s390/pci: DMA support

Add DMA IOMMU support using 4K page table entries. Implement dma_map_ops.

Signed-off-by: Jan Glauber <jang@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

8 files changed, 848 insertions, 11 deletions

diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
new file mode 100644
index 0000000..8a32f7d
--- /dev/null
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -0,0 +1,76 @@
+#ifndef _ASM_S390_DMA_MAPPING_H
+#define _ASM_S390_DMA_MAPPING_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
+#include <linux/io.h>
+
+#define DMA_ERROR_CODE		(~(dma_addr_t) 0x0)
+
+extern struct dma_map_ops s390_dma_ops;
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return &s390_dma_ops;
+}
+
+extern int dma_set_mask(struct device *dev, u64 mask);
+extern int dma_is_consistent(struct device *dev, dma_addr_t dma_handle);
+extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+			   enum dma_data_direction direction);
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	if (dma_ops->dma_supported == NULL)
+		return 1;
+	return dma_ops->dma_supported(dev, mask);
+}
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return 0;
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	if (dma_ops->mapping_error)
+		return dma_ops->mapping_error(dev, dma_addr);
+	return (dma_addr == 0UL);
+}
+
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *ret;
+
+	ret = ops->alloc(dev, size, dma_handle, flag, NULL);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
+	return ret;
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
+{
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	dma_ops->free(dev, size, cpu_addr, dma_handle, NULL);
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
+#endif /* _ASM_S390_DMA_MAPPING_H */
diff --git a/arch/s390/include/asm/dma.h b/arch/s390/include/asm/dma.h
index 6fb6de4..de015d8 100644
--- a/arch/s390/include/asm/dma.h
+++ b/arch/s390/include/asm/dma.h
@@ -1,14 +1,13 @@
-/*
- *  S390 version
- */
-
-#ifndef _ASM_DMA_H
-#define _ASM_DMA_H
+#ifndef _ASM_S390_DMA_H
+#define _ASM_S390_DMA_H
 
-#include <asm/io.h>		/* need byte IO */
+#include <asm/io.h>
 
+/*
+ * MAX_DMA_ADDRESS is ambiguous because on s390 its completely unrelated
+ * to DMA. It _is_ used for the s390 memory zone split at 2GB caused
+ * by the 31 bit heritage.
+ */
 #define MAX_DMA_ADDRESS         0x80000000
 
-#define free_dma(x)	do { } while (0)
-
-#endif /* _ASM_DMA_H */
+#endif /* _ASM_S390_DMA_H */
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 2a6084f..e9dc009 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -75,8 +75,23 @@ struct zpci_dev {
 	struct msi_map *msi_map[ZPCI_NR_MSI_VECS];
 	unsigned int	aisb;		/* number of the summary bit */
 
+	/* DMA stuff */
+	unsigned long	*dma_table;
+	spinlock_t	dma_table_lock;
+	int		tlb_refresh;
+
+	spinlock_t	iommu_bitmap_lock;
+	unsigned long	*iommu_bitmap;
+	unsigned long	iommu_size;
+	unsigned long	iommu_pages;
+	unsigned int	next_bit;
+
 	struct zpci_bar_struct bars[PCI_BAR_COUNT];
 
+	u64		start_dma;	/* Start of available DMA addresses */
+	u64		end_dma;	/* End of available DMA addresses */
+	u64		dma_mask;	/* DMA address space mask */
+
 	enum pci_bus_speed max_bus_speed;
 };
 
@@ -95,6 +110,8 @@ int zpci_enable_device(struct zpci_dev *);
 void zpci_stop_device(struct zpci_dev *);
 void zpci_free_device(struct zpci_dev *);
 int zpci_scan_device(struct zpci_dev *);
+int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
+int zpci_unregister_ioat(struct zpci_dev *, u8);
 
 /* CLP */
 int clp_find_pci_devices(void);
@@ -115,4 +132,8 @@ struct zpci_dev *get_zdev(struct pci_dev *);
 struct zpci_dev *get_zdev_by_fid(u32);
 bool zpci_fid_present(u32);
 
