return 0;
}
-static int __init
-dmar_parse_dev(struct dmar_drhd_unit *dmaru)
+static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
{
struct acpi_dmar_hardware_unit *drhd;
- static int include_all;
- int ret;
+ int ret = 0;
drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
- if (!dmaru->include_all)
- ret = dmar_parse_dev_scope((void *)(drhd + 1),
+ if (dmaru->include_all)
+ return 0;
+
+ ret = dmar_parse_dev_scope((void *)(drhd + 1),
((void *)drhd) + drhd->header.length,
&dmaru->devices_cnt, &dmaru->devices,
drhd->segment);
- else {
- /* Only allow one INCLUDE_ALL */
- if (include_all) {
- printk(KERN_WARNING PREFIX "Only one INCLUDE_ALL "
- "device scope is allowed\n");
- ret = -EINVAL;
- }
- include_all = 1;
- }
-
- if (ret || (dmaru->devices_cnt == 0 && !dmaru->include_all)) {
+ if (ret) {
list_del(&dmaru->list);
kfree(dmaru);
}
drhd = (struct acpi_dmar_hardware_unit *)header;
printk (KERN_INFO PREFIX
"DRHD (flags: 0x%08x)base: 0x%016Lx\n",
- drhd->flags, drhd->address);
+ drhd->flags, (unsigned long long)drhd->address);
break;
case ACPI_DMAR_TYPE_RESERVED_MEMORY:
rmrr = (struct acpi_dmar_reserved_memory *)header;
printk (KERN_INFO PREFIX
"RMRR base: 0x%016Lx end: 0x%016Lx\n",
- rmrr->base_address, rmrr->end_address);
+ (unsigned long long)rmrr->base_address,
+ (unsigned long long)rmrr->end_address);
break;
}
}
+/**
+ * dmar_table_detect - checks to see if the platform supports DMAR devices
+ */
+static int __init dmar_table_detect(void)
+{
+ acpi_status status = AE_OK;
+
+ /* if we could find DMAR table, then there are DMAR devices */
+ status = acpi_get_table(ACPI_SIG_DMAR, 0,
+ (struct acpi_table_header **)&dmar_tbl);
+
+ if (ACPI_SUCCESS(status) && !dmar_tbl) {
+ printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
+ status = AE_NOT_FOUND;
+ }
+
+ return (ACPI_SUCCESS(status) ? 1 : 0);
+}
/**
* parse_dmar_table - parses the DMA reporting table
struct acpi_dmar_header *entry_header;
int ret = 0;
+ /*
+ * Do it again, earlier dmar_tbl mapping could be mapped with
+ * fixed map.
+ */
+ dmar_table_detect();
+
dmar = (struct acpi_table_dmar *)dmar_tbl;
if (!dmar)
return -ENODEV;
- if (dmar->width < PAGE_SHIFT_4K - 1) {
+ if (dmar->width < PAGE_SHIFT - 1) {
printk(KERN_WARNING PREFIX "Invalid DMAR haw\n");
return -EINVAL;
}
entry_header = (struct acpi_dmar_header *)(dmar + 1);
while (((unsigned long)entry_header) <
(((unsigned long)dmar) + dmar_tbl->length)) {
+ /* Avoid looping forever on bad ACPI tables */
+ if (entry_header->length == 0) {
+ printk(KERN_WARNING PREFIX
+ "Invalid 0-length structure\n");
+ ret = -EINVAL;
+ break;
+ }
+
dmar_table_print_dmar_entry(entry_header);
switch (entry_header->type) {
struct dmar_drhd_unit *
dmar_find_matched_drhd_unit(struct pci_dev *dev)
{
- struct dmar_drhd_unit *drhd = NULL;
+ struct dmar_drhd_unit *dmaru = NULL;
+ struct acpi_dmar_hardware_unit *drhd;
+
+ list_for_each_entry(dmaru, &dmar_drhd_units, list) {
+ drhd = container_of(dmaru->hdr,
+ struct acpi_dmar_hardware_unit,
+ header);
- list_for_each_entry(drhd, &dmar_drhd_units, list) {
- if (drhd->include_all || dmar_pci_device_match(drhd->devices,
- drhd->devices_cnt, dev))
- return drhd;
