@@ -74,6 +74,8 @@ struct npu_link {
u16 fn_desired_actags[8];
struct actag_range fn_actags[8];
bool assignment_done;
+ struct iommu_group *group;
+ struct platform_data data;
};
static struct list_head links_list = LIST_HEAD_INIT(links_list);
static DEFINE_MUTEX(links_list_lock);
@@ -603,54 +605,56 @@ int pnv_ocxl_platform_setup(struct pci_dev *dev, int PE_mask,
{
struct pci_controller *hose = pci_bus_to_host(dev->bus);
struct pnv_phb *phb = hose->private_data;
- struct platform_data *data;
+ struct npu_link *link = NULL;
int xsl_irq;
u32 bdfn;
- int rc;
-
- data = kzalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
+ int rc = 0;
- rc = alloc_spa(dev, data);
- if (rc) {
- kfree(data);
- return rc;
+ mutex_lock(&links_list_lock);
+ link = find_link(dev);
+ if (!link) {
+ dev_err(&dev->dev, "Failed to setup platform\n");
+ mutex_unlock(&links_list_lock);
+ return -ENODEV;
}
+ rc = alloc_spa(dev, &link->data);
+ if (rc)
+ goto unlock;
+
rc = get_xsl_irq(dev, &xsl_irq);
if (rc) {
- free_spa(data);
- kfree(data);
- return rc;
+ free_spa(&link->data);
+ goto unlock;
}
- rc = map_xsl_regs(dev, &data->dsisr, &data->dar, &data->tfc,
- &data->pe_handle);
+ rc = map_xsl_regs(dev, &link->data.dsisr, &link->data.dar,
+ &link->data.tfc, &link->data.pe_handle);
if (rc) {
- free_spa(data);
- kfree(data);
- return rc;
+ free_spa(&link->data);
+ goto unlock;
}
bdfn = (dev->bus->number << 8) | dev->devfn;
rc = opal_npu_spa_setup(phb->opal_id, bdfn,
- virt_to_phys(data->spa->spa_mem),
+ virt_to_phys(link->data.spa->spa_mem),
PE_mask);
if (rc) {
dev_err(&dev->dev, "Can't setup Shared Process Area: %d\n", rc);
- unmap_xsl_regs(data->dsisr, data->dar, data->tfc,
- data->pe_handle);
- free_spa(data);
- kfree(data);
- return rc;
+ unmap_xsl_regs(link->data.dsisr, link->data.dar,
+ link->data.tfc, link->data.pe_handle);
+ free_spa(&link->data);
+ goto unlock;
}
- data->phb_opal_id = phb->opal_id;
- data->bdfn = bdfn;
- *platform_data = (void *) data;
+ link->data.phb_opal_id = phb->opal_id;
+ link->data.bdfn = bdfn;
*hwirq = xsl_irq;
- return 0;
+ *platform_data = (void *)&link->data;
+
+unlock:
+ mutex_unlock(&links_list_lock);
+ return rc;
}
EXPORT_SYMBOL_GPL(pnv_ocxl_platform_setup);
@@ -682,11 +686,13 @@ void pnv_ocxl_platform_release(void *platform_data)
struct platform_data *data = (struct platform_data *)platform_data;
int rc;
- rc = opal_npu_spa_setup(data->phb_opal_id, data->bdfn, 0, 0);
- WARN_ON(rc);
- unmap_xsl_regs(data->dsisr, data->dar, data->tfc, data->pe_handle);
- free_spa(data);
- kfree(data);
+ if (data->spa) {
+ rc = opal_npu_spa_setup(data->phb_opal_id, data->bdfn, 0, 0);
+ WARN_ON(rc);
+ unmap_xsl_regs(data->dsisr, data->dar, data->tfc,
+ data->pe_handle);
+ free_spa(data);
+ }
}
EXPORT_SYMBOL_GPL(pnv_ocxl_platform_release);
@@ -837,3 +843,95 @@ int pnv_ocxl_remove_pe(void *platform_data, int pasid, u32 *pid,
return remove_pe_from_cache(data, *pe_handle);
}
EXPORT_SYMBOL_GPL(pnv_ocxl_remove_pe);
+
+static void take_ownership(struct iommu_table_group *table_group)
+{
+}
+
+static void release_ownership(struct iommu_table_group *table_group)
+{
+ struct pnv_ioda_pe *pe = container_of(table_group,
+ struct pnv_ioda_pe,
+ table_group);
+ struct npu_link *link = NULL;
+
+ mutex_lock(&links_list_lock);
+
+ link = find_link(pe->pdev);
+ if (!link)
+ return;
+
+ if (link->data.spa)
+ pnv_ocxl_platform_release(&link->data);
+
+ mutex_unlock(&links_list_lock);
+}
+
+static long set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ return 0;
+}
+
+static long unset_window(struct iommu_table_group *table_group,
+ int num)
+{
+ return 0;
+}
+
+static long create_table(struct iommu_table_group *table_group,
+ int num, __u32 page_shift, __u64 window_size,
+ __u32 levels, struct iommu_table **ptbl)
