#include "kvm_i386.h"
#include "trace.h"
+static void vtd_address_space_refresh_all(IntelIOMMUState *s);
+static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n);
+
static void vtd_define_quad(IntelIOMMUState *s, hwaddr addr, uint64_t val,
uint64_t wmask, uint64_t w1cmask)
{
return new_val;
}
+static inline void vtd_iommu_lock(IntelIOMMUState *s)
+{
+ qemu_mutex_lock(&s->iommu_lock);
+}
+
+static inline void vtd_iommu_unlock(IntelIOMMUState *s)
+{
+ qemu_mutex_unlock(&s->iommu_lock);
+}
+
+/* Whether the address space needs to notify new mappings */
+static inline gboolean vtd_as_has_map_notifier(VTDAddressSpace *as)
+{
+ return as->notifier_flags & IOMMU_NOTIFIER_MAP;
+}
+
/* GHashTable functions */
static gboolean vtd_uint64_equal(gconstpointer v1, gconstpointer v2)
{
}
/* Reset all the gen of VTDAddressSpace to zero and set the gen of
- * IntelIOMMUState to 1.
+ * IntelIOMMUState to 1. Must be called with IOMMU lock held.
*/
-static void vtd_reset_context_cache(IntelIOMMUState *s)
+static void vtd_reset_context_cache_locked(IntelIOMMUState *s)
{
VTDAddressSpace *vtd_as;
VTDBus *vtd_bus;
g_hash_table_iter_init(&bus_it, s->vtd_as_by_busptr);
while (g_hash_table_iter_next (&bus_it, NULL, (void**)&vtd_bus)) {
- for (devfn_it = 0; devfn_it < X86_IOMMU_PCI_DEVFN_MAX; ++devfn_it) {
+ for (devfn_it = 0; devfn_it < PCI_DEVFN_MAX; ++devfn_it) {
vtd_as = vtd_bus->dev_as[devfn_it];
if (!vtd_as) {
continue;
s->context_cache_gen = 1;
}
-static void vtd_reset_iotlb(IntelIOMMUState *s)
+/* Must be called with IOMMU lock held. */
+static void vtd_reset_iotlb_locked(IntelIOMMUState *s)
{
assert(s->iotlb);
g_hash_table_remove_all(s->iotlb);
}
+static void vtd_reset_iotlb(IntelIOMMUState *s)
+{
+ vtd_iommu_lock(s);
+ vtd_reset_iotlb_locked(s);
+ vtd_iommu_unlock(s);
+}
+
+static void vtd_reset_caches(IntelIOMMUState *s)
+{
+ vtd_iommu_lock(s);
+ vtd_reset_iotlb_locked(s);
+ vtd_reset_context_cache_locked(s);
+ vtd_iommu_unlock(s);
+}
+
static uint64_t vtd_get_iotlb_key(uint64_t gfn, uint16_t source_id,
uint32_t level)
{
return (addr & vtd_slpt_level_page_mask(level)) >> VTD_PAGE_SHIFT_4K;
}
+/* Must be called with IOMMU lock held */
static VTDIOTLBEntry *vtd_lookup_iotlb(IntelIOMMUState *s, uint16_t source_id,
hwaddr addr)
{
return entry;
}
+/* 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,
- bool read_flags, bool write_flags,
- uint32_t level)
+ uint8_t access_flags, uint32_t level)
{
VTDIOTLBEntry *entry = g_malloc(sizeof(*entry));
uint64_t *key = g_malloc(sizeof(*key));
trace_vtd_iotlb_page_update(source_id, addr, slpte, domain_id);
if (g_hash_table_size(s->iotlb) >= VTD_IOTLB_MAX_SIZE) {
trace_vtd_iotlb_reset("iotlb exceeds size limit");
- vtd_reset_iotlb(s);
+ vtd_reset_iotlb_locked(s);
}
entry->gfn = gfn;
entry->domain_id = domain_id;
entry->slpte = slpte;
- entry->read_flags = read_flags;
- entry->write_flags = write_flags;
+ entry->access_flags = access_flags;
entry->mask = vtd_slpt_level_page_mask(level);
*key = vtd_get_iotlb_key(gfn, source_id, level);
g_hash_table_replace(s->iotlb, key, entry);
{
if (pre_fsts & VTD_FSTS_PPF || pre_fsts & VTD_FSTS_PFO ||
pre_fsts & VTD_FSTS_IQE) {
- trace_vtd_err("There are previous interrupt conditions "
- "to be serviced by software, fault event "
- "is not generated.");
+ error_report_once("There are previous interrupt conditions "
+ "to be serviced by software, fault event "
+ "is not generated");
return;
}
vtd_set_clear_mask_long(s, DMAR_FECTL_REG, 0, VTD_FECTL_IP);
if (vtd_get_long_raw(s, DMAR_FECTL_REG) & VTD_FECTL_IM) {
- trace_vtd_err("Interrupt Mask set, irq is not generated.");
+ error_report_once("Interrupt Mask set, irq is not generated");
} else {
vtd_generate_interrupt(s, DMAR_FEADDR_REG, DMAR_FEDATA_REG);
vtd_set_clear_mask_long(s, DMAR_FECTL_REG, VTD_FECTL_IP, 0);
trace_vtd_dmar_fault(source_id, fault, addr, is_write);
if (fsts_reg & VTD_FSTS_PFO) {
- trace_vtd_err("New fault is not recorded due to "
- "Primary Fault Overflow.");
+ error_report_once("New fault is not recorded due to "
+ "Primary Fault Overflow");
return;
}
if (vtd_try_collapse_fault(s, source_id)) {
- trace_vtd_err("New fault is not recorded due to "
- "compression of faults.");
+ error_report_once("New fault is not recorded due to "
+ "compression of faults");
return;
}
if (vtd_is_frcd_set(s, s->next_frcd_reg)) {
- trace_vtd_err("Next Fault Recording Reg is used, "
- "new fault is not recorded, set PFO field.");
+ error_report_once("Next Fault Recording Reg is used, "
+ "new fault is not recorded, set PFO field");
vtd_set_clear_mask_long(s, DMAR_FSTS_REG, 0, VTD_FSTS_PFO);
return;
}
vtd_record_frcd(s, s->next_frcd_reg, source_id, addr, fault, is_write);
if (fsts_reg & VTD_FSTS_PPF) {
- trace_vtd_err("There are pending faults already, "
- "fault event is not generated.");
+ error_report_once("There are pending faults already, "
+ "fault event is not generated");
vtd_set_frcd_and_update_ppf(s, s->next_frcd_reg);
s->next_frcd_reg++;
if (s->next_frcd_reg == DMAR_FRCD_REG_NR) {
return ce->lo & VTD_CONTEXT_ENTRY_SLPTPTR;
}
-static inline uint64_t vtd_get_slpte_addr(uint64_t slpte)
+static inline uint64_t vtd_get_slpte_addr(uint64_t slpte, uint8_t aw)
{
- return slpte & VTD_SL_PT_BASE_ADDR_MASK;
+ return slpte & VTD_SL_PT_BASE_ADDR_MASK(aw);
}
/* Whether the pte indicates the address of the page frame */
return true;
}
-static inline uint64_t vtd_iova_limit(VTDContextEntry *ce)
+static inline uint64_t vtd_iova_limit(VTDContextEntry *ce, uint8_t aw)
{
uint32_t ce_agaw = vtd_ce_get_agaw(ce);
- return 1ULL << MIN(ce_agaw, VTD_MGAW);
+ return 1ULL << MIN(ce_agaw, aw);
}
/* Return true if IOVA passes range check, otherwise false. */
-static inline bool vtd_iova_range_check(uint64_t iova, VTDContextEntry *ce)
+static inline bool vtd_iova_range_check(uint64_t iova, VTDContextEntry *ce,
+ uint8_t aw)
{
/*
* Check if @iova is above 2^X-1, where X is the minimum of MGAW
* in CAP_REG and AW in context-entry.
