diff options
Diffstat (limited to 'hw/i386/intel_iommu.c')
| -rw-r--r-- | hw/i386/intel_iommu.c | 787 |
1 files changed, 628 insertions, 159 deletions
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index a8c275f..69d72ad 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -48,7 +48,10 @@ /* pe operations */ #define VTD_PE_GET_TYPE(pe) ((pe)->val[0] & VTD_SM_PASID_ENTRY_PGTT) -#define VTD_PE_GET_LEVEL(pe) (2 + (((pe)->val[0] >> 2) & VTD_SM_PASID_ENTRY_AW)) +#define VTD_PE_GET_FL_LEVEL(pe) \ + (4 + (((pe)->val[2] >> 2) & VTD_SM_PASID_ENTRY_FLPM)) +#define VTD_PE_GET_SL_LEVEL(pe) \ + (2 + (((pe)->val[0] >> 2) & VTD_SM_PASID_ENTRY_AW)) /* * PCI bus number (or SID) is not reliable since the device is usaully @@ -67,6 +70,11 @@ struct vtd_hiod_key { uint8_t devfn; }; +struct vtd_as_raw_key { + uint16_t sid; + uint32_t pasid; +}; + struct vtd_iotlb_key { uint64_t gfn; uint32_t pasid; @@ -284,15 +292,15 @@ static gboolean vtd_hash_remove_by_domain(gpointer key, gpointer value, } /* The shift of an addr for a certain level of paging structure */ -static inline uint32_t vtd_slpt_level_shift(uint32_t level) +static inline uint32_t vtd_pt_level_shift(uint32_t level) { assert(level != 0); - return VTD_PAGE_SHIFT_4K + (level - 1) * VTD_SL_LEVEL_BITS; + return VTD_PAGE_SHIFT_4K + (level - 1) * VTD_LEVEL_BITS; } -static inline uint64_t vtd_slpt_level_page_mask(uint32_t level) +static inline uint64_t vtd_pt_level_page_mask(uint32_t level) { - return ~((1ULL << vtd_slpt_level_shift(level)) - 1); + return ~((1ULL << vtd_pt_level_shift(level)) - 1); } static gboolean vtd_hash_remove_by_page(gpointer key, gpointer value, @@ -302,9 +310,43 @@ static gboolean vtd_hash_remove_by_page(gpointer key, gpointer value, VTDIOTLBPageInvInfo *info = (VTDIOTLBPageInvInfo *)user_data; uint64_t gfn = (info->addr >> VTD_PAGE_SHIFT_4K) & info->mask; uint64_t gfn_tlb = (info->addr & entry->mask) >> VTD_PAGE_SHIFT_4K; - return (entry->domain_id == info->domain_id) && - (((entry->gfn & info->mask) == gfn) || - (entry->gfn == gfn_tlb)); + + if (entry->domain_id != info->domain_id) { + return false; + } + + /* + * According to spec, IOTLB entries caching first-stage (PGTT=001b) or + * nested (PGTT=011b) mapping associated with specified domain-id are + * invalidated. Nested isn't supported yet, so only need to check 001b. + */ + if (entry->pgtt == VTD_SM_PASID_ENTRY_FLT) { + return true; + } + + return (entry->gfn & info->mask) == gfn || entry->gfn == gfn_tlb; +} + +static gboolean vtd_hash_remove_by_page_piotlb(gpointer key, gpointer value, + gpointer user_data) +{ + VTDIOTLBEntry *entry = (VTDIOTLBEntry *)value; + VTDIOTLBPageInvInfo *info = (VTDIOTLBPageInvInfo *)user_data; + uint64_t gfn = (info->addr >> VTD_PAGE_SHIFT_4K) & info->mask; + uint64_t gfn_tlb = (info->addr & entry->mask) >> VTD_PAGE_SHIFT_4K; + + /* + * According to spec, PASID-based-IOTLB Invalidation in page granularity + * doesn't invalidate IOTLB entries caching second-stage (PGTT=010b) + * or pass-through (PGTT=100b) mappings. Nested isn't supported yet, + * so only need to check first-stage (PGTT=001b) mappings. + */ + if (entry->pgtt != VTD_SM_PASID_ENTRY_FLT) { + return false; + } + + return entry->domain_id == info->domain_id && entry->pasid == info->pasid && + ((entry->gfn & info->mask) == gfn || entry->gfn == gfn_tlb); } /* Reset all the gen of VTDAddressSpace to zero and set the gen of @@ -349,7 +391,7 @@ static void vtd_reset_caches(IntelIOMMUState *s) static uint64_t vtd_get_iotlb_gfn(hwaddr addr, uint32_t level) { - return (addr & vtd_slpt_level_page_mask(level)) >> VTD_PAGE_SHIFT_4K; + return (addr & vtd_pt_level_page_mask(level)) >> VTD_PAGE_SHIFT_4K; } /* Must be called with IOMMU lock held */ @@ -360,7 +402,7 @@ static VTDIOTLBEntry *vtd_lookup_iotlb(IntelIOMMUState *s, uint16_t source_id, VTDIOTLBEntry *entry; unsigned level; - for (level = VTD_SL_PT_LEVEL; level < VTD_SL_PML4_LEVEL; level++) { + for (level = VTD_PT_LEVEL; level < VTD_PML4_LEVEL; level++) { key.gfn = vtd_get_iotlb_gfn(addr, level); key.level = level; key.sid = source_id; @@ -377,15 +419,15 @@ out: /* Must be with IOMMU lock held */ static void vtd_update_iotlb(IntelIOMMUState *s, uint16_t source_id, - uint16_t domain_id, hwaddr addr, uint64_t slpte, + uint16_t domain_id, hwaddr addr, uint64_t pte, uint8_t access_flags, uint32_t level, - uint32_t pasid) + uint32_t pasid, uint8_t pgtt) { VTDIOTLBEntry *entry = g_malloc(sizeof(*entry)); struct vtd_iotlb_key *key = g_malloc(sizeof(*key)); uint64_t gfn = vtd_get_iotlb_gfn(addr, level); - trace_vtd_iotlb_page_update(source_id, addr, slpte, domain_id); + trace_vtd_iotlb_page_update(source_id, addr, pte, domain_id); if (g_hash_table_size(s->iotlb) >= VTD_IOTLB_MAX_SIZE) { trace_vtd_iotlb_reset("iotlb exceeds size limit"); vtd_reset_iotlb_locked(s); @@ -393,10 +435,11 @@ static void vtd_update_iotlb(IntelIOMMUState *s, uint16_t source_id, entry->gfn = gfn; entry->domain_id = domain_id; - entry->slpte = slpte; + entry->pte = pte; entry->access_flags = access_flags; - entry->mask = vtd_slpt_level_page_mask(level); + entry->mask = vtd_pt_level_page_mask(level); entry->pasid = pasid; + entry->pgtt = pgtt; key->gfn = gfn; key->sid = source_id; @@ -710,32 +753,32 @@ static inline dma_addr_t vtd_ce_get_slpt_base(VTDContextEntry *ce) return ce->lo & VTD_CONTEXT_ENTRY_SLPTPTR; } -static inline uint64_t vtd_get_slpte_addr(uint64_t slpte, uint8_t aw) +static inline uint64_t vtd_get_pte_addr(uint64_t pte, uint8_t aw) { - return slpte & VTD_SL_PT_BASE_ADDR_MASK(aw); + return pte & VTD_PT_BASE_ADDR_MASK(aw); } /* Whether the pte indicates the address of the page frame */ -static inline bool vtd_is_last_slpte(uint64_t slpte, uint32_t level) +static inline bool vtd_is_last_pte(uint64_t pte, uint32_t level) { - return level == VTD_SL_PT_LEVEL || (slpte & VTD_SL_PT_PAGE_SIZE_MASK); + return level == VTD_PT_LEVEL || (pte & VTD_PT_PAGE_SIZE_MASK); } -/* Get the content of a spte located in @base_addr[@index] */ -static uint64_t vtd_get_slpte(dma_addr_t base_addr, uint32_t index) +/* Get the content of a pte located in @base_addr[@index] */ +static uint64_t vtd_get_pte(dma_addr_t base_addr, uint32_t index) { - uint64_t slpte; + uint64_t pte; - assert(index < VTD_SL_PT_ENTRY_NR); + assert(index < VTD_PT_ENTRY_NR); if (dma_memory_read(&address_space_memory, - base_addr + index * sizeof(slpte), - &slpte, sizeof(slpte), MEMTXATTRS_UNSPECIFIED)) { - slpte = (uint64_t)-1; - return slpte; + base_addr + index * sizeof(pte), + &pte, sizeof(pte), MEMTXATTRS_UNSPECIFIED)) { + pte = (uint64_t)-1; + return pte; } - slpte = le64_to_cpu(slpte); - return slpte; + pte = le64_to_cpu(pte); + return pte; } /* Given an iova and the level of paging structure, return the offset @@ -743,36 +786,39 @@ static uint64_t vtd_get_slpte(dma_addr_t base_addr, uint32_t index) */ static inline uint32_t vtd_iova_level_offset(uint64_t iova, uint32_t level) { - return (iova >> vtd_slpt_level_shift(level)) & - ((1ULL << VTD_SL_LEVEL_BITS) - 1); + return (iova >> vtd_pt_level_shift(level)) & + ((1ULL << VTD_LEVEL_BITS) - 1); } /* Check Capability Register to see if the @level of page-table is supported */ -static inline bool vtd_is_level_supported(IntelIOMMUState *s, uint32_t level) +static inline bool vtd_is_sl_level_supported(IntelIOMMUState *s, uint32_t level) { return VTD_CAP_SAGAW_MASK & s->cap & (1ULL << (level - 2 + VTD_CAP_SAGAW_SHIFT)); } +static inline bool vtd_is_fl_level_supported(IntelIOMMUState *s, uint32_t level) +{ + return level == VTD_PML4_LEVEL; +} + /* Return true if check passed, otherwise false */ -static inline bool vtd_pe_type_check(X86IOMMUState *x86_iommu, - VTDPASIDEntry *pe) +static inline bool vtd_pe_type_check(IntelIOMMUState *s, VTDPASIDEntry *pe) { switch (VTD_PE_GET_TYPE(pe)) { case VTD_SM_PASID_ENTRY_FLT: + return !!(s->ecap & VTD_ECAP_FLTS); case VTD_SM_PASID_ENTRY_SLT: + return !!(s->ecap & VTD_ECAP_SLTS); case VTD_SM_PASID_ENTRY_NESTED: - break; + /* Not support NESTED page table type yet */ + return false; case VTD_SM_PASID_ENTRY_PT: - if (!x86_iommu->pt_supported) { - return false; - } - break; + return !!(s->ecap & VTD_ECAP_PT); default: /* Unknown type */ return false; } - return true; } static inline bool vtd_pdire_present(VTDPASIDDirEntry *pdire) @@ -796,7 +842,7 @@ static int vtd_get_pdire_from_pdir_table(dma_addr_t pasid_dir_base, addr = pasid_dir_base + index * entry_size; if (dma_memory_read(&address_space_memory, addr, pdire, entry_size, MEMTXATTRS_UNSPECIFIED)) { - return -VTD_FR_PASID_TABLE_INV; + return -VTD_FR_PASID_DIR_ACCESS_ERR; } pdire->val = le64_to_cpu(pdire->val); @@ -814,28 +860,35 @@ static int vtd_get_pe_in_pasid_leaf_table(IntelIOMMUState *s, dma_addr_t addr, VTDPASIDEntry *pe) { + uint8_t pgtt; uint32_t index; dma_addr_t entry_size; - X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s); index = VTD_PASID_TABLE_INDEX(pasid); entry_size = VTD_PASID_ENTRY_SIZE; addr = addr + index * entry_size; if (dma_memory_read(&address_space_memory, addr, pe, entry_size, MEMTXATTRS_UNSPECIFIED)) { - return -VTD_FR_PASID_TABLE_INV; + return -VTD_FR_PASID_TABLE_ACCESS_ERR; } for (size_t i = 0; i < ARRAY_SIZE(pe->val); i++) { pe->val[i] = le64_to_cpu(pe->val[i]); } /* Do translation type check */ - if (!vtd_pe_type_check(x86_iommu, pe)) { - return -VTD_FR_PASID_TABLE_INV; + if (!vtd_pe_type_check(s, pe)) { + return -VTD_FR_PASID_TABLE_ENTRY_INV; + } + + pgtt = VTD_PE_GET_TYPE(pe); + if (pgtt == VTD_SM_PASID_ENTRY_SLT && + !vtd_is_sl_level_supported(s, VTD_PE_GET_SL_LEVEL(pe))) { + return -VTD_FR_PASID_TABLE_ENTRY_INV; } - if (!vtd_is_level_supported(s, VTD_PE_GET_LEVEL(pe))) { - return -VTD_FR_PASID_TABLE_INV; + if (pgtt == VTD_SM_PASID_ENTRY_FLT && + !vtd_is_fl_level_supported(s, VTD_PE_GET_FL_LEVEL(pe))) { + return -VTD_FR_PASID_TABLE_ENTRY_INV; } return 0; @@ -876,7 +929,7 @@ static int vtd_get_pe_from_pasid_table(IntelIOMMUState *s, } if (!vtd_pdire_present(&pdire)) { - return -VTD_FR_PASID_TABLE_INV; + return -VTD_FR_PASID_DIR_ENTRY_P; } ret = vtd_get_pe_from_pdire(s, pasid, &pdire, pe); @@ -885,7 +938,7 @@ static int vtd_get_pe_from_pasid_table(IntelIOMMUState *s, } if (!vtd_pe_present(pe)) { - return -VTD_FR_PASID_TABLE_INV; + return -VTD_FR_PASID_ENTRY_P; } return 0; @@ -938,7 +991,7 @@ static int vtd_ce_get_pasid_fpd(IntelIOMMUState *s, } if (!vtd_pdire_present(&pdire)) { - return -VTD_FR_PASID_TABLE_INV; + return -VTD_FR_PASID_DIR_ENTRY_P; } /* @@ -973,7 +1026,11 @@ static uint32_t vtd_get_iova_level(IntelIOMMUState *s, if (s->root_scalable) { vtd_ce_get_rid2pasid_entry(s, ce, &pe, pasid); - return VTD_PE_GET_LEVEL(&pe); + if (s->flts) { + return VTD_PE_GET_FL_LEVEL(&pe); + } else { + return VTD_PE_GET_SL_LEVEL(&pe); + } } return vtd_ce_get_level(ce); @@ -1041,9 +1098,9 @@ static inline uint64_t vtd_iova_limit(IntelIOMMUState *s, } /* Return true if IOVA passes range check, otherwise false. */ -static inline bool vtd_iova_range_check(IntelIOMMUState *s, - uint64_t iova, VTDContextEntry *ce, - uint8_t aw, uint32_t pasid) +static inline bool vtd_iova_sl_range_check(IntelIOMMUState *s, + uint64_t iova, VTDContextEntry *ce, + uint8_t aw, uint32_t pasid) { /* * Check if @iova is above 2^X-1, where X is the minimum of MGAW @@ -1060,7 +1117,11 @@ static dma_addr_t vtd_get_iova_pgtbl_base(IntelIOMMUState *s, if (s->root_scalable) { vtd_ce_get_rid2pasid_entry(s, ce, &pe, pasid); - return pe.val[0] & VTD_SM_PASID_ENTRY_SLPTPTR; + if (s->flts) { + return pe.val[2] & VTD_SM_PASID_ENTRY_FLPTPTR; + } else { + return pe.val[0] & VTD_SM_PASID_ENTRY_SLPTPTR; + } } return vtd_ce_get_slpt_base(ce); @@ -1084,17 +1145,17 @@ static bool vtd_slpte_nonzero_rsvd(uint64_t slpte, uint32_t level) /* * We should have caught a guest-mis-programmed level earlier, - * via vtd_is_level_supported. + * via vtd_is_sl_level_supported. */ assert(level < VTD_SPTE_RSVD_LEN); /* - * Zero level doesn't exist. The smallest level is VTD_SL_PT_LEVEL=1 and - * checked by vtd_is_last_slpte(). + * Zero level doesn't exist. The smallest level is VTD_PT_LEVEL=1 and + * checked by vtd_is_last_pte(). */ assert(level); - if ((level == VTD_SL_PD_LEVEL || level == VTD_SL_PDP_LEVEL) && - (slpte & VTD_SL_PT_PAGE_SIZE_MASK)) { + if ((level == VTD_PD_LEVEL || level == VTD_PDP_LEVEL) && + (slpte & VTD_PT_PAGE_SIZE_MASK)) { /* large page */ rsvd_mask = vtd_spte_rsvd_large[level]; } else { @@ -1118,9 +1179,8 @@ static int vtd_iova_to_slpte(IntelIOMMUState *s, VTDContextEntry *ce, uint32_t offset; uint64_t slpte; uint64_t access_right_check; - uint64_t xlat, size; - if (!vtd_iova_range_check(s, iova, ce, aw_bits, pasid)) { + if (!vtd_iova_sl_range_check(s, iova, ce, aw_bits, pasid)) { error_report_once("%s: detected IOVA overflow (iova=0x%" PRIx64 "," "pasid=0x%" PRIx32 ")", __func__, iova, pasid); return -VTD_FR_ADDR_BEYOND_MGAW; @@ -1131,7 +1191,7 @@ static int vtd_iova_to_slpte(IntelIOMMUState *s, VTDContextEntry *ce, while (true) { offset = vtd_iova_level_offset(iova, level); - slpte = vtd_get_slpte(addr, offset); + slpte = vtd_get_pte(addr, offset); if (slpte == (uint64_t)-1) { error_report_once("%s: detected read error on DMAR slpte " @@ -1162,37 +1222,16 @@ static int vtd_iova_to_slpte(IntelIOMMUState *s, VTDContextEntry *ce, return -VTD_FR_PAGING_ENTRY_RSVD; } - if (vtd_is_last_slpte(slpte, level)) { + if (vtd_is_last_pte(slpte, level)) { *slptep = slpte; *slpte_level = level; break; } - addr = vtd_get_slpte_addr(slpte, aw_bits); + addr = vtd_get_pte_addr(slpte, aw_bits); level--; } - xlat = vtd_get_slpte_addr(*slptep, aw_bits); - size = ~vtd_slpt_level_page_mask(level) + 1; - - /* - * From VT-d spec 3.14: Untranslated requests and translation - * requests that result in an address in the interrupt range will be - * blocked with condition code LGN.4 or SGN.8. - */ - if ((xlat > VTD_INTERRUPT_ADDR_LAST || - xlat + size - 1 < VTD_INTERRUPT_ADDR_FIRST)) { - return 0; - } else { - error_report_once("%s: xlat address is in interrupt range " - "(iova=0x%" PRIx64 ", level=0x%" PRIx32 ", " - "slpte=0x%" PRIx64 ", write=%d, " - "xlat=0x%" PRIx64 ", size=0x%" PRIx64 ", " - "pasid=0x%" PRIx32 ")", - __func__, iova, level, slpte, is_write, - xlat, size, pasid); - return s->scalable_mode ? -VTD_FR_SM_INTERRUPT_ADDR : - -VTD_FR_INTERRUPT_ADDR; - } + return 0; } typedef int (*vtd_page_walk_hook)(const IOMMUTLBEvent *event, void *private); @@ -1323,14 +1362,14 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start, trace_vtd_page_walk_level(addr, level, start, end); - subpage_size = 1ULL << vtd_slpt_level_shift(level); - subpage_mask = vtd_slpt_level_page_mask(level); + subpage_size = 1ULL << vtd_pt_level_shift(level); + subpage_mask = vtd_pt_level_page_mask(level); while (iova < end) { iova_next = (iova & subpage_mask) + subpage_size; offset = vtd_iova_level_offset(iova, level); - slpte = vtd_get_slpte(addr, offset); + slpte = vtd_get_pte(addr, offset); if (slpte == (uint64_t)-1) { trace_vtd_page_walk_skip_read(iova, iova_next); @@ -1353,12 +1392,12 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start, */ entry_valid = read_cur | write_cur; - if (!vtd_is_last_slpte(slpte, level) && entry_valid) { + if (!vtd_is_last_pte(slpte, level) && entry_valid) { /* * This is a valid PDE (or even bigger than PDE). We need * to walk one further level. */ - ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte, info->aw), + ret = vtd_page_walk_level(vtd_get_pte_addr(slpte, info->aw), iova, MIN(iova_next, end), level - 1, read_cur, write_cur, info); } else { @@ -1375,7 +1414,7 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start, event.entry.perm = IOMMU_ACCESS_FLAG(read_cur, write_cur); event.entry.addr_mask = ~subpage_mask; /* NOTE: this is only meaningful if entry_valid == true */ - event.entry.translated_addr = vtd_get_slpte_addr(slpte, info->aw); + event.entry.translated_addr = vtd_get_pte_addr(slpte, info->aw); event.type = event.entry.perm ? IOMMU_NOTIFIER_MAP : IOMMU_NOTIFIER_UNMAP; ret = vtd_page_walk_one(&event, info); @@ -1409,11 +1448,11 @@ static int vtd_page_walk(IntelIOMMUState *s, VTDContextEntry *ce, dma_addr_t addr = vtd_get_iova_pgtbl_base(s, ce, pasid); uint32_t level = vtd_get_iova_level(s, ce, pasid); - if (!vtd_iova_range_check(s, start, ce, info->aw, pasid)) { + if (!vtd_iova_sl_range_check(s, start, ce, info->aw, pasid)) { return -VTD_FR_ADDR_BEYOND_MGAW; } - if (!vtd_iova_range_check(s, end, ce, info->aw, pasid)) { + if (!vtd_iova_sl_range_check(s, end, ce, info->aw, pasid)) { /* Fix end so that it reaches the maximum */ end = vtd_iova_limit(s, ce, info->aw, pasid); } @@ -1528,7 +1567,7 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num, /* Check if the programming of context-entry is valid */ if (!s->root_scalable && - !vtd_is_level_supported(s, vtd_ce_get_level(ce))) { + !vtd_is_sl_level_supported(s, vtd_ce_get_level(ce))) { error_report_once("%s: invalid context entry: hi=%"PRIx64 ", lo=%"PRIx64" (level %d not supported)", __func__, ce->hi, ce->lo, @@ -1689,8 +1728,6 @@ static bool vtd_as_pt_enabled(VTDAddressSpace *as) static bool vtd_switch_address_space(VTDAddressSpace *as) { bool use_iommu, pt; - /* Whether we need to take the BQL on our own */ - bool take_bql = !bql_locked(); assert(as); @@ -1707,9 +1744,7 @@ static bool vtd_switch_address_space(VTDAddressSpace *as) * from vtd_pt_enable_fast_path(). However the memory APIs need * it. We'd better make sure we have had it already, or, take it. */ - if (take_bql) { - bql_lock(); - } + BQL_LOCK_GUARD(); /* Turn off first then on the other */ if (use_iommu) { @@ -1762,10 +1797,6 @@ static bool vtd_switch_address_space(VTDAddressSpace *as) memory_region_set_enabled(&as->iommu_ir_fault, false); } - if (take_bql) { - bql_unlock(); - } - return use_iommu; } @@ -1795,8 +1826,20 @@ static const bool vtd_qualified_faults[] = { [VTD_FR_ROOT_ENTRY_RSVD] = false, [VTD_FR_PAGING_ENTRY_RSVD] = true, [VTD_FR_CONTEXT_ENTRY_TT] = true, - [VTD_FR_PASID_TABLE_INV] = false, + [VTD_FR_PASID_DIR_ACCESS_ERR] = false, + [VTD_FR_PASID_DIR_ENTRY_P] = true, + [VTD_FR_PASID_TABLE_ACCESS_ERR] = false, + [VTD_FR_PASID_ENTRY_P] = true, + [VTD_FR_PASID_TABLE_ENTRY_INV] = true, + [VTD_FR_FS_PAGING_ENTRY_INV] = true, + [VTD_FR_FS_PAGING_ENTRY_P] = true, + [VTD_FR_FS_PAGING_ENTRY_RSVD] = true, + [VTD_FR_PASID_ENTRY_FSPTPTR_INV] = true, + [VTD_FR_FS_NON_CANONICAL] = true, + [VTD_FR_FS_PAGING_ENTRY_US] = true, + [VTD_FR_SM_WRITE] = true, [VTD_FR_SM_INTERRUPT_ADDR] = true, + [VTD_FR_FS_BIT_UPDATE_FAILED] = true, [VTD_FR_MAX] = false, }; @@ -1814,29 +1857,32 @@ static inline bool vtd_is_interrupt_addr(hwaddr addr) return VTD_INTERRUPT_ADDR_FIRST <= addr && addr <= VTD_INTERRUPT_ADDR_LAST; } -static gboolean vtd_find_as_by_sid(gpointer key, gpointer value, - gpointer user_data) +static gboolean vtd_find_as_by_sid_and_pasid(gpointer key, gpointer value, + gpointer user_data) { struct vtd_as_key *as_key = (struct vtd_as_key *)key; - uint16_t target_sid = *(uint16_t *)user_data; + struct vtd_as_raw_key *target = (struct vtd_as_raw_key *)user_data; uint16_t sid = PCI_BUILD_BDF(pci_bus_num(as_key->bus), as_key->devfn); - return sid == target_sid; + + return (as_key->pasid == target->pasid) && (sid == target->sid); } -static VTDAddressSpace *vtd_get_as_by_sid(IntelIOMMUState *s, uint16_t sid) +static VTDAddressSpace *vtd_get_as_by_sid_and_pasid(IntelIOMMUState *s, + uint16_t sid, + uint32_t pasid) { - uint8_t bus_num = PCI_BUS_NUM(sid); - VTDAddressSpace *vtd_as = s->vtd_as_cache[bus_num]; - - if (vtd_as && - (sid == PCI_BUILD_BDF(pci_bus_num(vtd_as->bus), vtd_as->devfn))) { - return vtd_as; - } + struct vtd_as_raw_key key = { + .sid = sid, + .pasid = pasid + }; - vtd_as = g_hash_table_find(s->vtd_address_spaces, vtd_find_as_by_sid, &sid); - s->vtd_as_cache[bus_num] = vtd_as; + return g_hash_table_find(s->vtd_address_spaces, + vtd_find_as_by_sid_and_pasid, &key); +} - return vtd_as; +static VTDAddressSpace *vtd_get_as_by_sid(IntelIOMMUState *s, uint16_t sid) +{ + return vtd_get_as_by_sid_and_pasid(s, sid, PCI_NO_PASID); } static void vtd_pt_enable_fast_path(IntelIOMMUState *s, uint16_t source_id) @@ -1858,6 +1904,157 @@ out: trace_vtd_pt_enable_fast_path(source_id, success); } +/* + * Rsvd field masks for fpte: + * vtd_fpte_rsvd 4k pages + * vtd_fpte_rsvd_large large pages + * + * We support only 4-level page tables. + */ +#define VTD_FPTE_RSVD_LEN 5 +static uint64_t vtd_fpte_rsvd[VTD_FPTE_RSVD_LEN]; +static uint64_t vtd_fpte_rsvd_large[VTD_FPTE_RSVD_LEN]; + +static bool vtd_flpte_nonzero_rsvd(uint64_t flpte, uint32_t level) +{ + uint64_t rsvd_mask; + + /* + * We should have caught a guest-mis-programmed level earlier, + * via vtd_is_fl_level_supported. + */ + assert(level < VTD_FPTE_RSVD_LEN); + /* + * Zero level doesn't exist. The smallest level is VTD_PT_LEVEL=1 and + * checked by vtd_is_last_pte(). + */ + assert(level); + + if ((level == VTD_PD_LEVEL || level == VTD_PDP_LEVEL) && + (flpte & VTD_PT_PAGE_SIZE_MASK)) { + /* large page */ + rsvd_mask = vtd_fpte_rsvd_large[level]; + } else { + rsvd_mask = vtd_fpte_rsvd[level]; + } + + return flpte & rsvd_mask; +} + +static inline bool vtd_flpte_present(uint64_t flpte) +{ + return !!