+ if (dmaru->include_all &&
+ drhd->segment == pci_domain_nr(dev->bus))
+ return dmaru;
+
+ if (dmar_pci_device_match(dmaru->devices,
+ dmaru->devices_cnt, dev))
+ return dmaru;
}
return NULL;
int __init dmar_dev_scope_init(void)
{
- struct dmar_drhd_unit *drhd;
+ struct dmar_drhd_unit *drhd, *drhd_n;
int ret = -ENODEV;
- for_each_drhd_unit(drhd) {
+ list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
ret = dmar_parse_dev(drhd);
if (ret)
return ret;
#ifdef CONFIG_DMAR
{
- struct dmar_rmrr_unit *rmrr;
- for_each_rmrr_units(rmrr) {
+ struct dmar_rmrr_unit *rmrr, *rmrr_n;
+ list_for_each_entry_safe(rmrr, rmrr_n, &dmar_rmrr_units, list) {
ret = rmrr_parse_dev(rmrr);
if (ret)
return ret;
return 0;
}
-/**
- * early_dmar_detect - checks to see if the platform supports DMAR devices
- */
-int __init early_dmar_detect(void)
-{
- acpi_status status = AE_OK;
-
- /* if we could find DMAR table, then there are DMAR devices */
- status = acpi_get_table(ACPI_SIG_DMAR, 0,
- (struct acpi_table_header **)&dmar_tbl);
-
- if (ACPI_SUCCESS(status) && !dmar_tbl) {
- printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
- status = AE_NOT_FOUND;
- }
-
- return (ACPI_SUCCESS(status) ? 1 : 0);
-}
-
void __init detect_intel_iommu(void)
{
int ret;
- ret = early_dmar_detect();
+ ret = dmar_table_detect();
-#ifdef CONFIG_DMAR
{
+#ifdef CONFIG_INTR_REMAP
struct acpi_table_dmar *dmar;
/*
* for now we will disable dma-remapping when interrupt
* is added, we will not need this any more.
*/
dmar = (struct acpi_table_dmar *) dmar_tbl;
- if (ret && cpu_has_x2apic && dmar->flags & 0x1) {
+ if (ret && cpu_has_x2apic && dmar->flags & 0x1)
printk(KERN_INFO
"Queued invalidation will be enabled to support "
"x2apic and Intr-remapping.\n");
- printk(KERN_INFO
- "Disabling IOMMU detection, because of missing "
- "queued invalidation support for IOTLB "
- "invalidation\n");
- printk(KERN_INFO
- "Use \"nox2apic\", if you want to use Intel "
- " IOMMU for DMA-remapping and don't care about "
- " x2apic support\n");
-
- dmar_disabled = 1;
- return;
- }
-
+#endif
+#ifdef CONFIG_DMAR
if (ret && !no_iommu && !iommu_detected && !swiotlb &&
!dmar_disabled)
iommu_detected = 1;
- }
#endif
+ }
+ dmar_tbl = NULL;
}
int map_size;
u32 ver;
static int iommu_allocated = 0;
+ int agaw = 0;
iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
if (!iommu)
iommu->seq_id = iommu_allocated++;
- iommu->reg = ioremap(drhd->reg_base_addr, PAGE_SIZE_4K);
+ iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
if (!iommu->reg) {
printk(KERN_ERR "IOMMU: can't map the region\n");
goto error;
iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
+#ifdef CONFIG_DMAR
+ agaw = iommu_calculate_agaw(iommu);
+ if (agaw < 0) {
+ printk(KERN_ERR
+ "Cannot get a valid agaw for iommu (seq_id = %d)\n",
+ iommu->seq_id);
+ goto error;
+ }
+#endif
+ iommu->agaw = agaw;
+
/* the registers might be more than one page */
map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
cap_max_fault_reg_offset(iommu->cap));
- map_size = PAGE_ALIGN_4K(map_size);
- if (map_size > PAGE_SIZE_4K) {
+ map_size = VTD_PAGE_ALIGN(map_size);
+ if (map_size > VTD_PAGE_SIZE) {
iounmap(iommu->reg);