*/
- return !(iova & ~(vtd_iova_limit(ce) - 1));
-}
-
-static const uint64_t vtd_paging_entry_rsvd_field[] = {
- [0] = ~0ULL,
- /* For not large page */
- [1] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- [2] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- [3] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- [4] = 0x880ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- /* For large page */
- [5] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- [6] = 0x1ff800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- [7] = 0x3ffff800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
- [8] = 0x880ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
-};
+ return !(iova & ~(vtd_iova_limit(ce, aw) - 1));
+}
+
+/*
+ * Rsvd field masks for spte:
+ * Index [1] to [4] 4k pages
+ * Index [5] to [8] large pages
+ */
+static uint64_t vtd_paging_entry_rsvd_field[9];
static bool vtd_slpte_nonzero_rsvd(uint64_t slpte, uint32_t level)
{
*/
static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
uint64_t *slptep, uint32_t *slpte_level,
- bool *reads, bool *writes)
+ bool *reads, bool *writes, uint8_t aw_bits)
{
dma_addr_t addr = vtd_ce_get_slpt_base(ce);
uint32_t level = vtd_ce_get_level(ce);
uint64_t slpte;
uint64_t access_right_check;
- if (!vtd_iova_range_check(iova, ce)) {
- trace_vtd_err_dmar_iova_overflow(iova);
+ if (!vtd_iova_range_check(iova, ce, aw_bits)) {
+ error_report_once("%s: detected IOVA overflow (iova=0x%" PRIx64 ")",
+ __func__, iova);
return -VTD_FR_ADDR_BEYOND_MGAW;
}
slpte = vtd_get_slpte(addr, offset);
if (slpte == (uint64_t)-1) {
- trace_vtd_err_dmar_slpte_read_error(iova, level);
+ error_report_once("%s: detected read error on DMAR slpte "
+ "(iova=0x%" PRIx64 ")", __func__, iova);
if (level == vtd_ce_get_level(ce)) {
/* Invalid programming of context-entry */
return -VTD_FR_CONTEXT_ENTRY_INV;
*reads = (*reads) && (slpte & VTD_SL_R);
*writes = (*writes) && (slpte & VTD_SL_W);
if (!(slpte & access_right_check)) {
- trace_vtd_err_dmar_slpte_perm_error(iova, level, slpte, is_write);
+ error_report_once("%s: detected slpte permission error "
+ "(iova=0x%" PRIx64 ", level=0x%" PRIx32 ", "
+ "slpte=0x%" PRIx64 ", write=%d)", __func__,
+ iova, level, slpte, is_write);
return is_write ? -VTD_FR_WRITE : -VTD_FR_READ;
}
if (vtd_slpte_nonzero_rsvd(slpte, level)) {
- trace_vtd_err_dmar_slpte_resv_error(iova, level, slpte);
+ error_report_once("%s: detected splte reserve non-zero "
+ "iova=0x%" PRIx64 ", level=0x%" PRIx32
+ "slpte=0x%" PRIx64 ")", __func__, iova,
+ level, slpte);
return -VTD_FR_PAGING_ENTRY_RSVD;
}
*slpte_level = level;
return 0;
}
- addr = vtd_get_slpte_addr(slpte);
+ addr = vtd_get_slpte_addr(slpte, aw_bits);
level--;
}
}
typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
+/**
+ * Constant information used during page walking
+ *
+ * @hook_fn: hook func to be called when detected page
+ * @private: private data to be passed into hook func
+ * @notify_unmap: whether we should notify invalid entries
+ * @as: VT-d address space of the device
+ * @aw: maximum address width
+ * @domain: domain ID of the page walk
+ */
+typedef struct {
+ VTDAddressSpace *as;
+ vtd_page_walk_hook hook_fn;
+ void *private;
+ bool notify_unmap;
+ uint8_t aw;
+ uint16_t domain_id;
+} vtd_page_walk_info;
+
+static int vtd_page_walk_one(IOMMUTLBEntry *entry, vtd_page_walk_info *info)
+{
+ VTDAddressSpace *as = info->as;
+ vtd_page_walk_hook hook_fn = info->hook_fn;
+ void *private = info->private;
+ DMAMap target = {
+ .iova = entry->iova,
+ .size = entry->addr_mask,
+ .translated_addr = entry->translated_addr,
+ .perm = entry->perm,
+ };
+ DMAMap *mapped = iova_tree_find(as->iova_tree, &target);
+
+ if (entry->perm == IOMMU_NONE && !info->notify_unmap) {
+ trace_vtd_page_walk_one_skip_unmap(entry->iova, entry->addr_mask);
+ return 0;
+ }
+
+ assert(hook_fn);
+
+ /* Update local IOVA mapped ranges */
+ if (entry->perm) {
+ if (mapped) {
+ /* If it's exactly the same translation, skip */
+ if (!memcmp(mapped, &target, sizeof(target))) {
+ trace_vtd_page_walk_one_skip_map(entry->iova, entry->addr_mask,
+ entry->translated_addr);
+ return 0;
+ } else {
+ /*
+ * Translation changed. Normally this should not
+ * happen, but it can happen when with buggy guest
+ * OSes. Note that there will be a small window that
+ * we don't have map at all. But that's the best
+ * effort we can do. The ideal way to emulate this is
+ * atomically modify the PTE to follow what has
+ * changed, but we can't. One example is that vfio
+ * driver only has VFIO_IOMMU_[UN]MAP_DMA but no
+ * interface to modify a mapping (meanwhile it seems
+ * meaningless to even provide one). Anyway, let's
+ * mark this as a TODO in case one day we'll have
+ * a better solution.
+ */
+ IOMMUAccessFlags cache_perm = entry->perm;
+ int ret;
+
+ /* Emulate an UNMAP */
+ entry->perm = IOMMU_NONE;
+ trace_vtd_page_walk_one(info->domain_id,
+ entry->iova,
+ entry->translated_addr,
+ entry->addr_mask,
+ entry->perm);
+ ret = hook_fn(entry, private);
+ if (ret) {
+ return ret;
+ }
+ /* Drop any existing mapping */
+ iova_tree_remove(as->iova_tree, &target);
+ /* Recover the correct permission */
+ entry->perm = cache_perm;
+ }
+ }
+ iova_tree_insert(as->iova_tree, &target);
+ } else {
+ if (!mapped) {
+ /* Skip since we didn't map this range at all */
+ trace_vtd_page_walk_one_skip_unmap(entry->iova, entry->addr_mask);
+ return 0;
+ }
+ iova_tree_remove(as->iova_tree, &target);
+ }
+
+ trace_vtd_page_walk_one(info->domain_id, entry->iova,
+ entry->translated_addr, entry->addr_mask,
+ entry->perm);
+ return hook_fn(entry, private);
+}
+
/**
* vtd_page_walk_level - walk over specific level for IOVA range
*
* @addr: base GPA addr to start the walk
* @start: IOVA range start address
* @end: IOVA range end address (start <= addr < end)
- * @hook_fn: hook func to be called when detected page
- * @private: private data to be passed into hook func
* @read: whether parent level has read permission
* @write: whether parent level has write permission
- * @notify_unmap: whether we should notify invalid entries
+ * @info: constant information for the page walk
*/
static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
- uint64_t end, vtd_page_walk_hook hook_fn,
- void *private, uint32_t level,
- bool read, bool write, bool notify_unmap)
+ uint64_t end, uint32_t level, bool read,
+ bool write, vtd_page_walk_info *info)
{
bool read_cur, write_cur, entry_valid;
uint32_t offset;
*/
entry_valid = read_cur | write_cur;
- if (vtd_is_last_slpte(slpte, level)) {
+ if (!vtd_is_last_slpte(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),
+ iova, MIN(iova_next, end), level - 1,
+ read_cur, write_cur, info);
+ } else {
+ /*
+ * This means we are either:
+ *
+ * (1) the real page entry (either 4K page, or huge page)
+ * (2) the whole range is invalid
+ *
+ * In either case, we send an IOTLB notification down.