(flpte & VTD_FL_P); +} + +/* Return true if IOVA is canonical, otherwise false. */ +static bool vtd_iova_fl_check_canonical(IntelIOMMUState *s, uint64_t iova, + VTDContextEntry *ce, uint32_t pasid) +{ + uint64_t iova_limit = vtd_iova_limit(s, ce, s->aw_bits, pasid); + uint64_t upper_bits_mask = ~(iova_limit - 1); + uint64_t upper_bits = iova & upper_bits_mask; + bool msb = ((iova & (iova_limit >> 1)) != 0); + + if (msb) { + return upper_bits == upper_bits_mask; + } else { + return !upper_bits; + } +} + +static MemTxResult vtd_set_flag_in_pte(dma_addr_t base_addr, uint32_t index, + uint64_t pte, uint64_t flag) +{ + if (pte & flag) { + return MEMTX_OK; + } + pte |= flag; + pte = cpu_to_le64(pte); + return dma_memory_write(&address_space_memory, + base_addr + index * sizeof(pte), + &pte, sizeof(pte), + MEMTXATTRS_UNSPECIFIED); +} + +/* + * Given the @iova, get relevant @flptep. @flpte_level will be the last level + * of the translation, can be used for deciding the size of large page. + */ +static int vtd_iova_to_flpte(IntelIOMMUState *s, VTDContextEntry *ce, + uint64_t iova, bool is_write, + uint64_t *flptep, uint32_t *flpte_level, + bool *reads, bool *writes, uint8_t aw_bits, + uint32_t pasid) +{ + dma_addr_t addr = vtd_get_iova_pgtbl_base(s, ce, pasid); + uint32_t level = vtd_get_iova_level(s, ce, pasid); + uint32_t offset; + uint64_t flpte, flag_ad = VTD_FL_A; + + if (!vtd_iova_fl_check_canonical(s, iova, ce, pasid)) { + error_report_once("%s: detected non canonical IOVA (iova=0x%" PRIx64 "," + "pasid=0x%" PRIx32 ")", __func__, iova, pasid); + return -VTD_FR_FS_NON_CANONICAL; + } + + while (true) { + offset = vtd_iova_level_offset(iova, level); + flpte = vtd_get_pte(addr, offset); + + if (flpte == (uint64_t)-1) { + if (level == vtd_get_iova_level(s, ce, pasid)) { + /* Invalid programming of pasid-entry */ + return -VTD_FR_PASID_ENTRY_FSPTPTR_INV; + } else { + return -VTD_FR_FS_PAGING_ENTRY_INV; + } + } + + if (!vtd_flpte_present(flpte)) { + *reads = false; + *writes = false; + return -VTD_FR_FS_PAGING_ENTRY_P; + } + + /* No emulated device supports supervisor privilege request yet */ + if (!(flpte & VTD_FL_US)) { + *reads = false; + *writes = false; + return -VTD_FR_FS_PAGING_ENTRY_US; + } + + *reads = true; + *writes = (*writes) && (flpte & VTD_FL_RW); + if (is_write && !(flpte & VTD_FL_RW)) { + return -VTD_FR_SM_WRITE; + } + if (vtd_flpte_nonzero_rsvd(flpte, level)) { + error_report_once("%s: detected flpte reserved non-zero " + "iova=0x%" PRIx64 ", level=0x%" PRIx32 + "flpte=0x%" PRIx64 ", pasid=0x%" PRIX32 ")", + __func__, iova, level, flpte, pasid); + return -VTD_FR_FS_PAGING_ENTRY_RSVD; + } + + if (vtd_is_last_pte(flpte, level) && is_write) { + flag_ad |= VTD_FL_D; + } + + if (vtd_set_flag_in_pte(addr, offset, flpte, flag_ad) != MEMTX_OK) { + return -VTD_FR_FS_BIT_UPDATE_FAILED; + } + + if (vtd_is_last_pte(flpte, level)) { + *flptep = flpte; + *flpte_level = level; + return 0; + } + + addr = vtd_get_pte_addr(flpte, aw_bits); + level--; + } +} + static void vtd_report_fault(IntelIOMMUState *s, int err, bool is_fpd_set, uint16_t source_id, @@ -1894,16 +2091,17 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus, VTDContextEntry ce; uint8_t bus_num = pci_bus_num(bus); VTDContextCacheEntry *cc_entry; - uint64_t slpte, page_mask; + uint64_t pte, page_mask; uint32_t level, pasid = vtd_as->pasid; uint16_t source_id = PCI_BUILD_BDF(bus_num, devfn); int ret_fr; bool is_fpd_set = false; bool reads = true; bool writes = true; - uint8_t access_flags; + uint8_t access_flags, pgtt; bool rid2pasid = (pasid == PCI_NO_PASID) && s->root_scalable; VTDIOTLBEntry *iotlb_entry; + uint64_t xlat, size; /* * We have standalone memory region for interrupt addresses, we @@ -1915,13 +2113,13 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus, cc_entry = &vtd_as->context_cache_entry; - /* Try to fetch slpte form IOTLB, we don't need RID2PASID logic */ + /* Try to fetch pte from IOTLB, we don't need RID2PASID logic */ if (!rid2pasid) { iotlb_entry = vtd_lookup_iotlb(s, source_id, pasid, addr); if (iotlb_entry) { - trace_vtd_iotlb_page_hit(source_id, addr, iotlb_entry->slpte, + trace_vtd_iotlb_page_hit(source_id, addr, iotlb_entry->pte, iotlb_entry->domain_id); - slpte = iotlb_entry->slpte; + pte = iotlb_entry->pte; access_flags = iotlb_entry->access_flags; page_mask = iotlb_entry->mask; goto out; @@ -1993,35 +2191,65 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus, return true; } - /* Try to fetch slpte form IOTLB for RID2PASID slow path */ + /* Try to fetch pte from IOTLB for RID2PASID slow path */ if (rid2pasid) { iotlb_entry = vtd_lookup_iotlb(s, source_id, pasid, addr); if (iotlb_entry) { - trace_vtd_iotlb_page_hit(source_id, addr, iotlb_entry->slpte, + trace_vtd_iotlb_page_hit(source_id, addr, iotlb_entry->pte, iotlb_entry->domain_id); - slpte = iotlb_entry->slpte; + pte = iotlb_entry->pte; access_flags = iotlb_entry->access_flags; page_mask = iotlb_entry->mask; goto