups have been tested for compatibility at the attach time. + */ + list_for_each_entry(tcegrp, &container->group_list, next) { + table_group = iommu_group_get_iommudata(tcegrp->grp); + + ret = table_group->ops->set_window(table_group, num, tbl); + if (ret) + goto unset_exit; + } + + container->tables[num] = tbl; + + /* Return start address assigned by platform in create_table() */ + *start_addr = tbl->it_offset << tbl->it_page_shift; + + return 0; + +unset_exit: + list_for_each_entry(tcegrp, &container->group_list, next) { + table_group = iommu_group_get_iommudata(tcegrp->grp); + table_group->ops->unset_window(table_group, num); + } + tce_iommu_free_table(tbl); + + return ret; +} + +static long tce_iommu_remove_window(struct tce_container *container, + __u64 start_addr) +{ + struct iommu_table_group *table_group = NULL; + struct iommu_table *tbl; + struct tce_iommu_group *tcegrp; + int num; + + num = tce_iommu_find_table(container, start_addr, &tbl); + if (num < 0) + return -EINVAL; + + BUG_ON(!tbl->it_size); + + /* Detach groups from IOMMUs */ + list_for_each_entry(tcegrp, &container->group_list, next) { + table_group = iommu_group_get_iommudata(tcegrp->grp); + + /* + * SPAPR TCE IOMMU exposes the default DMA window to + * the guest via dma32_window_start/size of + * VFIO_IOMMU_SPAPR_TCE_GET_INFO. Some platforms allow + * the userspace to remove this window, some do not so + * here we check for the platform capability. + */ + if (!table_group->ops || !table_group->ops->unset_window) + return -EPERM; + + table_group->ops->unset_window(table_group, num); + } + + /* Free table */ + tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size); + tce_iommu_free_table(tbl); + container->tables[num] = NULL; + + return 0; +} + static long tce_iommu_ioctl(void *iommu_data, unsigned int cmd, unsigned long arg) { struct tce_container *container = iommu_data; - unsigned long minsz; + unsigned long minsz, ddwsz; long ret; switch (cmd) { @@ -641,6 +757,21 @@ static long tce_iommu_ioctl(void *iommu_data, info.dma32_window_start = table_group->tce32_start; info.dma32_window_size = table_group->tce32_size; info.flags = 0; + memset(&info.ddw, 0, sizeof(info.ddw)); + + if (table_group->max_dynamic_windows_supported && + container->v2) { + info.flags |= VFIO_IOMMU_SPAPR_INFO_DDW; + info.ddw.pgsizes = table_group->pgsizes; + info.ddw.max_dynamic_windows_supported = + table_group->max_dynamic_windows_supported; + info.ddw.levels = table_group->max_levels; + } + + ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info, ddw); + + if (info.argsz >= ddwsz) + minsz = ddwsz; if (copy_to_user((void __user *)arg, &info, minsz)) return -EFAULT; @@ -834,6 +965,69 @@ static long tce_iommu_ioctl(void *iommu_data, return ret; } + case VFIO_IOMMU_SPAPR_TCE_CREATE: { + struct vfio_iommu_spapr_tce_create create; + + if (!container->v2) + break; + + if (!tce_groups_attached(container)) + return -ENXIO; + + minsz = offsetofend(struct vfio_iommu_spapr_tce_create, + start_addr); + + if (copy_from_user(&create, (void __user *)arg, minsz)) + return -EFAULT; + + if (create.argsz < minsz) + return -EINVAL; + + if (create.flags) + return -EINVAL; + + mutex_lock(&container->lock); + + ret = tce_iommu_create_window(container, create.page_shift, + create.window_size, create.levels, + &create.start_addr); + + mutex_unlock(&container->lock); + + if (!ret && copy_to_user((void __user *)arg, &create, minsz)) + ret = -EFAULT; + + return ret; + } + case VFIO_IOMMU_SPAPR_TCE_REMOVE: { + struct vfio_iommu_spapr_tce_remove remove; + + if (!container->v2) + break; + + if (!tce_groups_attached(container)) + return -ENXIO; + + minsz = offsetofend(struct vfio_iommu_spapr_tce_remove, + start_addr); + + if (copy_from_user(&remove, (void __user *)arg, minsz)) + return -EFAULT; + + if (remove.argsz < minsz) + return -EINVAL; + + if (remove.flags) + return -EINVAL; + + mutex_lock(&container->lock); + + ret = tce_iommu_remove_window(container, remove.start_addr); + + mutex_unlock(&container->lock); + + return ret; + } } return -ENOTTY; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index fa84391a0d00..9fd7b5d8df2f 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -444,6 +444,23 @@ struct vfio_iommu_type1_dma_unmap { /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */ +/* + * The SPAPR TCE DDW info struct provides the information about + * the details of Dynamic DMA window capability. + * + * @pgsizes contains a page size bitmask, 4K/64K/16M are supported. + * @max_dynamic_windows_supported tells the maximum number of windows + * which the platform can create. + * @levels tells the maximum number of levels in multi-level IOMMU tables; + * this allows splitting a table into smaller chunks which reduces + * the amount of physically contiguous memory required for the table. + */ +struct vfio_iommu_spapr_tce_ddw_info { + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 levels; +}; + /* * The SPAPR TCE info struct provides the information about the PCI bus * address ranges available for DMA, these values are programmed into @@ -454,14 +471,17 @@ struct vfio_iommu_type1_dma_unmap { * addresses too so the window works as a filter rather than an offset * for IOVA addresses. * - * A flag will need to be added if other page sizes are supported, - * so as defined here, it is always 4k. + * Flags supported: + * - VFIO_IOMMU_SPAPR_INFO_DDW: informs the userspace that dynamic DMA windows + * (DDW) support is present. @ddw is only supported when DDW is present. */ struct vfio_iommu_spapr_tce_info { __u32 argsz; - __u32 flags; /* reserved for future use */ + __u32 flags; +#define VFIO_IOMMU_SPAPR_INFO_DDW (1 << 0) /* DDW supported */ __u32 dma32_window_start; /* 32 bit window start (bytes) */ __u32 dma32_window_size; /* 32 bit window size (bytes) */ + struct vfio_iommu_spapr_tce_ddw_info ddw; }; #define VFIO_IOMMU_SPAPR_TCE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) @@ -534,6 +554,41 @@ struct vfio_iommu_spapr_register_memory { */ #define VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 18) +/** + * VFIO_IOMMU_SPAPR_TCE_CREATE - _IOWR(VFIO_TYPE, VFIO_BASE + 19, struct vfio_iommu_spapr_tce_create) + * + * Creates an additional TCE table and programs it (sets a new DMA window) + * to every IOMMU group in the container. It receives page shift, window + * size and number of levels in the TCE table being created. + * + * It allocates and returns an offset on a PCI bus of the new DMA window. + */ +struct vfio_iommu_spapr_tce_create { + __u32 argsz; + __u32 flags; + /* in */ + __u32 page_shift; + __u64 window_size; + __u32 levels; + /* out */ + __u64 start_addr; +}; +#define VFIO_IOMMU_SPAPR_TCE_CREATE _IO(VFIO_TYPE, VFIO_BASE + 19) + +/** + * VFIO_IOMMU_SPAPR_TCE_REMOVE - _IOW(VFIO_TYPE, VFIO_BASE + 20, struct vfio_iommu_spapr_tce_remove) + * + * Unprograms a TCE table from all groups in the container and destroys it. + * It receives a PCI bus offset as a window id. + */ +struct vfio_iommu_spapr_tce_remove { + __u32 argsz; + __u32 flags; + /* in */ + __u64 start_addr; +}; +#define VFIO_IOMMU_SPAPR_TCE_REMOVE _IO(VFIO_TYPE, VFIO_BASE + 20) + /* ***************************************************************** */ #endif /* _UAPIVFIO_H */ -- cgit v1.2.3