+/* DMA */
+int zpci_dma_init(void);
+void zpci_dma_exit(void);
+
 #endif
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
new file mode 100644
index 0000000..30b4c17
--- /dev/null
+++ b/arch/s390/include/asm/pci_dma.h
@@ -0,0 +1,196 @@
+#ifndef _ASM_S390_PCI_DMA_H
+#define _ASM_S390_PCI_DMA_H
+
+/* I/O Translation Anchor (IOTA) */
+enum zpci_ioat_dtype {
+	ZPCI_IOTA_STO = 0,
+	ZPCI_IOTA_RTTO = 1,
+	ZPCI_IOTA_RSTO = 2,
+	ZPCI_IOTA_RFTO = 3,
+	ZPCI_IOTA_PFAA = 4,
+	ZPCI_IOTA_IOPFAA = 5,
+	ZPCI_IOTA_IOPTO = 7
+};
+
+#define ZPCI_IOTA_IOT_ENABLED		0x800UL
+#define ZPCI_IOTA_DT_ST			(ZPCI_IOTA_STO	<< 2)
+#define ZPCI_IOTA_DT_RT			(ZPCI_IOTA_RTTO << 2)
+#define ZPCI_IOTA_DT_RS			(ZPCI_IOTA_RSTO << 2)
+#define ZPCI_IOTA_DT_RF			(ZPCI_IOTA_RFTO << 2)
+#define ZPCI_IOTA_DT_PF			(ZPCI_IOTA_PFAA << 2)
+#define ZPCI_IOTA_FS_4K			0
+#define ZPCI_IOTA_FS_1M			1
+#define ZPCI_IOTA_FS_2G			2
+#define ZPCI_KEY			(PAGE_DEFAULT_KEY << 5)
+
+#define ZPCI_IOTA_STO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_ST)
+#define ZPCI_IOTA_RTTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RT)
+#define ZPCI_IOTA_RSTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RS)
+#define ZPCI_IOTA_RFTO_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_RF)
+#define ZPCI_IOTA_RFAA_FLAG	(ZPCI_IOTA_IOT_ENABLED | ZPCI_KEY | ZPCI_IOTA_DT_PF | ZPCI_IOTA_FS_2G)
+
+/* I/O Region and segment tables */
+#define ZPCI_INDEX_MASK			0x7ffUL
+
+#define ZPCI_TABLE_TYPE_MASK		0xc
+#define ZPCI_TABLE_TYPE_RFX		0xc
+#define ZPCI_TABLE_TYPE_RSX		0x8
+#define ZPCI_TABLE_TYPE_RTX		0x4
+#define ZPCI_TABLE_TYPE_SX		0x0
+
+#define ZPCI_TABLE_LEN_RFX		0x3
+#define ZPCI_TABLE_LEN_RSX		0x3
+#define ZPCI_TABLE_LEN_RTX		0x3
+
+#define ZPCI_TABLE_OFFSET_MASK		0xc0
+#define ZPCI_TABLE_SIZE			0x4000
+#define ZPCI_TABLE_ALIGN		ZPCI_TABLE_SIZE
+#define ZPCI_TABLE_ENTRY_SIZE		(sizeof(unsigned long))
+#define ZPCI_TABLE_ENTRIES		(ZPCI_TABLE_SIZE / ZPCI_TABLE_ENTRY_SIZE)
+
+#define ZPCI_TABLE_BITS			11
+#define ZPCI_PT_BITS			8
+#define ZPCI_ST_SHIFT			(ZPCI_PT_BITS + PAGE_SHIFT)
+#define ZPCI_RT_SHIFT			(ZPCI_ST_SHIFT + ZPCI_TABLE_BITS)
+
+#define ZPCI_RTE_FLAG_MASK		0x3fffUL
+#define ZPCI_RTE_ADDR_MASK		(~ZPCI_RTE_FLAG_MASK)
+#define ZPCI_STE_FLAG_MASK		0x7ffUL
+#define ZPCI_STE_ADDR_MASK		(~ZPCI_STE_FLAG_MASK)
+
+/* I/O Page tables */
+#define ZPCI_PTE_VALID_MASK		0x400
+#define ZPCI_PTE_INVALID		0x400
+#define ZPCI_PTE_VALID			0x000
+#define ZPCI_PT_SIZE			0x800
+#define ZPCI_PT_ALIGN			ZPCI_PT_SIZE
+#define ZPCI_PT_ENTRIES			(ZPCI_PT_SIZE / ZPCI_TABLE_ENTRY_SIZE)
+#define ZPCI_PT_MASK			(ZPCI_PT_ENTRIES - 1)
+
+#define ZPCI_PTE_FLAG_MASK		0xfffUL
+#define ZPCI_PTE_ADDR_MASK		(~ZPCI_PTE_FLAG_MASK)
+
+/* Shared bits */
+#define ZPCI_TABLE_VALID		0x00
+#define ZPCI_TABLE_INVALID		0x20
+#define ZPCI_TABLE_PROTECTED		0x200
+#define ZPCI_TABLE_UNPROTECTED		0x000
+
+#define ZPCI_TABLE_VALID_MASK		0x20
+#define ZPCI_TABLE_PROT_MASK		0x200
+
+static inline unsigned int calc_rtx(dma_addr_t ptr)
+{
+	return ((unsigned long) ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK;
+}
+
+static inline unsigned int calc_sx(dma_addr_t ptr)
+{
+	return ((unsigned long) ptr >> ZPCI_ST_SHIFT) & ZPCI_INDEX_MASK;
