Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 update from Martin Schwidefsky:
 "Add support to generate code for the latest machine zEC12, MOD and XOR
  instruction support for the BPF jit compiler, the dasd safe offline
  feature and the big one: the s390 architecture gets PCI support!!
  Right before the world ends on the 21st ;-)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (41 commits)
  s390/qdio: rename the misleading PCI flag of qdio devices
  s390/pci: remove obsolete email addresses
  s390/pci: speed up __iowrite64_copy by using pci store block insn
  s390/pci: enable NEED_DMA_MAP_STATE
  s390/pci: no msleep in potential IRQ context
  s390/pci: fix potential NULL pointer dereference in dma_free_seg_table()
  s390/pci: use kmem_cache_zalloc instead of kmem_cache_alloc/memset
  s390/bpf,jit: add support for XOR instruction
  s390/bpf,jit: add support MOD instruction
  s390/cio: fix pgid reserved check
  vga: compile fix, disable vga for s390
  s390/pci: add PCI Kconfig options
  s390/pci: s390 specific PCI sysfs attributes
  s390/pci: PCI hotplug support via SCLP
  s390/pci: CHSC PCI support for error and availability events
  s390/pci: DMA support
  s390/pci: PCI adapter interrupts for MSI/MSI-X
  s390/bitops: find leftmost bit instruction support
  s390/pci: CLP interface
  s390/pci: base support
  ...

arch/s390/Kbuild

@@ -6,3 +6,4 @@ obj-$(CONFIG_S390_HYPFS_FS)	+= hypfs/
 obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
 obj-$(CONFIG_MATHEMU)		+= math-emu/
 obj-y				+= net/
+obj-$(CONFIG_PCI)		+= pci/

arch/s390/Kconfig

@@ -34,12 +34,6 @@ config GENERIC_BUG
 config GENERIC_BUG_RELATIVE_POINTERS
 	def_bool y
 
-config NO_IOMEM
-	def_bool y
-
-config NO_DMA
-	def_bool y
-
 config ARCH_DMA_ADDR_T_64BIT
 	def_bool 64BIT
 
@@ -58,6 +52,12 @@ config KEXEC
 config AUDIT_ARCH
 	def_bool y
 
+config NO_IOPORT
+	def_bool y
+
+config PCI_QUIRKS
+	def_bool n
+
 config S390
 	def_bool y
 	select USE_GENERIC_SMP_HELPERS if SMP
@@ -171,6 +171,10 @@ config HAVE_MARCH_Z196_FEATURES
 	def_bool n
 	select HAVE_MARCH_Z10_FEATURES
 
+config HAVE_MARCH_ZEC12_FEATURES
+	def_bool n
+	select HAVE_MARCH_Z196_FEATURES
+
 choice
 	prompt "Processor type"
 	default MARCH_G5
@@ -222,6 +226,13 @@ config MARCH_Z196
 	  (2818 and 2817 series). The kernel will be slightly faster but will
 	  not work on older machines.
 
+config MARCH_ZEC12
+	bool "IBM zEC12"
+	select HAVE_MARCH_ZEC12_FEATURES if 64BIT
+	help
+	  Select this to enable optimizations for IBM zEC12 (2827 series). The
+	  kernel will be slightly faster but will not work on older machines.
+
 endchoice
 
 config 64BIT
@@ -426,6 +437,53 @@ config QDIO
 
 	  If unsure, say Y.
 
+menuconfig PCI
+	bool "PCI support"
+	default n
+	depends on 64BIT
+	select ARCH_SUPPORTS_MSI
+	select PCI_MSI
+	help
+	  Enable PCI support.
+
+if PCI
+
+config PCI_NR_FUNCTIONS
+	int "Maximum number of PCI functions (1-4096)"
+	range 1 4096
+	default "64"
+	help
+	  This allows you to specify the maximum number of PCI functions which
+	  this kernel will support.
+
+source "drivers/pci/Kconfig"
+source "drivers/pci/pcie/Kconfig"
+source "drivers/pci/hotplug/Kconfig"
+
+endif	# PCI
+
+config PCI_DOMAINS
+	def_bool PCI
+
+config HAS_IOMEM
+	def_bool PCI
+
+config IOMMU_HELPER
+	def_bool PCI
+
+config HAS_DMA
+	def_bool PCI
+	select HAVE_DMA_API_DEBUG
+
+config NEED_SG_DMA_LENGTH
+	def_bool PCI
+
+config HAVE_DMA_ATTRS
+	def_bool PCI
+
+config NEED_DMA_MAP_STATE
+	def_bool PCI
+
 config CHSC_SCH
 	def_tristate m
 	prompt "Support for CHSC subchannels"

arch/s390/Makefile

@@ -41,6 +41,7 @@ cflags-$(CONFIG_MARCH_Z990) += $(call cc-option,-march=z990)
 cflags-$(CONFIG_MARCH_Z9_109) += $(call cc-option,-march=z9-109)
 cflags-$(CONFIG_MARCH_Z10) += $(call cc-option,-march=z10)
 cflags-$(CONFIG_MARCH_Z196) += $(call cc-option,-march=z196)
+cflags-$(CONFIG_MARCH_ZEC12) += $(call cc-option,-march=zEC12)
 
 #KBUILD_IMAGE is necessary for make rpm
 KBUILD_IMAGE	:=arch/s390/boot/image

arch/s390/crypto/aes_s390.c

@@ -325,7 +325,8 @@ static int ecb_aes_crypt(struct blkcipher_desc *desc, long func, void *param,
 		u8 *in = walk->src.virt.addr;
 
 		ret = crypt_s390_km(func, param, out, in, n);
-		BUG_ON((ret < 0) || (ret != n));
+		if (ret < 0 || ret != n)
+			return -EIO;
 
 		nbytes &= AES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
@@ -457,7 +458,8 @@ static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, void *param,
 		u8 *in = walk->src.virt.addr;
 
 		ret = crypt_s390_kmc(func, param, out, in, n);
-		BUG_ON((ret < 0) || (ret != n));
+		if (ret < 0 || ret != n)
+			return -EIO;
 
 		nbytes &= AES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
@@ -625,7 +627,8 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, long func,
 	memcpy(xts_ctx->pcc.tweak, walk->iv, sizeof(xts_ctx->pcc.tweak));
 	param = xts_ctx->pcc.key + offset;
 	ret = crypt_s390_pcc(func, param);
-	BUG_ON(ret < 0);
+	if (ret < 0)
+		return -EIO;
 
 	memcpy(xts_ctx->xts_param, xts_ctx->pcc.xts, 16);
 	param = xts_ctx->key + offset;
@@ -636,7 +639,8 @@ static int xts_aes_crypt(struct blkcipher_desc *desc, long func,
 		in = walk->src.virt.addr;
 
 		ret = crypt_s390_km(func, param, out, in, n);
-		BUG_ON(ret < 0 || ret != n);
+		if (ret < 0 || ret != n)
+			return -EIO;
 
 		nbytes &= AES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
@@ -769,7 +773,8 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 				crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
 			}
 			ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
-			BUG_ON(ret < 0 || ret != n);
+			if (ret < 0 || ret != n)
+				return -EIO;
 			if (n > AES_BLOCK_SIZE)
 				memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
@@ -788,7 +793,8 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, sctx->key, buf, in,
 				       AES_BLOCK_SIZE, ctrblk);
-		BUG_ON(ret < 0 || ret != AES_BLOCK_SIZE);
+		if (ret < 0 || ret != AES_BLOCK_SIZE)
+			return -EIO;
 		memcpy(out, buf, nbytes);
 		crypto_inc(ctrblk, AES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);

arch/s390/crypto/des_s390.c

@@ -94,7 +94,8 @@ static int ecb_desall_crypt(struct blkcipher_desc *desc, long func,
 		u8 *in = walk->src.virt.addr;
 
 		ret = crypt_s390_km(func, key, out, in, n);
-		BUG_ON((ret < 0) || (ret != n));
+		if (ret < 0 || ret != n)
+			return -EIO;
 
 		nbytes &= DES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
@@ -120,7 +121,8 @@ static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
 		u8 *in = walk->src.virt.addr;
 
 		ret = crypt_s390_kmc(func, iv, out, in, n);
-		BUG_ON((ret < 0) || (ret != n));
+		if (ret < 0 || ret != n)
+			return -EIO;
 
 		nbytes &= DES_BLOCK_SIZE - 1;
 		ret = blkcipher_walk_done(desc, walk, nbytes);
@@ -386,7 +388,8 @@ static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
 				crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
 			}
 			ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
-			BUG_ON((ret < 0) || (ret != n));
+			if (ret < 0 || ret != n)
+				return -EIO;
 			if (n > DES_BLOCK_SIZE)
 				memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
 				       DES_BLOCK_SIZE);
@@ -404,7 +407,8 @@ static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
 		in = walk->src.virt.addr;
 		ret = crypt_s390_kmctr(func, ctx->key, buf, in,
 				       DES_BLOCK_SIZE, ctrblk);
-		BUG_ON(ret < 0 || ret != DES_BLOCK_SIZE);
+		if (ret < 0 || ret != DES_BLOCK_SIZE)
+			return -EIO;
 		memcpy(out, buf, nbytes);
 		crypto_inc(ctrblk, DES_BLOCK_SIZE);
 		ret = blkcipher_walk_done(desc, walk, 0);

arch/s390/crypto/ghash_s390.c

@@ -72,14 +72,16 @@ static int ghash_update(struct shash_desc *desc,
 		if (!dctx->bytes) {
 			ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf,
 					      GHASH_BLOCK_SIZE);
-			BUG_ON(ret != GHASH_BLOCK_SIZE);
+			if (ret != GHASH_BLOCK_SIZE)
+				return -EIO;
 		}
 	}
 
 	n = srclen & ~(GHASH_BLOCK_SIZE - 1);
 	if (n) {
 		ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n);
-		BUG_ON(ret != n);
+		if (ret != n)
+			return -EIO;
 		src += n;
 		srclen -= n;
 	}
@@ -92,7 +94,7 @@ static int ghash_update(struct shash_desc *desc,
 	return 0;
 }
 
-static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
 {
 	u8 *buf = dctx->buffer;
 	int ret;
@@ -103,21 +105,24 @@ static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
 		memset(pos, 0, dctx->bytes);
 
 		ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE);
-		BUG_ON(ret != GHASH_BLOCK_SIZE);
+		if (ret != GHASH_BLOCK_SIZE)
+			return -EIO;
 	}
 
 	dctx->bytes = 0;
+	return 0;
 }
 
 static int ghash_final(struct shash_desc *desc, u8 *dst)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	int ret;
 
-	ghash_flush(ctx, dctx);
-	memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE);
-
-	return 0;
+	ret = ghash_flush(ctx, dctx);
+	if (!ret)
+		memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE);
+	return ret;
 }
 
 static struct shash_alg ghash_alg = {

arch/s390/crypto/sha_common.c

@@ -36,7 +36,8 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len)
 	if (index) {
 		memcpy(ctx->buf + index, data, bsize - index);
 		ret = crypt_s390_kimd(ctx->func, ctx->state, ctx->buf, bsize);
-		BUG_ON(ret != bsize);
+		if (ret != bsize)
+			return -EIO;
 		data += bsize - index;
 		len -= bsize - index;
 		index = 0;
@@ -46,7 +47,8 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len)
 	if (len >= bsize) {
 		ret = crypt_s390_kimd(ctx->func, ctx->state, data,
 				      len & ~(bsize - 1));
-		BUG_ON(ret != (len & ~(bsize - 1)));
+		if (ret != (len & ~(bsize - 1)))
+			return -EIO;
 		data += ret;
 		len -= ret;
 	}
@@ -88,7 +90,8 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	memcpy(ctx->buf + end - 8, &bits, sizeof(bits));
 
 	ret = crypt_s390_kimd(ctx->func, ctx->state, ctx->buf, end);
-	BUG_ON(ret != end);
+	if (ret != end)
+		return -EIO;
 
 	/* copy digest to out */
 	memcpy(out, ctx->state, crypto_shash_digestsize(desc->tfm));

arch/s390/include/asm/bitops.h

@@ -640,6 +640,87 @@ static inline unsigned long find_first_bit(const unsigned long * addr,
 }
 #define find_first_bit find_first_bit
 
+/*
+ * Big endian variant whichs starts bit counting from left using
+ * the flogr (find leftmost one) instruction.
+ */
+static inline unsigned long __flo_word(unsigned long nr, unsigned long val)
+{
+	register unsigned long bit asm("2") = val;
+	register unsigned long out asm("3");
+
+	asm volatile (
+		"	.insn	rre,0xb9830000,%[bit],%[bit]\n"
+		: [bit] "+d" (bit), [out] "=d" (out) : : "cc");
+	return nr + bit;
+}
+
+/*
+ * 64 bit special left bitops format:
+ * order in memory:
+ *    00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
+ *    10 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f
+ *    20 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f
+ *    30 31 32 33 34 35 36 37 38 39 3a 3b 3c 3d 3e 3f
+ * after that follows the next long with bit numbers
+ *    40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f
+ *    50 51 52 53 54 55 56 57 58 59 5a 5b 5c 5d 5e 5f
+ *    60 61 62 63 64 65 66 67 68 69 6a 6b 6c 6d 6e 6f
+ *    70 71 72 73 74 75 76 77 78 79 7a 7b 7c 7d 7e 7f
+ * The reason for this bit ordering is the fact that
+ * the hardware sets bits in a bitmap starting at bit 0
+ * and we don't want to scan the bitmap from the 'wrong
+ * end'.
+ */
+static inline unsigned long find_first_bit_left(const unsigned long *addr,
+						unsigned long size)
+{
+	unsigned long bytes, bits;
+
+	if (!size)
+		return 0;
+	bytes = __ffs_word_loop(addr, size);
+	bits = __flo_word(bytes * 8, __load_ulong_be(addr, bytes));
+	return (bits < size) ? bits : size;
+}
+
+static inline int find_next_bit_left(const unsigned long *addr,
+				     unsigned long size,
+				     unsigned long offset)
+{
+	const unsigned long *p;
+	unsigned long bit, set;
+
+	if (offset >= size)
+		return size;
+	bit = offset & (__BITOPS_WORDSIZE - 1);
+	offset -= bit;
+	size -= offset;
+	p = addr + offset / __BITOPS_WORDSIZE;
+	if (bit) {
+		set = __flo_word(0, *p & (~0UL << bit));
+		if (set >= size)
+			return size + offset;
+		if (set < __BITOPS_WORDSIZE)
+			return set + offset;
+		offset += __BITOPS_WORDSIZE;
+		size -= __BITOPS_WORDSIZE;
+		p++;
+	}
+	return offset + find_first_bit_left(p, size);
+}
+
+#define for_each_set_bit_left(bit, addr, size)				\
+	for ((bit) = find_first_bit_left((addr), (size));		\
+	     (bit) < (size);						\
+	     (bit) = find_next_bit_left((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_left_cont(bit, addr, size)			\
+	for ((bit) = find_next_bit_left((addr), (size), (bit));		\
+	     (bit) < (size);						\
+	     (bit) = find_next_bit_left((addr), (size), (bit) + 1))
+
 /**
  * find_next_zero_bit - find the first zero bit in a memory region
  * @addr: The address to base the search on

arch/s390/include/asm/ccwdev.h

@@ -18,6 +18,9 @@ struct irb;
 struct ccw1;
 struct ccw_dev_id;
 
+/* from asm/schid.h */
+struct subchannel_id;
+
 /* simplified initializers for struct ccw_device:
  * CCW_DEVICE and CCW_DEVICE_DEVTYPE initialize one
  * entry in your MODULE_DEVICE_TABLE and set the match_flag correctly */
@@ -223,8 +226,7 @@ extern int ccw_device_force_console(void);
 
 int ccw_device_siosl(struct ccw_device *);
 
-// FIXME: these have to go
-extern int _ccw_device_get_subchannel_number(struct ccw_device *);
+extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
 
 extern void *ccw_device_get_chp_desc(struct ccw_device *, int);
 #endif /* _S390_CCWDEV_H_ */

arch/s390/include/asm/ccwgroup.h

@@ -59,6 +59,9 @@ extern void ccwgroup_driver_unregister (struct ccwgroup_driver *cdriver);
 int ccwgroup_create_dev(struct device *root, struct ccwgroup_driver *gdrv,
 			int num_devices, const char *buf);
 