+ */
entry.target_as = &address_space_memory;
entry.iova = iova & subpage_mask;
- /* NOTE: this is only meaningful if entry_valid == true */
- entry.translated_addr = vtd_get_slpte_addr(slpte);
- entry.addr_mask = ~subpage_mask;
entry.perm = IOMMU_ACCESS_FLAG(read_cur, write_cur);
- if (!entry_valid && !notify_unmap) {
- trace_vtd_page_walk_skip_perm(iova, iova_next);
- goto next;
- }
- trace_vtd_page_walk_one(level, entry.iova, entry.translated_addr,
- entry.addr_mask, entry.perm);
- if (hook_fn) {
- ret = hook_fn(&entry, private);
- if (ret < 0) {
- return ret;
- }
- }
- } else {
- if (!entry_valid) {
- trace_vtd_page_walk_skip_perm(iova, iova_next);
- goto next;
- }
- ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte), iova,
- MIN(iova_next, end), hook_fn, private,
- level - 1, read_cur, write_cur,
- notify_unmap);
- if (ret < 0) {
- return ret;
- }
+ entry.addr_mask = ~subpage_mask;
+ /* NOTE: this is only meaningful if entry_valid == true */
+ entry.translated_addr = vtd_get_slpte_addr(slpte, info->aw);
+ ret = vtd_page_walk_one(&entry, info);
+ }
+
+ if (ret < 0) {
+ return ret;
}
next:
* @ce: context entry to walk upon
* @start: IOVA address to start the walk
* @end: IOVA range end address (start <= addr < end)
- * @hook_fn: the hook that to be called for each detected area
- * @private: private data for the hook function
+ * @info: page walking information struct
*/
static int vtd_page_walk(VTDContextEntry *ce, uint64_t start, uint64_t end,
- vtd_page_walk_hook hook_fn, void *private,
- bool notify_unmap)
+ vtd_page_walk_info *info)
{
dma_addr_t addr = vtd_ce_get_slpt_base(ce);
uint32_t level = vtd_ce_get_level(ce);
- if (!vtd_iova_range_check(start, ce)) {
+ if (!vtd_iova_range_check(start, ce, info->aw)) {
return -VTD_FR_ADDR_BEYOND_MGAW;
}
- if (!vtd_iova_range_check(end, ce)) {
+ if (!vtd_iova_range_check(end, ce, info->aw)) {
/* Fix end so that it reaches the maximum */
- end = vtd_iova_limit(ce);
+ end = vtd_iova_limit(ce, info->aw);
}
- return vtd_page_walk_level(addr, start, end, hook_fn, private,
- level, true, true, notify_unmap);
+ return vtd_page_walk_level(addr, start, end, level, true, true, info);
}
/* Map a device to its corresponding domain (context-entry) */
return -VTD_FR_ROOT_ENTRY_P;
}
- if (re.rsvd || (re.val & VTD_ROOT_ENTRY_RSVD)) {
+ if (re.rsvd || (re.val & VTD_ROOT_ENTRY_RSVD(s->aw_bits))) {
trace_vtd_re_invalid(re.rsvd, re.val);
return -VTD_FR_ROOT_ENTRY_RSVD;
}
}
if ((ce->hi & VTD_CONTEXT_ENTRY_RSVD_HI) ||
- (ce->lo & VTD_CONTEXT_ENTRY_RSVD_LO)) {
+ (ce->lo & VTD_CONTEXT_ENTRY_RSVD_LO(s->aw_bits))) {
trace_vtd_ce_invalid(ce->hi, ce->lo);
return -VTD_FR_CONTEXT_ENTRY_RSVD;
}
return 0;
}
+static int vtd_sync_shadow_page_hook(IOMMUTLBEntry *entry,
+ void *private)
+{
+ memory_region_notify_iommu((IOMMUMemoryRegion *)private, 0, *entry);
+ return 0;
+}
+
+static int vtd_sync_shadow_page_table_range(VTDAddressSpace *vtd_as,
+ VTDContextEntry *ce,
+ hwaddr addr, hwaddr size)
+{
+ IntelIOMMUState *s = vtd_as->iommu_state;
+ vtd_page_walk_info info = {
+ .hook_fn = vtd_sync_shadow_page_hook,
+ .private = (void *)&vtd_as->iommu,
+ .notify_unmap = true,
+ .aw = s->aw_bits,
+ .as = vtd_as,
+ .domain_id = VTD_CONTEXT_ENTRY_DID(ce->hi),
+ };
+
+ return vtd_page_walk(ce, addr, addr + size, &info);
+}
+
+static int vtd_sync_shadow_page_table(VTDAddressSpace *vtd_as)
+{
+ int ret;
+ VTDContextEntry ce;
+ IOMMUNotifier *n;
+
+ ret = vtd_dev_to_context_entry(vtd_as->iommu_state,
+ pci_bus_num(vtd_as->bus),
+ vtd_as->devfn, &ce);
+ if (ret) {
+ if (ret == -VTD_FR_CONTEXT_ENTRY_P) {
+ /*
+ * It's a valid scenario to have a context entry that is
+ * not present. For example, when a device is removed
+ * from an existing domain then the context entry will be
+ * zeroed by the guest before it was put into another
+ * domain. When this happens, instead of synchronizing
+ * the shadow pages we should invalidate all existing
+ * mappings and notify the backends.
