powerpc/iommu: Add "borrowing" iommu_table_group_ops

PPC64 IOMMU API defines iommu_table_group_ops which handles DMA windows
for PEs: control the ownership, create/set/unset a table the hardware
for dynamic DMA windows (DDW). VFIO uses the API to implement support on
POWER.

So far only PowerNV IODA2 (POWER8 and newer machines) implemented this
and other cases (POWER7 or nested KVM) did not and instead reused
existing iommu_table structs. This means 1) no DDW 2) ownership transfer
is done directly in the VFIO SPAPR TCE driver.

Soon POWER is going to get its own iommu_ops and ownership control is
going to move there. This implements spapr_tce_table_group_ops which
borrows iommu_table tables. The upside is that VFIO needs to know less
about POWER.

The new ops returns the existing table from create_table() and only
checks if the same window is already set. This is only going to work if
the default DMA window starts table_group.tce32_start and as big as
pe->table_group.tce32_size (not the case for IODA2+ PowerNV).

This changes iommu_table_group_ops::take_ownership() to return an error
if borrowing a table failed.

This should not cause any visible change in behavior for PowerNV.
pSeries was not that well tested/supported anyway.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Timothy Pearson <tpearson@raptorengineering.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
[mpe: Fix CONFIG_IOMMU_API=n build (skiroot_defconfig), & formatting]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/525438831.16998517.1678123820075.JavaMail.zimbra@raptorengineeringinc.com

1 files changed, 94 insertions, 4 deletions

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ee95937bdaf1..4cd3d68784b6 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1086,7 +1086,7 @@ void iommu_tce_kill(struct iommu_table *tbl,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
-int iommu_take_ownership(struct iommu_table *tbl)
+static int iommu_take_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
 	int ret = 0;
@@ -1118,9 +1118,8 @@ int iommu_take_ownership(struct iommu_table *tbl)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_take_ownership);
 
-void iommu_release_ownership(struct iommu_table *tbl)
+static void iommu_release_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
 
@@ -1137,7 +1136,6 @@ void iommu_release_ownership(struct iommu_table *tbl)
 		spin_unlock(&tbl->pools[i].lock);
 	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
 }
-EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
 int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
 {
@@ -1179,4 +1177,96 @@ void iommu_del_device(struct device *dev)
 	iommu_group_remove_device(dev);
 }
 EXPORT_SYMBOL_GPL(iommu_del_device);
+
+/*
+ * A simple iommu_table_group_ops which only allows reusing the existing
+ * iommu_table. This handles VFIO for POWER7 or the nested KVM.
+ * The ops does not allow creating windows and only allows reusing the existing
+ * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ */
+static unsigned long spapr_tce_get_table_size(__u32 page_shift,
+					      __u64 window_size, __u32 levels)
+{
+	unsigned long size;
+
+	if (levels > 1)
+		return ~0U;
+	size = window_size >> (page_shift - 3);
+	return size;
+}
+
+static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
+				   __u32 page_shift, __u64 window_size, __u32 levels,
+				   struct iommu_table **ptbl)
+{
+	struct iommu_table *tbl = table_group->tables[0];
+
+	if (num > 0)
+		return -EPERM;
+
+	if (tbl->it_page_shift != page_shift ||
+	    tbl->it_size != (window_size >> page_shift) ||
+	    tbl->it_indirect_levels != levels - 1)
+		return -EINVAL;
+
+	*ptbl = iommu_tce_table_get(tbl);
+	return 0;
+}
+
+static long spapr_tce_set_window(struct iommu_table_group *table_group,
+				 int num, struct iommu_table *tbl)
+{
+	return tbl == table_group->tables[num] ? 0 : -EPERM;
+}
+
+static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
+{
+	return 0;
+}
+
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
+{
+	int i, j, rc = 0;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = table_group->tables[i];
+
+		if (!tbl || !tbl->it_map)
+			continue;
+
+		rc = iommu_take_ownership(tbl);
+		if (!rc)
+			continue;
+		for (j = 0; j < i; ++j)
+			iommu_release_ownership(table_group->tables[j]);
+		return rc;
+	}
+	return 0;
+}
+
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
+{
+	int i;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = table_group->tables[i];
+
+		if (!tbl)
+			continue;
+
+		iommu_table_clear(tbl);
+		if (tbl->it_map)
+			iommu_release_ownership(tbl);
+	}
+}
+
+struct iommu_table_group_ops spapr_tce_table_group_ops = {
+	.get_table_size = spapr_tce_get_table_size,
+	.create_table = spapr_tce_create_table,
+	.set_window = spapr_tce_set_window,
+	.unset_window = spapr_tce_unset_window,
+	.take_ownership = spapr_tce_take_ownership,
+	.release_ownership = spapr_tce_release_ownership,
+};
+
 #endif /* CONFIG_IOMMU_API */