summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorAlexey Kardashevskiy <aik@ozlabs.ru>2015-06-05 16:35:26 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2015-06-11 15:16:55 +1000
commite633bc86a922468a82300eef5b9802e17be5e23d (patch)
treeccbe3f4a7dc46dc8caed2aff7733548ba9d60c30 /drivers
parent2157e7b82f3b81f57bd80cd67cef09ef26e5f74c (diff)
vfio: powerpc/spapr: Support Dynamic DMA windows
This adds create/remove window ioctls to create and remove DMA windows. sPAPR defines a Dynamic DMA windows capability which allows para-virtualized guests to create additional DMA windows on a PCI bus. The existing linux kernels use this new window to map the entire guest memory and switch to the direct DMA operations saving time on map/unmap requests which would normally happen in a big amounts. This adds 2 ioctl handlers - VFIO_IOMMU_SPAPR_TCE_CREATE and VFIO_IOMMU_SPAPR_TCE_REMOVE - to create and remove windows. Up to 2 windows are supported now by the hardware and by this driver. This changes VFIO_IOMMU_SPAPR_TCE_GET_INFO handler to return additional information such as a number of supported windows and maximum number levels of TCE tables. DDW is added as a capability, not as a SPAPR TCE IOMMU v2 unique feature as we still want to support v2 on platforms which cannot do DDW for the sake of TCE acceleration in KVM (coming soon). Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> [aw: for the vfio related changes] Acked-by: Alex Williamson <alex.williamson@redhat.com> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c196
1 files changed, 195 insertions, 1 deletions
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 91a32239bd0a..0582b72ef377 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -211,6 +211,18 @@ static long tce_iommu_find_table(struct tce_container *container,
return -1;
}
+static int tce_iommu_find_free_table(struct tce_container *container)
+{
+ int i;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ if (!container->tables[i])
+ return i;
+ }
+
+ return -ENOSPC;
+}
+
static int tce_iommu_enable(struct tce_container *container)
{
int ret = 0;
@@ -593,11 +605,115 @@ static void tce_iommu_free_table(struct iommu_table *tbl)
decrement_locked_vm(pages);
}
+static long tce_iommu_create_window(struct tce_container *container,
+ __u32 page_shift, __u64 window_size, __u32 levels,
+ __u64 *start_addr)
+{
+ struct tce_iommu_group *tcegrp;
+ struct iommu_table_group *table_group;
+ struct iommu_table *tbl = NULL;
+ long ret, num;
+
+ num = tce_iommu_find_free_table(container);
+ if (num < 0)
+ return num;
+
+ /* Get the first group for ops::create_table */
+ tcegrp = list_first_entry(&container->group_list,
+ struct tce_iommu_group, next);
+ table_group = iommu_group_get_iommudata(tcegrp->grp);
+ if (!table_group)
+ return -EFAULT;
+
+ if (!(table_group->pgsizes & (1ULL << page_shift)))
+ return -EINVAL;
+
+ if (!table_group->ops->set_window || !table_group->ops->unset_window ||
+ !table_group->ops->get_table_size ||
+ !table_group->ops->create_table)
+ return -EPERM;
+
+ /* Create TCE table */
+ ret = tce_iommu_create_table(container, table_group, num,
+ page_shift, window_size, levels, &tbl);
+ if (ret)
+ return ret;
+
+ BUG_ON(!tbl->it_ops->free);
+
+ /*
+ * Program the table to every group.
+ * Groups have been tested for compatibility at the attach time.
