diff options
Diffstat (limited to 'drivers/vfio')
| -rw-r--r-- | drivers/vfio/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/vfio/vfio_iommu_spapr_tce.c | 1101 | ||||
| -rw-r--r-- | drivers/vfio/vfio_spapr_eeh.c | 10 |
3 files changed, 1011 insertions, 102 deletions
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 7d092ddc8119..454017928ed0 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -21,7 +21,7 @@ config VFIO_VIRQFD menuconfig VFIO tristate "VFIO Non-Privileged userspace driver framework" depends on IOMMU_API - select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU) + select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU || ARM_SMMU_V3) select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES) select VFIO_SPAPR_EEH if (PPC_POWERNV || PPC_PSERIES) select ANON_INODES diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 730b4ef3e0cc..0582b72ef377 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -19,8 +19,10 @@ #include <linux/uaccess.h> #include <linux/err.h> #include <linux/vfio.h> +#include <linux/vmalloc.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/mmu_context.h> #define DRIVER_VERSION "0.1" #define DRIVER_AUTHOR "aik@ozlabs.ru" @@ -29,6 +31,51 @@ static void tce_iommu_detach_group(void *iommu_data, struct iommu_group *iommu_group); +static long try_increment_locked_vm(long npages) +{ + long ret = 0, locked, lock_limit; + + if (!current || !current->mm) + return -ESRCH; /* process exited */ + + if (!npages) + return 0; + + down_write(¤t->mm->mmap_sem); + locked = current->mm->locked_vm + npages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + ret = -ENOMEM; + else + current->mm->locked_vm += npages; + + pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid, + npages << PAGE_SHIFT, + current->mm->locked_vm << PAGE_SHIFT, + rlimit(RLIMIT_MEMLOCK), + ret ? " - exceeded" : ""); + + up_write(¤t->mm->mmap_sem); + + return ret; +} + +static void decrement_locked_vm(long npages) +{ + if (!current || !current->mm || !npages) + return; /* process exited */ + + down_write(¤t->mm->mmap_sem); + if (WARN_ON_ONCE(npages > current->mm->locked_vm)) + npages = current->mm->locked_vm; + current->mm->locked_vm -= npages; + pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid, + npages << PAGE_SHIFT, + current->mm->locked_vm << PAGE_SHIFT, + rlimit(RLIMIT_MEMLOCK)); + up_write(¤t->mm->mmap_sem); +} + /* * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation * @@ -36,6 +83,11 @@ static void tce_iommu_detach_group(void *iommu_data, * 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 @@ -43,18 +95,140 @@ static void tce_iommu_detach_group(void *iommu_data, */ struct tce_container { struct mutex lock; - struct iommu_table *tbl; 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) +{ + /* + * Check that the TCE table granularity is not bigger than the size of + * a page we just found. Otherwise the hardware can get access to + * a bigger memory chunk that it should. + */ + 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; + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + struct iommu_table *tbl = container->tables[i]; + + if (tbl) { + unsigned long entry = ioba >> tbl->it_page_shift; + unsigned long start = tbl->it_offset; + unsigned long end = start + tbl->it_size; + + if ((start <= entry) && (entry < end)) { + *ptbl = tbl; + return i; + } + } + } + + 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; - unsigned long locked, lock_limit, npages; - struct iommu_table *tbl = container->tbl; - - if (!container->tbl) - return -ENXIO; + unsigned long locked; + struct iommu_table_group *table_group; + struct tce_iommu_group *tcegrp; if (!current->mm) return -ESRCH; /* process exited */ @@ -79,21 +253,38 @@ static int tce_iommu_enable(struct tce_container *container) * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits, * that would effectively kill the guest at random points, much better * enforcing the limit based on the max that the guest can map. + * + * Unfortunately at the moment it counts whole tables, no matter how + * much memory the guest has. I.e. for 4GB guest and 4 IOMMU groups + * each with 2GB DMA window, 8GB will be counted here. The reason for + * this is that we cannot tell here the amount of RAM used by the guest + * as this information is only available from KVM and VFIO is + * KVM agnostic. + * + * So we do not allow enabling a container without a group attached + * as there is no way to know how much we should increment + * the locked_vm counter. */ - down_write(¤t->mm->mmap_sem); - npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT; - locked = current->mm->locked_vm + npages; - lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { - pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n", - rlimit(RLIMIT_MEMLOCK)); - ret = -ENOMEM; - } else { + if (!tce_groups_attached(container)) + return -ENODEV; - current->mm->locked_vm += npages; - container->enabled = true; - } - up_write(¤t->mm->mmap_sem); + 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; + + if (!table_group->tce32_size) + return -EPERM; + + locked = table_group->tce32_size >> PAGE_SHIFT; + ret = try_increment_locked_vm(locked); + if (ret) + return ret; + + container->locked_pages = locked; + + container->enabled = true; return ret; } @@ -105,20 +296,17 @@ static void tce_iommu_disable(struct tce_container *container) container->enabled = false; - if (!container->tbl || !current->mm) + if (!current->mm) return; - down_write(¤t->mm->mmap_sem); - current->mm->locked_vm -= (container->tbl->it_size << - IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT; - up_write(¤t->mm->mmap_sem); + decrement_locked_vm(container->locked_pages); } 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); } @@ -128,36 +316,411 @@ 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; + + 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); + } - WARN_ON(container->tbl && !container->tbl->it_group); - tce_iommu_disable(container); + /* + * 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; - if (container->tbl && container->tbl->it_group) - tce_iommu_detach_group(iommu_data, container->tbl->it_group); + tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size); + tce_iommu_free_table(tbl); + } + tce_iommu_disable(container); mutex_destroy(&container->lock); kfree(container); } +static void tce_iommu_unuse_page(struct tce_container *container, + unsigned long hpa) +{ + struct page *page; + + page = pfn_to_page(hpa >> PAGE_SHIFT); + 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) +{ + unsigned long oldhpa; + long ret; + enum dma_data_direction direction; + + for ( ; pages; --pages, ++entry) { + direction = DMA_NONE; + oldhpa = 0; + ret = iommu_tce_xchg(tbl, entry, &oldhpa, &direction); + if (ret) + continue; + + if (direction == DMA_NONE) + continue; + + if (container->v2) { + tce_iommu_unuse_page_v2(tbl, entry); + continue; + } + + tce_iommu_unuse_page(container, oldhpa); + } + + return 0; +} + +static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa) +{ + struct page *page = NULL; + enum dma_data_direction direction = iommu_tce_direction(tce); + + if (get_user_pages_fast(tce & PAGE_MASK, 1, + direction != DMA_TO_DEVICE, &page) != 1) + return -EFAULT; + + *hpa = __pa((unsigned long) page_address(page)); + + return 0; +} + +static long tce_iommu_build(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) { + unsigned long offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK; + + ret = tce_iommu_use_page(tce, &hpa); + if (ret) + break; + + page = pfn_to_page(hpa >> PAGE_SHIFT); + if (!tce_page_is_contained(page, tbl->it_page_shift)) { + ret = -EPERM; + break; + } + + hpa |= offset; + dirtmp = direction; + ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp); + if (ret) { + tce_iommu_unuse_page(container, hpa); + 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(container, hpa); + + tce += IOMMU_PAGE_SIZE(tbl); + } + + if (ret) + tce_iommu_clear(container, tbl, entry, i); + + 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, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table **ptbl) +{ + long ret, table_size; + + table_size = table_group->ops->get_table_size(page_shift, window_size, + levels); + if (!table_size) + return -EINVAL; + + ret = try_increment_locked_vm(table_size >> PAGE_SHIFT); + if (ret) + return ret; + + ret = table_group->ops->create_table(table_group, num, + page_shift, window_size, levels, ptbl); + + 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); + + return ret; +} + +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); +} + +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) { case VFIO_CHECK_EXTENSION: switch (arg) { case VFIO_SPAPR_TCE_IOMMU: + case VFIO_SPAPR_TCE_v2_IOMMU: ret = 1; break; default: @@ -169,9 +732,17 @@ static long tce_iommu_ioctl(void *iommu_data, case VFIO_IOMMU_SPAPR_TCE_GET_INFO: { struct vfio_iommu_spapr_tce_info info; - struct iommu_table *tbl = container->tbl; + struct