+extern int ccwgroup_set_online(struct ccwgroup_device *gdev);
+extern int ccwgroup_set_offline(struct ccwgroup_device *gdev);
+
 extern int ccwgroup_probe_ccwdev(struct ccw_device *cdev);
 extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev);
 

arch/s390/include/asm/clp.h

@@ -0,0 +1,28 @@
+#ifndef _ASM_S390_CLP_H
+#define _ASM_S390_CLP_H
+
+/* CLP common request & response block size */
+#define CLP_BLK_SIZE			(PAGE_SIZE * 2)
+
+struct clp_req_hdr {
+	u16 len;
+	u16 cmd;
+} __packed;
+
+struct clp_rsp_hdr {
+	u16 len;
+	u16 rsp;
+} __packed;
+
+/* CLP Response Codes */
+#define CLP_RC_OK			0x0010	/* Command request successfully */
+#define CLP_RC_CMD			0x0020	/* Command code not recognized */
+#define CLP_RC_PERM			0x0030	/* Command not authorized */
+#define CLP_RC_FMT			0x0040	/* Invalid command request format */
+#define CLP_RC_LEN			0x0050	/* Invalid command request length */
+#define CLP_RC_8K			0x0060	/* Command requires 8K LPCB */
+#define CLP_RC_RESNOT0			0x0070	/* Reserved field not zero */
+#define CLP_RC_NODATA			0x0080	/* No data available */
+#define CLP_RC_FC_UNKNOWN		0x0100	/* Function code not recognized */
+
+#endif

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/hw_irq.h

@@ -0,0 +1,22 @@
+#ifndef _HW_IRQ_H
+#define _HW_IRQ_H
+
+#include <linux/msi.h>
+#include <linux/pci.h>
+
+static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
+{
+	return __irq_get_msi_desc(irq);
+}
+
+/* Must be called with msi map lock held */
+static inline int irq_set_msi_desc(unsigned int irq, struct msi_desc *msi)
+{
+	if (!msi)
+		return -EINVAL;
+
+	msi->irq = irq;
+	return 0;
+}
+
+#endif

arch/s390/include/asm/io.h

@@ -9,9 +9,9 @@
 #ifndef _S390_IO_H
 #define _S390_IO_H
 
+#include <linux/kernel.h>
 #include <asm/page.h>
-
-#define IO_SPACE_LIMIT 0xffffffff
+#include <asm/pci_io.h>
 
 /*
  * Change virtual addresses to physical addresses and vv.
@@ -24,10 +24,11 @@ static inline unsigned long virt_to_phys(volatile void * address)
 		 "	lra	%0,0(%1)\n"
 		 "	jz	0f\n"
 		 "	la	%0,0\n"
-                 "0:"
+		 "0:"
 		 : "=a" (real_address) : "a" (address) : "cc");
-        return real_address;
+	return real_address;
 }
+#define virt_to_phys virt_to_phys
 
 static inline void * phys_to_virt(unsigned long address)
 {
@@ -42,4 +43,50 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+#define IO_SPACE_LIMIT 0
+
+#ifdef CONFIG_PCI
+
+#define ioremap_nocache(addr, size)	ioremap(addr, size)
+#define ioremap_wc			ioremap_nocache
+
+/* TODO: s390 cannot support io_remap_pfn_range... */
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) 	       \
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
+{
+	return (void __iomem *) offset;
+}
+
+static inline void iounmap(volatile void __iomem *addr)
+{
+}
+
+/*
+ * s390 needs a private implementation of pci_iomap since ioremap with its
+ * offset parameter isn't sufficient. That's because BAR spaces are not
+ * disjunctive on s390 so we need the bar parameter of pci_iomap to find
+ * the corresponding device and create the mapping cookie.
+ */
+#define pci_iomap pci_iomap
+#define pci_iounmap pci_iounmap
+
+#define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
+#define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)
+#define memset_io(dst, val, count)	zpci_memset_io(dst, val, count)
+
+#define __raw_readb	zpci_read_u8
+#define __raw_readw	zpci_read_u16
+#define __raw_readl	zpci_read_u32
+#define __raw_readq	zpci_read_u64
+#define __raw_writeb	zpci_write_u8
+#define __raw_writew	zpci_write_u16
+#define __raw_writel	zpci_write_u32
+#define __raw_writeq	zpci_write_u64
+
+#endif /* CONFIG_PCI */
+
+#include <asm-generic/io.h>
+
 #endif

arch/s390/include/asm/irq.h

@@ -33,6 +33,8 @@ enum interruption_class {
 	IOINT_APB,
 	IOINT_ADM,
 	IOINT_CSC,
+	IOINT_PCI,
+	IOINT_MSI,
 	NMI_NMI,
 	NR_IRQS,
 };
@@ -51,4 +53,14 @@ void service_subclass_irq_unregister(void);
 void measurement_alert_subclass_register(void);
 void measurement_alert_subclass_unregister(void);
 
+#ifdef CONFIG_LOCKDEP
+#  define disable_irq_nosync_lockdep(irq)	disable_irq_nosync(irq)
+#  define disable_irq_nosync_lockdep_irqsave(irq, flags) \
+						disable_irq_nosync(irq)
+#  define disable_irq_lockdep(irq)		disable_irq(irq)
+#  define enable_irq_lockdep(irq)		enable_irq(irq)
+#  define enable_irq_lockdep_irqrestore(irq, flags) \
+						enable_irq(irq)
+#endif
+
 #endif /* _ASM_IRQ_H */

arch/s390/include/asm/isc.h

@@ -18,6 +18,7 @@
 #define CHSC_SCH_ISC 7			/* CHSC subchannels */
 /* Adapter interrupts. */
 #define QDIO_AIRQ_ISC IO_SCH_ISC	/* I/O subchannel in qdio mode */
+#define PCI_ISC 2			/* PCI I/O subchannels */
 #define AP_ISC 6			/* adjunct processor (crypto) devices */
 
 /* Functions for registration of I/O interruption subclasses */

arch/s390/include/asm/page.h

@@ -30,6 +30,8 @@
 #include <asm/setup.h>
 #ifndef __ASSEMBLY__
 
+void storage_key_init_range(unsigned long start, unsigned long end);
+
 static unsigned long pfmf(unsigned long function, unsigned long address)
 {
 	asm volatile(

arch/s390/include/asm/pci.h

@@ -1,10 +1,158 @@
 #ifndef __ASM_S390_PCI_H
 #define __ASM_S390_PCI_H
 
-/* S/390 systems don't have a PCI bus. This file is just here because some stupid .c code
- * includes it even if CONFIG_PCI is not set.
- */
+/* must be set before including asm-generic/pci.h */
 #define PCI_DMA_BUS_IS_PHYS (0)
+/* must be set before including pci_clp.h */
+#define PCI_BAR_COUNT	6
 
-#endif /* __ASM_S390_PCI_H */
+#include <asm-generic/pci.h>
+#include <asm-generic/pci-dma-compat.h>
+#include <asm/pci_clp.h>
 
+#define PCIBIOS_MIN_IO		0x1000
+#define PCIBIOS_MIN_MEM		0x10000000
+
+#define pcibios_assign_all_busses()	(0)
+
+void __iomem *pci_iomap(struct pci_dev *, int, unsigned long);
+void pci_iounmap(struct pci_dev *, void __iomem *);
+int pci_domain_nr(struct pci_bus *);
+int pci_proc_domain(struct pci_bus *);
+
+/* MSI arch hooks */
+#define arch_setup_msi_irqs	arch_setup_msi_irqs
+#define arch_teardown_msi_irqs	arch_teardown_msi_irqs
+
+#define ZPCI_BUS_NR			0	/* default bus number */
+#define ZPCI_DEVFN			0	/* default device number */
+
+/* PCI Function Controls */
+#define ZPCI_FC_FN_ENABLED		0x80
+#define ZPCI_FC_ERROR			0x40
+#define ZPCI_FC_BLOCKED			0x20
+#define ZPCI_FC_DMA_ENABLED		0x10
+
+struct msi_map {
+	unsigned long irq;
+	struct msi_desc *msi;
+	struct hlist_node msi_chain;
+};
+
+#define ZPCI_NR_MSI_VECS	64
+#define ZPCI_MSI_MASK		(ZPCI_NR_MSI_VECS - 1)
+
+enum zpci_state {
+	ZPCI_FN_STATE_RESERVED,
+	ZPCI_FN_STATE_STANDBY,
+	ZPCI_FN_STATE_CONFIGURED,
+	ZPCI_FN_STATE_ONLINE,
+	NR_ZPCI_FN_STATES,
+};
+
+struct zpci_bar_struct {
+	u32		val;		/* bar start & 3 flag bits */
+	u8		size;		/* order 2 exponent */
+	u16		map_idx;	/* index into bar mapping array */
+};
+
+/* Private data per function */
+struct zpci_dev {
+	struct pci_dev	*pdev;
+	struct pci_bus	*bus;
+	struct list_head entry;		/* list of all zpci_devices, needed for hotplug, etc. */
+
+	enum zpci_state state;
+	u32		fid;		/* function ID, used by sclp */
+	u32		fh;		/* function handle, used by insn's */
+	u16		pchid;		/* physical channel ID */
+	u8		pfgid;		/* function group ID */
+	u16		domain;
+
+	/* IRQ stuff */
+	u64		msi_addr;	/* MSI address */
+	struct zdev_irq_map *irq_map;
+	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;
+};
+
+struct pci_hp_callback_ops {
+	int (*create_slot)	(struct zpci_dev *zdev);
+	void (*remove_slot)	(struct zpci_dev *zdev);
+};
+
+static inline bool zdev_enabled(struct zpci_dev *zdev)
+{
+	return (zdev->fh & (1UL << 31)) ? true : false;
+}
+
+/* -----------------------------------------------------------------------------
+  Prototypes
+----------------------------------------------------------------------------- */
+/* Base stuff */
+struct zpci_dev *zpci_alloc_device(void);
+int zpci_create_device(struct zpci_dev *);
+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);
+int clp_add_pci_device(u32, u32, int);
+int clp_enable_fh(struct zpci_dev *, u8);
+int clp_disable_fh(struct zpci_dev *);
+
+/* MSI */
+struct msi_desc *__irq_get_msi_desc(unsigned int);
+int zpci_msi_set_mask_bits(struct msi_desc *, u32, u32);
+int zpci_setup_msi_irq(struct zpci_dev *, struct msi_desc *, unsigned int, int);
+void zpci_teardown_msi_irq(struct zpci_dev *, struct msi_desc *);
+int zpci_msihash_init(void);
+void zpci_msihash_exit(void);
+
+/* Error handling and recovery */
+void zpci_event_error(void *);
+void zpci_event_availability(void *);
+
+/* Helpers */
+struct zpci_dev *get_zdev(struct pci_dev *);
+struct zpci_dev *get_zdev_by_fid(u32);
+bool zpci_fid_present(u32);
+
+/* sysfs */
+int zpci_sysfs_add_device(struct device *);
+void zpci_sysfs_remove_device(struct device *);
+
+/* DMA */
+int zpci_dma_init(void);
+void zpci_dma_exit(void);
+
+/* Hotplug */
+extern struct mutex zpci_list_lock;
+extern struct list_head zpci_list;
+extern struct pci_hp_callback_ops hotplug_ops;
+extern unsigned int pci_probe;
+
+#endif

arch/s390/include/asm/pci_clp.h

@@ -0,0 +1,182 @@
+#ifndef _ASM_S390_PCI_CLP_H
+#define _ASM_S390_PCI_CLP_H
+
+#include <asm/clp.h>
+
+/*
+ * Call Logical Processor - Command Codes
+ */
+#define CLP_LIST_PCI		0x0002
+#define CLP_QUERY_PCI_FN	0x0003
+#define CLP_QUERY_PCI_FNGRP	0x0004
+#define CLP_SET_PCI_FN		0x0005
+
+/* PCI function handle list entry */
+struct clp_fh_list_entry {
+	u16 device_id;
+	u16 vendor_id;
+	u32 config_state :  1;
+	u32		 : 31;
+	u32 fid;		/* PCI function id */
+	u32 fh;			/* PCI function handle */
+} __packed;
+
+#define CLP_RC_SETPCIFN_FH	0x0101	/* Invalid PCI fn handle */
+#define CLP_RC_SETPCIFN_FHOP	0x0102	/* Fn handle not valid for op */
+#define CLP_RC_SETPCIFN_DMAAS	0x0103	/* Invalid DMA addr space */
+#define CLP_RC_SETPCIFN_RES	0x0104	/* Insufficient resources */
+#define CLP_RC_SETPCIFN_ALRDY	0x0105	/* Fn already in requested state */
+#define CLP_RC_SETPCIFN_ERR	0x0106	/* Fn in permanent error state */
+#define CLP_RC_SETPCIFN_RECPND	0x0107	/* Error recovery pending */
+#define CLP_RC_SETPCIFN_BUSY	0x0108	/* Fn busy */
+#define CLP_RC_LISTPCI_BADRT	0x010a	/* Resume token not recognized */
+#define CLP_RC_QUERYPCIFG_PFGID	0x010b	/* Unrecognized PFGID */
+
+/* request or response block header length */
+#define LIST_PCI_HDR_LEN	32
+
+/* Number of function handles fitting in response block */
+#define CLP_FH_LIST_NR_ENTRIES				\
+	((CLP_BLK_SIZE - 2 * LIST_PCI_HDR_LEN)		\
+		/ sizeof(struct clp_fh_list_entry))
+
+#define CLP_SET_ENABLE_PCI_FN	0	/* Yes, 0 enables it */
+#define CLP_SET_DISABLE_PCI_FN	1	/* Yes, 1 disables it */
+
+#define CLP_UTIL_STR_LEN	64
+
+/* List PCI functions request */
+struct clp_req_list_pci {
+	struct clp_req_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u64 resume_token;
+	u64 reserved2;
+} __packed;
+
+/* List PCI functions response */
+struct clp_rsp_list_pci {
+	struct clp_rsp_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u64 resume_token;
+	u32 reserved2;
+	u16 max_fn;
+	u8 reserved3;
+	u8 entry_size;
+	struct clp_fh_list_entry fh_list[CLP_FH_LIST_NR_ENTRIES];
+} __packed;
+
+/* Query PCI function request */
+struct clp_req_query_pci {
+	struct clp_req_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u32 fh;				/* function handle */
+	u32 reserved2;
+	u64 reserved3;
+} __packed;
+
+/* Query PCI function response */
+struct clp_rsp_query_pci {
+	struct clp_rsp_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u16 vfn;			/* virtual fn number */
+	u16			:  7;
+	u16 util_str_avail	:  1;	/* utility string available? */
+	u16 pfgid		:  8;	/* pci function group id */
+	u32 fid;			/* pci function id */
+	u8 bar_size[PCI_BAR_COUNT];
+	u16 pchid;
+	u32 bar[PCI_BAR_COUNT];
+	u64 reserved2;
+	u64 sdma;			/* start dma as */
+	u64 edma;			/* end dma as */
+	u64 reserved3[6];
+	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
+} __packed;
+
+/* Query PCI function group request */
+struct clp_req_query_pci_grp {
+	struct clp_req_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u32			: 24;
+	u32 pfgid		:  8;	/* function group id */
+	u32 reserved2;
+	u64 reserved3;
+} __packed;
+
+/* Query PCI function group response */
+struct clp_rsp_query_pci_grp {
+	struct clp_rsp_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u16			:  4;
+	u16 noi			: 12;	/* number of interrupts */
+	u8 version;
+	u8			:  6;
+	u8 frame		:  1;
+	u8 refresh		:  1;	/* TLB refresh mode */
+	u16 reserved2;
+	u16 mui;
+	u64 reserved3;
+	u64 dasm;			/* dma address space mask */
+	u64 msia;			/* MSI address */
+	u64 reserved4;
+	u64 reserved5;
+} __packed;
+
+/* Set PCI function request */
+struct clp_req_set_pci {
+	struct clp_req_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u32 fh;				/* function handle */
+	u16 reserved2;
+	u8 oc;				/* operation controls */
+	u8 ndas;			/* number of dma spaces */
+	u64 reserved3;
+} __packed;
+
+/* Set PCI function response */
+struct clp_rsp_set_pci {
+	struct clp_rsp_hdr hdr;
+	u32 fmt			:  4;	/* cmd request block format */
+	u32			: 28;
+	u64 reserved1;
+	u32 fh;				/* function handle */
+	u32 reserved3;
+	u64 reserved4;
+} __packed;
+
+/* Combined request/response block structures used by clp insn */
+struct clp_req_rsp_list_pci {
+	struct clp_req_list_pci request;
+	struct clp_rsp_list_pci response;
+} __packed;
+
+struct clp_req_rsp_set_pci {
+	struct clp_req_set_pci request;
+	struct clp_rsp_set_pci response;
+} __packed;
+
+struct clp_req_rsp_query_pci {
+	struct clp_req_query_pci request;
+	struct clp_rsp_query_pci response;
+} __packed;
+
+struct clp_req_rsp_query_pci_grp {
+	struct clp_req_query_pci_grp request;
+	struct clp_rsp_query_pci_grp response;
+} __packed;
+
+#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/include/asm/pci_insn.h