+ */
+ IOMMU_NOTIFIER_FOREACH(n, &vtd_as->iommu) {
+ vtd_address_space_unmap(vtd_as, n);
+ }
+ ret = 0;
+ }
+ return ret;
+ }
+
+ return vtd_sync_shadow_page_table_range(vtd_as, &ce, 0, UINT64_MAX);
+}
+
/*
* Fetch translation type for specific device. Returns <0 if error
* happens, otherwise return the shifted type to check against
static bool vtd_switch_address_space(VTDAddressSpace *as)
{
bool use_iommu;
+ /* Whether we need to take the BQL on our own */
+ bool take_bql = !qemu_mutex_iothread_locked();
assert(as);
VTD_PCI_FUNC(as->devfn),
use_iommu);
+ /*
+ * It's possible that we reach here without BQL, e.g., when called
+ * 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) {
+ qemu_mutex_lock_iothread();
+ }
+
/* Turn off first then on the other */
if (use_iommu) {
memory_region_set_enabled(&as->sys_alias, false);
- memory_region_set_enabled(&as->iommu, true);
+ memory_region_set_enabled(MEMORY_REGION(&as->iommu), true);
} else {
- memory_region_set_enabled(&as->iommu, false);
+ memory_region_set_enabled(MEMORY_REGION(&as->iommu), false);
memory_region_set_enabled(&as->sys_alias, true);
}
+ if (take_bql) {
+ qemu_mutex_unlock_iothread();
+ }
+
return use_iommu;
}
g_hash_table_iter_init(&iter, s->vtd_as_by_busptr);
while (g_hash_table_iter_next(&iter, NULL, (void **)&vtd_bus)) {
- for (i = 0; i < X86_IOMMU_PCI_DEVFN_MAX; i++) {
+ for (i = 0; i < PCI_DEVFN_MAX; i++) {
if (!vtd_bus->dev_as[i]) {
continue;
}
IntelIOMMUState *s = vtd_as->iommu_state;
VTDContextEntry ce;
uint8_t bus_num = pci_bus_num(bus);
- VTDContextCacheEntry *cc_entry = &vtd_as->context_cache_entry;
+ VTDContextCacheEntry *cc_entry;
uint64_t slpte, page_mask;
uint32_t level;
uint16_t source_id = vtd_make_source_id(bus_num, devfn);
bool is_fpd_set = false;
bool reads = true;
bool writes = true;
+ uint8_t access_flags;
VTDIOTLBEntry *iotlb_entry;
/*
*/
assert(!vtd_is_interrupt_addr(addr));
+ vtd_iommu_lock(s);
+
+ cc_entry = &vtd_as->context_cache_entry;
+
/* Try to fetch slpte form IOTLB */
iotlb_entry = vtd_lookup_iotlb(s, source_id, addr);
if (iotlb_entry) {
trace_vtd_iotlb_page_hit(source_id, addr, iotlb_entry->slpte,
iotlb_entry->domain_id);
slpte = iotlb_entry->slpte;
- reads = iotlb_entry->read_flags;
- writes = iotlb_entry->write_flags;
+ access_flags = iotlb_entry->access_flags;
page_mask = iotlb_entry->mask;
goto out;
}
* Also, let's ignore IOTLB caching as well for PT devices.
*/
if (vtd_ce_get_type(&ce) == VTD_CONTEXT_TT_PASS_THROUGH) {
- entry->iova = addr & VTD_PAGE_MASK;
+ entry->iova = addr & VTD_PAGE_MASK_4K;
entry->translated_addr = entry->iova;
- entry->addr_mask = VTD_PAGE_MASK;
+ entry->addr_mask = ~VTD_PAGE_MASK_4K;
entry->perm = IOMMU_RW;
trace_vtd_translate_pt(source_id, entry->iova);
* IOMMU region can be swapped back.
*/
vtd_pt_enable_fast_path(s, source_id);
-
+ vtd_iommu_unlock(s);
return true;
}
ret_fr = vtd_iova_to_slpte(&ce, addr, is_write, &slpte, &level,
- &reads, &writes);
+ &reads, &writes, s->aw_bits);
if (ret_fr) {
ret_fr = -ret_fr;
if (is_fpd_set && vtd_is_qualified_fault(ret_fr)) {
}
page_mask = vtd_slpt_level_page_mask(level);
+ access_flags = IOMMU_ACCESS_FLAG(reads, writes);
vtd_update_iotlb(s, source_id, VTD_CONTEXT_ENTRY_DID(ce.hi), addr, slpte,
- reads, writes, level);
+ access_flags, level);
out:
+ vtd_iommu_unlock(s);
entry->iova = addr & page_mask;
- entry->translated_addr = vtd_get_slpte_addr(slpte) & page_mask;
+ entry->translated_addr = vtd_get_slpte_addr(slpte, s->aw_bits) & page_mask;
entry->addr_mask = ~page_mask;
- entry->perm = IOMMU_ACCESS_FLAG(reads, writes);
+ entry->perm = access_flags;
return true;
error:
+ vtd_iommu_unlock(s);
entry->iova = 0;
entry->translated_addr = 0;
entry->addr_mask = 0;
{
s->root = vtd_get_quad_raw(s, DMAR_RTADDR_REG);
s->root_extended = s->root & VTD_RTADDR_RTT;
- s->root &= VTD_RTADDR_ADDR_MASK;
+ s->root &= VTD_RTADDR_ADDR_MASK(s->aw_bits);
trace_vtd_reg_dmar_root(s->root, s->root_extended);
}
uint64_t value = 0;
value = vtd_get_quad_raw(s, DMAR_IRTA_REG);
s->intr_size = 1UL << ((value & VTD_IRTA_SIZE_MASK) + 1);
- s->intr_root = value & VTD_IRTA_ADDR_MASK;
+ s->intr_root = value & VTD_IRTA_ADDR_MASK(s->aw_bits);
s->intr_eime = value & VTD_IRTA_EIME;
/* Notify global invalidation */
static void vtd_iommu_replay_all(IntelIOMMUState *s)
{
- IntelIOMMUNotifierNode *node;
+ VTDAddressSpace *vtd_as;
- QLIST_FOREACH(node, &s->notifiers_list, next) {
- memory_region_iommu_replay_all(&node->vtd_as->iommu);
+ QLIST_FOREACH(vtd_as, &s->vtd_as_with_notifiers, next) {
+ vtd_sync_shadow_page_table(vtd_as);
}
}
static void vtd_context_global_invalidate(IntelIOMMUState *s)
{
trace_vtd_inv_desc_cc_global();
+ /* Protects context cache */
+ vtd_iommu_lock(s);
s->context_cache_gen++;
if (s->context_cache_gen == VTD_CONTEXT_CACHE_GEN_MAX) {
- vtd_reset_context_cache(s);
+ vtd_reset_context_cache_locked(s);
}
- vtd_switch_address_space_all(s);
+ vtd_iommu_unlock(s);
+ vtd_address_space_refresh_all(s);
/*
* From VT-d spec 6.5.2.1, a global context entry invalidation
* should be followed by a IOTLB global invalidation, so we should
vtd_bus = vtd_find_as_from_bus_num(s, bus_n);
if (vtd_bus) {
devfn = VTD_SID_TO_DEVFN(source_id);
- for (devfn_it = 0; devfn_it < X86_IOMMU_PCI_DEVFN_MAX; ++devfn_it) {
+ for (devfn_it = 0; devfn_it < PCI_DEVFN_MAX; ++devfn_it) {
vtd_as = vtd_bus->dev_as[devfn_it];
if (vtd_as && ((devfn_it & mask) == (devfn & mask))) {
trace_vtd_inv_desc_cc_device(bus_n, VTD_PCI_SLOT(devfn_it),
VTD_PCI_FUNC(devfn_it));
+ vtd_iommu_lock(s);
vtd_as->context_cache_entry.context_cache_gen = 0;
+ vtd_iommu_unlock(s);
/*
* Do switch address space when needed, in case if the
* device passthrough bit is switched.
vtd_switch_address_space(vtd_as);
/*
* So a device is moving out of (or moving into) a
- * domain, a replay() suites here to notify all the
- * IOMMU_NOTIFIER_MAP registers about this change.
+ * domain, resync the shadow page table.
* This won't bring bad even if we have no such
* notifier registered - the IOMMU notification
* framework will skip MAP notifications if that
* happened.