tce_iommu_group *tcegrp; + struct iommu_table_group *table_group; + + if (!tce_groups_attached(container)) + return -ENXIO; + + tcegrp = list_first_entry(&container->group_list, + struct tce_iommu_group, next); + table_group = iommu_group_get_iommudata(tcegrp->grp); - if (WARN_ON(!tbl)) + if (!table_group) return -ENXIO; minsz = offsetofend(struct vfio_iommu_spapr_tce_info, @@ -183,9 +754,24 @@ static long tce_iommu_ioctl(void *iommu_data, if (info.argsz < minsz) return -EINVAL; - info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K; - info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K; + 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; @@ -194,13 +780,12 @@ static long tce_iommu_ioctl(void *iommu_data, } case VFIO_IOMMU_MAP_DMA: { struct vfio_iommu_type1_dma_map param; - struct iommu_table *tbl = container->tbl; - unsigned long tce, i; + struct iommu_table *tbl = NULL; + long num; + enum dma_data_direction direction; - if (!tbl) - return -ENXIO; - - BUG_ON(!tbl->it_group); + if (!container->enabled) + return -EPERM; minsz = offsetofend(struct vfio_iommu_type1_dma_map, size); @@ -214,32 +799,43 @@ static long tce_iommu_ioctl(void *iommu_data, VFIO_DMA_MAP_FLAG_WRITE)) return -EINVAL; - if ((param.size & ~IOMMU_PAGE_MASK_4K) || - (param.vaddr & ~IOMMU_PAGE_MASK_4K)) + num = tce_iommu_find_table(container, param.iova, &tbl); + if (num < 0) + return -ENXIO; + + if ((param.size & ~IOMMU_PAGE_MASK(tbl)) || + (param.vaddr & ~IOMMU_PAGE_MASK(tbl))) return -EINVAL; /* iova is checked by the IOMMU API */ - tce = param.vaddr; - if (param.flags & VFIO_DMA_MAP_FLAG_READ) - tce |= TCE_PCI_READ; - if (param.flags & VFIO_DMA_MAP_FLAG_WRITE) - tce |= TCE_PCI_WRITE; + if (param.flags & VFIO_DMA_MAP_FLAG_READ) { + if (param.flags & VFIO_DMA_MAP_FLAG_WRITE) + direction = DMA_BIDIRECTIONAL; + else + direction = DMA_TO_DEVICE; + } else { + if (param.flags & VFIO_DMA_MAP_FLAG_WRITE) + direction = DMA_FROM_DEVICE; + else + return -EINVAL; + } - ret = iommu_tce_put_param_check(tbl, param.iova, tce); + ret = iommu_tce_put_param_check(tbl, param.iova, param.vaddr); if (ret) return ret; - for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) { - ret = iommu_put_tce_user_mode(tbl, - (param.iova >> IOMMU_PAGE_SHIFT_4K) + i, - tce); - if (ret) - break; - tce += IOMMU_PAGE_SIZE_4K; - } - if (ret) - iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT_4K, i); + 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); @@ -247,10 +843,11 @@ static long tce_iommu_ioctl(void *iommu_data, } case VFIO_IOMMU_UNMAP_DMA: { struct vfio_iommu_type1_dma_unmap param; - struct iommu_table *tbl = container->tbl; + struct iommu_table *tbl = NULL; + long num; - if (WARN_ON(!tbl)) - return -ENXIO; + if (!container->enabled) + return -EPERM; minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); @@ -265,22 +862,81 @@ static long tce_iommu_ioctl(void *iommu_data, if (param.flags) return -EINVAL; - if (param.size & ~IOMMU_PAGE_MASK_4K) + num = tce_iommu_find_table(container, param.iova, &tbl); + if (num < 0) + return -ENXIO; + + if (param.size & ~IOMMU_PAGE_MASK(tbl)) return -EINVAL; ret = iommu_tce_clear_param_check(tbl, param.iova, 0, - param.size >> IOMMU_PAGE_SHIFT_4K); + param.size >> tbl->it_page_shift); if (ret) return ret; - ret = iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT_4K, - param.size >> IOMMU_PAGE_SHIFT_4K); + ret = tce_iommu_clear(container, tbl, + param.iova >> tbl->it_page_shift, + param.size >> tbl->it_page_shift); iommu_flush_tce(tbl); 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); @@ -288,48 +944,280 @@ 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->tbl || !container->tbl->it_group) - return -ENODEV; - return vfio_spapr_iommu_eeh_ioctl(container->tbl->it_group, - 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; + } + + 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; } +static void tce_iommu_release_ownership(struct tce_container *container, + struct iommu_table_group *table_group) +{ + int i; + + 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_userspace_view_free(tbl); + if (tbl->it_map) + iommu_release_ownership(tbl); + + container->tables[i] = NULL; + } +} + +static int tce_iommu_take_ownership(struct tce_container *container, + struct iommu_table_group *table_group) +{ + int i, j, rc = 0; + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + struct iommu_table *tbl = table_group->tables[i]; + + if (!tbl || !tbl->it_map) + continue; + + 