+{
+ return 0;
+}
+
+static struct iommu_table_group_ops pnv_ocxl_ops = {
+ .take_ownership = take_ownership,
+ .release_ownership = release_ownership,
+ .set_window = set_window,
+ .unset_window = unset_window,
+ .create_table = create_table,
+};
+
+static void group_release(void *iommu_data)
+{
+ struct iommu_table_group *table_group = iommu_data;
+
+ table_group->group = NULL;
+}
+
+struct iommu_table_group *pnv_ocxl_setup_table_group(struct pnv_ioda_pe *pe)
+{
+ struct iommu_table_group *table_group;
+ struct npu_link *link = NULL;
+ struct pci_controller *hose;
+
+ mutex_lock(&links_list_lock);
+
+ /* The functions of a device all share the same link and by
+ * default the same table group
+ */
+ link = find_link(pe->pdev);
+ if (!link)
+ return NULL;
+
+ hose = pe->phb->hose;
+ table_group = &pe->table_group;
+ table_group->ops = &pnv_ocxl_ops;
+ if (link->group) {
+ table_group->group = link->group;
+ iommu_group_set_iommudata(link->group, table_group,
+ group_release);
+ } else {
+ if (!table_group->group) {
+ iommu_register_group(table_group,
+ hose->global_number,
+ pe->pe_number);
+ link->group = table_group->group;
+ }
+ }
+
+ mutex_unlock(&links_list_lock);
+ return table_group;
+}
@@ -2629,22 +2629,27 @@ static void pnv_pci_ioda_setup_iommu_api(void)
list_for_each_entry(hose, &hose_list, list_node) {
phb = hose->private_data;
- if (phb->type == PNV_PHB_NPU_NVLINK ||
- phb->type == PNV_PHB_NPU_OCAPI)
+ if (phb->type == PNV_PHB_NPU_NVLINK)
continue;
list_for_each_entry(pe, &phb->ioda.pe_list, list) {
struct iommu_table_group *table_group;
- table_group = pnv_try_setup_npu_table_group(pe);
- if (!table_group) {
- if (!pnv_pci_ioda_pe_dma_weight(pe))
+ if (phb->type == PNV_PHB_NPU_OCAPI) {
+ table_group = pnv_ocxl_setup_table_group(pe);
+ if (!table_group)
continue;
+ } else {
+ table_group = pnv_try_setup_npu_table_group(pe);
+ if (!table_group) {
+ if (!pnv_pci_ioda_pe_dma_weight(pe))
+ continue;
- table_group = &pe->table_group;
- iommu_register_group(&pe->table_group,
+ table_group = &pe->table_group;
+ iommu_register_group(&pe->table_group,
pe->phb->hose->global_number,
pe->pe_number);
+ }
}
pnv_ioda_setup_bus_iommu_group(pe, table_group,
pe->pbus);
@@ -218,6 +218,19 @@ extern struct iommu_table_group *pnv_try_setup_npu_table_group(
extern struct iommu_table_group *pnv_npu_compound_attach(
struct pnv_ioda_pe *pe);
+/* OpenCAPI functions */
+#if IS_ENABLED(CONFIG_OCXL_BASE)
+extern struct iommu_table_group *pnv_ocxl_setup_table_group(
+ struct pnv_ioda_pe *pe);
+#else
+static inline struct iommu_table_group *pnv_ocxl_setup_table_group(
+ struct pnv_ioda_pe *pe)
+{
+ return NULL;
+}
+#endif /* CONFIG_OCXL_BASE */
+
+
/* pci-ioda-tce.c */
#define POWERNV_IOMMU_DEFAULT_LEVELS 1
#define POWERNV_IOMMU_MAX_LEVELS 5
This patch adds group registration for the OpenCAPI devices. An unique iommu group is register for multiple PE, ie for a set of multiple devices sharing the same domain, same bus and same slot. This groud registration will be used to assign an OpenCAPI device to a guest to participate in VFIO, like vfio-pci. The release_ownership hook is used to disable the Scheduled Process Area and clean allocated data if it's not done previously when the ocxl driver is unloaded. To support multiple OpenCAPI devices on the same machine, iommu group and platform data are declared in the npu_link which is common for each devices sharing the same domain, same bus and same slot. Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com> --- arch/powerpc/platforms/powernv/ocxl.c | 164 +++++++++++++++++----- arch/powerpc/platforms/powernv/pci-ioda.c | 19 ++- arch/powerpc/platforms/powernv/pci.h | 13 ++ 3 files changed, 156 insertions(+), 40 deletions(-)