*/
- memory_region_iommu_replay_all(&vtd_as->iommu);
+ vtd_sync_shadow_page_table(vtd_as);
}
}
}
break;
default:
- trace_vtd_err("Context cache invalidate type error.");
+ error_report_once("%s: invalid context: 0x%" PRIx64,
+ __func__, val);
caig = 0;
}
return caig;
static void vtd_iotlb_domain_invalidate(IntelIOMMUState *s, uint16_t domain_id)
{
- IntelIOMMUNotifierNode *node;
VTDContextEntry ce;
VTDAddressSpace *vtd_as;
trace_vtd_inv_desc_iotlb_domain(domain_id);
+ vtd_iommu_lock(s);
g_hash_table_foreach_remove(s->iotlb, vtd_hash_remove_by_domain,
&domain_id);
+ vtd_iommu_unlock(s);
- QLIST_FOREACH(node, &s->notifiers_list, next) {
- vtd_as = node->vtd_as;
+ 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_CONTEXT_ENTRY_DID(ce.hi)) {
- memory_region_iommu_replay_all(&vtd_as->iommu);
+ vtd_sync_shadow_page_table(vtd_as);
}
}
}
-static int vtd_page_invalidate_notify_hook(IOMMUTLBEntry *entry,
- void *private)
-{
- memory_region_notify_iommu((MemoryRegion *)private, *entry);
- return 0;
-}
-
static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s,
uint16_t domain_id, hwaddr addr,
uint8_t am)
{
- IntelIOMMUNotifierNode *node;
+ VTDAddressSpace *vtd_as;
VTDContextEntry ce;
int ret;
+ hwaddr size = (1 << am) * VTD_PAGE_SIZE;
- QLIST_FOREACH(node, &(s->notifiers_list), next) {
- VTDAddressSpace *vtd_as = node->vtd_as;
+ QLIST_FOREACH(vtd_as, &(s->vtd_as_with_notifiers), next) {
ret = vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus),
vtd_as->devfn, &ce);
if (!ret && domain_id == VTD_CONTEXT_ENTRY_DID(ce.hi)) {
- vtd_page_walk(&ce, addr, addr + (1 << am) * VTD_PAGE_SIZE,
- vtd_page_invalidate_notify_hook,
- (void *)&vtd_as->iommu, true);
+ 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.
+ */
+ vtd_sync_shadow_page_table_range(vtd_as, &ce, addr, size);
+ } else {
+ /*
+ * For UNMAP-only notifiers, we don't need to walk the
+ * page tables. We just deliver the PSI down to
+ * invalidate caches.
+ */
+ IOMMUTLBEntry entry = {
+ .target_as = &address_space_memory,
+ .iova = addr,
+ .translated_addr = 0,
+ .addr_mask = size - 1,
+ .perm = IOMMU_NONE,
+ };
+ memory_region_notify_iommu(&vtd_as->iommu, 0, entry);
+ }
}
}
}
info.domain_id = domain_id;
info.addr = addr;
info.mask = ~((1 << am) - 1);
+ vtd_iommu_lock(s);
g_hash_table_foreach_remove(s->iotlb, vtd_hash_remove_by_page, &info);
+ vtd_iommu_unlock(s);
vtd_iotlb_page_invalidate_notify(s, domain_id, addr, am);
}
am = VTD_IVA_AM(addr);
addr = VTD_IVA_ADDR(addr);
if (am > VTD_MAMV) {
- trace_vtd_err("IOTLB PSI flush: address mask overflow.");
+ error_report_once("%s: address mask overflow: 0x%" PRIx64,
+ __func__, vtd_get_quad_raw(s, DMAR_IVA_REG));
iaig = 0;
break;
}
break;
default:
- trace_vtd_err("IOTLB flush: invalid granularity.");
+ error_report_once("%s: invalid granularity: 0x%" PRIx64,
+ __func__, val);
iaig = 0;
}
return iaig;
}
-static inline bool vtd_queued_inv_enable_check(IntelIOMMUState *s)
-{
- return s->iq_tail == 0;
-}
+static void vtd_fetch_inv_desc(IntelIOMMUState *s);
static inline bool vtd_queued_inv_disable_check(IntelIOMMUState *s)
{
trace_vtd_inv_qi_enable(en);
if (en) {
- if (vtd_queued_inv_enable_check(s)) {
- s->iq = iqa_val & VTD_IQA_IQA_MASK;
- /* 2^(x+8) entries */
- s->iq_size = 1UL << ((iqa_val & VTD_IQA_QS) + 8);
- s->qi_enabled = true;
- trace_vtd_inv_qi_setup(s->iq, s->iq_size);
- /* Ok - report back to driver */
- vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_QIES);
- } else {
- trace_vtd_err_qi_enable(s->iq_tail);
+ s->iq = iqa_val & VTD_IQA_IQA_MASK(s->aw_bits);
+ /* 2^(x+8) entries */
+ s->iq_size = 1UL << ((iqa_val & VTD_IQA_QS) + 8);
+ s->qi_enabled = true;
+ trace_vtd_inv_qi_setup(s->iq, s->iq_size);
+ /* Ok - report back to driver */
+ vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_QIES);
+
+ if (s->iq_tail != 0) {
+ /*
+ * This is a spec violation but Windows guests are known to set up
+ * Queued Invalidation this way so we allow the write and process
+ * Invalidation Descriptors right away.
+ */
+ trace_vtd_warn_invalid_qi_tail(s->iq_tail);
+ if (!(vtd_get_long_raw(s, DMAR_FSTS_REG) & VTD_FSTS_IQE)) {
+ vtd_fetch_inv_desc(s);
+ }
}
} else {
if (vtd_queued_inv_disable_check(s)) {
/* Ok - report back to driver */
vtd_set_clear_mask_long(s, DMAR_GSTS_REG, VTD_GSTS_QIES, 0);
} else {
- trace_vtd_err_qi_disable(s->iq_head, s->iq_tail, s->iq_last_desc_type);
+ error_report_once("%s: detected improper state when disable QI "
+ "(head=0x%x, tail=0x%x, last_type=%d)",
+ __func__,
+ s->iq_head, s->iq_tail, s->iq_last_desc_type);
}
}
}
vtd_root_table_setup(s);
/* Ok - report back to driver */
vtd_set_clear_mask_long(s, DMAR_GSTS_REG, 0, VTD_GSTS_RTPS);
+ vtd_reset_caches(s);
+ vtd_address_space_refresh_all(s);
}
/* Set Interrupt Remap Table Pointer */
vtd_set_clear_mask_long(s, DMAR_GSTS_REG, VTD_GSTS_TES, 0);
}
- vtd_switch_address_space_all(s);
+ vtd_reset_caches(s);
+ vtd_address_space_refresh_all(s);
}
/* Handle Interrupt Remap Enable/Disable */
/* Context-cache invalidation request */
if (val & VTD_CCMD_ICC) {
if (s->qi_enabled) {
- trace_vtd_err("Queued Invalidation enabled, "
- "should not use register-based invalidation");
+ error_report_once("Queued Invalidation enabled, "
+ "should not use register-based invalidation");
return;
}
ret = vtd_context_cache_invalidate(s, val);
/* IOTLB invalidation request */
if (val & VTD_TLB_IVT) {
if (s->qi_enabled) {
- trace_vtd_err("Queued Invalidation enabled, "
- "should not use register-based invalidation.");
+ error_report_once("Queued Invalidation enabled, "
+ "should not use register-based invalidation");
return;
}
ret = vtd_iotlb_flush(s, val);
dma_addr_t addr = base_addr + offset * sizeof(*inv_desc);
if (dma_memory_read(&address_space_memory, addr, inv_desc,
sizeof(*inv_desc))) {
- trace_vtd_err("Read INV DESC failed.");
+ error_report_once("Read INV DESC failed");
inv_desc->lo = 0;
inv_desc->hi = 0;
return false;
entry.iova = addr;
entry.perm = IOMMU_NONE;
entry.translated_addr = 0;
- memory_region_notify_iommu(&vtd_dev_as->iommu, entry);
+ memory_region_notify_iommu(&vtd_dev_as->iommu, 0, entry);
done:
return true;
if (s->iq_tail >= s->iq_size) {
/* Detects an invalid Tail pointer */
- trace_vtd_err_qi_tail(s->iq_tail, s->iq_size);
+ error_report_once("%s: detected invalid QI tail "
+ "(tail=0x%x, size=0x%x)",
+ __func__, s->iq_tail, s->iq_size);
vtd_handle_inv_queue_error(s);
return;
}
trace_vtd_reg_read(addr, size);
if (addr + size > DMAR_REG_SIZE) {
- trace_vtd_err("Read MMIO over range.");
+ error_report_once("%s: MMIO over range: addr=0x%" PRIx64
+ " size=0x%u", __func__, addr, size);
return (uint64_t)-1;
}
trace_vtd_reg_write(addr, size, val);
if (addr + size > DMAR_REG_SIZE) {
- trace_vtd_err("Write MMIO over range.");
+ error_report_once("%s: MMIO over range: addr=0x%" PRIx64
+ " size=0x%u", __func__, addr, size);
return;
}
/* Fault Event Address Register, 32-bit */
case DMAR_FEADDR_REG:
- assert(size == 4);
- vtd_set_long(s, addr, val);
+ if (size == 4) {
+ vtd_set_long(s, addr, val);
+ } else {
+ /*
+ * While the register is 32-bit only, some guests (Xen...) write to
+ * it with 64-bit.