@@ -0,0 +1,280 @@
+#ifndef _ASM_S390_PCI_INSN_H
+#define _ASM_S390_PCI_INSN_H
+
+#include <linux/delay.h>
+
+#define ZPCI_INSN_BUSY_DELAY	1	/* 1 microsecond */
+
+/* Load/Store status codes */
+#define ZPCI_PCI_ST_FUNC_NOT_ENABLED		4
+#define ZPCI_PCI_ST_FUNC_IN_ERR			8
+#define ZPCI_PCI_ST_BLOCKED			12
+#define ZPCI_PCI_ST_INSUF_RES			16
+#define ZPCI_PCI_ST_INVAL_AS			20
+#define ZPCI_PCI_ST_FUNC_ALREADY_ENABLED	24
+#define ZPCI_PCI_ST_DMA_AS_NOT_ENABLED		28
+#define ZPCI_PCI_ST_2ND_OP_IN_INV_AS		36
+#define ZPCI_PCI_ST_FUNC_NOT_AVAIL		40
+#define ZPCI_PCI_ST_ALREADY_IN_RQ_STATE		44
+
+/* Load/Store return codes */
+#define ZPCI_PCI_LS_OK				0
+#define ZPCI_PCI_LS_ERR				1
+#define ZPCI_PCI_LS_BUSY			2
+#define ZPCI_PCI_LS_INVAL_HANDLE		3
+
+/* Load/Store address space identifiers */
+#define ZPCI_PCIAS_MEMIO_0			0
+#define ZPCI_PCIAS_MEMIO_1			1
+#define ZPCI_PCIAS_MEMIO_2			2
+#define ZPCI_PCIAS_MEMIO_3			3
+#define ZPCI_PCIAS_MEMIO_4			4
+#define ZPCI_PCIAS_MEMIO_5			5
+#define ZPCI_PCIAS_CFGSPC			15
+
+/* Modify PCI Function Controls */
+#define ZPCI_MOD_FC_REG_INT	2
+#define ZPCI_MOD_FC_DEREG_INT	3
+#define ZPCI_MOD_FC_REG_IOAT	4
+#define ZPCI_MOD_FC_DEREG_IOAT	5
+#define ZPCI_MOD_FC_REREG_IOAT	6
+#define ZPCI_MOD_FC_RESET_ERROR	7
+#define ZPCI_MOD_FC_RESET_BLOCK	9
+#define ZPCI_MOD_FC_SET_MEASURE	10
+
+/* FIB function controls */
+#define ZPCI_FIB_FC_ENABLED	0x80
+#define ZPCI_FIB_FC_ERROR	0x40
+#define ZPCI_FIB_FC_LS_BLOCKED	0x20
+#define ZPCI_FIB_FC_DMAAS_REG	0x10
+
+/* FIB function controls */
+#define ZPCI_FIB_FC_ENABLED	0x80
+#define ZPCI_FIB_FC_ERROR	0x40
+#define ZPCI_FIB_FC_LS_BLOCKED	0x20
+#define ZPCI_FIB_FC_DMAAS_REG	0x10
+
+/* Function Information Block */
+struct zpci_fib {
+	u32 fmt		:  8;	/* format */
+	u32		: 24;
+	u32 reserved1;
+	u8 fc;			/* function controls */
+	u8 reserved2;
+	u16 reserved3;
+	u32 reserved4;
+	u64 pba;		/* PCI base address */
+	u64 pal;		/* PCI address limit */
+	u64 iota;		/* I/O Translation Anchor */
+	u32		:  1;
+	u32 isc		:  3;	/* Interrupt subclass */
+	u32 noi		: 12;	/* Number of interrupts */
+	u32		:  2;
+	u32 aibvo	:  6;	/* Adapter interrupt bit vector offset */
+	u32 sum		:  1;	/* Adapter int summary bit enabled */
+	u32		:  1;
+	u32 aisbo	:  6;	/* Adapter int summary bit offset */
+	u32 reserved5;
+	u64 aibv;		/* Adapter int bit vector address */
+	u64 aisb;		/* Adapter int summary bit address */
+	u64 fmb_addr;		/* Function measurement block address and key */
+	u64 reserved6;
+	u64 reserved7;
+} __packed;
+
+/* Modify PCI Function Controls */
+static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status)
+{
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rxy,0xe300000000d0,%[req],%[fib]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (req), [fib] "+Q" (*fib)
+		: : "cc");
+	*status = req >> 24 & 0xff;
+	return cc;
+}
+
+static inline int mpcifc_instr(u64 req, struct zpci_fib *fib)
+{
+	u8 cc, status;
+
+	do {
+		cc = __mpcifc(req, fib, &status);
+		if (cc == 2)
+			msleep(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d\n",
+			     __func__, cc, status);
+	return (cc) ? -EIO : 0;
+}
+
+/* Refresh PCI Translations */
+static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status)
+{
+	register u64 __addr asm("2") = addr;
+	register u64 __range asm("3") = range;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d30000,%[fn],%[addr]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [fn] "+d" (fn)
+		: [addr] "d" (__addr), "d" (__range)
+		: "cc");
+	*status = fn >> 24 & 0xff;
+	return cc;
+}
+
+static inline int rpcit_instr(u64 fn, u64 addr, u64 range)
+{
+	u8 cc, status;
+
+	do {
+		cc = __rpcit(fn, addr, range, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  dma_addr: %Lx  size: %Lx\n",
+			    __func__, cc, status, addr, range);
+	return (cc) ? -EIO : 0;
+}
+
+/* Store PCI function controls */
+static inline u8 __stpcifc(u32 handle, u8 space, struct zpci_fib *fib, u8 *status)
+{
+	u64 fn = (u64) handle << 32 | space << 16;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rxy,0xe300000000d4,%[fn],%[fib]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [fn] "+d" (fn), [fib] "=m" (*fib)
+		: : "cc");
+	*status = fn >> 24 & 0xff;
+	return cc;
+}
+
+/* Set Interruption Controls */
+static inline void sic_instr(u16 ctl, char *unused, u8 isc)
+{
+	asm volatile (
+		"	.insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
+		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+}
+
+/* PCI Load */
+static inline u8 __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
+{
+	register u64 __req asm("2") = req;
+	register u64 __offset asm("3") = offset;
+	u64 __data;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d20000,%[data],%[req]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [data] "=d" (__data), [req] "+d" (__req)
+		:  "d" (__offset)
+		: "cc");
+	*status = __req >> 24 & 0xff;
+	*data = __data;
+	return cc;
+}
+
+static inline int pcilg_instr(u64 *data, u64 req, u64 offset)
+{
+	u8 cc, status;
+
+	do {
+		cc = __pcilg(data, req, offset, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc) {
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			    __func__, cc, status, req, offset);
+		/* TODO: on IO errors set data to 0xff...
+		 * here or in users of pcilg (le conversion)?
+		 */
+	}
+	return (cc) ? -EIO : 0;
+}
+
+/* PCI Store */
+static inline u8 __pcistg(u64 data, u64 req, u64 offset, u8 *status)
+{
+	register u64 __req asm("2") = req;
+	register u64 __offset asm("3") = offset;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rre,0xb9d00000,%[data],%[req]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (__req)
+		: "d" (__offset), [data] "d" (data)
+		: "cc");
+	*status = __req >> 24 & 0xff;
+	return cc;
+}
+
+static inline int pcistg_instr(u64 data, u64 req, u64 offset)
+{
+	u8 cc, status;
+
+	do {
+		cc = __pcistg(data, req, offset, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			__func__, cc, status, req, offset);
+	return (cc) ? -EIO : 0;
+}
+
+/* PCI Store Block */
+static inline u8 __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
+{
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rsy,0xeb00000000d0,%[req],%[offset],%[data]\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [req] "+d" (req)
+		: [offset] "d" (offset), [data] "Q" (*data)
+		: "cc");
+	*status = req >> 24 & 0xff;
+	return cc;
+}
+
+static inline int pcistb_instr(const u64 *data, u64 req, u64 offset)
+{
+	u8 cc, status;
+
+	do {
+		cc = __pcistb(data, req, offset, &status);
+		if (cc == 2)
+			udelay(ZPCI_INSN_BUSY_DELAY);
+	} while (cc == 2);
+
+	if (cc)
+		printk_once(KERN_ERR "%s: error cc: %d  status: %d  req: %Lx  offset: %Lx\n",
+			    __func__, cc, status, req, offset);
+	return (cc) ? -EIO : 0;
+}
+
+#endif

arch/s390/include/asm/pci_io.h

@@ -0,0 +1,194 @@
+#ifndef _ASM_S390_PCI_IO_H
+#define _ASM_S390_PCI_IO_H
+
+#ifdef CONFIG_PCI
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <asm/pci_insn.h>
+
+/* I/O Map */
+#define ZPCI_IOMAP_MAX_ENTRIES		0x7fff
+#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000ULL
+#define ZPCI_IOMAP_ADDR_IDX_MASK	0x7fff000000000000ULL
+#define ZPCI_IOMAP_ADDR_OFF_MASK	0x0000ffffffffffffULL
+
+struct zpci_iomap_entry {
+	u32 fh;
+	u8 bar;
+};
+
+extern struct zpci_iomap_entry *zpci_iomap_start;
+
+#define ZPCI_IDX(addr)								\
+	(((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> 48)
+#define ZPCI_OFFSET(addr)							\
+	((__force u64) addr & ZPCI_IOMAP_ADDR_OFF_MASK)
+
+#define ZPCI_CREATE_REQ(handle, space, len)					\
+	((u64) handle << 32 | space << 16 | len)
+
+#define zpci_read(LENGTH, RETTYPE)						\
+static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
+{										\
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
+	u64 data;								\
+	int rc;									\
+										\
+	rc = pcilg_instr(&data, req, ZPCI_OFFSET(addr));			\
+	if (rc)									\
+		data = -1ULL;							\
+	return (RETTYPE) data;							\
+}
+
+#define zpci_write(LENGTH, VALTYPE)						\
+static inline void zpci_write_##VALTYPE(VALTYPE val,				\
+					const volatile void __iomem *addr)	\
+{										\
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
+	u64 data = (VALTYPE) val;						\
+										\
+	pcistg_instr(data, req, ZPCI_OFFSET(addr));				\
+}
+
+zpci_read(8, u64)
+zpci_read(4, u32)
+zpci_read(2, u16)
+zpci_read(1, u8)
+zpci_write(8, u64)
+zpci_write(4, u32)
+zpci_write(2, u16)
+zpci_write(1, u8)
+
+static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len)
+{
+	u64 val;
+
+	switch (len) {
+	case 1:
+		val = (u64) *((u8 *) data);
+		break;
+	case 2:
+		val = (u64) *((u16 *) data);
+		break;
+	case 4:
+		val = (u64) *((u32 *) data);
+		break;
+	case 8:
+		val = (u64) *((u64 *) data);
+		break;
+	default:
+		val = 0;		/* let FW report error */
+		break;
+	}
+	return pcistg_instr(val, req, offset);
+}
+
+static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
+{
+	u64 data;
+	u8 cc;
+
+	cc = pcilg_instr(&data,	 req, offset);
+	switch (len) {
+	case 1:
+		*((u8 *) dst) = (u8) data;
+		break;
+	case 2:
+		*((u16 *) dst) = (u16) data;
+		break;
+	case 4:
+		*((u32 *) dst) = (u32) data;
+		break;
+	case 8:
+		*((u64 *) dst) = (u64) data;
+		break;
+	}
+	return cc;
+}
+
+static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
+{
+	return pcistb_instr(data, req, offset);
+}
+
+static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
+{
+	int count = len > max ? max : len, size = 1;
+
+	while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) {
+		dst = dst >> 1;
+		src = src >> 1;
+		size = size << 1;
+	}
+	return size;
+}
+
+static inline int zpci_memcpy_fromio(void *dst,
+				     const volatile void __iomem *src,
+				     unsigned long n)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(src)];
+	u64 req, offset = ZPCI_OFFSET(src);
+	int size, rc = 0;
+
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64) src, (u64) dst, n, 8);
+		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
+		rc = zpci_read_single(req, dst, offset, size);
+		if (rc)
+			break;
+		offset += size;
+		dst += size;
+		n -= size;
+	}
+	return rc;
+}
+
+static inline int zpci_memcpy_toio(volatile void __iomem *dst,
+				   const void *src, unsigned long n)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
+	u64 req, offset = ZPCI_OFFSET(dst);
+	int size, rc = 0;
+
+	if (!src)
+		return -EINVAL;
+
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64) dst, (u64) src, n, 128);
+		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
+
+		if (size > 8) /* main path */
+			rc = zpci_write_block(req, src, offset);
+		else
+			rc = zpci_write_single(req, src, offset, size);
+		if (rc)
+			break;
+		offset += size;
+		src += size;
+		n -= size;
+	}
+	return rc;
+}
+
+static inline int zpci_memset_io(volatile void __iomem *dst,
+				 unsigned char val, size_t count)
+{
+	u8 *src = kmalloc(count, GFP_KERNEL);
+	int rc;
+
+	if (src == NULL)
+		return -ENOMEM;
+	memset(src, val, count);
+
+	rc = zpci_memcpy_toio(dst, src, count);
+	kfree(src);
+	return rc;
+}
+
+#endif /* CONFIG_PCI */
+
+#endif /* _ASM_S390_PCI_IO_H */

arch/s390/include/asm/pgtable.h

@@ -35,7 +35,6 @@
 extern pgd_t swapper_pg_dir[] __attribute__ ((aligned (4096)));
 extern void paging_init(void);
 extern void vmem_map_init(void);
-extern void fault_init(void);
 
 /*
  * The S390 doesn't have any external MMU info: the kernel page
@@ -336,6 +335,8 @@ extern unsigned long MODULES_END;
 #define _REGION3_ENTRY		(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
 #define _REGION3_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV)
 
+#define _REGION3_ENTRY_LARGE	0x400	/* RTTE-format control, large page  */
+
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* segment table origin		    */
 #define _SEGMENT_ENTRY_RO	0x200	/* page protection bit		    */
@@ -435,6 +436,7 @@ static inline int pgd_bad(pgd_t pgd)     { return 0; }
 
 static inline int pud_present(pud_t pud) { return 1; }
 static inline int pud_none(pud_t pud)	 { return 0; }
+static inline int pud_large(pud_t pud)	 { return 0; }
 static inline int pud_bad(pud_t pud)	 { return 0; }
 
 #else /* CONFIG_64BIT */
@@ -480,6 +482,13 @@ static inline int pud_none(pud_t pud)
 	return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL;
 }
 
+static inline int pud_large(pud_t pud)
+{
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) != _REGION_ENTRY_TYPE_R3)
+		return 0;
+	return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
+}
+
 static inline int pud_bad(pud_t pud)
 {
 	/*

arch/s390/include/asm/sclp.h

@@ -55,5 +55,7 @@ int sclp_chp_read_info(struct sclp_chp_info *info);
 void sclp_get_ipl_info(struct sclp_ipl_info *info);
 bool sclp_has_linemode(void);
 bool sclp_has_vt220(void);
+int sclp_pci_configure(u32 fid);
+int sclp_pci_deconfigure(u32 fid);
 
 #endif /* _ASM_S390_SCLP_H */

arch/s390/include/asm/topology.h

@@ -8,32 +8,34 @@ struct cpu;
 
 #ifdef CONFIG_SCHED_BOOK
 
-extern unsigned char cpu_socket_id[NR_CPUS];
-#define topology_physical_package_id(cpu) (cpu_socket_id[cpu])
+struct cpu_topology_s390 {
+	unsigned short core_id;
+	unsigned short socket_id;
+	unsigned short book_id;
+	cpumask_t core_mask;
+	cpumask_t book_mask;
+};
+
+extern struct cpu_topology_s390 cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_core_id(cpu)			(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)		(&cpu_topology[cpu].core_mask)
+#define topology_book_id(cpu)			(cpu_topology[cpu].book_id)
+#define topology_book_cpumask(cpu)		(&cpu_topology[cpu].book_mask)
 
-extern unsigned char cpu_core_id[NR_CPUS];
-extern cpumask_t cpu_core_map[NR_CPUS];
+#define mc_capable() 1
 
 static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	return &cpu_core_map[cpu];
+	return &cpu_topology[cpu].core_mask;
 }
 
-#define topology_core_id(cpu)		(cpu_core_id[cpu])
-#define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
-#define mc_capable()			(1)
-
-extern unsigned char cpu_book_id[NR_CPUS];
-extern cpumask_t cpu_book_map[NR_CPUS];
-
 static inline const struct cpumask *cpu_book_mask(int cpu)
 {
-	return &cpu_book_map[cpu];
+	return &cpu_topology[cpu].book_mask;
 }
 