+}
+
+static inline unsigned int calc_px(dma_addr_t ptr)
+{
+	return ((unsigned long) ptr >> PAGE_SHIFT) & ZPCI_PT_MASK;
+}
+
+static inline void set_pt_pfaa(unsigned long *entry, void *pfaa)
+{
+	*entry &= ZPCI_PTE_FLAG_MASK;
+	*entry |= ((unsigned long) pfaa & ZPCI_PTE_ADDR_MASK);
+}
+
+static inline void set_rt_sto(unsigned long *entry, void *sto)
+{
+	*entry &= ZPCI_RTE_FLAG_MASK;
+	*entry |= ((unsigned long) sto & ZPCI_RTE_ADDR_MASK);
+	*entry |= ZPCI_TABLE_TYPE_RTX;
+}
+
+static inline void set_st_pto(unsigned long *entry, void *pto)
+{
+	*entry &= ZPCI_STE_FLAG_MASK;
+	*entry |= ((unsigned long) pto & ZPCI_STE_ADDR_MASK);
+	*entry |= ZPCI_TABLE_TYPE_SX;
+}
+
+static inline void validate_rt_entry(unsigned long *entry)
+{
+	*entry &= ~ZPCI_TABLE_VALID_MASK;
+	*entry &= ~ZPCI_TABLE_OFFSET_MASK;
+	*entry |= ZPCI_TABLE_VALID;
+	*entry |= ZPCI_TABLE_LEN_RTX;
+}
+
+static inline void validate_st_entry(unsigned long *entry)
+{
+	*entry &= ~ZPCI_TABLE_VALID_MASK;
+	*entry |= ZPCI_TABLE_VALID;
+}
+
+static inline void invalidate_table_entry(unsigned long *entry)
+{
+	*entry &= ~ZPCI_TABLE_VALID_MASK;
+	*entry |= ZPCI_TABLE_INVALID;
+}
+
+static inline void invalidate_pt_entry(unsigned long *entry)
+{
+	WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_INVALID);
+	*entry &= ~ZPCI_PTE_VALID_MASK;
+	*entry |= ZPCI_PTE_INVALID;
+}
+
+static inline void validate_pt_entry(unsigned long *entry)
+{
+	WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID);
+	*entry &= ~ZPCI_PTE_VALID_MASK;
+	*entry |= ZPCI_PTE_VALID;
+}
+
+static inline void entry_set_protected(unsigned long *entry)
+{
+	*entry &= ~ZPCI_TABLE_PROT_MASK;
+	*entry |= ZPCI_TABLE_PROTECTED;
+}
+
+static inline void entry_clr_protected(unsigned long *entry)
+{
+	*entry &= ~ZPCI_TABLE_PROT_MASK;
+	*entry |= ZPCI_TABLE_UNPROTECTED;
+}
+
+static inline int reg_entry_isvalid(unsigned long entry)
+{
+	return (entry & ZPCI_TABLE_VALID_MASK) == ZPCI_TABLE_VALID;
+}
+
+static inline int pt_entry_isvalid(unsigned long entry)
+{
+	return (entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID;
+}
+
+static inline int entry_isprotected(unsigned long entry)
+{
+	return (entry & ZPCI_TABLE_PROT_MASK) == ZPCI_TABLE_PROTECTED;
+}
+
+static inline unsigned long *get_rt_sto(unsigned long entry)
+{
+	return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
+		? (unsigned long *) (entry & ZPCI_RTE_ADDR_MASK)
+		: NULL;
+}
+
+static inline unsigned long *get_st_pto(unsigned long entry)
+{
+	return ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
+		? (unsigned long *) (entry & ZPCI_STE_ADDR_MASK)
+		: NULL;
+}
+
+/* Prototypes */
+int zpci_dma_init_device(struct zpci_dev *);
+void zpci_dma_exit_device(struct zpci_dev *);
+
+#endif
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 628be7b..4590596 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)	+= pci.o pci_clp.o pci_msi.o
+obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_msi.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index d11dc8a..5a2ef9e 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -34,6 +34,7 @@
 #include <asm/facility.h>
 #include <asm/pci_insn.h>
 #include <asm/pci_clp.h>
+#include <asm/pci_dma.h>
 