+ */
+ vtd_set_quad(s, addr, val);
+ }
break;
/* Fault Event Upper Address Register, 32-bit */
}
}
-static IOMMUTLBEntry vtd_iommu_translate(MemoryRegion *iommu, hwaddr addr,
- IOMMUAccessFlags flag)
+static IOMMUTLBEntry vtd_iommu_translate(IOMMUMemoryRegion *iommu, hwaddr addr,
+ IOMMUAccessFlags flag, int iommu_idx)
{
VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
IntelIOMMUState *s = vtd_as->iommu_state;
iotlb.iova, iotlb.translated_addr,
iotlb.addr_mask);
} else {
- trace_vtd_err_dmar_translate(pci_bus_num(vtd_as->bus),
- VTD_PCI_SLOT(vtd_as->devfn),
- VTD_PCI_FUNC(vtd_as->devfn),
- iotlb.iova);
+ error_report_once("%s: detected translation failure "
+ "(dev=%02x:%02x:%02x, iova=0x%" PRIx64 ")",
+ __func__, pci_bus_num(vtd_as->bus),
+ VTD_PCI_SLOT(vtd_as->devfn),
+ VTD_PCI_FUNC(vtd_as->devfn),
+ iotlb.iova);
}
return iotlb;
}
-static void vtd_iommu_notify_flag_changed(MemoryRegion *iommu,
+static void vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu,
IOMMUNotifierFlag old,
IOMMUNotifierFlag new)
{
VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu);
IntelIOMMUState *s = vtd_as->iommu_state;
- IntelIOMMUNotifierNode *node = NULL;
- IntelIOMMUNotifierNode *next_node = NULL;
if (!s->caching_mode && new & IOMMU_NOTIFIER_MAP) {
- error_report("We need to set cache_mode=1 for intel-iommu to enable "
+ error_report("We need to set caching-mode=1 for intel-iommu to enable "
"device assignment with IOMMU protection.");
exit(1);
}
+ /* Update per-address-space notifier flags */
+ vtd_as->notifier_flags = new;
+
if (old == IOMMU_NOTIFIER_NONE) {
- node = g_malloc0(sizeof(*node));
- node->vtd_as = vtd_as;
- QLIST_INSERT_HEAD(&s->notifiers_list, node, next);
- return;
+ QLIST_INSERT_HEAD(&s->vtd_as_with_notifiers, vtd_as, next);
+ } else if (new == IOMMU_NOTIFIER_NONE) {
+ QLIST_REMOVE(vtd_as, next);
}
+}
- /* update notifier node with new flags */
- QLIST_FOREACH_SAFE(node, &s->notifiers_list, next, next_node) {
- if (node->vtd_as == vtd_as) {
- if (new == IOMMU_NOTIFIER_NONE) {
- QLIST_REMOVE(node, next);
- g_free(node);
- }
- return;
- }
- }
+static int vtd_post_load(void *opaque, int version_id)
+{
+ IntelIOMMUState *iommu = opaque;
+
+ /*
+ * Memory regions are dynamically turned on/off depending on
+ * context entry configurations from the guest. After migration,
+ * we need to make sure the memory regions are still correct.
+ */
+ vtd_switch_address_space_all(iommu);
+
+ return 0;
}
static const VMStateDescription vtd_vmstate = {
.version_id = 1,
.minimum_version_id = 1,
.priority = MIG_PRI_IOMMU,
+ .post_load = vtd_post_load,
.fields = (VMStateField[]) {
VMSTATE_UINT64(root, IntelIOMMUState),
VMSTATE_UINT64(intr_root, IntelIOMMUState),
DEFINE_PROP_ON_OFF_AUTO("eim", IntelIOMMUState, intr_eim,
ON_OFF_AUTO_AUTO),
DEFINE_PROP_BOOL("x-buggy-eim", IntelIOMMUState, buggy_eim, false),
+ DEFINE_PROP_UINT8("x-aw-bits", IntelIOMMUState, aw_bits,
+ VTD_HOST_ADDRESS_WIDTH),
DEFINE_PROP_BOOL("caching-mode", IntelIOMMUState, caching_mode, FALSE),
DEFINE_PROP_END_OF_LIST(),
};
addr = iommu->intr_root + index * sizeof(*entry);
if (dma_memory_read(&address_space_memory, addr, entry,
sizeof(*entry))) {
- trace_vtd_err("Memory read failed for IRTE.");
+ error_report_once("%s: read failed: ind=0x%x addr=0x%" PRIx64,
+ __func__, index, addr);
return -VTD_FR_IR_ROOT_INVAL;
}
le64_to_cpu(entry->data[0]));
if (!entry->irte.present) {
- trace_vtd_err_irte(index, le64_to_cpu(entry->data[1]),
- le64_to_cpu(entry->data[0]));
+ error_report_once("%s: detected non-present IRTE "
+ "(index=%u, high=0x%" PRIx64 ", low=0x%" PRIx64 ")",
+ __func__, index, le64_to_cpu(entry->data[1]),
+ le64_to_cpu(entry->data[0]));
return -VTD_FR_IR_ENTRY_P;
}
if (entry->irte.__reserved_0 || entry->irte.__reserved_1 ||
entry->irte.__reserved_2) {
- trace_vtd_err_irte(index, le64_to_cpu(entry->data[1]),
- le64_to_cpu(entry->data[0]));
+ error_report_once("%s: detected non-zero reserved IRTE "
+ "(index=%u, high=0x%" PRIx64 ", low=0x%" PRIx64 ")",
+ __func__, index, le64_to_cpu(entry->data[1]),
+ le64_to_cpu(entry->data[0]));
return -VTD_FR_IR_IRTE_RSVD;
}
case VTD_SVT_ALL:
mask = vtd_svt_mask[entry->irte.sid_q];
if ((source_id & mask) != (sid & mask)) {
- trace_vtd_err_irte_sid(index, sid, source_id);
+ error_report_once("%s: invalid IRTE SID "
+ "(index=%u, sid=%u, source_id=%u)",
+ __func__, index, sid, source_id);
return -VTD_FR_IR_SID_ERR;
}
break;
bus_min = source_id & 0xff;
bus = sid >> 8;
if (bus > bus_max || bus < bus_min) {
- trace_vtd_err_irte_sid_bus(index, bus, bus_min, bus_max);