-#define topology_book_id(cpu)		(cpu_book_id[cpu])
-#define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
-
 int topology_cpu_init(struct cpu *);
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);

arch/s390/include/asm/vga.h

@@ -0,0 +1,6 @@
+#ifndef _ASM_S390_VGA_H
+#define _ASM_S390_VGA_H
+
+/* Avoid compile errors due to missing asm/vga.h */
+
+#endif /* _ASM_S390_VGA_H */

arch/s390/kernel/Makefile

@@ -23,7 +23,7 @@ CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \
 	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \
 	    debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \
-	    sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o
+	    sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)

arch/s390/kernel/entry.S

@@ -231,12 +231,12 @@ sysc_work:
 	jo	sysc_mcck_pending
 	tm	__TI_flags+3(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
+	tm	__TI_flags+3(%r12),_TIF_PER_TRAP
+	jo	sysc_singlestep
 	tm	__TI_flags+3(%r12),_TIF_SIGPENDING
 	jo	sysc_sigpending
 	tm	__TI_flags+3(%r12),_TIF_NOTIFY_RESUME
 	jo	sysc_notify_resume
-	tm	__TI_flags+3(%r12),_TIF_PER_TRAP
-	jo	sysc_singlestep
 	j	sysc_return		# beware of critical section cleanup
 
 #
@@ -259,7 +259,6 @@ sysc_mcck_pending:
 # _TIF_SIGPENDING is set, call do_signal
 #
 sysc_sigpending:
-	ni	__TI_flags+3(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP
 	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r1,BASED(.Ldo_signal)
 	basr	%r14,%r1		# call do_signal
@@ -286,7 +285,7 @@ sysc_notify_resume:
 # _TIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
-	ni	__TI_flags+3(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP)
+	ni	__TI_flags+3(%r12),255-_TIF_PER_TRAP
 	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r1,BASED(.Ldo_per_trap)
 	la	%r14,BASED(sysc_return)

arch/s390/kernel/entry.h

@@ -6,7 +6,6 @@
 #include <asm/ptrace.h>
 #include <asm/cputime.h>
 
-extern void (*pgm_check_table[128])(struct pt_regs *);
 extern void *restart_stack;
 
 void system_call(void);
@@ -25,6 +24,26 @@ void do_protection_exception(struct pt_regs *regs);
 void do_dat_exception(struct pt_regs *regs);
 void do_asce_exception(struct pt_regs *regs);
 
+void addressing_exception(struct pt_regs *regs);
+void data_exception(struct pt_regs *regs);
+void default_trap_handler(struct pt_regs *regs);
+void divide_exception(struct pt_regs *regs);
+void execute_exception(struct pt_regs *regs);
+void hfp_divide_exception(struct pt_regs *regs);
+void hfp_overflow_exception(struct pt_regs *regs);
+void hfp_significance_exception(struct pt_regs *regs);
+void hfp_sqrt_exception(struct pt_regs *regs);
+void hfp_underflow_exception(struct pt_regs *regs);
+void illegal_op(struct pt_regs *regs);
+void operand_exception(struct pt_regs *regs);
+void overflow_exception(struct pt_regs *regs);
+void privileged_op(struct pt_regs *regs);
+void space_switch_exception(struct pt_regs *regs);
+void special_op_exception(struct pt_regs *regs);
+void specification_exception(struct pt_regs *regs);
+void transaction_exception(struct pt_regs *regs);
+void translation_exception(struct pt_regs *regs);
+
 void do_per_trap(struct pt_regs *regs);
 void syscall_trace(struct pt_regs *regs, int entryexit);
 void kernel_stack_overflow(struct pt_regs * regs);

arch/s390/kernel/entry64.S

@@ -80,14 +80,21 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 #endif
 	.endm
 
-	.macro	HANDLE_SIE_INTERCEPT scratch
+	.macro	HANDLE_SIE_INTERCEPT scratch,pgmcheck
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
 	tmhh	%r8,0x0001		# interrupting from user ?
 	jnz	.+42
 	lgr	\scratch,%r9
 	slg	\scratch,BASED(.Lsie_loop)
 	clg	\scratch,BASED(.Lsie_length)
+	.if	\pgmcheck
+	# Some program interrupts are suppressing (e.g. protection).
+	# We must also check the instruction after SIE in that case.
+	# do_protection_exception will rewind to rewind_pad
+	jh	.+22
+	.else
 	jhe	.+22
+	.endif
 	lg	%r9,BASED(.Lsie_loop)
 	SPP	BASED(.Lhost_id)	# set host id
 #endif
@@ -262,12 +269,12 @@ sysc_work:
 	jo	sysc_mcck_pending
 	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
+	tm	__TI_flags+7(%r12),_TIF_PER_TRAP
+	jo	sysc_singlestep
 	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
 	jo	sysc_sigpending
 	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
 	jo	sysc_notify_resume
-	tm	__TI_flags+7(%r12),_TIF_PER_TRAP
-	jo	sysc_singlestep
 	j	sysc_return		# beware of critical section cleanup
 
 #
@@ -288,7 +295,6 @@ sysc_mcck_pending:
 # _TIF_SIGPENDING is set, call do_signal
 #
 sysc_sigpending:
-	ni	__TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,do_signal
 	tm	__TI_flags+7(%r12),_TIF_SYSCALL
@@ -313,7 +319,7 @@ sysc_notify_resume:
 # _TIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
-	ni	__TI_flags+7(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP)
+	ni	__TI_flags+7(%r12),255-_TIF_PER_TRAP
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	larl	%r14,sysc_return
 	jg	do_per_trap
@@ -375,7 +381,7 @@ ENTRY(pgm_check_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_PGM_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14
+	HANDLE_SIE_INTERCEPT %r14,1
 	tmhh	%r8,0x0001		# test problem state bit
 	jnz	1f			# -> fault in user space
 	tmhh	%r8,0x4000		# PER bit set in old PSW ?
@@ -413,9 +419,9 @@ ENTRY(pgm_check_handler)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
 	nill	%r10,0x007f
-	sll	%r10,3
+	sll	%r10,2
 	je	sysc_return
-	lg	%r1,0(%r10,%r1)		# load address of handler routine
+	lgf	%r1,0(%r10,%r1)		# load address of handler routine
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	basr	%r14,%r1		# branch to interrupt-handler
 	j	sysc_return
@@ -451,7 +457,7 @@ ENTRY(io_int_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_IO_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14
+	HANDLE_SIE_INTERCEPT %r14,0
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
 	tmhh	%r8,0x0001		# interrupting from user?
 	jz	io_skip
@@ -597,7 +603,7 @@ ENTRY(ext_int_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_EXT_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14
+	HANDLE_SIE_INTERCEPT %r14,0
 	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
 	tmhh	%r8,0x0001		# interrupting from user ?
 	jz	ext_skip
@@ -645,7 +651,7 @@ ENTRY(mcck_int_handler)
 	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
-	HANDLE_SIE_INTERCEPT %r14
+	HANDLE_SIE_INTERCEPT %r14,0
 	tm	__LC_MCCK_CODE,0x80	# system damage?
 	jo	mcck_panic		# yes -> rest of mcck code invalid
 	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
@@ -944,6 +950,13 @@ ENTRY(sie64a)
 	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
 	xc	__SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0
 	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
+# some program checks are suppressing. C code (e.g. do_protection_exception)
+# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
+# instructions in the sie_loop should not cause program interrupts. So
+# lets use a nop (47 00 00 00) as a landing pad.
+# See also HANDLE_SIE_INTERCEPT
+rewind_pad:
+	nop	0
 sie_loop:
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
@@ -983,6 +996,7 @@ sie_fault:
 .Lhost_id:
 	.quad	0
 
+	EX_TABLE(rewind_pad,sie_fault)
 	EX_TABLE(sie_loop,sie_fault)
 #endif
 

arch/s390/kernel/head.S

@@ -393,30 +393,35 @@ ENTRY(startup_kdump)
 	xc	0x300(256),0x300
 	xc	0xe00(256),0xe00
 	stck	__LC_LAST_UPDATE_CLOCK
-	spt	5f-.LPG0(%r13)
-	mvc	__LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13)
+	spt	6f-.LPG0(%r13)
+	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
 	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 #ifndef CONFIG_MARCH_G5
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
 	.insn	s,0xb2b10000,__LC_STFL_FAC_LIST	# store facility list
 	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
 	jz	0f
-	la	%r0,0
+	la	%r0,1
 	.insn	s,0xb2b00000,__LC_STFL_FAC_LIST	# store facility list extended
-0:	l	%r0,__LC_STFL_FAC_LIST
-	n	%r0,2f+8-.LPG0(%r13)
-	cl	%r0,2f+8-.LPG0(%r13)
-	jne	1f
-	l	%r0,__LC_STFL_FAC_LIST+4
-	n	%r0,2f+12-.LPG0(%r13)
-	cl	%r0,2f+12-.LPG0(%r13)
-	je	3f
-1:	l	%r15,.Lstack-.LPG0(%r13)
+	# verify if all required facilities are supported by the machine
+0:	la	%r1,__LC_STFL_FAC_LIST
+	la	%r2,3f+8-.LPG0(%r13)
+	l	%r3,0(%r2)
+1:	l	%r0,0(%r1)
+	n	%r0,4(%r2)
+	cl	%r0,4(%r2)
+	jne	2f
+	la	%r1,4(%r1)
+	la	%r2,4(%r2)
+	ahi	%r3,-1
+	jnz	1b
+	j	4f
+2:	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-96
 	la	%r2,.Lals_string-.LPG0(%r13)
 	l	%r3,.Lsclp_print-.LPG0(%r13)
 	basr	%r14,%r3
-	lpsw	2f-.LPG0(%r13)		# machine type not good enough, crash
+	lpsw	3f-.LPG0(%r13)		# machine type not good enough, crash
 .Lals_string:
 	.asciz	"The Linux kernel requires more recent processor hardware"
 .Lsclp_print:
@@ -424,33 +429,42 @@ ENTRY(startup_kdump)
 .Lstack:
 	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
 	.align 16
-2:	.long	0x000a0000,0x8badcccc
+3:	.long	0x000a0000,0x8badcccc
+
+# List of facilities that are required. If not all facilities are present
+# the kernel will crash. Format is number of facility words with bits set,
+# followed by the facility words.
+
 #if defined(CONFIG_64BIT)
-#if defined(CONFIG_MARCH_Z196)
-	.long 0xc100efe3, 0xf46c0000
+#if defined(CONFIG_MARCH_ZEC12)
+	.long 3, 0xc100efe3, 0xf46ce000, 0x00400000
+#elif defined(CONFIG_MARCH_Z196)
+	.long 2, 0xc100efe3, 0xf46c0000
 #elif defined(CONFIG_MARCH_Z10)
-	.long 0xc100efe3, 0xf0680000
+	.long 2, 0xc100efe3, 0xf0680000
 #elif defined(CONFIG_MARCH_Z9_109)
-	.long 0xc100efc3, 0x00000000
+	.long 1, 0xc100efc3
 #elif defined(CONFIG_MARCH_Z990)
-	.long 0xc0002000, 0x00000000
+	.long 1, 0xc0002000
 #elif defined(CONFIG_MARCH_Z900)
-	.long 0xc0000000, 0x00000000
+	.long 1, 0xc0000000
 #endif
 #else
-#if defined(CONFIG_MARCH_Z196)
-	.long 0x8100c880, 0x00000000
+#if defined(CONFIG_MARCH_ZEC12)
+	.long 1, 0x8100c880
+#elif defined(CONFIG_MARCH_Z196)
+	.long 1, 0x8100c880
 #elif defined(CONFIG_MARCH_Z10)
-	.long 0x8100c880, 0x00000000
+	.long 1, 0x8100c880
 #elif defined(CONFIG_MARCH_Z9_109)
-	.long 0x8100c880, 0x00000000
+	.long 1, 0x8100c880
 #elif defined(CONFIG_MARCH_Z990)
-	.long 0x80002000, 0x00000000
+	.long 1, 0x80002000
 #elif defined(CONFIG_MARCH_Z900)
-	.long 0x80000000, 0x00000000
+	.long 1, 0x80000000
 #endif
 #endif
-3:
+4:
 #endif
 
 #ifdef CONFIG_64BIT
@@ -459,14 +473,14 @@ ENTRY(startup_kdump)
 	jg	startup_continue
 #else
 	/* Continue with 31bit startup code in head31.S */
-	l	%r13,4f-.LPG0(%r13)
+	l	%r13,5f-.LPG0(%r13)
 	b	0(%r13)
 	.align	8
-4:	.long	startup_continue
+5:	.long	startup_continue
 #endif
 
 	.align	8
-5:	.long	0x7fffffff,0xffffffff
+6:	.long	0x7fffffff,0xffffffff
 
 #include "head_kdump.S"
 

arch/s390/kernel/irq.c

@@ -58,6 +58,8 @@ static const struct irq_class intrclass_names[] = {
 	[IOINT_APB]  = {.name = "APB", .desc = "[I/O] AP Bus"},
 	[IOINT_ADM]  = {.name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	[IOINT_CSC]  = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"},
+	[IOINT_PCI]  = {.name = "PCI", .desc = "[I/O] PCI Interrupt" },
+	[IOINT_MSI] =  {.name = "MSI", .desc = "[I/O] MSI Interrupt" },
 	[NMI_NMI]    = {.name = "NMI", .desc = "[NMI] Machine Check"},
 };
 