 #define DEBUG				/* enable pr_debug */
 
@@ -232,6 +233,25 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args
 	return rc;
 }
 
+/* Modify PCI: Register I/O address translation parameters */
+int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
+		       u64 base, u64 limit, u64 iota)
+{
+	struct mod_pci_args args = { base, limit, iota };
+
+	WARN_ON_ONCE(iota & 0x3fff);
+	args.iota |= ZPCI_IOTA_RTTO_FLAG;
+	return mod_pci(zdev, ZPCI_MOD_FC_REG_IOAT, dmaas, &args);
+}
+
+/* Modify PCI: Unregister I/O address translation parameters */
+int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas)
+{
+	struct mod_pci_args args = { 0, 0, 0 };
+
+	return mod_pci(zdev, ZPCI_MOD_FC_DEREG_IOAT, dmaas, &args);
+}
+
 /* Modify PCI: Unregister adapter interruptions */
 static int zpci_unregister_airq(struct zpci_dev *zdev)
 {
@@ -602,6 +622,7 @@ static void zpci_remove_device(struct pci_dev *pdev)
 
 	dev_info(&pdev->dev, "Removing device %u\n", zdev->domain);
 	zdev->state = ZPCI_FN_STATE_CONFIGURED;
+	zpci_dma_exit_device(zdev);
 	zpci_unmap_resources(pdev);
 	list_del(&zdev->entry);		/* can be called from init */
 	zdev->pdev = NULL;
@@ -887,7 +908,14 @@ int zpci_enable_device(struct zpci_dev *zdev)
 	if (rc)
 		goto out;
 	pr_info("Enabled fh: 0x%x fid: 0x%x\n", zdev->fh, zdev->fid);
+
+	rc = zpci_dma_init_device(zdev);
+	if (rc)
+		goto out_dma;
 	return 0;
+
+out_dma:
+	clp_disable_fh(zdev);
 out:
 	return rc;
 }
@@ -929,6 +957,7 @@ out:
 
 void zpci_stop_device(struct zpci_dev *zdev)
 {
+	zpci_dma_exit_device(zdev);
 	/*
 	 * Note: SCLP disables fh via set-pci-fn so don't
 	 * do that here.
@@ -953,6 +982,7 @@ int zpci_scan_device(struct zpci_dev *zdev)
 	return 0;
 
 out:
+	zpci_dma_exit_device(zdev);
 	clp_disable_fh(zdev);
 	return -EIO;
 }
@@ -1028,6 +1058,10 @@ static int __init pci_base_init(void)
 	if (rc)
 		goto out_irq;
 