+ error_report_once("%s: invalid SVT_BUS "
+ "(index=%u, bus=%u, min=%u, max=%u)",
+ __func__, index, bus, bus_min, bus_max);
return -VTD_FR_IR_SID_ERR;
}
break;
default:
- trace_vtd_err_irte_svt(index, entry->irte.sid_vtype);
+ error_report_once("%s: detected invalid IRTE SVT "
+ "(index=%u, type=%d)", __func__,
+ index, entry->irte.sid_vtype);
/* Take this as verification failure. */
return -VTD_FR_IR_SID_ERR;
break;
/* Fetch IRQ information of specific IR index */
static int vtd_remap_irq_get(IntelIOMMUState *iommu, uint16_t index,
- VTDIrq *irq, uint16_t sid)
+ X86IOMMUIrq *irq, uint16_t sid)
{
VTD_IR_TableEntry irte = {};
int ret = 0;
return 0;
}
-/* Generate one MSI message from VTDIrq info */
-static void vtd_generate_msi_message(VTDIrq *irq, MSIMessage *msg_out)
-{
- VTD_MSIMessage msg = {};
-
- /* Generate address bits */
- msg.dest_mode = irq->dest_mode;
- msg.redir_hint = irq->redir_hint;
- msg.dest = irq->dest;
- msg.__addr_hi = irq->dest & 0xffffff00;
- msg.__addr_head = cpu_to_le32(0xfee);
- /* Keep this from original MSI address bits */
- msg.__not_used = irq->msi_addr_last_bits;
-
- /* Generate data bits */
- msg.vector = irq->vector;
- msg.delivery_mode = irq->delivery_mode;
- msg.level = 1;
- msg.trigger_mode = irq->trigger_mode;
-
- msg_out->address = msg.msi_addr;
- msg_out->data = msg.msi_data;
-}
-
/* Interrupt remapping for MSI/MSI-X entry */
static int vtd_interrupt_remap_msi(IntelIOMMUState *iommu,
MSIMessage *origin,
int ret = 0;
VTD_IR_MSIAddress addr;
uint16_t index;
- VTDIrq irq = {};
+ X86IOMMUIrq irq = {};
assert(origin && translated);
}
if (origin->address & VTD_MSI_ADDR_HI_MASK) {
- trace_vtd_err("MSI address high 32 bits non-zero when "
- "Interrupt Remapping enabled.");
+ error_report_once("%s: MSI address high 32 bits non-zero detected: "
+ "address=0x%" PRIx64, __func__, origin->address);
return -VTD_FR_IR_REQ_RSVD;
}
addr.data = origin->address & VTD_MSI_ADDR_LO_MASK;
if (addr.addr.__head != 0xfee) {
- trace_vtd_err("MSI addr low 32 bit invalid.");
+ error_report_once("%s: MSI address low 32 bit invalid: 0x%" PRIx32,
+ __func__, addr.data);
return -VTD_FR_IR_REQ_RSVD;
}
if (addr.addr.sub_valid) {
trace_vtd_ir_remap_type("MSI");
if (origin->data & VTD_IR_MSI_DATA_RESERVED) {
- trace_vtd_err_ir_msi_invalid(sid, origin->address, origin->data);
+ error_report_once("%s: invalid IR MSI "
+ "(sid=%u, address=0x%" PRIx64
+ ", data=0x%" PRIx32 ")",
+ __func__, sid, origin->address, origin->data);
return -VTD_FR_IR_REQ_RSVD;
}
} else {
*/
irq.msi_addr_last_bits = addr.addr.__not_care;
- /* Translate VTDIrq to MSI message */
- vtd_generate_msi_message(&irq, translated);
+ /* Translate X86IOMMUIrq to MSI message */
+ x86_iommu_irq_to_msi_message(&irq, translated);
out:
trace_vtd_ir_remap_msi(origin->address, origin->data,
*new_key = (uintptr_t)bus;
/* No corresponding free() */
vtd_bus = g_malloc0(sizeof(VTDBus) + sizeof(VTDAddressSpace *) * \
- X86_IOMMU_PCI_DEVFN_MAX);
+ PCI_DEVFN_MAX);
vtd_bus->bus = bus;
g_hash_table_insert(s->vtd_as_by_busptr, new_key, vtd_bus);
}
vtd_dev_as->devfn = (uint8_t)devfn;
vtd_dev_as->iommu_state = s;
vtd_dev_as->context_cache_entry.context_cache_gen = 0;
+ vtd_dev_as->iova_tree = iova_tree_new();
/*
* Memory region relationships looks like (Address range shows
* vtd_sys_alias and intel_iommu regions. IR region is always
* enabled.
*/
- memory_region_init_iommu(&vtd_dev_as->iommu, OBJECT(s),
- &s->iommu_ops, "intel_iommu_dmar",
+ memory_region_init_iommu(&vtd_dev_as->iommu, sizeof(vtd_dev_as->iommu),
+ TYPE_INTEL_IOMMU_MEMORY_REGION, OBJECT(s),
+ "intel_iommu_dmar",
UINT64_MAX);
memory_region_init_alias(&vtd_dev_as->sys_alias, OBJECT(s),
"vtd_sys_alias", get_system_memory(),
memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
&vtd_dev_as->sys_alias, 1);
memory_region_add_subregion_overlap(&vtd_dev_as->root, 0,
- &vtd_dev_as->iommu, 1);
+ MEMORY_REGION(&vtd_dev_as->iommu),
+ 1);
vtd_switch_address_space(vtd_dev_as);
}
return vtd_dev_as;
hwaddr size;
hwaddr start = n->start;
hwaddr end = n->end;
+ IntelIOMMUState *s = as->iommu_state;
+ DMAMap map;
/*
* Note: all the codes in this function has a assumption that IOVA
* VT-d spec), otherwise we need to consider overflow of 64 bits.
*/
- if (end > VTD_ADDRESS_SIZE) {
+ if (end > VTD_ADDRESS_SIZE(s->aw_bits)) {
/*
* Don't need to unmap regions that is bigger than the whole
* VT-d supported address space size
*/
- end = VTD_ADDRESS_SIZE;
+ end = VTD_ADDRESS_SIZE(s->aw_bits);
}
assert(start <= end);
* suite the minimum available mask.
