powerpc/spapr: vfio: Switch from iommu_table to new iommu_table_group

So far one TCE table could only be used by one IOMMU group. However
IODA2 hardware allows programming the same TCE table address to
multiple PE allowing sharing tables.

This replaces a single pointer to a group in a iommu_table struct
with a linked list of groups which provides the way of invalidating
TCE cache for every PE when an actual TCE table is updated. This adds
pnv_pci_link_table_and_group() and pnv_pci_unlink_table_and_group()
helpers to manage the list. However without VFIO, it is still going
to be a single IOMMU group per iommu_table.

This changes iommu_add_device() to add a device to a first group
from the group list of a table as it is only called from the platform
init code or PCI bus notifier and at these moments there is only
one group per table.

This does not change TCE invalidation code to loop through all
attached groups in order to simplify this patch and because
it is not really needed in most cases. IODA2 is fixed in a later
patch.

This should cause no behavioural change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[aw: for the vfio related changes]
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 24 insertions, 3 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 307d704ffaa3..10510dea16b3 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -37,6 +37,7 @@
 #include <linux/memory.h>
 #include <linux/of.h>
 #include <linux/iommu.h>
+#include <linux/rculist.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -56,6 +57,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 {
 	struct iommu_table_group *table_group = NULL;
 	struct iommu_table *tbl = NULL;
+	struct iommu_table_group_link *tgl = NULL;
 
 	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
 			   node);
@@ -66,12 +68,21 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 	if (!tbl)
 		goto fail_exit;
 
-	tbl->it_table_group = table_group;
+	tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
+			node);
+	if (!tgl)
+		goto fail_exit;
+
+	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	tgl->table_group = table_group;
+	list_add_rcu(&tgl->next, &tbl->it_group_list);
+
 	table_group->tables[0] = tbl;
 
 	return table_group;
 
 fail_exit:
+	kfree(tgl);
 	kfree(table_group);
 	kfree(tbl);
 
@@ -82,18 +93,28 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		const char *node_name)
 {
 	struct iommu_table *tbl;
+#ifdef CONFIG_IOMMU_API
+	struct iommu_table_group_link *tgl;
+#endif
 
 	if (!table_group)
 		return;
 
+	tbl = table_group->tables[0];
 #ifdef CONFIG_IOMMU_API
+	tgl = list_first_entry_or_null(&tbl->it_group_list,
+			struct iommu_table_group_link, next);
+
+	WARN_ON_ONCE(!tgl);
+	if (tgl) {
+		list_del_rcu(&tgl->next);
+		kfree(tgl);
+	}
 	if (table_group->group) {
 		iommu_group_put(table_group->group);
 		BUG_ON(table_group->group);
 	}
 #endif
-
-	tbl = table_group->tables[0];
 	iommu_free_table(tbl, node_name);
 
 	kfree(table_group);