out; } } - ret_fr = vtd_iova_to_slpte(s, &ce, addr, is_write, &slpte, &level, - &reads, &writes, s->aw_bits, pasid); + if (s->flts && s->root_scalable) { + ret_fr = vtd_iova_to_flpte(s, &ce, addr, is_write, &pte, &level, + &reads, &writes, s->aw_bits, pasid); + pgtt = VTD_SM_PASID_ENTRY_FLT; + } else { + ret_fr = vtd_iova_to_slpte(s, &ce, addr, is_write, &pte, &level, + &reads, &writes, s->aw_bits, pasid); + pgtt = VTD_SM_PASID_ENTRY_SLT; + } + if (!ret_fr) { + xlat = vtd_get_pte_addr(pte, s->aw_bits); + size = ~vtd_pt_level_page_mask(level) + 1; + + /* + * Per VT-d spec 4.1 section 3.15: Untranslated requests and translation + * requests that result in an address in the interrupt range will be + * blocked with condition code LGN.4 or SGN.8. + */ + if ((xlat <= VTD_INTERRUPT_ADDR_LAST && + xlat + size - 1 >= VTD_INTERRUPT_ADDR_FIRST)) { + error_report_once("%s: xlat address is in interrupt range " + "(iova=0x%" PRIx64 ", level=0x%" PRIx32 ", " + "pte=0x%" PRIx64 ", write=%d, " + "xlat=0x%" PRIx64 ", size=0x%" PRIx64 ", " + "pasid=0x%" PRIx32 ")", + __func__, addr, level, pte, is_write, + xlat, size, pasid); + ret_fr = s->scalable_mode ? -VTD_FR_SM_INTERRUPT_ADDR : + -VTD_FR_INTERRUPT_ADDR; + } + } + if (ret_fr) { vtd_report_fault(s, -ret_fr, is_fpd_set, source_id, addr, is_write, pasid != PCI_NO_PASID, pasid); goto error; } - page_mask = vtd_slpt_level_page_mask(level); + page_mask = vtd_pt_level_page_mask(level); access_flags = IOMMU_ACCESS_FLAG(reads, writes); vtd_update_iotlb(s, source_id, vtd_get_domain_id(s, &ce, pasid), - addr, slpte, access_flags, level, pasid); + addr, pte, access_flags, level, pasid, pgtt); out: vtd_iommu_unlock(s); entry->iova = addr & page_mask; - entry->translated_addr = vtd_get_slpte_addr(slpte, s->aw_bits) & page_mask; + entry->translated_addr = vtd_get_pte_addr(pte, s->aw_bits) & page_mask; entry->addr_mask = ~page_mask; entry->perm = access_flags; return true; @@ -2215,8 +2443,13 @@ static void vtd_iotlb_domain_invalidate(IntelIOMMUState *s, uint16_t domain_id) } } +/* + * There is no pasid field in iotlb invalidation descriptor, so PCI_NO_PASID + * is passed as parameter. Piotlb invalidation supports pasid, pasid in its + * descriptor is passed which should not be PCI_NO_PASID. + */ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s, - uint16_t domain_id, hwaddr addr, + uint16_t domain_id, hwaddr addr, uint8_t am, uint32_t pasid) { VTDAddressSpace *vtd_as; @@ -2225,19 +2458,37 @@ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s, hwaddr size = (1 << am) * VTD_PAGE_SIZE; QLIST_FOREACH(vtd_as, &(s->vtd_as_with_notifiers), next) { - if (pasid != PCI_NO_PASID && pasid != vtd_as->pasid) { - continue; - } ret = vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus), vtd_as->devfn, &ce); if (!ret && domain_id == vtd_get_domain_id(s, &ce, vtd_as->pasid)) { + uint32_t rid2pasid = PCI_NO_PASID; + + if (s->root_scalable) { + rid2pasid = VTD_CE_GET_RID2PASID(&ce); + } + + /* + * In legacy mode, vtd_as->pasid == pasid is always true. + * In scalable mode, for vtd address space backing a PCI + * device without pasid, needs to compare pasid with + * rid2pasid of this device. + */ + if (!(vtd_as->pasid == pasid || + (vtd_as->pasid == PCI_NO_PASID && pasid == rid2pasid))) { + continue; + } + if (vtd_as_has_map_notifier(vtd_as)) { /* - * As long as we have MAP notifications registered in - * any of our IOMMU notifiers, we need to sync the - * shadow page table. + * When stage-1 translation is off, as long as we have MAP + * notifications registered in any of our IOMMU notifiers, + * we need to sync the shadow page table. Otherwise VFIO + * device attaches to nested page table instead of shadow + * page table, so no need to sync. */ - vtd_sync_shadow_page_table_range(vtd_as, &ce, addr, size); + if (!s->flts || !s->root_scalable) { + vtd_sync_shadow_page_table_range(vtd_as, &ce, addr, size); + } } else { /* * For UNMAP-only notifiers, we don't need to walk the @@ -2689,6 +2940,106 @@ static bool vtd_process_iotlb_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) return true; } +static gboolean vtd_hash_remove_by_pasid(gpointer key, gpointer value, + gpointer user_data) +{ + VTDIOTLBEntry *entry = (VTDIOTLBEntry *)value; + VTDIOTLBPageInvInfo *info = (VTDIOTLBPageInvInfo *)user_data; + + return ((entry->domain_id == info->domain_id) && + (entry->pasid == info->pasid)); +} + +static void vtd_piotlb_pasid_invalidate(IntelIOMMUState *s, + uint16_t domain_id, uint32_t pasid) +{ + VTDIOTLBPageInvInfo info; + VTDAddressSpace *vtd_as; + VTDContextEntry ce; + + info.domain_id = domain_id; + info.pasid = pasid; + + vtd_iommu_lock(s); + g_hash_table_foreach_remove(s->iotlb, vtd_hash_remove_by_pasid, + &info); + vtd_iommu_unlock(s); + + QLIST_FOREACH(vtd_as, &s->vtd_as_with_notifiers, next) { + if (!vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus), + vtd_as->devfn, &ce) && + domain_id == vtd_get_domain_id(s, &ce, vtd_as->pasid)) { + uint32_t rid2pasid = VTD_CE_GET_RID2PASID(&ce); + + if ((vtd_as->pasid != PCI_NO_PASID || pasid != rid2pasid) && + vtd_as->pasid != pasid) { + continue; + } + + if (!s->flts || !vtd_as_has_map_notifier(vtd_as)) { + vtd_address_space_sync(vtd_as); + } + } + } +} + +static