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>

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 */

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 */

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

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

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