[PATCH kernel v4 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table

[Alexey Kardashevskiy <aik@ozlabs.ru>]

So far iommu_table obejcts were only used in virtual mode and had
a single owner. We are going to change this by implementing in-kernel
acceleration of DMA mapping requests. The proposed acceleration
will handle requests in real mode and KVM will keep references to tables.

This adds a kref to iommu_table and defines new helpers to update it.
This replaces iommu_free_table() with iommu_table_put() and makes
iommu_free_table() static. iommu_table_get() is not used in this patch
but it will be in the following patch.

Since this touches prototypes, this also removes @node_name parameter as
it has never been really useful on powernv and carrying it for
the pseries platform code to iommu_free_table() seems to be quite
useless as well.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/iommu.h          |  5 +++--
 arch/powerpc/kernel/iommu.c               | 24 +++++++++++++++++++-----
 arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++++++-------
 arch/powerpc/platforms/powernv/pci.c      |  1 +
 arch/powerpc/platforms/pseries/iommu.c    |  3 ++-
 arch/powerpc/platforms/pseries/vio.c      |  2 +-
 drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
 7 files changed, 34 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 4554699aec02..82e77ebf85f4 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -119,6 +119,7 @@ struct iommu_table {
 	struct list_head it_group_list;/* List of iommu_table_group_link */
 	unsigned long *it_userspace; /* userspace view of the table */
 	struct iommu_table_ops *it_ops;
+	struct kref    it_kref;
 };
 
 #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
@@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev)
 
 extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
 
-/* Frees table for an individual device node */
-extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
+extern void iommu_table_get(struct iommu_table *tbl);
+extern void iommu_table_put(struct iommu_table *tbl);
 
 /* Initializes an iommu_table based in values set in the passed-in
  * structure
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index bc142d87130f..d02b8d22fb50 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	return tbl;
 }
 
-void iommu_free_table(struct iommu_table *tbl, const char *node_name)
+static void iommu_table_free(struct kref *kref)
 {
 	unsigned long bitmap_sz;
 	unsigned int order;
+	struct iommu_table *tbl;
 
-	if (!tbl)
-		return;
+	tbl = container_of(kref, struct iommu_table, it_kref);
 
 	if (tbl->it_ops->free)
 		tbl->it_ops->free(tbl);
@@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
-		pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
+		pr_warn("%s: Unexpected TCEs\n", __func__);
 
 	/* calculate bitmap size in bytes */
 	bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
@@ -748,7 +748,21 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	/* free table */
 	kfree(tbl);
 }
-EXPORT_SYMBOL_GPL(iommu_free_table);
+
+void iommu_table_get(struct iommu_table *tbl)
+{
+	kref_get(&tbl->it_kref);
+}
+EXPORT_SYMBOL_GPL(iommu_table_get);
+
+void iommu_table_put(struct iommu_table *tbl)
+{
+	if (!tbl)
+		return;
+
+	kref_put(&tbl->it_kref, iommu_table_free);
+}
+EXPORT_SYMBOL_GPL(iommu_table_put);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index cf0d8aed652a..f2c2ab8fbb3e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1422,7 +1422,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
 		iommu_group_put(pe->table_group.group);
 		BUG_ON(pe->table_group.group);
 	}
-	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+	iommu_table_put(tbl);
 }
 
 static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
@@ -2221,7 +2221,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 		__free_pages(tce_mem, get_order(tce32_segsz * segs));
 	if (tbl) {
 		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
-		iommu_free_table(tbl, "pnv");
+		iommu_table_put(tbl);
 	}
 }
 
@@ -2315,7 +2315,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 			bus_offset, page_shift, window_size,
 			levels, tbl);
 	if (ret) {
-		iommu_free_table(tbl, "pnv");
+		iommu_table_put(tbl);
 		return ret;
 	}
 
@@ -2361,7 +2361,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (rc) {
 		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
 				rc);
-		iommu_free_table(tbl, "");
+		iommu_table_put(tbl);
 		return rc;
 	}
 
@@ -2447,7 +2447,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 
 	pnv_pci_ioda2_set_bypass(pe, false);
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
-	iommu_free_table(tbl, "pnv");
+	iommu_table_put(tbl);
 }
 
 static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
@@ -3417,7 +3417,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
 	}
 
 	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
-	iommu_free_table(tbl, "pnv");
+	iommu_table_put(tbl);
 }
 
 static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
@@ -3444,7 +3444,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
 	}
 
 	pnv_pci_ioda2_table_free_pages(tbl);
-	iommu_free_table(tbl, "pnv");
+	iommu_table_put(tbl);
 }
 
 static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index c6d554fe585c..471210913e42 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -767,6 +767,7 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
 
 	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 
 	return tbl;
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index dc2577fc5fbb..47f0501a94f9 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 		goto fail_exit;
 
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 	tgl->table_group = table_group;
 	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
@@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_free_table(tbl, node_name);
+	iommu_table_put(tbl);
 
 	kfree(table_group);
 }
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 2c8fb3ec989e..41e8aa5c0d6a 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (tbl)
-		iommu_free_table(tbl, of_node_full_name(dev->of_node));
+		iommu_table_put(tbl);
 	of_node_put(dev->of_node);
 	kfree(to_vio_dev(dev));
 }
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 6e79be9dfb43..b29ccb54aa7a 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -677,7 +677,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	tce_iommu_userspace_view_free(tbl, container->mm);
-	iommu_free_table(tbl, "");
+	iommu_table_put(tbl);
 	decrement_locked_vm(container->mm, pages);
 }
 
-- 
2.11.0