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( + table_group->tables[j]); + + return rc; + } + } + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) + container->tables[i] = table_group->tables[i]; + + return 0; +} + +static void tce_iommu_release_ownership_ddw(struct tce_container *container, + struct iommu_table_group *table_group) +{ + long i; + + if (!table_group->ops->unset_window) { + WARN_ON_ONCE(1); + return; + } + + 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); +} + +static long tce_iommu_take_ownership_ddw(struct tce_container *container, + struct iommu_table_group *table_group) +{ + long i, ret = 0; + struct iommu_table *tbl = NULL; + + if (!table_group->ops->create_table || !table_group->ops->set_window || + !table_group->ops->release_ownership) { + WARN_ON_ONCE(1); + return -EFAULT; + } + + table_group->ops->take_ownership(table_group); + + /* + * 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) + goto release_exit; + else + container->tables[0] = tbl; + } + + /* 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; +} + static int tce_iommu_attach_group(void *iommu_data, struct iommu_group *iommu_group) { int ret; struct tce_container *container = iommu_data; - struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group); + struct iommu_table_group *table_group; + struct tce_iommu_group *tcegrp = NULL; - BUG_ON(!tbl); mutex_lock(&container->lock); /* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n", iommu_group_id(iommu_group), iommu_group); */ - if (container->tbl) { - pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n", - iommu_group_id(container->tbl->it_group), - iommu_group_id(iommu_group)); - ret = -EBUSY; - } else if (container->enabled) { - pr_err("tce_vfio: attaching group #%u to enabled container\n", - 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; - } else { - ret = iommu_take_ownership(tbl); - if (!ret) - container->tbl = tbl; + 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; + } + } + + tcegrp = kzalloc(sizeof(*tcegrp), GFP_KERNEL); + if (!tcegrp) { + ret = -ENOMEM; + goto unlock_exit; } + if (!table_group->ops || !table_group->ops->take_ownership || + !table_group->ops->release_ownership) + ret = tce_iommu_take_ownership(container, table_group); + else + ret = tce_iommu_take_ownership_ddw(container, table_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; @@ -339,26 +1227,37 @@ static void tce_iommu_detach_group(void *iommu_data, struct iommu_group *iommu_group) { struct tce_container *container = iommu_data; - struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group); + struct iommu_table_group *table_group; + bool found = false; + struct tce_iommu_group *tcegrp; - BUG_ON(!tbl); mutex_lock(&container->lock); - if (tbl != container->tbl) { - pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n", - iommu_group_id(iommu_group), - iommu_group_id(tbl->it_group)); - } else { - if (container->enabled) { - pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n", - iommu_group_id(tbl->it_group)); - tce_iommu_disable(container); + + list_for_each_entry(tcegrp, &container->group_list, next) { + if (tcegrp->grp == iommu_group) { + found = true; + break; } + } - /* pr_debug("tce_vfio: detaching group #%u from iommu %p\n", - iommu_group_id(iommu_group), iommu_group); */ - container->tbl = NULL; - iommu_release_ownership(tbl); + if (!found) { + pr_warn("tce_vfio: detaching unattached group #%u\n", + iommu_group_id(iommu_group)); + goto unlock_exit; } + + list_del(&tcegrp->next); + kfree(tcegrp); + + table_group = iommu_group_get_iommudata(iommu_group); + BUG_ON(!table_group); + + if (!table_group->ops || !table_group->ops->release_ownership) + tce_iommu_release_ownership(container, table_group); + else + tce_iommu_release_ownership_ddw(container, table_group); + +unlock_exit: mutex_unlock(&container->lock); } diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c index 5fa42db769ee..38edeb4729a9 100644 --- a/drivers/vfio/vfio_spapr_eeh.c +++ b/drivers/vfio/vfio_spapr_eeh.c @@ -85,6 +85,16 @@ long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, case VFIO_EEH_PE_CONFIGURE: ret = eeh_pe_configure(pe); break; + case VFIO_EEH_PE_INJECT_ERR: + minsz = offsetofend(struct vfio_eeh_pe_op, err.mask); + if (op.argsz < minsz) + return -EINVAL; + if (copy_from_user(&op, (void __user *)arg, minsz)) + return -EFAULT; + + ret = eeh_pe_inject_err(pe, op.err.type, op.err.func, + op.err.addr, op.err.mask); + break; default: ret = -EINVAL; } |