powerpc/iommu: Move pSeries specific functions to pseries/iommu.c

The PowerNV specific table_group_ops are defined in powernv/pci-ioda.c.
The pSeries specific table_group_ops are sitting in the generic powerpc
file. Move it to where it actually belong(pseries/iommu.c).

The functions are currently defined even for CONFIG_PPC_POWERNV
which are unused on PowerNV.

Only code movement, no functional changes intended.

Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/171923269701.1397.15758640002786937132.stgit@linux.ibm.com

1 files changed, 144 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index bbc87e53db56..c01081a6898c 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -54,6 +54,57 @@ enum {
 	DDW_EXT_QUERY_OUT_SIZE = 2
 };
 
+static int iommu_take_ownership(struct iommu_table *tbl)
+{
+	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+	int ret = 0;
+
+	/*
+	 * VFIO does not control TCE entries allocation and the guest
+	 * can write new TCEs on top of existing ones so iommu_tce_build()
+	 * must be able to release old pages. This functionality
+	 * requires exchange() callback defined so if it is not
+	 * implemented, we disallow taking ownership over the table.
+	 */
+	if (!tbl->it_ops->xchg_no_kill)
+		return -EINVAL;
+
+	spin_lock_irqsave(&tbl->large_pool.lock, flags);
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
+
+	if (iommu_table_in_use(tbl)) {
+		pr_err("iommu_tce: it_map is not empty");
+		ret = -EBUSY;
+	} else {
+		memset(tbl->it_map, 0xff, sz);
+	}
+
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_unlock(&tbl->pools[i].lock);
+	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+
+	return ret;
+}
+
+static void iommu_release_ownership(struct iommu_table *tbl)
+{
+	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+
+	spin_lock_irqsave(&tbl->large_pool.lock, flags);
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
+
+	memset(tbl->it_map, 0, sz);
+
+	iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
+			tbl->it_reserved_end);
+
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_unlock(&tbl->pools[i].lock);
+	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+}
+
 static struct iommu_table *iommu_pseries_alloc_table(int node)
 {
 	struct iommu_table *tbl;
@@ -67,6 +118,8 @@ static struct iommu_table *iommu_pseries_alloc_table(int node)
 	return tbl;
 }
 
+static struct iommu_table_group_ops spapr_tce_table_group_ops;
+
 static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 {
 	struct iommu_table_group *table_group;
@@ -1686,6 +1739,97 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
 	return false;
 }
 
+/*
+ * 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;
+
+		if (tbl->it_map)
+			iommu_release_ownership(tbl);
+	}
+}
+
+static 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,
+};
+
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 		void *data)
 {