+	rc = zpci_dma_init();
+	if (rc)
+		goto out_dma;
+
 	rc = clp_find_pci_devices();
 	if (rc)
 		goto out_find;
@@ -1036,6 +1070,8 @@ static int __init pci_base_init(void)
 	return 0;
 
 out_find:
+	zpci_dma_exit();
+out_dma:
 	zpci_irq_exit();
 out_irq:
 	zpci_msihash_exit();
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 72694fb..7f4ce8d 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -48,6 +48,8 @@ static void clp_free_block(void *ptr)
 static void clp_store_query_pci_fngrp(struct zpci_dev *zdev,
 				      struct clp_rsp_query_pci_grp *response)
 {
+	zdev->tlb_refresh = response->refresh;
+	zdev->dma_mask = response->dasm;
 	zdev->msi_addr = response->msia;
 
 	pr_debug("Supported number of MSI vectors: %u\n", response->noi);
@@ -97,6 +99,8 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev,
 		zdev->bars[i].val = le32_to_cpu(response->bar[i]);
 		zdev->bars[i].size = response->bar_size[i];
 	}
+	zdev->start_dma = response->sdma;
+	zdev->end_dma = response->edma;
 	zdev->pchid = response->pchid;
 	zdev->pfgid = response->pfgid;
 	return 0;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
new file mode 100644
index 0000000..de48625
--- /dev/null
+++ b/arch/s390/pci/pci_dma.c
@@ -0,0 +1,505 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/iommu-helper.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include <asm/pci_dma.h>
+
+static enum zpci_ioat_dtype zpci_ioat_dt = ZPCI_IOTA_RTTO;
+
+static struct kmem_cache *dma_region_table_cache;
+static struct kmem_cache *dma_page_table_cache;
+
+static unsigned long *dma_alloc_cpu_table(void)
+{
+	unsigned long *table, *entry;
+
+	table = kmem_cache_alloc(dma_region_table_cache, GFP_ATOMIC);
+	if (!table)
+		return NULL;
+
+	for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++)
+		*entry = ZPCI_TABLE_INVALID | ZPCI_TABLE_PROTECTED;
+	return table;
+}
+
+static void dma_free_cpu_table(void *table)
+{
+	kmem_cache_free(dma_region_table_cache, table);
+}
+
+static unsigned long *dma_alloc_page_table(void)
+{
+	unsigned long *table, *entry;
+
+	table = kmem_cache_alloc(dma_page_table_cache, GFP_ATOMIC);
+	if (!table)
+		return NULL;
+
+	for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++)
+		*entry = ZPCI_PTE_INVALID | ZPCI_TABLE_PROTECTED;
+	return table;
+}
+
+static void dma_free_page_table(void *table)
+{
+	kmem_cache_free(dma_page_table_cache, table);
+}
+
+static unsigned long *dma_get_seg_table_origin(unsigned long *entry)
+{
+	unsigned long *sto;
+
+	if (reg_entry_isvalid(*entry))
+		sto = get_rt_sto(*entry);
+	else {
+		sto = dma_alloc_cpu_table();
+		if (!sto)
+			return NULL;
+
+		set_rt_sto(entry, sto);
+		validate_rt_entry(entry);
+		entry_clr_protected(entry);
+	}
+	return sto;
+}
+
+static unsigned long *dma_get_page_table_origin(unsigned long *entry)
+{
+	unsigned long *pto;
+
+	if (reg_entry_isvalid(*entry))
+		pto = get_st_pto(*entry);
+	else {
+		pto = dma_alloc_page_table();
+		if (!pto)
+			return NULL;
+		set_st_pto(entry, pto);
+		validate_st_entry(entry);
+		entry_clr_protected(entry);
+	}
+	return pto;
+}
+
+static unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
+{
+	unsigned long *sto, *pto;
+	unsigned int rtx, sx, px;
+
+	rtx = calc_rtx(dma_addr);
+	sto = dma_get_seg_table_origin(&rto[rtx]);
+	if (!sto)
+		return NULL;
+
+	sx = calc_sx(dma_addr);
+	pto = dma_get_page_table_origin(&sto[sx]);
+	if (!pto)
+		return NULL;
+