arch/s390/kernel/pgm_check.S

@@ -0,0 +1,152 @@
+/*
+ *    Program check table.
+ *
+ *    Copyright IBM Corp. 2012
+ */
+
+#include <linux/linkage.h>
+
+#ifdef CONFIG_32BIT
+#define PGM_CHECK_64BIT(handler) .long default_trap_handler
+#else
+#define PGM_CHECK_64BIT(handler) .long handler
+#endif
+
+#define PGM_CHECK(handler)	.long handler
+#define PGM_CHECK_DEFAULT	PGM_CHECK(default_trap_handler)
+
+/*
+ * The program check table contains exactly 128 (0x00-0x7f) entries. Each
+ * line defines the 31 and/or 64 bit function to be called corresponding
+ * to the program check interruption code.
+ */
+.section .rodata, "a"
+ENTRY(pgm_check_table)
+PGM_CHECK_DEFAULT			/* 00 */
+PGM_CHECK(illegal_op)			/* 01 */
+PGM_CHECK(privileged_op)		/* 02 */
+PGM_CHECK(execute_exception)		/* 03 */
+PGM_CHECK(do_protection_exception)	/* 04 */
+PGM_CHECK(addressing_exception)		/* 05 */
+PGM_CHECK(specification_exception)	/* 06 */
+PGM_CHECK(data_exception)		/* 07 */
+PGM_CHECK(overflow_exception)		/* 08 */
+PGM_CHECK(divide_exception)		/* 09 */
+PGM_CHECK(overflow_exception)		/* 0a */
+PGM_CHECK(divide_exception)		/* 0b */
+PGM_CHECK(hfp_overflow_exception)	/* 0c */
+PGM_CHECK(hfp_underflow_exception)	/* 0d */
+PGM_CHECK(hfp_significance_exception)	/* 0e */
+PGM_CHECK(hfp_divide_exception)		/* 0f */
+PGM_CHECK(do_dat_exception)		/* 10 */
+PGM_CHECK(do_dat_exception)		/* 11 */
+PGM_CHECK(translation_exception)	/* 12 */
+PGM_CHECK(special_op_exception)		/* 13 */
+PGM_CHECK_DEFAULT			/* 14 */
+PGM_CHECK(operand_exception)		/* 15 */
+PGM_CHECK_DEFAULT			/* 16 */
+PGM_CHECK_DEFAULT			/* 17 */
+PGM_CHECK_64BIT(transaction_exception)	/* 18 */
+PGM_CHECK_DEFAULT			/* 19 */
+PGM_CHECK_DEFAULT			/* 1a */
+PGM_CHECK_DEFAULT			/* 1b */
+PGM_CHECK(space_switch_exception)	/* 1c */
+PGM_CHECK(hfp_sqrt_exception)		/* 1d */
+PGM_CHECK_DEFAULT			/* 1e */
+PGM_CHECK_DEFAULT			/* 1f */
+PGM_CHECK_DEFAULT			/* 20 */
+PGM_CHECK_DEFAULT			/* 21 */
+PGM_CHECK_DEFAULT			/* 22 */
+PGM_CHECK_DEFAULT			/* 23 */
+PGM_CHECK_DEFAULT			/* 24 */
+PGM_CHECK_DEFAULT			/* 25 */
+PGM_CHECK_DEFAULT			/* 26 */
+PGM_CHECK_DEFAULT			/* 27 */
+PGM_CHECK_DEFAULT			/* 28 */
+PGM_CHECK_DEFAULT			/* 29 */
+PGM_CHECK_DEFAULT			/* 2a */
+PGM_CHECK_DEFAULT			/* 2b */
+PGM_CHECK_DEFAULT			/* 2c */
+PGM_CHECK_DEFAULT			/* 2d */
+PGM_CHECK_DEFAULT			/* 2e */
+PGM_CHECK_DEFAULT			/* 2f */
+PGM_CHECK_DEFAULT			/* 30 */
+PGM_CHECK_DEFAULT			/* 31 */
+PGM_CHECK_DEFAULT			/* 32 */
+PGM_CHECK_DEFAULT			/* 33 */
+PGM_CHECK_DEFAULT			/* 34 */
+PGM_CHECK_DEFAULT			/* 35 */
+PGM_CHECK_DEFAULT			/* 36 */
+PGM_CHECK_DEFAULT			/* 37 */
+PGM_CHECK_64BIT(do_asce_exception)	/* 38 */
+PGM_CHECK_64BIT(do_dat_exception)	/* 39 */
+PGM_CHECK_64BIT(do_dat_exception)	/* 3a */
+PGM_CHECK_64BIT(do_dat_exception)	/* 3b */
+PGM_CHECK_DEFAULT			/* 3c */
+PGM_CHECK_DEFAULT			/* 3d */
+PGM_CHECK_DEFAULT			/* 3e */
+PGM_CHECK_DEFAULT			/* 3f */
+PGM_CHECK_DEFAULT			/* 40 */
+PGM_CHECK_DEFAULT			/* 41 */
+PGM_CHECK_DEFAULT			/* 42 */
+PGM_CHECK_DEFAULT			/* 43 */
+PGM_CHECK_DEFAULT			/* 44 */
+PGM_CHECK_DEFAULT			/* 45 */
+PGM_CHECK_DEFAULT			/* 46 */
+PGM_CHECK_DEFAULT			/* 47 */
+PGM_CHECK_DEFAULT			/* 48 */
+PGM_CHECK_DEFAULT			/* 49 */
+PGM_CHECK_DEFAULT			/* 4a */
+PGM_CHECK_DEFAULT			/* 4b */
+PGM_CHECK_DEFAULT			/* 4c */
+PGM_CHECK_DEFAULT			/* 4d */
+PGM_CHECK_DEFAULT			/* 4e */
+PGM_CHECK_DEFAULT			/* 4f */
+PGM_CHECK_DEFAULT			/* 50 */
+PGM_CHECK_DEFAULT			/* 51 */
+PGM_CHECK_DEFAULT			/* 52 */
+PGM_CHECK_DEFAULT			/* 53 */
+PGM_CHECK_DEFAULT			/* 54 */
+PGM_CHECK_DEFAULT			/* 55 */
+PGM_CHECK_DEFAULT			/* 56 */
+PGM_CHECK_DEFAULT			/* 57 */
+PGM_CHECK_DEFAULT			/* 58 */
+PGM_CHECK_DEFAULT			/* 59 */
+PGM_CHECK_DEFAULT			/* 5a */
+PGM_CHECK_DEFAULT			/* 5b */
+PGM_CHECK_DEFAULT			/* 5c */
+PGM_CHECK_DEFAULT			/* 5d */
+PGM_CHECK_DEFAULT			/* 5e */
+PGM_CHECK_DEFAULT			/* 5f */
+PGM_CHECK_DEFAULT			/* 60 */
+PGM_CHECK_DEFAULT			/* 61 */
+PGM_CHECK_DEFAULT			/* 62 */
+PGM_CHECK_DEFAULT			/* 63 */
+PGM_CHECK_DEFAULT			/* 64 */
+PGM_CHECK_DEFAULT			/* 65 */
+PGM_CHECK_DEFAULT			/* 66 */
+PGM_CHECK_DEFAULT			/* 67 */
+PGM_CHECK_DEFAULT			/* 68 */
+PGM_CHECK_DEFAULT			/* 69 */
+PGM_CHECK_DEFAULT			/* 6a */
+PGM_CHECK_DEFAULT			/* 6b */
+PGM_CHECK_DEFAULT			/* 6c */
+PGM_CHECK_DEFAULT			/* 6d */
+PGM_CHECK_DEFAULT			/* 6e */
+PGM_CHECK_DEFAULT			/* 6f */
+PGM_CHECK_DEFAULT			/* 70 */
+PGM_CHECK_DEFAULT			/* 71 */
+PGM_CHECK_DEFAULT			/* 72 */
+PGM_CHECK_DEFAULT			/* 73 */
+PGM_CHECK_DEFAULT			/* 74 */
+PGM_CHECK_DEFAULT			/* 75 */
+PGM_CHECK_DEFAULT			/* 76 */
+PGM_CHECK_DEFAULT			/* 77 */
+PGM_CHECK_DEFAULT			/* 78 */
+PGM_CHECK_DEFAULT			/* 79 */
+PGM_CHECK_DEFAULT			/* 7a */
+PGM_CHECK_DEFAULT			/* 7b */
+PGM_CHECK_DEFAULT			/* 7c */
+PGM_CHECK_DEFAULT			/* 7d */
+PGM_CHECK_DEFAULT			/* 7e */
+PGM_CHECK_DEFAULT			/* 7f */

arch/s390/kernel/setup.c

@@ -777,40 +777,6 @@ static void __init reserve_crashkernel(void)
 #endif
 }
 
-static void __init init_storage_keys(unsigned long start, unsigned long end)
-{
-	unsigned long boundary, function, size;
-
-	while (start < end) {
-		if (MACHINE_HAS_EDAT2) {
-			/* set storage keys for a 2GB frame */
-			function = 0x22000 | PAGE_DEFAULT_KEY;
-			size = 1UL << 31;
-			boundary = (start + size) & ~(size - 1);
-			if (boundary <= end) {
-				do {
-					start = pfmf(function, start);
-				} while (start < boundary);
-				continue;
-			}
-		}
-		if (MACHINE_HAS_EDAT1) {
-			/* set storage keys for a 1MB frame */
-			function = 0x21000 | PAGE_DEFAULT_KEY;
-			size = 1UL << 20;
-			boundary = (start + size) & ~(size - 1);
-			if (boundary <= end) {
-				do {
-					start = pfmf(function, start);
-				} while (start < boundary);
-				continue;
-			}
-		}
-		page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
-		start += PAGE_SIZE;
-	}
-}
-
 static void __init setup_memory(void)
 {
         unsigned long bootmap_size;
@@ -889,7 +855,7 @@ static void __init setup_memory(void)
 		memblock_add_node(PFN_PHYS(start_chunk),
 				  PFN_PHYS(end_chunk - start_chunk), 0);
 		pfn = max(start_chunk, start_pfn);
-		init_storage_keys(PFN_PHYS(pfn), PFN_PHYS(end_chunk));
+		storage_key_init_range(PFN_PHYS(pfn), PFN_PHYS(end_chunk));
 	}
 
 	psw_set_key(PAGE_DEFAULT_KEY);
@@ -1040,6 +1006,9 @@ static void __init setup_hwcaps(void)
 	case 0x2818:
 		strcpy(elf_platform, "z196");
 		break;
+	case 0x2827:
+		strcpy(elf_platform, "zEC12");
+		break;
 	}
 }
 

arch/s390/kernel/signal.c

@@ -461,6 +461,8 @@ void do_signal(struct pt_regs *regs)
 			/* Restart system call with magic TIF bit. */
 			regs->gprs[2] = regs->orig_gpr2;
 			set_thread_flag(TIF_SYSCALL);
+			if (test_thread_flag(TIF_SINGLE_STEP))
+				set_thread_flag(TIF_PER_TRAP);
 			break;
 		}
 	}

arch/s390/kernel/topology.c

@@ -29,48 +29,38 @@ struct mask_info {
 	cpumask_t mask;
 };
 
-static int topology_enabled = 1;
+static void set_topology_timer(void);
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
-static void set_topology_timer(void);
-static DECLARE_WORK(topology_work, topology_work_fn);
-/* topology_lock protects the core linked list */
-static DEFINE_SPINLOCK(topology_lock);
 
-static struct mask_info core_info;
-cpumask_t cpu_core_map[NR_CPUS];
-unsigned char cpu_core_id[NR_CPUS];
-unsigned char cpu_socket_id[NR_CPUS];
+static int topology_enabled = 1;
+static DECLARE_WORK(topology_work, topology_work_fn);
 
+/* topology_lock protects the socket and book linked lists */
+static DEFINE_SPINLOCK(topology_lock);
+static struct mask_info socket_info;
 static struct mask_info book_info;
-cpumask_t cpu_book_map[NR_CPUS];
-unsigned char cpu_book_id[NR_CPUS];
+
+struct cpu_topology_s390 cpu_topology[NR_CPUS];
 
 static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
 	cpumask_t mask;
 
-	cpumask_clear(&mask);
-	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY) {
-		cpumask_copy(&mask, cpumask_of(cpu));
+	cpumask_copy(&mask, cpumask_of(cpu));
+	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
 		return mask;
+	for (; info; info = info->next) {
+		if (cpumask_test_cpu(cpu, &info->mask))
+			return info->mask;
 	}
-	while (info) {
-		if (cpumask_test_cpu(cpu, &info->mask)) {
-			mask = info->mask;
-			break;
-		}
-		info = info->next;
-	}
-	if (cpumask_empty(&mask))
-		cpumask_copy(&mask, cpumask_of(cpu));
 	return mask;
 }
 
 static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
 					  struct mask_info *book,
-					  struct mask_info *core,
-					  int one_core_per_cpu)
+					  struct mask_info *socket,
+					  int one_socket_per_cpu)
 {
 	unsigned int cpu;
 
@@ -80,28 +70,28 @@ static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
 
 		rcpu = TOPOLOGY_CPU_BITS - 1 - cpu + tl_cpu->origin;
 		lcpu = smp_find_processor_id(rcpu);
-		if (lcpu >= 0) {
-			cpumask_set_cpu(lcpu, &book->mask);
-			cpu_book_id[lcpu] = book->id;
-			cpumask_set_cpu(lcpu, &core->mask);
-			cpu_core_id[lcpu] = rcpu;
-			if (one_core_per_cpu) {
-				cpu_socket_id[lcpu] = rcpu;
-				core = core->next;
-			} else {
-				cpu_socket_id[lcpu] = core->id;
-			}
-			smp_cpu_set_polarization(lcpu, tl_cpu->pp);
+		if (lcpu < 0)
+			continue;
+		cpumask_set_cpu(lcpu, &book->mask);
+		cpu_topology[lcpu].book_id = book->id;
+		cpumask_set_cpu(lcpu, &socket->mask);
+		cpu_topology[lcpu].core_id = rcpu;
+		if (one_socket_per_cpu) {
+			cpu_topology[lcpu].socket_id = rcpu;
+			socket = socket->next;
+		} else {
+			cpu_topology[lcpu].socket_id = socket->id;
 		}
+		smp_cpu_set_polarization(lcpu, tl_cpu->pp);
 	}
-	return core;
+	return socket;
 }
 
 static void clear_masks(void)
 {
 	struct mask_info *info;
 
-	info = &core_info;
+	info = &socket_info;
 	while (info) {
 		cpumask_clear(&info->mask);
 		info = info->next;
@@ -120,9 +110,9 @@ static union topology_entry *next_tle(union topology_entry *tle)
 	return (union topology_entry *)((struct topology_container *)tle + 1);
 }
 
-static void __tl_to_cores_generic(struct sysinfo_15_1_x *info)
+static void __tl_to_masks_generic(struct sysinfo_15_1_x *info)
 {
-	struct mask_info *core = &core_info;
+	struct mask_info *socket = &socket_info;
 	struct mask_info *book = &book_info;
 	union topology_entry *tle, *end;
 
@@ -135,11 +125,11 @@ static void __tl_to_cores_generic(struct sysinfo_15_1_x *info)
 			book->id = tle->container.id;
 			break;
 		case 1:
-			core = core->next;
-			core->id = tle->container.id;
+			socket = socket->next;
+			socket->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_mask(&tle->cpu, book, core, 0);
+			add_cpus_to_mask(&tle->cpu, book, socket, 0);
 			break;
 		default:
 			clear_masks();
@@ -149,9 +139,9 @@ static void __tl_to_cores_generic(struct sysinfo_15_1_x *info)
 	}
 }
 
-static void __tl_to_cores_z10(struct sysinfo_15_1_x *info)
+static void __tl_to_masks_z10(struct sysinfo_15_1_x *info)
 {
-	struct mask_info *core = &core_info;
+	struct mask_info *socket = &socket_info;
 	struct mask_info *book = &book_info;
 	union topology_entry *tle, *end;
 
@@ -164,7 +154,7 @@ static void __tl_to_cores_z10(struct sysinfo_15_1_x *info)
 			book->id = tle->container.id;
 			break;
 		case 0:
-			core = add_cpus_to_mask(&tle->cpu, book, core, 1);
+			socket = add_cpus_to_mask(&tle->cpu, book, socket, 1);
 			break;
 		default:
 			clear_masks();
@@ -174,20 +164,20 @@ static void __tl_to_cores_z10(struct sysinfo_15_1_x *info)
 	}
 }
 
-static void tl_to_cores(struct sysinfo_15_1_x *info)
+static void tl_to_masks(struct sysinfo_15_1_x *info)
 {
 	struct cpuid cpu_id;
 
-	get_cpu_id(&cpu_id);
 	spin_lock_irq(&topology_lock);
+	get_cpu_id(&cpu_id);
 	clear_masks();
 	switch (cpu_id.machine) {
 	case 0x2097:
 	case 0x2098:
-		__tl_to_cores_z10(info);
+		__tl_to_masks_z10(info);
 		break;
 	default:
-		__tl_to_cores_generic(info);
+		__tl_to_masks_generic(info);
 	}
 	spin_unlock_irq(&topology_lock);
 }
@@ -232,15 +222,20 @@ int topology_set_cpu_management(int fc)
 	return rc;
 }
 
-static void update_cpu_core_map(void)
+static void update_cpu_masks(void)
 {
 	unsigned long flags;
 	int cpu;
 
 	spin_lock_irqsave(&topology_lock, flags);
 	for_each_possible_cpu(cpu) {
-		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
-		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+		cpu_topology[cpu].core_mask = cpu_group_map(&socket_info, cpu);
+		cpu_topology[cpu].book_mask = cpu_group_map(&book_info, cpu);
+		if (!MACHINE_HAS_TOPOLOGY) {
+			cpu_topology[cpu].core_id = cpu;
+			cpu_topology[cpu].socket_id = cpu;
+			cpu_topology[cpu].book_id = cpu;
+		}
 	}
 	spin_unlock_irqrestore(&topology_lock, flags);
 }
@@ -260,13 +255,13 @@ int arch_update_cpu_topology(void)
 	int cpu;
 
 	if (!MACHINE_HAS_TOPOLOGY) {
-		update_cpu_core_map();
+		update_cpu_masks();
 		topology_update_polarization_simple();
 		return 0;
 	}
 	store_topology(info);
-	tl_to_cores(info);
-	update_cpu_core_map();
+	tl_to_masks(info);
+	update_cpu_masks();
 	for_each_online_cpu(cpu) {
 		dev = get_cpu_device(cpu);
 		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
@@ -355,7 +350,7 @@ void __init s390_init_cpu_topology(void)
 	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
 		printk(KERN_CONT " %d", info->mag[i]);
 	printk(KERN_CONT " / %d\n", info->mnest);
-	alloc_masks(info, &core_info, 1);
+	alloc_masks(info, &socket_info, 1);
 	alloc_masks(info, &book_info, 2);
 }
 
@@ -454,7 +449,7 @@ static int __init topology_init(void)
 	}
 	set_topology_timer();
 out:
-	update_cpu_core_map();
+	update_cpu_masks();
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);

arch/s390/kernel/traps.c

@@ -41,8 +41,6 @@
 #include <asm/ipl.h>
 #include "entry.h"
 
-void (*pgm_check_table[128])(struct pt_regs *regs);
-
 int show_unhandled_signals = 1;
 
 #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
@@ -350,7 +348,7 @@ void __kprobes do_per_trap(struct pt_regs *regs)
 	force_sig_info(SIGTRAP, &info, current);
 }
 
-static void default_trap_handler(struct pt_regs *regs)
+void default_trap_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		report_user_fault(regs, SIGSEGV);
@@ -360,9 +358,9 @@ static void default_trap_handler(struct pt_regs *regs)
 }
 
 #define DO_ERROR_INFO(name, signr, sicode, str) \
-static void name(struct pt_regs *regs) \
-{ \
-	do_trap(regs, signr, sicode, str); \
+void name(struct pt_regs *regs)			\
+{						\
+	do_trap(regs, signr, sicode, str);	\
 }
 
 DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR,
@@ -417,7 +415,7 @@ static inline void do_fp_trap(struct pt_regs *regs, int fpc)
 	do_trap(regs, SIGFPE, si_code, "floating point exception");
 }
 
-static void __kprobes illegal_op(struct pt_regs *regs)
+void __kprobes illegal_op(struct pt_regs *regs)
 {
 	siginfo_t info;
         __u8 opcode[6];
@@ -536,7 +534,7 @@ DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
 	      "specification exception");
 #endif
 
