Merge branch 'topic/ppc-kvm' into next

Merge the topic branch we were sharing with kvm-ppc, Paul has also
merged it.

arch/powerpc/include/asm/iommu.h

@@ -64,6 +64,11 @@ struct iommu_table_ops {
 			long index,
 			unsigned long *hpa,
 			enum dma_data_direction *direction);
+	/* Real mode */
+	int (*exchange_rm)(struct iommu_table *tbl,
+			long index,
+			unsigned long *hpa,
+			enum dma_data_direction *direction);
 #endif
 	void (*clear)(struct iommu_table *tbl,
 			long index, long npages);
@@ -114,6 +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) \
@@ -146,8 +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 struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl);
-extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
+extern int iommu_tce_table_put(struct iommu_table *tbl);
 
 /* Initializes an iommu_table based in values set in the passed-in
  * structure
@@ -208,6 +214,8 @@ extern void iommu_del_device(struct device *dev);
 extern int __init tce_iommu_bus_notifier_init(void);
 extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction);
+extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction);
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,

arch/powerpc/include/asm/mmu_context.h

@@ -29,10 +29,14 @@ extern void mm_iommu_init(struct mm_struct *mm);
 extern void mm_iommu_cleanup(struct mm_struct *mm);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 		unsigned long ua, unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
+		struct mm_struct *mm, unsigned long ua, unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned long *hpa);
+extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif

arch/powerpc/kernel/iommu.c

@@ -711,13 +711,16 @@ 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)
+	tbl = container_of(kref, struct iommu_table, it_kref);
-		return;
+
+	if (tbl->it_ops->free)
+		tbl->it_ops->free(tbl);
 
 	if (!tbl->it_map) {
 		kfree(tbl);
@@ -733,7 +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);
@@ -746,6 +749,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	kfree(tbl);
 }
 
+struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
+{
+	if (kref_get_unless_zero(&tbl->it_kref))
+		return tbl;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_get);
+
+int iommu_tce_table_put(struct iommu_table *tbl)
+{
+	if (WARN_ON(!tbl))
+		return 0;
+
+	return kref_put(&tbl->it_kref, iommu_table_free);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_put);
+
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
  * comprises a page address and offset into that page. The dma_addr_t
@@ -1004,6 +1025,31 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_xchg);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret;
+
+	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+			(*direction == DMA_BIDIRECTIONAL))) {
+		struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
+
+		if (likely(pg)) {
+			SetPageDirty(pg);
+		} else {
+			tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+			ret = -EFAULT;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
+#endif
+
 int iommu_take_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;

arch/powerpc/mm/mmu_context_iommu.c

@@ -314,6 +314,25 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_lookup);
 
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua <= ua) &&
+				(ua + size <= mem->ua +
+				 (mem->entries << PAGE_SHIFT))) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
+
 struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
 {
@@ -345,6 +364,26 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
+long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa)
+{
+	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+	void *va = &mem->hpas[entry];
+	unsigned long *pa;
+
+	if (entry >= mem->entries)
+		return -EFAULT;
+
+	pa = (void *) vmalloc_to_phys(va);
+	if (!pa)
+		return -EFAULT;
+
+	*hpa = *pa | (ua & ~PAGE_MASK);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
 long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
 {
 	if (atomic64_inc_not_zero(&mem->mapped))

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1425,8 +1425,7 @@ 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);
 	}
-	pnv_pci_ioda2_table_free_pages(tbl);
+	iommu_tce_table_put(tbl);
-	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
 }
 
 static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
@@ -1861,6 +1860,17 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 
 	return ret;
 }
+
+static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret)
+		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
+
+	return ret;
+}
 #endif
 
 static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
@@ -1875,6 +1885,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.set = pnv_ioda1_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda1_tce_xchg,
+	.exchange_rm = pnv_ioda1_tce_xchg_rm,
 #endif
 	.clear = pnv_ioda1_tce_free,
 	.get = pnv_tce_get,
@@ -1949,7 +1960,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 {
 	struct iommu_table_group_link *tgl;
 
-	list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+	list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
 		struct pnv_ioda_pe *pe = container_of(tgl->table_group,
 				struct pnv_ioda_pe, table_group);
 		struct pnv_phb *phb = pe->phb;
@@ -2005,6 +2016,17 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 
 	return ret;
 }
+
+static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret)
+		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
+
+	return ret;
+}
 #endif
 
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
@@ -2018,13 +2040,13 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 static void pnv_ioda2_table_free(struct iommu_table *tbl)
 {
 	pnv_pci_ioda2_table_free_pages(tbl);
-	iommu_free_table(tbl, "pnv");
 }
 
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda2_tce_xchg,
+	.exchange_rm = pnv_ioda2_tce_xchg_rm,
 #endif
 	.clear = pnv_ioda2_tce_free,
 	.get = pnv_tce_get,
@@ -2204,7 +2226,7 @@ found:
 		__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_tce_table_put(tbl);
 	}
 }
 
@@ -2294,16 +2316,16 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 	if (!tbl)
 		return -ENOMEM;
 
+	tbl->it_ops = &pnv_ioda2_iommu_ops;
+
 	ret = pnv_pci_ioda2_table_alloc_pages(nid,
 			bus_offset, page_shift, window_size,
 			levels, tbl);
 	if (ret) {
-		iommu_free_table(tbl, "pnv");
+		iommu_tce_table_put(tbl);
 		return ret;
 	}
 
-	tbl->it_ops = &pnv_ioda2_iommu_ops;
-
 	*ptbl = tbl;
 
 	return 0;
@@ -2344,7 +2366,7 @@ 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);
-		pnv_ioda2_table_free(tbl);
+		iommu_tce_table_put(tbl);
 		return rc;
 	}
 
@@ -2432,7 +2454,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
-	pnv_ioda2_table_free(tbl);
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
@@ -3405,7 +3427,7 @@ 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_tce_table_put(tbl);
 }
 
 static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
@@ -3432,7 +3454,7 @@ 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_tce_table_put(tbl);
 }
 
 static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,

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;
 }

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_tce_table_put(tbl);
 
 	kfree(table_group);
 }

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_tce_table_put(tbl);
 	of_node_put(dev->of_node);
 	kfree(to_vio_dev(dev));
 }

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -680,7 +680,7 @@ 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);
-	tbl->it_ops->free(tbl);
+	iommu_tce_table_put(tbl);
 	decrement_locked_vm(container->mm, pages);
 }