void vtd_piotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id, + uint32_t pasid, hwaddr addr, uint8_t am) +{ + VTDIOTLBPageInvInfo info; + + info.domain_id = domain_id; + info.pasid = pasid; + info.addr = addr; + info.mask = ~((1 << am) - 1); + + vtd_iommu_lock(s); + g_hash_table_foreach_remove(s->iotlb, + vtd_hash_remove_by_page_piotlb, &info); + vtd_iommu_unlock(s); + + vtd_iotlb_page_invalidate_notify(s, domain_id, addr, am, pasid); +} + +static bool vtd_process_piotlb_desc(IntelIOMMUState *s, + VTDInvDesc *inv_desc) +{ + uint16_t domain_id; + uint32_t pasid; + hwaddr addr; + uint8_t am; + uint64_t mask[4] = {VTD_INV_DESC_PIOTLB_RSVD_VAL0, + VTD_INV_DESC_PIOTLB_RSVD_VAL1, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; + + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, true, + __func__, "piotlb inv")) { + return false; + } + + domain_id = VTD_INV_DESC_PIOTLB_DID(inv_desc->val[0]); + pasid = VTD_INV_DESC_PIOTLB_PASID(inv_desc->val[0]); + switch (inv_desc->val[0] & VTD_INV_DESC_PIOTLB_G) { + case VTD_INV_DESC_PIOTLB_ALL_IN_PASID: + vtd_piotlb_pasid_invalidate(s, domain_id, pasid); + break; + + case VTD_INV_DESC_PIOTLB_PSI_IN_PASID: + am = VTD_INV_DESC_PIOTLB_AM(inv_desc->val[1]); + addr = (hwaddr) VTD_INV_DESC_PIOTLB_ADDR(inv_desc->val[1]); + vtd_piotlb_page_invalidate(s, domain_id, pasid, addr, am); + break; + + default: + error_report_once("%s: invalid piotlb inv desc: hi=0x%"PRIx64 + ", lo=0x%"PRIx64" (type mismatch: 0x%llx)", + __func__, inv_desc->val[1], inv_desc->val[0], + inv_desc->val[0] & VTD_INV_DESC_IOTLB_G); + return false; + } + return true; +} + static bool vtd_process_inv_iec_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) { @@ -2742,6 +3093,49 @@ static void do_invalidate_device_tlb(VTDAddressSpace *vtd_dev_as, memory_region_notify_iommu(&vtd_dev_as->iommu, 0, event); } +static bool vtd_process_device_piotlb_desc(IntelIOMMUState *s, + VTDInvDesc *inv_desc) +{ + uint16_t sid; + VTDAddressSpace *vtd_dev_as; + bool size; + bool global; + hwaddr addr; + uint32_t pasid; + uint64_t mask[4] = {VTD_INV_DESC_PASID_DEVICE_IOTLB_RSVD_VAL0, + VTD_INV_DESC_PASID_DEVICE_IOTLB_RSVD_VAL1, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; + + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, true, + __func__, "device piotlb inv")) { + return false; + } + + global = VTD_INV_DESC_PASID_DEVICE_IOTLB_GLOBAL(inv_desc->hi); + size = VTD_INV_DESC_PASID_DEVICE_IOTLB_SIZE(inv_desc->hi); + addr = VTD_INV_DESC_PASID_DEVICE_IOTLB_ADDR(inv_desc->hi); + sid = VTD_INV_DESC_PASID_DEVICE_IOTLB_SID(inv_desc->lo); + if (global) { + QLIST_FOREACH(vtd_dev_as, &s->vtd_as_with_notifiers, next) { + if ((vtd_dev_as->pasid != PCI_NO_PASID) && + (PCI_BUILD_BDF(pci_bus_num(vtd_dev_as->bus), + vtd_dev_as->devfn) == sid)) { + do_invalidate_device_tlb(vtd_dev_as, size, addr); + } + } + } else { + pasid = VTD_INV_DESC_PASID_DEVICE_IOTLB_PASID(inv_desc->lo); + vtd_dev_as = vtd_get_as_by_sid_and_pasid(s, sid, pasid); + if (!vtd_dev_as) { + return true; + } + + do_invalidate_device_tlb(vtd_dev_as, size, addr); + } + + return true; +} + static bool vtd_process_device_iotlb_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) { @@ -2807,6 +3201,13 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s) } break; + case VTD_INV_DESC_PIOTLB: + trace_vtd_inv_desc("p-iotlb", inv_desc.val[1], inv_desc.val[0]); + if (!vtd_process_piotlb_desc(s, &inv_desc)) { + return false; + } + break; + case VTD_INV_DESC_WAIT: trace_vtd_inv_desc("wait", inv_desc.hi, inv_desc.lo); if (!vtd_process_wait_desc(s, &inv_desc)) { @@ -2821,6 +3222,13 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s) } break; + case VTD_INV_DESC_DEV_PIOTLB: + trace_vtd_inv_desc("device-piotlb", inv_desc.hi, inv_desc.lo); + if (!vtd_process_device_piotlb_desc(s, &inv_desc)) { + return false; + } + break; + case VTD_INV_DESC_DEVICE: trace_vtd_inv_desc("device", inv_desc.hi, inv_desc.lo); if (!vtd_process_device_iotlb_desc(s, &inv_desc)) { @@ -2834,7 +3242,6 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s) * iommu driver) work, just return true is enough so far. */ case VTD_INV_DESC_PC: - case VTD_INV_DESC_PIOTLB: if (s->scalable_mode) { break; } @@ -3413,11 +3820,13 @@ static const Property vtd_properties[] = { VTD_HOST_ADDRESS_WIDTH), DEFINE_PROP_BOOL("caching-mode", IntelIOMMUState, caching_mode, FALSE), DEFINE_PROP_BOOL("x-scalable-mode", IntelIOMMUState, scalable_mode, FALSE), + DEFINE_PROP_BOOL("x-flts", IntelIOMMUState, flts, FALSE), DEFINE_PROP_BOOL("snoop-control", IntelIOMMUState, snoop_control, false), DEFINE_PROP_BOOL("x-pasid-mode", IntelIOMMUState, pasid, false), DEFINE_PROP_BOOL("dma-drain", IntelIOMMUState, dma_drain, true), DEFINE_PROP_BOOL("dma-translation", IntelIOMMUState, dma_translation, true), DEFINE_PROP_BOOL("stale-tm", IntelIOMMUState, stale_tm, false), + DEFINE_PROP_BOOL("fs1gp", IntelIOMMUState, fs1gp, true), }; /* Read IRTE entry with specific index */ @@ -3796,9 +4205,30 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, VTDAddressSpace *vtd_dev_as; char name[128]; + vtd_iommu_lock(s); vtd_dev_as = g_hash_table_lookup(s->vtd_address_spaces, &key); + vtd_iommu_unlock(s); + if (!vtd_dev_as) { - struct