-static void data_exception(struct pt_regs *regs)
+void data_exception(struct pt_regs *regs)
 {
 	__u16 __user *location;
 	int signal = 0;
@@ -611,7 +609,7 @@ static void data_exception(struct pt_regs *regs)
 		do_trap(regs, signal, ILL_ILLOPN, "data exception");
 }
 
-static void space_switch_exception(struct pt_regs *regs)
+void space_switch_exception(struct pt_regs *regs)
 {
 	/* Set user psw back to home space mode. */
 	if (user_mode(regs))
@@ -629,43 +627,7 @@ void __kprobes kernel_stack_overflow(struct pt_regs * regs)
 	panic("Corrupt kernel stack, can't continue.");
 }
 
-/* init is done in lowcore.S and head.S */
-
 void __init trap_init(void)
 {
-        int i;
-
-        for (i = 0; i < 128; i++)
-          pgm_check_table[i] = &default_trap_handler;
-        pgm_check_table[1] = &illegal_op;
-        pgm_check_table[2] = &privileged_op;
-        pgm_check_table[3] = &execute_exception;
-        pgm_check_table[4] = &do_protection_exception;
-        pgm_check_table[5] = &addressing_exception;
-        pgm_check_table[6] = &specification_exception;
-        pgm_check_table[7] = &data_exception;
-        pgm_check_table[8] = &overflow_exception;
-        pgm_check_table[9] = &divide_exception;
-        pgm_check_table[0x0A] = &overflow_exception;
-        pgm_check_table[0x0B] = &divide_exception;
-        pgm_check_table[0x0C] = &hfp_overflow_exception;
-        pgm_check_table[0x0D] = &hfp_underflow_exception;
-        pgm_check_table[0x0E] = &hfp_significance_exception;
-        pgm_check_table[0x0F] = &hfp_divide_exception;
-        pgm_check_table[0x10] = &do_dat_exception;
-        pgm_check_table[0x11] = &do_dat_exception;
-        pgm_check_table[0x12] = &translation_exception;
-        pgm_check_table[0x13] = &special_op_exception;
-#ifdef CONFIG_64BIT
-	pgm_check_table[0x18] = &transaction_exception;
-	pgm_check_table[0x38] = &do_asce_exception;
-	pgm_check_table[0x39] = &do_dat_exception;
-	pgm_check_table[0x3A] = &do_dat_exception;
-        pgm_check_table[0x3B] = &do_dat_exception;
-#endif /* CONFIG_64BIT */
-        pgm_check_table[0x15] = &operand_exception;
-        pgm_check_table[0x1C] = &space_switch_exception;
-        pgm_check_table[0x1D] = &hfp_sqrt_exception;
-	/* Enable machine checks early. */
 	local_mcck_enable();
 }

arch/s390/mm/Makefile

@@ -2,9 +2,9 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-obj-y	 := init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o \
-	    page-states.o gup.o extable.o
-obj-$(CONFIG_CMM) += cmm.o
-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-obj-$(CONFIG_DEBUG_SET_MODULE_RONX) += pageattr.o
-obj-$(CONFIG_S390_PTDUMP) += dump_pagetables.o
+obj-y		:= init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o
+obj-y		+= page-states.o gup.o extable.o pageattr.o
+
+obj-$(CONFIG_CMM)		+= cmm.o
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_S390_PTDUMP)	+= dump_pagetables.o

arch/s390/mm/dump_pagetables.c

@@ -150,6 +150,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st,
 static void walk_pud_level(struct seq_file *m, struct pg_state *st,
 			   pgd_t *pgd, unsigned long addr)
 {
+	unsigned int prot;
 	pud_t *pud;
 	int i;
 
@@ -157,7 +158,11 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st,
 		st->current_address = addr;
 		pud = pud_offset(pgd, addr);
 		if (!pud_none(*pud))
-			walk_pmd_level(m, st, pud, addr);
+			if (pud_large(*pud)) {
+				prot = pud_val(*pud) & _PAGE_RO;
+				note_page(m, st, prot, 2);
+			} else
+				walk_pmd_level(m, st, pud, addr);
 		else
 			note_page(m, st, _PAGE_INVALID, 2);
 		addr += PUD_SIZE;

arch/s390/mm/fault.c

@@ -49,15 +49,19 @@
 #define VM_FAULT_BADCONTEXT	0x010000
 #define VM_FAULT_BADMAP		0x020000
 #define VM_FAULT_BADACCESS	0x040000
-#define VM_FAULT_SIGNAL	0x080000
+#define VM_FAULT_SIGNAL		0x080000
 
-static unsigned long store_indication;
+static unsigned long store_indication __read_mostly;
 
-void fault_init(void)
+#ifdef CONFIG_64BIT
+static int __init fault_init(void)
 {
-	if (test_facility(2) && test_facility(75))
+	if (test_facility(75))
 		store_indication = 0xc00;
+	return 0;
 }
+early_initcall(fault_init);
+#endif
 
 static inline int notify_page_fault(struct pt_regs *regs)
 {
@@ -273,10 +277,16 @@ static inline int do_exception(struct pt_regs *regs, int access)
 	unsigned int flags;
 	int fault;
 
+	tsk = current;
+	/*
+	 * The instruction that caused the program check has
+	 * been nullified. Don't signal single step via SIGTRAP.
+	 */
+	clear_tsk_thread_flag(tsk, TIF_PER_TRAP);
+
 	if (notify_page_fault(regs))
 		return 0;
 
-	tsk = current;
 	mm = tsk->mm;
 	trans_exc_code = regs->int_parm_long;
 
@@ -372,11 +382,6 @@ retry:
 			goto retry;
 		}
 	}
-	/*
-	 * The instruction that caused the program check will
-	 * be repeated. Don't signal single step via SIGTRAP.
-	 */
-	clear_tsk_thread_flag(tsk, TIF_PER_TRAP);
 	fault = 0;
 out_up:
 	up_read(&mm->mmap_sem);
@@ -423,6 +428,12 @@ void __kprobes do_asce_exception(struct pt_regs *regs)
 	struct vm_area_struct *vma;
 	unsigned long trans_exc_code;
 
+	/*
+	 * The instruction that caused the program check has
+	 * been nullified. Don't signal single step via SIGTRAP.
+	 */
+	clear_tsk_thread_flag(current, TIF_PER_TRAP);
+
 	trans_exc_code = regs->int_parm_long;
 	if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
 		goto no_context;

arch/s390/mm/init.c

@@ -125,7 +125,6 @@ void __init paging_init(void)
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 	free_area_init_nodes(max_zone_pfns);
-	fault_init();
 }
 
 void __init mem_init(void)
@@ -159,34 +158,6 @@ void __init mem_init(void)
 	       PFN_ALIGN((unsigned long)&_eshared) - 1);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-void kernel_map_pages(struct page *page, int numpages, int enable)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	unsigned long address;
-	int i;
-
-	for (i = 0; i < numpages; i++) {
-		address = page_to_phys(page + i);
-		pgd = pgd_offset_k(address);
-		pud = pud_offset(pgd, address);
-		pmd = pmd_offset(pud, address);
-		pte = pte_offset_kernel(pmd, address);
-		if (!enable) {
-			__ptep_ipte(address, pte);
-			pte_val(*pte) = _PAGE_TYPE_EMPTY;
-			continue;
-		}
-		*pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW));
-		/* Flush cpu write queue. */
-		mb();
-	}
-}
-#endif
-
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr = begin;

arch/s390/mm/pageattr.c

@@ -2,11 +2,46 @@
  * Copyright IBM Corp. 2011
  * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
  */
+#include <linux/hugetlb.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/hugetlb.h>
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
+#include <asm/page.h>
+
+void storage_key_init_range(unsigned long start, unsigned long end)
+{
+	unsigned long boundary, function, size;
+
+	while (start < end) {
+		if (MACHINE_HAS_EDAT2) {
+			/* set storage keys for a 2GB frame */
+			function = 0x22000 | PAGE_DEFAULT_KEY;
+			size = 1UL << 31;
+			boundary = (start + size) & ~(size - 1);
+			if (boundary <= end) {
+				do {
+					start = pfmf(function, start);
+				} while (start < boundary);
+				continue;
+			}
+		}
+		if (MACHINE_HAS_EDAT1) {
+			/* set storage keys for a 1MB frame */
+			function = 0x21000 | PAGE_DEFAULT_KEY;
+			size = 1UL << 20;
+			boundary = (start + size) & ~(size - 1);
+			if (boundary <= end) {
+				do {
+					start = pfmf(function, start);
+				} while (start < boundary);
+				continue;
+			}
+		}
+		page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
+		start += PAGE_SIZE;
+	}
+}
 
 static pte_t *walk_page_table(unsigned long addr)
 {
@@ -19,7 +54,7 @@ static pte_t *walk_page_table(unsigned long addr)
 	if (pgd_none(*pgdp))
 		return NULL;
 	pudp = pud_offset(pgdp, addr);
-	if (pud_none(*pudp))
+	if (pud_none(*pudp) || pud_large(*pudp))
 		return NULL;
 	pmdp = pmd_offset(pudp, addr);
 	if (pmd_none(*pmdp) || pmd_large(*pmdp))
@@ -70,3 +105,46 @@ int set_memory_x(unsigned long addr, int numpages)
 {
 	return 0;
 }
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+void kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	unsigned long address;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	int i;
+
+	for (i = 0; i < numpages; i++) {
+		address = page_to_phys(page + i);
+		pgd = pgd_offset_k(address);
+		pud = pud_offset(pgd, address);
+		pmd = pmd_offset(pud, address);
+		pte = pte_offset_kernel(pmd, address);
+		if (!enable) {
+			__ptep_ipte(address, pte);
+			pte_val(*pte) = _PAGE_TYPE_EMPTY;
+			continue;
+		}
+		*pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW));
+	}
+}
+
+#ifdef CONFIG_HIBERNATION
+bool kernel_page_present(struct page *page)
+{
+	unsigned long addr;
+	int cc;
+
+	addr = page_to_phys(page);
+	asm volatile(
+		"	lra	%1,0(%1)\n"
+		"	ipm	%0\n"
+		"	srl	%0,28"
+		: "=d" (cc), "+a" (addr) : : "cc");
+	return cc == 0;
+}
+#endif /* CONFIG_HIBERNATION */
+
+#endif /* CONFIG_DEBUG_PAGEALLOC */

arch/s390/mm/pgtable.c

@@ -881,22 +881,6 @@ int s390_enable_sie(void)
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) && defined(CONFIG_HIBERNATION)
-bool kernel_page_present(struct page *page)
-{
-	unsigned long addr;
-	int cc;
-
-	addr = page_to_phys(page);
-	asm volatile(
-		"	lra	%1,0(%1)\n"
-		"	ipm	%0\n"
-		"	srl	%0,28"
-		: "=d" (cc), "+a" (addr) : : "cc");
-	return cc == 0;
-}
-#endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmdp)

arch/s390/mm/vmem.c

@@ -89,6 +89,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 	int ret = -ENOMEM;
 
 	while (address < end) {
+		pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0));
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
 			pu_dir = vmem_pud_alloc();
@@ -96,18 +97,24 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 				goto out;
 			pgd_populate(&init_mm, pg_dir, pu_dir);
 		}
-
 		pu_dir = pud_offset(pg_dir, address);
+#if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC)
+		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
+		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) {
+			pte_val(pte) |= _REGION3_ENTRY_LARGE;
+			pte_val(pte) |= _REGION_ENTRY_TYPE_R3;
+			pud_val(*pu_dir) = pte_val(pte);
+			address += PUD_SIZE;
+			continue;
+		}
+#endif
 		if (pud_none(*pu_dir)) {
 			pm_dir = vmem_pmd_alloc();
 			if (!pm_dir)
 				goto out;
 			pud_populate(&init_mm, pu_dir, pm_dir);
 		}
-
-		pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0));
 		pm_dir = pmd_offset(pu_dir, address);
-
 #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC)
 		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
 		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) {
@@ -160,6 +167,11 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
 			address += PUD_SIZE;
 			continue;
 		}
+		if (pud_large(*pu_dir)) {
+			pud_clear(pu_dir);
+			address += PUD_SIZE;
+			continue;
+		}
 		pm_dir = pmd_offset(pu_dir, address);
 		if (pmd_none(*pm_dir)) {
 			address += PMD_SIZE;
@@ -193,7 +205,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 	start_addr = (unsigned long) start;
 	end_addr = (unsigned long) (start + nr);
 
-	for (address = start_addr; address < end_addr; address += PAGE_SIZE) {
+	for (address = start_addr; address < end_addr;) {
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
 			pu_dir = vmem_pud_alloc();
@@ -212,10 +224,33 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 
 		pm_dir = pmd_offset(pu_dir, address);
 		if (pmd_none(*pm_dir)) {
+#ifdef CONFIG_64BIT
+			/* Use 1MB frames for vmemmap if available. We always
+			 * use large frames even if they are only partially
+			 * used.
+			 * Otherwise we would have also page tables since
+			 * vmemmap_populate gets called for each section
+			 * separately. */
+			if (MACHINE_HAS_EDAT1) {
+				void *new_page;
+
+				new_page = vmemmap_alloc_block(PMD_SIZE, node);
+				if (!new_page)
+					goto out;
+				pte = mk_pte_phys(__pa(new_page), PAGE_RW);
+				pte_val(pte) |= _SEGMENT_ENTRY_LARGE;
+				pmd_val(*pm_dir) = pte_val(pte);
+				address = (address + PMD_SIZE) & PMD_MASK;
+				continue;
+			}
+#endif
 			pt_dir = vmem_pte_alloc(address);
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);
+		} else if (pmd_large(*pm_dir)) {
+			address = (address + PMD_SIZE) & PMD_MASK;
+			continue;
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
@@ -228,6 +263,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 			pte = pfn_pte(new_page >> PAGE_SHIFT, PAGE_KERNEL);
 			*pt_dir = pte;
 		}
+		address += PAGE_SIZE;
 	}
 	memset(start, 0, nr * sizeof(struct page));
 	ret = 0;

arch/s390/net/bpf_jit_comp.c

@@ -341,6 +341,27 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
+	case BPF_S_ALU_MOD_X: /* A %= X */
+		jit->seen |= SEEN_XREG | SEEN_RET0;
+		/* ltr %r12,%r12 */
+		EMIT2(0x12cc);
+		/* jz <ret0> */
+		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
+		/* lhi %r4,0 */
+		EMIT4(0xa7480000);
+		/* dr %r4,%r12 */
+		EMIT2(0x1d4c);
+		/* lr %r5,%r4 */
+		EMIT2(0x1854);
+		break;
+	case BPF_S_ALU_MOD_K: /* A %= K */
+		/* lhi %r4,0 */
+		EMIT4(0xa7480000);
+		/* d %r4,<d(K)>(%r13) */
+		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+		/* lr %r5,%r4 */
+		EMIT2(0x1854);
+		break;
 	case BPF_S_ALU_AND_X: /* A &= X */
 		jit->seen |= SEEN_XREG;
 		/* nr %r5,%r12 */
@@ -368,10 +389,17 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			EMIT4_DISP(0x5650d000, EMIT_CONST(K));
 		break;
 	case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
+	case BPF_S_ALU_XOR_X:
 		jit->seen |= SEEN_XREG;
 		/* xr %r5,%r12 */
 		EMIT2(0x175c);
 		break;
+	case BPF_S_ALU_XOR_K: /* A ^= K */
+		if (!K)
+			break;
+		/* x %r5,<d(K)>(%r13) */
+		EMIT4_DISP(0x5750d000, EMIT_CONST(K));
+		break;
 	case BPF_S_ALU_LSH_X: /* A <<= X; */
 		jit->seen |= SEEN_XREG;
 		/* sll %r5,0(%r12) */

arch/s390/pci/Makefile

@@ -0,0 +1,6 @@
+#
+# Makefile for the s390 PCI subsystem.
+#
+
+obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_msi.o \
+			   pci_sysfs.o pci_event.o