iommu->reg = ioremap(drhd->reg_base_addr, map_size);
if (!iommu->reg) {
ver = readl(iommu->reg + DMAR_VER_REG);
pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
- drhd->reg_base_addr, DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
- iommu->cap, iommu->ecap);
+ (unsigned long long)drhd->reg_base_addr,
+ DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
+ (unsigned long long)iommu->cap,
+ (unsigned long long)iommu->ecap);
spin_lock_init(&iommu->register_lock);
}
}
+static int qi_check_fault(struct intel_iommu *iommu, int index)
+{
+ u32 fault;
+ int head;
+ struct q_inval *qi = iommu->qi;
+ int wait_index = (index + 1) % QI_LENGTH;
+
+ fault = readl(iommu->reg + DMAR_FSTS_REG);
+
+ /*
+ * If IQE happens, the head points to the descriptor associated
+ * with the error. No new descriptors are fetched until the IQE
+ * is cleared.
+ */
+ if (fault & DMA_FSTS_IQE) {
+ head = readl(iommu->reg + DMAR_IQH_REG);
+ if ((head >> 4) == index) {
+ memcpy(&qi->desc[index], &qi->desc[wait_index],
+ sizeof(struct qi_desc));
+ __iommu_flush_cache(iommu, &qi->desc[index],
+ sizeof(struct qi_desc));
+ writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
/*
* Submit the queued invalidation descriptor to the remapping
* hardware unit and wait for its completion.
*/
-void qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
+int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
{
+ int rc = 0;
struct q_inval *qi = iommu->qi;
struct qi_desc *hw, wait_desc;
int wait_index, index;
unsigned long flags;
if (!qi)
- return;
+ return 0;
hw = qi->desc;
hw[index] = *desc;
- wait_desc.low = QI_IWD_STATUS_DATA(2) | QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
+ wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
+ QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);
hw[wait_index] = wait_desc;
qi->free_head = (qi->free_head + 2) % QI_LENGTH;
qi->free_cnt -= 2;
- spin_lock(&iommu->register_lock);
/*
* update the HW tail register indicating the presence of
* new descriptors.
*/
writel(qi->free_head << 4, iommu->reg + DMAR_IQT_REG);
- spin_unlock(&iommu->register_lock);
while (qi->desc_status[wait_index] != QI_DONE) {
/*
* a deadlock where the interrupt context can wait indefinitely
* for free slots in the queue.
*/
+ rc = qi_check_fault(iommu, index);
+ if (rc)
+ goto out;
+
spin_unlock(&qi->q_lock);
cpu_relax();
spin_lock(&qi->q_lock);
}
-
- qi->desc_status[index] = QI_DONE;
+out:
+ qi->desc_status[index] = qi->desc_status[wait_index] = QI_DONE;
reclaim_free_desc(qi);
spin_unlock_irqrestore(&qi->q_lock, flags);
+
+ return rc;
}
/*
desc.low = QI_IEC_TYPE;
desc.high = 0;
+ /* should never fail */
qi_submit_sync(&desc, iommu);
}
int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
u64 type, int non_present_entry_flush)
{
-
struct qi_desc desc;
if (non_present_entry_flush) {
| QI_CC_GRAN(type) | QI_CC_TYPE;
desc.high = 0;
- qi_submit_sync(&desc, iommu);
-
- return 0;
-
+ return qi_submit_sync(&desc, iommu);
}
int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
| QI_IOTLB_AM(size_order);
- qi_submit_sync(&desc, iommu);
-
- return 0;
-
+ return qi_submit_sync(&desc, iommu);
}
/*