vtd_as_key *new_key = g_malloc(sizeof(*new_key)); + struct vtd_as_key *new_key; + /* Slow path */ + + /* + * memory_region_add_subregion_overlap requires the bql, + * make sure we own it. + */ + BQL_LOCK_GUARD(); + vtd_iommu_lock(s); + + /* Check again as we released the lock for a moment */ + vtd_dev_as = g_hash_table_lookup(s->vtd_address_spaces, &key); + if (vtd_dev_as) { + vtd_iommu_unlock(s); + return vtd_dev_as; + } + + /* Still nothing, allocate a new address space */ + new_key = g_malloc(sizeof(*new_key)); new_key->bus = bus; new_key->devfn = devfn; @@ -3889,6 +4319,8 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, vtd_switch_address_space(vtd_dev_as); g_hash_table_insert(s->vtd_address_spaces, new_key, vtd_dev_as); + + vtd_iommu_unlock(s); } return vtd_dev_as; } @@ -3914,7 +4346,13 @@ static bool vtd_check_hiod(IntelIOMMUState *s, HostIOMMUDevice *hiod, return false; } - return true; + if (!s->flts) { + /* All checks requested by VTD stage-2 translation pass */ + return true; + } + + error_setg(errp, "host device is uncompatible with stage-1 translation"); + return false; } static bool vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn, @@ -4092,8 +4530,6 @@ static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n) trace_vtd_replay_ce_invalid(bus_n, PCI_SLOT(vtd_as->devfn), PCI_FUNC(vtd_as->devfn)); } - - return; } static void vtd_cap_init(IntelIOMMUState *s) @@ -4137,7 +4573,12 @@ static void vtd_cap_init(IntelIOMMUState *s) } /* TODO: read cap/ecap from host to decide which cap to be exposed. */ - if (s->scalable_mode) { + if (s->flts) { + s->ecap |= VTD_ECAP_SMTS | VTD_ECAP_FLTS; + if (s->fs1gp) { + s->cap |= VTD_CAP_FS1GP; + } + } else if (s->scalable_mode) { s->ecap |= VTD_ECAP_SMTS | VTD_ECAP_SRS | VTD_ECAP_SLTS; } @@ -4193,6 +4634,18 @@ static void vtd_init(IntelIOMMUState *s) vtd_spte_rsvd_large[3] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits, x86_iommu->dt_supported && s->stale_tm); + /* + * Rsvd field masks for fpte + */ + vtd_fpte_rsvd[0] = ~0ULL; + vtd_fpte_rsvd[1] = VTD_FPTE_PAGE_L1_RSVD_MASK(s->aw_bits); + vtd_fpte_rsvd[2] = VTD_FPTE_PAGE_L2_RSVD_MASK(s->aw_bits); + vtd_fpte_rsvd[3] = VTD_FPTE_PAGE_L3_RSVD_MASK(s->aw_bits); + vtd_fpte_rsvd[4] = VTD_FPTE_PAGE_L4_RSVD_MASK(s->aw_bits); + + vtd_fpte_rsvd_large[2] = VTD_FPTE_LPAGE_L2_RSVD_MASK(s->aw_bits); + vtd_fpte_rsvd_large[3] = VTD_FPTE_LPAGE_L3_RSVD_MASK(s->aw_bits); + if (s->scalable_mode || s->snoop_control) { vtd_spte_rsvd[1] &= ~VTD_SPTE_SNP; vtd_spte_rsvd_large[2] &= ~VTD_SPTE_SNP; @@ -4257,10 +4710,11 @@ static void vtd_init(IntelIOMMUState *s) /* Should not reset address_spaces when reset because devices will still use * the address space they got at first (won't ask the bus again). */ -static void vtd_reset(DeviceState *dev) +static void vtd_reset_exit(Object *obj, ResetType type) { - IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev); + IntelIOMMUState *s = INTEL_IOMMU_DEVICE(obj); + trace_vtd_reset_exit(); vtd_init(s); vtd_address_space_refresh_all(s); } @@ -4304,14 +4758,26 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp) } } - /* Currently only address widths supported are 39 and 48 bits */ - if ((s->aw_bits != VTD_HOST_AW_39BIT) && - (s->aw_bits != VTD_HOST_AW_48BIT)) { - error_setg(errp, "Supported values for aw-bits are: %d, %d", + if (!s->scalable_mode && s->flts) { + error_setg(errp, "x-flts is only available in scalable mode"); + return false; + } + + if (!s->flts && s->aw_bits != VTD_HOST_AW_39BIT && + s->aw_bits != VTD_HOST_AW_48BIT) { + error_setg(errp, "%s: supported values for aw-bits are: %d, %d", + s->scalable_mode ? "Scalable mode(flts=off)" : "Legacy mode", VTD_HOST_AW_39BIT, VTD_HOST_AW_48BIT); return false; } + if (s->flts && s->aw_bits != VTD_HOST_AW_48BIT) { + error_setg(errp, + "Scalable mode(flts=on): supported value for aw-bits is: %d", + VTD_HOST_AW_48BIT); + return false; + } + if (s->scalable_mode && !s->dma_drain) { error_setg(errp, "Need to set dma_drain for scalable mode"); return false; @@ -4408,19 +4874,22 @@ static void vtd_realize(DeviceState *dev, Error **errp) qemu_add_machine_init_done_notifier(&vtd_machine_done_notify); } -static void vtd_class_init(ObjectClass *klass, void *data) +static void vtd_class_init(ObjectClass *klass, const void *data) { DeviceClass *dc = DEVICE_CLASS(klass); X86IOMMUClass *x86_class = X86_IOMMU_DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); - device_class_set_legacy_reset(dc, vtd_reset); + /* + * Use 'exit' reset phase to make sure all DMA requests + * have been quiesced during 'enter' or 'hold' phase + */ + rc->phases.exit = vtd_reset_exit; dc->vmsd = &vtd_vmstate; device_class_set_props(dc, vtd_properties); dc->hotpluggable = false; x86_class->realize = vtd_realize; x86_class->int_remap = vtd_int_remap; - /* Supported by the pc-q35-* machine types */ - dc->user_creatable = true; set_bit(DEVICE_CATEGORY_MISC, dc->categories); dc->desc = "Intel IOMMU (VT-d) DMA Remapping device"; } @@ -4433,7 +4902,7 @@ static const TypeInfo vtd_info = { }; static void vtd_iommu_memory_region_class_init(ObjectClass *klass, - void *data) + const void *data) { IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_CLASS(klass); |