arch/s390/pci/pci.c

@@ -0,0 +1,1103 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ *
+ * The System z PCI code is a rewrite from a prototype by
+ * the following people (Kudoz!):
+ *   Alexander Schmidt
+ *   Christoph Raisch
+ *   Hannes Hering
+ *   Hoang-Nam Nguyen
+ *   Jan-Bernd Themann
+ *   Stefan Roscher
+ *   Thomas Klein
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/kernel_stat.h>
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+
+#include <asm/isc.h>
+#include <asm/airq.h>
+#include <asm/facility.h>
+#include <asm/pci_insn.h>
+#include <asm/pci_clp.h>
+#include <asm/pci_dma.h>
+
+#define DEBUG				/* enable pr_debug */
+
+#define	SIC_IRQ_MODE_ALL		0
+#define	SIC_IRQ_MODE_SINGLE		1
+
+#define ZPCI_NR_DMA_SPACES		1
+#define ZPCI_MSI_VEC_BITS		6
+#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
+
+/* list of all detected zpci devices */
+LIST_HEAD(zpci_list);
+EXPORT_SYMBOL_GPL(zpci_list);
+DEFINE_MUTEX(zpci_list_lock);
+EXPORT_SYMBOL_GPL(zpci_list_lock);
+
+struct pci_hp_callback_ops hotplug_ops;
+EXPORT_SYMBOL_GPL(hotplug_ops);
+
+static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
+static DEFINE_SPINLOCK(zpci_domain_lock);
+
+struct callback {
+	irq_handler_t	handler;
+	void		*data;
+};
+
+struct zdev_irq_map {
+	unsigned long	aibv;		/* AI bit vector */
+	int		msi_vecs;	/* consecutive MSI-vectors used */
+	int		__unused;
+	struct callback	cb[ZPCI_NR_MSI_VECS]; /* callback handler array */
+	spinlock_t	lock;		/* protect callbacks against de-reg */
+};
+
+struct intr_bucket {
+	/* amap of adapters, one bit per dev, corresponds to one irq nr */
+	unsigned long	*alloc;
+	/* AI summary bit, global page for all devices */
+	unsigned long	*aisb;
+	/* pointer to aibv and callback data in zdev */
+	struct zdev_irq_map *imap[ZPCI_NR_DEVICES];
+	/* protects the whole bucket struct */
+	spinlock_t	lock;
+};
+
+static struct intr_bucket *bucket;
+
+/* Adapter local summary indicator */
+static u8 *zpci_irq_si;
+
+static atomic_t irq_retries = ATOMIC_INIT(0);
+
+/* I/O Map */
+static DEFINE_SPINLOCK(zpci_iomap_lock);
+static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+struct zpci_iomap_entry *zpci_iomap_start;
+EXPORT_SYMBOL_GPL(zpci_iomap_start);
+
+/* highest irq summary bit */
+static int __read_mostly aisb_max;
+
+static struct kmem_cache *zdev_irq_cache;
+
+static inline int irq_to_msi_nr(unsigned int irq)
+{
+	return irq & ZPCI_MSI_MASK;
+}
+
+static inline int irq_to_dev_nr(unsigned int irq)
+{
+	return irq >> ZPCI_MSI_VEC_BITS;
+}
+
+static inline struct zdev_irq_map *get_imap(unsigned int irq)
+{
+	return bucket->imap[irq_to_dev_nr(irq)];
+}
+
+struct zpci_dev *get_zdev(struct pci_dev *pdev)
+{
+	return (struct zpci_dev *) pdev->sysdata;
+}
+
+struct zpci_dev *get_zdev_by_fid(u32 fid)
+{
+	struct zpci_dev *tmp, *zdev = NULL;
+
+	mutex_lock(&zpci_list_lock);
+	list_for_each_entry(tmp, &zpci_list, entry) {
+		if (tmp->fid == fid) {
+			zdev = tmp;
+			break;
+		}
+	}
+	mutex_unlock(&zpci_list_lock);
+	return zdev;
+}
+
+bool zpci_fid_present(u32 fid)
+{
+	return (get_zdev_by_fid(fid) != NULL) ? true : false;
+}
+
+static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus)
+{
+	return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL;
+}
+
+int pci_domain_nr(struct pci_bus *bus)
+{
+	return ((struct zpci_dev *) bus->sysdata)->domain;
+}
+EXPORT_SYMBOL_GPL(pci_domain_nr);
+
+int pci_proc_domain(struct pci_bus *bus)
+{
+	return pci_domain_nr(bus);
+}
+EXPORT_SYMBOL_GPL(pci_proc_domain);
+
+/* Store PCI function information block */
+static int zpci_store_fib(struct zpci_dev *zdev, u8 *fc)
+{
+	struct zpci_fib *fib;
+	u8 status, cc;
+
+	fib = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!fib)
+		return -ENOMEM;
+
+	do {
+		cc = __stpcifc(zdev->fh, 0, fib, &status);
+		if (cc == 2) {
+			msleep(ZPCI_INSN_BUSY_DELAY);
+			memset(fib, 0, PAGE_SIZE);
+		}
+	} while (cc == 2);
+
+	if (cc)
+		pr_err_once("%s: cc: %u  status: %u\n",
+			    __func__, cc, status);
+
+	/* Return PCI function controls */
+	*fc = fib->fc;
+
+	free_page((unsigned long) fib);
+	return (cc) ? -EIO : 0;
+}
+
+/* Modify PCI: Register adapter interruptions */
+static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb,
+			      u64 aibv)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+	struct zpci_fib *fib;
+	int rc;
+
+	fib = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!fib)
+		return -ENOMEM;
+
+	fib->isc = PCI_ISC;
+	fib->noi = zdev->irq_map->msi_vecs;
+	fib->sum = 1;		/* enable summary notifications */
+	fib->aibv = aibv;
+	fib->aibvo = 0;		/* every function has its own page */
+	fib->aisb = (u64) bucket->aisb + aisb / 8;
+	fib->aisbo = aisb & ZPCI_MSI_MASK;
+
+	rc = mpcifc_instr(req, fib);
+	pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi);
+
+	free_page((unsigned long) fib);
+	return rc;
+}
+
+struct mod_pci_args {
+	u64 base;
+	u64 limit;
+	u64 iota;
+};
+
+static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args *args)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, dmaas, fn);
+	struct zpci_fib *fib;
+	int rc;
+
+	/* The FIB must be available even if it's not used */
+	fib = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!fib)
+		return -ENOMEM;
+
+	fib->pba = args->base;
+	fib->pal = args->limit;
+	fib->iota = args->iota;
+
+	rc = mpcifc_instr(req, fib);
+	free_page((unsigned long) fib);
+	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)
+{
+	struct mod_pci_args args = { 0, 0, 0 };
+
+	return mod_pci(zdev, ZPCI_MOD_FC_DEREG_INT, 0, &args);
+}
+
+#define ZPCI_PCIAS_CFGSPC	15
+
+static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
+	u64 data;
+	int rc;
+
+	rc = pcilg_instr(&data, req, offset);
+	data = data << ((8 - len) * 8);
+	data = le64_to_cpu(data);
+	if (!rc)
+		*val = (u32) data;
+	else
+		*val = 0xffffffff;
+	return rc;
+}
+
+static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, ZPCI_PCIAS_CFGSPC, len);
+	u64 data = val;
+	int rc;
+
+	data = cpu_to_le64(data);
+	data = data >> ((8 - len) * 8);
+	rc = pcistg_instr(data, req, offset);
+	return rc;
+}
+
+void synchronize_irq(unsigned int irq)
+{
+	/*
+	 * Not needed, the handler is protected by a lock and IRQs that occur
+	 * after the handler is deleted are just NOPs.
+	 */
+}
+EXPORT_SYMBOL_GPL(synchronize_irq);
+
+void enable_irq(unsigned int irq)
+{
+	struct msi_desc *msi = irq_get_msi_desc(irq);
+
+	zpci_msi_set_mask_bits(msi, 1, 0);
+}
+EXPORT_SYMBOL_GPL(enable_irq);
+
+void disable_irq(unsigned int irq)
+{
+	struct msi_desc *msi = irq_get_msi_desc(irq);
+
+	zpci_msi_set_mask_bits(msi, 1, 1);
+}
+EXPORT_SYMBOL_GPL(disable_irq);
+
+void disable_irq_nosync(unsigned int irq)
+{
+	disable_irq(irq);
+}
+EXPORT_SYMBOL_GPL(disable_irq_nosync);
+
+unsigned long probe_irq_on(void)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(probe_irq_on);
+
+int probe_irq_off(unsigned long val)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(probe_irq_off);
+
+unsigned int probe_irq_mask(unsigned long val)
+{
+	return val;
+}
+EXPORT_SYMBOL_GPL(probe_irq_mask);
+
+void __devinit pcibios_fixup_bus(struct pci_bus *bus)
+{
+}
+
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				       resource_size_t size,
+				       resource_size_t align)
+{
+	return 0;
+}
+
+/* combine single writes by using store-block insn */
+void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
+{
+       zpci_memcpy_toio(to, from, count);
+}
+
+/* Create a virtual mapping cookie for a PCI BAR */
+void __iomem *pci_iomap(struct pci_dev *pdev, int bar, unsigned long max)
+{
+	struct zpci_dev *zdev =	get_zdev(pdev);
+	u64 addr;
+	int idx;
+
+	if ((bar & 7) != bar)
+		return NULL;
+
+	idx = zdev->bars[bar].map_idx;
+	spin_lock(&zpci_iomap_lock);
+	zpci_iomap_start[idx].fh = zdev->fh;
+	zpci_iomap_start[idx].bar = bar;
+	spin_unlock(&zpci_iomap_lock);
+
+	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
+	return (void __iomem *) addr;
+}
+EXPORT_SYMBOL_GPL(pci_iomap);
+
+void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+	unsigned int idx;
+
+	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
+	spin_lock(&zpci_iomap_lock);
+	zpci_iomap_start[idx].fh = 0;
+	zpci_iomap_start[idx].bar = 0;
+	spin_unlock(&zpci_iomap_lock);
+}
+EXPORT_SYMBOL_GPL(pci_iounmap);
+
+static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
+		    int size, u32 *val)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+
+	if (!zdev || devfn != ZPCI_DEVFN)
+		return 0;
+	return zpci_cfg_load(zdev, where, val, size);
+}
+
+static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
+		     int size, u32 val)
+{
+	struct zpci_dev *zdev = get_zdev_by_bus(bus);
+
+	if (!zdev || devfn != ZPCI_DEVFN)
+		return 0;
+	return zpci_cfg_store(zdev, where, val, size);
+}
+
+static struct pci_ops pci_root_ops = {
+	.read = pci_read,
+	.write = pci_write,
+};
+
+/* store the last handled bit to implement fair scheduling of devices */
+static DEFINE_PER_CPU(unsigned long, next_sbit);
+
+static void zpci_irq_handler(void *dont, void *need)
+{
+	unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit);
+	int rescan = 0, max = aisb_max;
+	struct zdev_irq_map *imap;
+
+	kstat_cpu(smp_processor_id()).irqs[IOINT_PCI]++;
+	sbit = start;
+
+scan:
+	/* find summary_bit */
+	for_each_set_bit_left_cont(sbit, bucket->aisb, max) {
+		clear_bit(63 - (sbit & 63), bucket->aisb + (sbit >> 6));
+		last = sbit;
+
+		/* find vector bit */
+		imap = bucket->imap[sbit];
+		for_each_set_bit_left(mbit, &imap->aibv, imap->msi_vecs) {
+			kstat_cpu(smp_processor_id()).irqs[IOINT_MSI]++;
+			clear_bit(63 - mbit, &imap->aibv);
+
+			spin_lock(&imap->lock);
+			if (imap->cb[mbit].handler)
+				imap->cb[mbit].handler(mbit,
+					imap->cb[mbit].data);
+			spin_unlock(&imap->lock);
+		}
+	}
+
+	if (rescan)
+		goto out;
+
+	/* scan the skipped bits */
+	if (start > 0) {
+		sbit = 0;
+		max = start;
+		start = 0;
+		goto scan;
+	}
+
+	/* enable interrupts again */
+	sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+
+	/* check again to not lose initiative */
+	rmb();
+	max = aisb_max;
+	sbit = find_first_bit_left(bucket->aisb, max);
+	if (sbit != max) {
+		atomic_inc(&irq_retries);
+		rescan++;
+		goto scan;
+	}
+out:
+	/* store next device bit to scan */
+	__get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last;
+}
+
+/* msi_vecs - number of requested interrupts, 0 place function to error state */
+static int zpci_setup_msi(struct pci_dev *pdev, int msi_vecs)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	unsigned int aisb, msi_nr;
+	struct msi_desc *msi;
+	int rc;
+
+	/* store the number of used MSI vectors */
+	zdev->irq_map->msi_vecs = min(msi_vecs, ZPCI_NR_MSI_VECS);
+
+	spin_lock(&bucket->lock);
+	aisb = find_first_zero_bit(bucket->alloc, PAGE_SIZE);
+	/* alloc map exhausted? */
+	if (aisb == PAGE_SIZE) {
+		spin_unlock(&bucket->lock);
+		return -EIO;
+	}
+	set_bit(aisb, bucket->alloc);
+	spin_unlock(&bucket->lock);
+
+	zdev->aisb = aisb;
+	if (aisb + 1 > aisb_max)
+		aisb_max = aisb + 1;
+
+	/* wire up IRQ shortcut pointer */
+	bucket->imap[zdev->aisb] = zdev->irq_map;
+	pr_debug("%s: imap[%u] linked to %p\n", __func__, zdev->aisb, zdev->irq_map);
+
+	/* TODO: irq number 0 wont be found if we return less than requested MSIs.
+	 * ignore it for now and fix in common code.
+	 */
+	msi_nr = aisb << ZPCI_MSI_VEC_BITS;
+
+	list_for_each_entry(msi, &pdev->msi_list, list) {
+		rc = zpci_setup_msi_irq(zdev, msi, msi_nr,
+					  aisb << ZPCI_MSI_VEC_BITS);
+		if (rc)
+			return rc;
+		msi_nr++;
+	}
+
+	rc = zpci_register_airq(zdev, aisb, (u64) &zdev->irq_map->aibv);
+	if (rc) {
+		clear_bit(aisb, bucket->alloc);
+		dev_err(&pdev->dev, "register MSI failed with: %d\n", rc);
+		return rc;
+	}
+	return (zdev->irq_map->msi_vecs == msi_vecs) ?
+		0 : zdev->irq_map->msi_vecs;
+}
+
+static void zpci_teardown_msi(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+	struct msi_desc *msi;
+	int aisb, rc;
+
+	rc = zpci_unregister_airq(zdev);
+	if (rc) {
+		dev_err(&pdev->dev, "deregister MSI failed with: %d\n", rc);
+		return;
+	}
+
+	msi = list_first_entry(&pdev->msi_list, struct msi_desc, list);
+	aisb = irq_to_dev_nr(msi->irq);
+
+	list_for_each_entry(msi, &pdev->msi_list, list)
+		zpci_teardown_msi_irq(zdev, msi);
+
+	clear_bit(aisb, bucket->alloc);
+	if (aisb + 1 == aisb_max)
+		aisb_max--;
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec);
+	if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI)
+		return -EINVAL;
+	return zpci_setup_msi(pdev, nvec);
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	pr_info("%s: on pdev: %p\n", __func__, pdev);
+	zpci_teardown_msi(pdev);
+}
+
+static void zpci_map_resources(struct zpci_dev *zdev)
+{
+	struct pci_dev *pdev = zdev->pdev;
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			continue;
+		pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0);
+		pdev->resource[i].end = pdev->resource[i].start + len - 1;
+		pr_debug("BAR%i: -> start: %Lx  end: %Lx\n",
+			i, pdev->resource[i].start, pdev->resource[i].end);
+	}
+};
+
+static void zpci_unmap_resources(struct pci_dev *pdev)
+{
+	resource_size_t len;
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			continue;
+		pci_iounmap(pdev, (void *) pdev->resource[i].start);
+	}
+};
+
+struct zpci_dev *zpci_alloc_device(void)
+{
+	struct zpci_dev *zdev;
+
+	/* Alloc memory for our private pci device data */
+	zdev = kzalloc(sizeof(*zdev), GFP_KERNEL);
+	if (!zdev)
+		return ERR_PTR(-ENOMEM);
+
+	/* Alloc aibv & callback space */
+	zdev->irq_map = kmem_cache_zalloc(zdev_irq_cache, GFP_KERNEL);
+	if (!zdev->irq_map)
+		goto error;
+	WARN_ON((u64) zdev->irq_map & 0xff);
+	return zdev;
+
+error:
+	kfree(zdev);
+	return ERR_PTR(-ENOMEM);
+}
+
+void zpci_free_device(struct zpci_dev *zdev)
+{
+	kmem_cache_free(zdev_irq_cache, zdev->irq_map);
+	kfree(zdev);
+}
+
+/* Called on removal of pci_dev, leaves zpci and bus device */
+static void zpci_remove_device(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = get_zdev(pdev);
+
+	dev_info(&pdev->dev, "Removing device %u\n", zdev->domain);
+	zdev->state = ZPCI_FN_STATE_CONFIGURED;
+	zpci_dma_exit_device(zdev);
+	zpci_sysfs_remove_device(&pdev->dev);
+	zpci_unmap_resources(pdev);
+	list_del(&zdev->entry);		/* can be called from init */
+	zdev->pdev = NULL;
+}
+
+static void zpci_scan_devices(void)
+{
+	struct zpci_dev *zdev;
+
+	mutex_lock(&zpci_list_lock);
+	list_for_each_entry(zdev, &zpci_list, entry)
+		if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
+			zpci_scan_device(zdev);
+	mutex_unlock(&zpci_list_lock);
+}
+
+/*
+ * Too late for any s390 specific setup, since interrupts must be set up
+ * already which requires DMA setup too and the pci scan will access the
+ * config space, which only works if the function handle is enabled.
+ */
+int pcibios_enable_device(struct pci_dev *pdev, int mask)
+{
+	struct resource *res;
+	u16 cmd;
+	int i;
+
+	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		res = &pdev->resource[i];
+
+		if (res->flags & IORESOURCE_IO)
+			return -EINVAL;
+
+		if (res->flags & IORESOURCE_MEM)
+			cmd |= PCI_COMMAND_MEMORY;
+	}
+	pci_write_config_word(pdev, PCI_COMMAND, cmd);
+	return 0;
+}
+
+void pcibios_disable_device(struct pci_dev *pdev)
+{
+	zpci_remove_device(pdev);
+	pdev->sysdata = NULL;
+}
+
+int pcibios_add_platform_entries(struct pci_dev *pdev)
+{
+	return zpci_sysfs_add_device(&pdev->dev);
+}
+
+int zpci_request_irq(unsigned int irq, irq_handler_t handler, void *data)
+{
+	int msi_nr = irq_to_msi_nr(irq);
+	struct zdev_irq_map *imap;
+	struct msi_desc *msi;
+
+	msi = irq_get_msi_desc(irq);
+	if (!msi)
+		return -EIO;
+
+	imap = get_imap(irq);
+	spin_lock_init(&imap->lock);
+
+	pr_debug("%s: register handler for IRQ:MSI %d:%d\n", __func__, irq >> 6, msi_nr);
+	imap->cb[msi_nr].handler = handler;
+	imap->cb[msi_nr].data = data;
+
+	/*
+	 * The generic MSI code returns with the interrupt disabled on the
+	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
+	 * at that level, so we do it here by hand.
+	 */
+	zpci_msi_set_mask_bits(msi, 1, 0);
+	return 0;
+}
+
+void zpci_free_irq(unsigned int irq)
+{
+	struct zdev_irq_map *imap = get_imap(irq);
+	int msi_nr = irq_to_msi_nr(irq);
+	unsigned long flags;
+
+	pr_debug("%s: for irq: %d\n", __func__, irq);
+
+	spin_lock_irqsave(&imap->lock, flags);
+	imap->cb[msi_nr].handler = NULL;
+	imap->cb[msi_nr].data = NULL;
+	spin_unlock_irqrestore(&imap->lock, flags);
+}
+
+int request_irq(unsigned int irq, irq_handler_t handler,
+		unsigned long irqflags, const char *devname, void *dev_id)
+{
+	pr_debug("%s: irq: %d  handler: %p  flags: %lx  dev: %s\n",
+		__func__, irq, handler, irqflags, devname);
+
+	return zpci_request_irq(irq, handler, dev_id);
+}
+EXPORT_SYMBOL_GPL(request_irq);
+
+void free_irq(unsigned int irq, void *dev_id)
+{
+	zpci_free_irq(irq);
+}
+EXPORT_SYMBOL_GPL(free_irq);
+
+static int __init zpci_irq_init(void)
+{
+	int cpu, rc;
+
+	bucket = kzalloc(sizeof(*bucket), GFP_KERNEL);
+	if (!bucket)
+		return -ENOMEM;
+
+	bucket->aisb = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+	if (!bucket->aisb) {
+		rc = -ENOMEM;
+		goto out_aisb;
+	}
+
+	bucket->alloc = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+	if (!bucket->alloc) {
+		rc = -ENOMEM;
+		goto out_alloc;
+	}
+
+	isc_register(PCI_ISC);
+	zpci_irq_si = s390_register_adapter_interrupt(&zpci_irq_handler, NULL, PCI_ISC);
+	if (IS_ERR(zpci_irq_si)) {
+		rc = PTR_ERR(zpci_irq_si);
+		zpci_irq_si = NULL;
+		goto out_ai;
+	}
+
+	for_each_online_cpu(cpu)
+		per_cpu(next_sbit, cpu) = 0;
+
+	spin_lock_init(&bucket->lock);
+	/* set summary to 1 to be called every time for the ISC */
+	*zpci_irq_si = 1;
+	sic_instr(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
+	return 0;
+
+out_ai:
+	isc_unregister(PCI_ISC);
+	free_page((unsigned long) bucket->alloc);
+out_alloc:
+	free_page((unsigned long) bucket->aisb);
+out_aisb:
+	kfree(bucket);
+	return rc;
+}
+
+static void zpci_irq_exit(void)
+{
+	free_page((unsigned long) bucket->alloc);
+	free_page((unsigned long) bucket->aisb);
+	s390_unregister_adapter_interrupt(zpci_irq_si, PCI_ISC);
+	isc_unregister(PCI_ISC);
+	kfree(bucket);
+}
+
+static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size,
+						unsigned long flags, int domain)
+{
+	struct resource *r;
+	char *name;
+	int rc;
+
+	r = kzalloc(sizeof(*r), GFP_KERNEL);
+	if (!r)
+		return ERR_PTR(-ENOMEM);
+	r->start = start;
+	r->end = r->start + size - 1;
+	r->flags = flags;
+	r->parent = &iomem_resource;
+	name = kmalloc(18, GFP_KERNEL);
+	if (!name) {
+		kfree(r);
+		return ERR_PTR(-ENOMEM);
+	}
+	sprintf(name, "PCI Bus: %04x:%02x", domain, ZPCI_BUS_NR);
+	r->name = name;
+
+	rc = request_resource(&iomem_resource, r);
+	if (rc)
+		pr_debug("request resource %pR failed\n", r);
+	return r;
+}
+
+static int zpci_alloc_iomap(struct zpci_dev *zdev)
+{
+	int entry;
+
+	spin_lock(&zpci_iomap_lock);
+	entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+	if (entry == ZPCI_IOMAP_MAX_ENTRIES) {
+		spin_unlock(&zpci_iomap_lock);
+		return -ENOSPC;
+	}
+	set_bit(entry, zpci_iomap);
+	spin_unlock(&zpci_iomap_lock);
+	return entry;
+}
+
+static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
+{
+	spin_lock(&zpci_iomap_lock);
+	memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry));
+	clear_bit(entry, zpci_iomap);
+	spin_unlock(&zpci_iomap_lock);
+}
+
+static int zpci_create_device_bus(struct zpci_dev *zdev)
+{
+	struct resource *res;
+	LIST_HEAD(resources);
+	int i;
+
+	/* allocate mapping entry for each used bar */
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		unsigned long addr, size, flags;
+		int entry;
+
+		if (!zdev->bars[i].size)
+			continue;
+		entry = zpci_alloc_iomap(zdev);
+		if (entry < 0)
+			return entry;
+		zdev->bars[i].map_idx = entry;
+
+		/* only MMIO is supported */
+		flags = IORESOURCE_MEM;
+		if (zdev->bars[i].val & 8)
+			flags |= IORESOURCE_PREFETCH;
+		if (zdev->bars[i].val & 4)
+			flags |= IORESOURCE_MEM_64;
+
+		addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48);
+
+		size = 1UL << zdev->bars[i].size;
+
+		res = zpci_alloc_bus_resource(addr, size, flags, zdev->domain);
+		if (IS_ERR(res)) {
+			zpci_free_iomap(zdev, entry);
+			return PTR_ERR(res);
+		}
+		pci_add_resource(&resources, res);
+	}
+
+	zdev->bus = pci_create_root_bus(NULL, ZPCI_BUS_NR, &pci_root_ops,
+					zdev, &resources);
+	if (!zdev->bus)
+		return -EIO;
+
+	zdev->bus->max_bus_speed = zdev->max_bus_speed;
+	return 0;
+}
+
+static int zpci_alloc_domain(struct zpci_dev *zdev)
+{
+	spin_lock(&zpci_domain_lock);
+	zdev->domain = find_first_zero_bit(zpci_domain, ZPCI_NR_DEVICES);
+	if (zdev->domain == ZPCI_NR_DEVICES) {
+		spin_unlock(&zpci_domain_lock);
+		return -ENOSPC;
+	}
+	set_bit(zdev->domain, zpci_domain);
+	spin_unlock(&zpci_domain_lock);
+	return 0;
+}
+
+static void zpci_free_domain(struct zpci_dev *zdev)
+{
+	spin_lock(&zpci_domain_lock);
+	clear_bit(zdev->domain, zpci_domain);
+	spin_unlock(&zpci_domain_lock);
+}
+
+int zpci_enable_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	rc = clp_enable_fh(zdev, ZPCI_NR_DMA_SPACES);
+	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;
+}
+EXPORT_SYMBOL_GPL(zpci_enable_device);
+
+int zpci_create_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	rc = zpci_alloc_domain(zdev);
+	if (rc)
+		goto out;
+
+	rc = zpci_create_device_bus(zdev);
+	if (rc)
+		goto out_bus;
+
+	mutex_lock(&zpci_list_lock);
+	list_add_tail(&zdev->entry, &zpci_list);
+	if (hotplug_ops.create_slot)
+		hotplug_ops.create_slot(zdev);
+	mutex_unlock(&zpci_list_lock);
+
+	if (zdev->state == ZPCI_FN_STATE_STANDBY)
+		return 0;
+
+	rc = zpci_enable_device(zdev);
+	if (rc)
+		goto out_start;
+	return 0;
+
+out_start:
+	mutex_lock(&zpci_list_lock);
+	list_del(&zdev->entry);
+	if (hotplug_ops.remove_slot)
+		hotplug_ops.remove_slot(zdev);
+	mutex_unlock(&zpci_list_lock);
+out_bus:
+	zpci_free_domain(zdev);
+out:
+	return rc;
+}
+
+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.
+	 */
+}
+EXPORT_SYMBOL_GPL(zpci_stop_device);
+
+int zpci_scan_device(struct zpci_dev *zdev)
+{
+	zdev->pdev = pci_scan_single_device(zdev->bus, ZPCI_DEVFN);
+	if (!zdev->pdev) {
+		pr_err("pci_scan_single_device failed for fid: 0x%x\n",
+			zdev->fid);
+		goto out;
+	}
+
+	zpci_map_resources(zdev);
+	pci_bus_add_devices(zdev->bus);
+
+	/* now that pdev was added to the bus mark it as used */
+	zdev->state = ZPCI_FN_STATE_ONLINE;
+	return 0;
+
+out:
+	zpci_dma_exit_device(zdev);
+	clp_disable_fh(zdev);
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(zpci_scan_device);
+
+static inline int barsize(u8 size)
+{
+	return (size) ? (1 << size) >> 10 : 0;
+}
+
+static int zpci_mem_init(void)
+{
+	zdev_irq_cache = kmem_cache_create("PCI_IRQ_cache", sizeof(struct zdev_irq_map),
+				L1_CACHE_BYTES, SLAB_HWCACHE_ALIGN, NULL);
+	if (!zdev_irq_cache)
+		goto error_zdev;
+
+	/* TODO: use realloc */
+	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
+				   GFP_KERNEL);
+	if (!zpci_iomap_start)
+		goto error_iomap;
+	return 0;
+
+error_iomap:
+	kmem_cache_destroy(zdev_irq_cache);
+error_zdev:
+	return -ENOMEM;
+}
+
+static void zpci_mem_exit(void)
+{
+	kfree(zpci_iomap_start);
+	kmem_cache_destroy(zdev_irq_cache);
+}
+
+unsigned int pci_probe = 1;
+EXPORT_SYMBOL_GPL(pci_probe);
+
+char * __init pcibios_setup(char *str)
+{
+	if (!strcmp(str, "off")) {
+		pci_probe = 0;
+		return NULL;
+	}
+	return str;
+}
+
+static int __init pci_base_init(void)
+{
+	int rc;
+
+	if (!pci_probe)
+		return 0;
+
+	if (!test_facility(2) || !test_facility(69)
+	    || !test_facility(71) || !test_facility(72))
+		return 0;
+
+	pr_info("Probing PCI hardware: PCI:%d  SID:%d  AEN:%d\n",
+		test_facility(69), test_facility(70),
+		test_facility(71));
+
+	rc = zpci_mem_init();
+	if (rc)
+		goto out_mem;
+
+	rc = zpci_msihash_init();
+	if (rc)
+		goto out_hash;
+
+	rc = zpci_irq_init();
+	if (rc)
+		goto out_irq;
+
+	rc = zpci_dma_init();
+	if (rc)
+		goto out_dma;
+
+	rc = clp_find_pci_devices();
+	if (rc)
+		goto out_find;
+
+	zpci_scan_devices();
+	return 0;
+
+out_find:
+	zpci_dma_exit();
+out_dma:
+	zpci_irq_exit();
+out_irq:
+	zpci_msihash_exit();
+out_hash:
+	zpci_mem_exit();
+out_mem:
+	return rc;
+}
+subsys_initcall(pci_base_init);