+	px = calc_px(dma_addr);
+	return &pto[px];
+}
+
+static void dma_update_cpu_trans(struct zpci_dev *zdev, void *page_addr,
+				 dma_addr_t dma_addr, int flags)
+{
+	unsigned long *entry;
+
+	entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+	if (!entry) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	if (flags & ZPCI_PTE_INVALID) {
+		invalidate_pt_entry(entry);
+		return;
+	} else {
+		set_pt_pfaa(entry, page_addr);
+		validate_pt_entry(entry);
+	}
+
+	if (flags & ZPCI_TABLE_PROTECTED)
+		entry_set_protected(entry);
+	else
+		entry_clr_protected(entry);
+}
+
+static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
+			    dma_addr_t dma_addr, size_t size, int flags)
+{
+	unsigned int nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	u8 *page_addr = (u8 *) (pa & PAGE_MASK);
+	dma_addr_t start_dma_addr = dma_addr;
+	unsigned long irq_flags;
+	int i, rc = 0;
+
+	if (!nr_pages)
+		return -EINVAL;
+
+	spin_lock_irqsave(&zdev->dma_table_lock, irq_flags);
+	if (!zdev->dma_table) {
+		dev_err(&zdev->pdev->dev, "Missing DMA table\n");
+		goto no_refresh;
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		dma_update_cpu_trans(zdev, page_addr, dma_addr, flags);
+		page_addr += PAGE_SIZE;
+		dma_addr += PAGE_SIZE;
+	}
+
+	/*
+	 * rpcit is not required to establish new translations when previously
+	 * invalid translation-table entries are validated, however it is
+	 * required when altering previously valid entries.
+	 */
+	if (!zdev->tlb_refresh &&
+	    ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID))
+		/*
+		 * TODO: also need to check that the old entry is indeed INVALID
+		 * and not only for one page but for the whole range...
+		 * -> now we WARN_ON in that case but with lazy unmap that
+		 * needs to be redone!
+		 */
+		goto no_refresh;
+	rc = rpcit_instr((u64) zdev->fh << 32, start_dma_addr,
+			  nr_pages * PAGE_SIZE);
+
+no_refresh:
+	spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags);
+	return rc;
+}
+
+static void dma_free_seg_table(unsigned long entry)
+{
+	unsigned long *sto = get_rt_sto(entry);
+	int sx;
+
+	for (sx = 0; sx < ZPCI_TABLE_ENTRIES; sx++)
+		if (reg_entry_isvalid(sto[sx]))
+			dma_free_page_table(get_st_pto(sto[sx]));
+
+	dma_free_cpu_table(sto);
+}
+
+static void dma_cleanup_tables(struct zpci_dev *zdev)
+{
+	unsigned long *table = zdev->dma_table;
+	int rtx;
+
+	if (!zdev || !zdev->dma_table)
+		return;
+
+	for (rtx = 0; rtx < ZPCI_TABLE_ENTRIES; rtx++)
+		if (reg_entry_isvalid(table[rtx]))
+			dma_free_seg_table(table[rtx]);
+
+	dma_free_cpu_table(table);
+	zdev->dma_table = NULL;
+}
+
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
+				   int size)
+{
+	unsigned long boundary_size = 0x1000000;
+
+	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
+				start, size, 0, boundary_size, 0);
+}
+
+static unsigned long dma_alloc_iommu(struct zpci_dev *zdev, int size)
+{
+	unsigned long offset, flags;
+
+	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
+	offset = __dma_alloc_iommu(zdev, zdev->next_bit, size);
+	if (offset == -1)
+		offset = __dma_alloc_iommu(zdev, 0, size);
+
+	if (offset != -1) {
+		zdev->next_bit = offset + size;
+		if (zdev->next_bit >= zdev->iommu_pages)
+			zdev->next_bit = 0;
+	}
+	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
+	return offset;
+}
+
+static void dma_free_iommu(struct zpci_dev *zdev, unsigned long offset, int size)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