*/
int n = 64 - clz64(size);
- if (n > VTD_MGAW) {
+ if (n > s->aw_bits) {
/* should not happen, but in case it happens, limit it */
- n = VTD_MGAW;
+ n = s->aw_bits;
}
size = 1ULL << n;
}
VTD_PCI_FUNC(as->devfn),
entry.iova, size);
+ map.iova = entry.iova;
+ map.size = entry.addr_mask;
+ iova_tree_remove(as->iova_tree, &map);
+
memory_region_notify_one(n, &entry);
}
static void vtd_address_space_unmap_all(IntelIOMMUState *s)
{
- IntelIOMMUNotifierNode *node;
VTDAddressSpace *vtd_as;
IOMMUNotifier *n;
- QLIST_FOREACH(node, &s->notifiers_list, next) {
- vtd_as = node->vtd_as;
+ QLIST_FOREACH(vtd_as, &s->vtd_as_with_notifiers, next) {
IOMMU_NOTIFIER_FOREACH(n, &vtd_as->iommu) {
vtd_address_space_unmap(vtd_as, n);
}
}
}
+static void vtd_address_space_refresh_all(IntelIOMMUState *s)
+{
+ vtd_address_space_unmap_all(s);
+ vtd_switch_address_space_all(s);
+}
+
static int vtd_replay_hook(IOMMUTLBEntry *entry, void *private)
{
memory_region_notify_one((IOMMUNotifier *)private, entry);
return 0;
}
-static void vtd_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n)
+static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n)
{
- VTDAddressSpace *vtd_as = container_of(mr, VTDAddressSpace, iommu);
+ VTDAddressSpace *vtd_as = container_of(iommu_mr, VTDAddressSpace, iommu);
IntelIOMMUState *s = vtd_as->iommu_state;
uint8_t bus_n = pci_bus_num(vtd_as->bus);
VTDContextEntry ce;
PCI_FUNC(vtd_as->devfn),
VTD_CONTEXT_ENTRY_DID(ce.hi),
ce.hi, ce.lo);
- vtd_page_walk(&ce, 0, ~0ULL, vtd_replay_hook, (void *)n, false);
+ if (vtd_as_has_map_notifier(vtd_as)) {
+ /* This is required only for MAP typed notifiers */
+ vtd_page_walk_info info = {
+ .hook_fn = vtd_replay_hook,
+ .private = (void *)n,
+ .notify_unmap = false,
+ .aw = s->aw_bits,
+ .as = vtd_as,
+ .domain_id = VTD_CONTEXT_ENTRY_DID(ce.hi),
+ };
+
+ vtd_page_walk(&ce, 0, ~0ULL, &info);
+ }
} else {
trace_vtd_replay_ce_invalid(bus_n, PCI_SLOT(vtd_as->devfn),
PCI_FUNC(vtd_as->devfn));
memset(s->w1cmask, 0, DMAR_REG_SIZE);
memset(s->womask, 0, DMAR_REG_SIZE);
- s->iommu_ops.translate = vtd_iommu_translate;
- s->iommu_ops.notify_flag_changed = vtd_iommu_notify_flag_changed;
- s->iommu_ops.replay = vtd_iommu_replay;
s->root = 0;
s->root_extended = false;
s->dmar_enabled = false;
s->qi_enabled = false;
s->iq_last_desc_type = VTD_INV_DESC_NONE;
s->next_frcd_reg = 0;
- s->cap = VTD_CAP_FRO | VTD_CAP_NFR | VTD_CAP_ND | VTD_CAP_MGAW |
- VTD_CAP_SAGAW | VTD_CAP_MAMV | VTD_CAP_PSI | VTD_CAP_SLLPS;
+ s->cap = VTD_CAP_FRO | VTD_CAP_NFR | VTD_CAP_ND |
+ VTD_CAP_MAMV | VTD_CAP_PSI | VTD_CAP_SLLPS |
+ VTD_CAP_SAGAW_39bit | VTD_CAP_MGAW(s->aw_bits);
+ if (s->aw_bits == VTD_HOST_AW_48BIT) {
+ s->cap |= VTD_CAP_SAGAW_48bit;
+ }
s->ecap = VTD_ECAP_QI | VTD_ECAP_IRO;
+ /*
+ * Rsvd field masks for spte
+ */
+ vtd_paging_entry_rsvd_field[0] = ~0ULL;
+ vtd_paging_entry_rsvd_field[1] = VTD_SPTE_PAGE_L1_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[2] = VTD_SPTE_PAGE_L2_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[3] = VTD_SPTE_PAGE_L3_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[4] = VTD_SPTE_PAGE_L4_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[5] = VTD_SPTE_LPAGE_L1_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[6] = VTD_SPTE_LPAGE_L2_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[7] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits);
+ vtd_paging_entry_rsvd_field[8] = VTD_SPTE_LPAGE_L4_RSVD_MASK(s->aw_bits);
+
if (x86_iommu->intr_supported) {
s->ecap |= VTD_ECAP_IR | VTD_ECAP_MHMV;
if (s->intr_eim == ON_OFF_AUTO_ON) {
s->cap |= VTD_CAP_CM;
}
- vtd_reset_context_cache(s);
- vtd_reset_iotlb(s);
+ vtd_reset_caches(s);
/* Define registers with default values and bit semantics */
vtd_define_long(s, DMAR_VER_REG, 0x10UL, 0, 0);
IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev);
vtd_init(s);
-
- /*
- * When device reset, throw away all mappings and external caches
- */
- vtd_address_space_unmap_all(s);
+ vtd_address_space_refresh_all(s);
}
static AddressSpace *vtd_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
IntelIOMMUState *s = opaque;
VTDAddressSpace *vtd_as;
- assert(0 <= devfn && devfn < X86_IOMMU_PCI_DEVFN_MAX);
+ assert(0 <= devfn && devfn < PCI_DEVFN_MAX);
vtd_as = vtd_find_add_as(s, bus, devfn);
return &vtd_as->as;
{
X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s);
- /* Currently Intel IOMMU IR only support "kernel-irqchip={off|split}" */
- if (x86_iommu->intr_supported && kvm_irqchip_in_kernel() &&
- !kvm_irqchip_is_split()) {
- error_setg(errp, "Intel Interrupt Remapping cannot work with "
- "kernel-irqchip=on, please use 'split|off'.");
- return false;
- }
if (s->intr_eim == ON_OFF_AUTO_ON && !x86_iommu->intr_supported) {
error_setg(errp, "eim=on cannot be selected without intremap=on");
return false;
}
}
+ /* 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 x-aw-bits are: %d, %d",
+ VTD_HOST_AW_39BIT, VTD_HOST_AW_48BIT);
+ return false;
+ }
+
return true;
}
static void vtd_realize(DeviceState *dev, Error **errp)
{
MachineState *ms = MACHINE(qdev_get_machine());
- MachineClass *mc = MACHINE_GET_CLASS(ms);
- PCMachineState *pcms =
- PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE));
- PCIBus *bus;
+ PCMachineState *pcms = PC_MACHINE(ms);
+ PCIBus *bus = pcms->bus;
IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev);
X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev);
- if (!pcms) {
- error_setg(errp, "Machine-type '%s' not supported by intel-iommu",
- mc->name);
- return;
- }
-
- bus = pcms->bus;
x86_iommu->type = TYPE_INTEL;
if (!vtd_decide_config(s, errp)) {
return;
}
- QLIST_INIT(&s->notifiers_list);
+ QLIST_INIT(&s->vtd_as_with_notifiers);
+ qemu_mutex_init(&s->iommu_lock);
memset(s->vtd_as_by_bus_num, 0, sizeof(s->vtd_as_by_bus_num));
memory_region_init_io(&s->csrmem, OBJECT(s), &vtd_mem_ops, s,
"intel_iommu", DMAR_REG_SIZE);
.class_init = vtd_class_init,
};
+static void vtd_iommu_memory_region_class_init(ObjectClass *klass,
+ void *data)
+{
+ IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_CLASS(klass);
+
+ imrc->translate = vtd_iommu_translate;
+ imrc->notify_flag_changed = vtd_iommu_notify_flag_changed;
+ imrc->replay = vtd_iommu_replay;
+}
+
+static const TypeInfo vtd_iommu_memory_region_info = {
+ .parent = TYPE_IOMMU_MEMORY_REGION,
+ .name = TYPE_INTEL_IOMMU_MEMORY_REGION,
+ .class_init = vtd_iommu_memory_region_class_init,
+};
+
static void vtd_register_types(void)
{
type_register_static(&vtd_info);
+ type_register_static(&vtd_iommu_memory_region_info);
}
type_init(vtd_register_types)