+ */
+ list_for_each_entry(tcegrp, &container->group_list, next) {
+ table_group = iommu_group_get_iommudata(tcegrp->grp);
+
+ ret = table_group->ops->set_window(table_group, num, tbl);
+ if (ret)
+ goto unset_exit;
+ }
+
+ container->tables[num] = tbl;
+
+ /* Return start address assigned by platform in create_table() */
+ *start_addr = tbl->it_offset << tbl->it_page_shift;
+
+ return 0;
+
+unset_exit:
+ list_for_each_entry(tcegrp, &container->group_list, next) {
+ table_group = iommu_group_get_iommudata(tcegrp->grp);
+ table_group->ops->unset_window(table_group, num);
+ }
+ tce_iommu_free_table(tbl);
+
+ return ret;
+}
+
+static long tce_iommu_remove_window(struct tce_container *container,
+ __u64 start_addr)
+{
+ struct iommu_table_group *table_group = NULL;
+ struct iommu_table *tbl;
+ struct tce_iommu_group *tcegrp;
+ int num;
+
+ num = tce_iommu_find_table(container, start_addr, &tbl);
+ if (num < 0)
+ return -EINVAL;
+
+ BUG_ON(!tbl->it_size);
+
+ /* Detach groups from IOMMUs */
+ list_for_each_entry(tcegrp, &container->group_list, next) {
+ table_group = iommu_group_get_iommudata(tcegrp->grp);
+
+ /*
+ * SPAPR TCE IOMMU exposes the default DMA window to
+ * the guest via dma32_window_start/size of
+ * VFIO_IOMMU_SPAPR_TCE_GET_INFO. Some platforms allow
+ * the userspace to remove this window, some do not so
+ * here we check for the platform capability.
+ */
+ if (!table_group->ops || !table_group->ops->unset_window)
+ return -EPERM;
+
+ table_group->ops->unset_window(table_group, num);
+ }
+
+ /* Free table */
+ tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+ tce_iommu_free_table(tbl);
+ container->tables[num] = NULL;
+
+ return 0;
+}
+
static long tce_iommu_ioctl(void *iommu_data,
unsigned int cmd, unsigned long arg)
{
struct tce_container *container = iommu_data;
- unsigned long minsz;
+ unsigned long minsz, ddwsz;
long ret;
switch (cmd) {
@@ -641,6 +757,21 @@ static long tce_iommu_ioctl(void *iommu_data,
info.dma32_window_start = table_group->tce32_start;
info.dma32_window_size = table_group->tce32_size;
info.flags = 0;
+ memset(&info.ddw, 0, sizeof(info.ddw));
+
+ if (table_group->max_dynamic_windows_supported &&
+ container->v2) {
+ info.flags |= VFIO_IOMMU_SPAPR_INFO_DDW;
+ info.ddw.pgsizes = table_group->pgsizes;
+ info.ddw.max_dynamic_windows_supported =
+ table_group->max_dynamic_windows_supported;
+ info.ddw.levels = table_group->max_levels;
+ }
+
+ ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info, ddw);
+
+ if (info.argsz >= ddwsz)
+ minsz = ddwsz;
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
@@ -834,6 +965,69 @@ static long tce_iommu_ioctl(void *iommu_data,
return ret;
}
+ case VFIO_IOMMU_SPAPR_TCE_CREATE: {
+ struct vfio_iommu_spapr_tce_create create;
+
+ if (!container->v2)
+ break;
+
+ if (!tce_groups_attached(container))
+ return -ENXIO;
+
+ minsz = offsetofend(struct vfio_iommu_spapr_tce_create,
+ start_addr);
+
+ if (copy_from_user(&create, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (create.argsz < minsz)
+ return -EINVAL;
+
+ if (create.flags)
+ return -EINVAL;
+
+ mutex_lock(&container->lock);
+
+ ret = tce_iommu_create_window(container, create.page_shift,
+ create.window_size, create.levels,
+ &create.start_addr);
+
+ mutex_unlock(&container->lock);
+
+ if (!ret && copy_to_user((void __user *)arg, &create, minsz))
+ ret = -EFAULT;
+
+ return ret;
+ }
+ case VFIO_IOMMU_SPAPR_TCE_REMOVE: {
+ struct vfio_iommu_spapr_tce_remove remove;
+
+ if (!container->v2)
+ break;
+
+ if (!tce_groups_attached(container))
+ return -ENXIO;
+
+ minsz = offsetofend(struct vfio_iommu_spapr_tce_remove,
+ start_addr);
+
+ if (copy_from_user(&remove, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (remove.argsz < minsz)
+ return -EINVAL;
+
+ if (remove.flags)
+ return -EINVAL;
+
+ mutex_lock(&container->lock);
+
+ ret = tce_iommu_remove_window(container, remove.start_addr);
+
+ mutex_unlock(&container->lock);
+
+ return ret;
+ }
}
return -ENOTTY;