+	if (!zdev->iommu_bitmap)
+		goto out;
+	bitmap_clear(zdev->iommu_bitmap, offset, size);
+	if (offset >= zdev->next_bit)
+		zdev->next_bit = offset + size;
+out:
+	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
+}
+
+int dma_set_mask(struct device *dev, u64 mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	*dev->dma_mask = mask;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_set_mask);
+
+static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs)
+{
+	struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev));
+	unsigned long nr_pages, iommu_page_index;
+	unsigned long pa = page_to_phys(page) + offset;
+	int flags = ZPCI_PTE_VALID;
+	dma_addr_t dma_addr;
+
+	WARN_ON_ONCE(offset > PAGE_SIZE);
+
+	/* This rounds up number of pages based on size and offset */
+	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
+	iommu_page_index = dma_alloc_iommu(zdev, nr_pages);
+	if (iommu_page_index == -1)
+		goto out_err;
+
+	/* Use rounded up size */
+	size = nr_pages * PAGE_SIZE;
+
+	dma_addr = zdev->start_dma + iommu_page_index * PAGE_SIZE;
+	if (dma_addr + size > zdev->end_dma) {
+		dev_err(dev, "(dma_addr: 0x%16.16LX + size: 0x%16.16lx) > end_dma: 0x%16.16Lx\n",
+			 dma_addr, size, zdev->end_dma);
+		goto out_free;
+	}
+
+	if (direction == DMA_NONE || direction == DMA_TO_DEVICE)
+		flags |= ZPCI_TABLE_PROTECTED;
+
+	if (!dma_update_trans(zdev, pa, dma_addr, size, flags))
+		return dma_addr + offset;
+
+out_free:
+	dma_free_iommu(zdev, iommu_page_index, nr_pages);
+out_err:
+	dev_err(dev, "Failed to map addr: %lx\n", pa);
+	return DMA_ERROR_CODE;
+}
+
+static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
+				 size_t size, enum dma_data_direction direction,
+				 struct dma_attrs *attrs)
+{
+	struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev));
+	unsigned long iommu_page_index;
+	int npages;
+
+	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
+	dma_addr = dma_addr & PAGE_MASK;
+	if (dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
+			     ZPCI_TABLE_PROTECTED | ZPCI_PTE_INVALID))
+		dev_err(dev, "Failed to unmap addr: %Lx\n", dma_addr);
+
+	iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT;
+	dma_free_iommu(zdev, iommu_page_index, npages);
+}
+
+static void *s390_dma_alloc(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t flag,
+			    struct dma_attrs *attrs)
+{
+	struct page *page;
+	unsigned long pa;
+	dma_addr_t map;
+
+	size = PAGE_ALIGN(size);
+	page = alloc_pages(flag, get_order(size));
+	if (!page)
+		return NULL;
+	pa = page_to_phys(page);
+	memset((void *) pa, 0, size);
+
+	map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE,
+				 size, DMA_BIDIRECTIONAL, NULL);
+	if (dma_mapping_error(dev, map)) {
+		free_pages(pa, get_order(size));
+		return NULL;
+	}
+
+	if (dma_handle)
+		*dma_handle = map;
+	return (void *) pa;
+}
+
+static void s390_dma_free(struct device *dev, size_t size,
+			  void *pa, dma_addr_t dma_handle,
+			  struct dma_attrs *attrs)
+{
+	s390_dma_unmap_pages(dev, dma_handle, PAGE_ALIGN(size),
+			     DMA_BIDIRECTIONAL, NULL);
+	free_pages((unsigned long) pa, get_order(size));
+}
+
+static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
+			   int nr_elements, enum dma_data_direction dir,
+			   struct dma_attrs *attrs)
+{
+	int mapped_elements = 0;
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nr_elements, i) {
+		struct page *page = sg_page(s);
+		s->dma_address = s390_dma_map_pages(dev, page, s->offset,
+						    s->length, dir, NULL);
+		if (!dma_mapping_error(dev, s->dma_address)) {
+			s->dma_length = s->length;
+			mapped_elements++;
+		} else
+			goto unmap;
+	}
+out:
+	return mapped_elements;
+
+unmap:
+	for_each_sg(sg, s, mapped_elements, i) {
+		if (s->dma_address)
+			s390_dma_unmap_pages(dev, s->dma_address, s->dma_length,
+					     dir, NULL);
+		s->dma_address = 0;
+		s->dma_length = 0;
+	}
+	mapped_elements = 0;
+	goto out;
+}
+
+static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+			      int nr_elements, enum dma_data_direction dir,
+			      struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nr_elements, i) {
+		s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, dir, NULL);
+		s->dma_address = 0;
+		s->dma_length = 0;
+	}
+}
+
+int zpci_dma_init_device(struct zpci_dev *zdev)
+{
+	unsigned int bitmap_order;
+	int rc;
+
+	spin_lock_init(&zdev->iommu_bitmap_lock);
+	spin_lock_init(&zdev->dma_table_lock);
+
+	zdev->dma_table = dma_alloc_cpu_table();
+	if (!zdev->dma_table) {
+		rc = -ENOMEM;
+		goto out_clean;
+	}
+
+	zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET;
+	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
+	bitmap_order = get_order(zdev->iommu_pages / 8);
+	pr_info("iommu_size: 0x%lx  iommu_pages: 0x%lx  bitmap_order: %i\n",
+		 zdev->iommu_size, zdev->iommu_pages, bitmap_order);
+
+	zdev->iommu_bitmap = (void *) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						       bitmap_order);
+	if (!zdev->iommu_bitmap) {
+		rc = -ENOMEM;
+		goto out_reg;
+	}
+
+	rc = zpci_register_ioat(zdev,
+				0,
+				zdev->start_dma + PAGE_OFFSET,
+				zdev->start_dma + zdev->iommu_size - 1,
+				(u64) zdev->dma_table);
+	if (rc)
+		goto out_reg;
+	return 0;
+
+out_reg:
+	dma_free_cpu_table(zdev->dma_table);
+out_clean:
+	return rc;
+}
+
+void zpci_dma_exit_device(struct zpci_dev *zdev)
+{
+	zpci_unregister_ioat(zdev, 0);
+	dma_cleanup_tables(zdev);
+	free_pages((unsigned long) zdev->iommu_bitmap,
+		   get_order(zdev->iommu_pages / 8));
+	zdev->iommu_bitmap = NULL;
+	zdev->next_bit = 0;
+}
+
+static int __init dma_alloc_cpu_table_caches(void)
+{
+	dma_region_table_cache = kmem_cache_create("PCI_DMA_region_tables",
+					ZPCI_TABLE_SIZE, ZPCI_TABLE_ALIGN,
+					0, NULL);
+	if (!dma_region_table_cache)
+		return -ENOMEM;
+
+	dma_page_table_cache = kmem_cache_create("PCI_DMA_page_tables",
+					ZPCI_PT_SIZE, ZPCI_PT_ALIGN,
+					0, NULL);
+	if (!dma_page_table_cache) {
+		kmem_cache_destroy(dma_region_table_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int __init zpci_dma_init(void)
+{
+	return dma_alloc_cpu_table_caches();
+}
+
+void zpci_dma_exit(void)
+{
+	kmem_cache_destroy(dma_page_table_cache);
+	kmem_cache_destroy(dma_region_table_cache);
+}
+
+#define PREALLOC_DMA_DEBUG_ENTRIES	(1 << 16)
+
+static int __init dma_debug_do_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+fs_initcall(dma_debug_do_init);
+
+struct dma_map_ops s390_dma_ops = {
+	.alloc		= s390_dma_alloc,
+	.free		= s390_dma_free,
+	.map_sg		= s390_dma_map_sg,
+	.unmap_sg	= s390_dma_unmap_sg,
+	.map_page	= s390_dma_map_pages,
+	.unmap_page	= s390_dma_unmap_pages,
+	/* if we support direct DMA this must be conditional */
+	.is_phys	= 0,
+	/* dma_supported is unconditionally true without a callback */
+};
+EXPORT_SYMBOL_GPL(s390_dma_ops);