arch/s390/pci/pci_clp.c

@@ -0,0 +1,324 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <asm/pci_clp.h>
+
+/*
+ * Call Logical Processor
+ * Retry logic is handled by the caller.
+ */
+static inline u8 clp_instr(void *req)
+{
+	u64 ilpm;
+	u8 cc;
+
+	asm volatile (
+		"	.insn	rrf,0xb9a00000,%[ilpm],%[req],0x0,0x2\n"
+		"	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		: [cc] "=d" (cc), [ilpm] "=d" (ilpm)
+		: [req] "a" (req)
+		: "cc", "memory");
+	return cc;
+}
+
+static void *clp_alloc_block(void)
+{
+	struct page *page = alloc_pages(GFP_KERNEL, get_order(CLP_BLK_SIZE));
+	return (page) ? page_address(page) : NULL;
+}
+
+static void clp_free_block(void *ptr)
+{
+	free_pages((unsigned long) ptr, get_order(CLP_BLK_SIZE));
+}
+
+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);
+	switch (response->version) {
+	case 1:
+		zdev->max_bus_speed = PCIE_SPEED_5_0GT;
+		break;
+	default:
+		zdev->max_bus_speed = PCI_SPEED_UNKNOWN;
+		break;
+	}
+}
+
+static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid)
+{
+	struct clp_req_rsp_query_pci_grp *rrb;
+	int rc;
+
+	rrb = clp_alloc_block();
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_QUERY_PCI_FNGRP;
+	rrb->response.hdr.len = sizeof(rrb->response);
+	rrb->request.pfgid = pfgid;
+
+	rc = clp_instr(rrb);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
+		clp_store_query_pci_fngrp(zdev, &rrb->response);
+	else {
+		pr_err("Query PCI FNGRP failed with response: %x  cc: %d\n",
+			rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+static int clp_store_query_pci_fn(struct zpci_dev *zdev,
+				  struct clp_rsp_query_pci *response)
+{
+	int i;
+
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		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;
+}
+
+static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh)
+{
+	struct clp_req_rsp_query_pci *rrb;
+	int rc;
+
+	rrb = clp_alloc_block();
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_QUERY_PCI_FN;
+	rrb->response.hdr.len = sizeof(rrb->response);
+	rrb->request.fh = fh;
+
+	rc = clp_instr(rrb);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		rc = clp_store_query_pci_fn(zdev, &rrb->response);
+		if (rc)
+			goto out;
+		if (rrb->response.pfgid)
+			rc = clp_query_pci_fngrp(zdev, rrb->response.pfgid);
+	} else {
+		pr_err("Query PCI failed with response: %x  cc: %d\n",
+			 rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+out:
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_add_pci_device(u32 fid, u32 fh, int configured)
+{
+	struct zpci_dev *zdev;
+	int rc;
+
+	zdev = zpci_alloc_device();
+	if (IS_ERR(zdev))
+		return PTR_ERR(zdev);
+
+	zdev->fh = fh;
+	zdev->fid = fid;
+
+	/* Query function properties and update zdev */
+	rc = clp_query_pci_fn(zdev, fh);
+	if (rc)
+		goto error;
+
+	if (configured)
+		zdev->state = ZPCI_FN_STATE_CONFIGURED;
+	else
+		zdev->state = ZPCI_FN_STATE_STANDBY;
+
+	rc = zpci_create_device(zdev);
+	if (rc)
+		goto error;
+	return 0;
+
+error:
+	zpci_free_device(zdev);
+	return rc;
+}
+
+/*
+ * Enable/Disable a given PCI function defined by its function handle.
+ */
+static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
+{
+	struct clp_req_rsp_set_pci *rrb;
+	int rc, retries = 1000;
+
+	rrb = clp_alloc_block();
+	if (!rrb)
+		return -ENOMEM;
+
+	do {
+		memset(rrb, 0, sizeof(*rrb));
+		rrb->request.hdr.len = sizeof(rrb->request);
+		rrb->request.hdr.cmd = CLP_SET_PCI_FN;
+		rrb->response.hdr.len = sizeof(rrb->response);
+		rrb->request.fh = *fh;
+		rrb->request.oc = command;
+		rrb->request.ndas = nr_dma_as;
+
+		rc = clp_instr(rrb);
+		if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) {
+			retries--;
+			if (retries < 0)
+				break;
+			msleep(1);
+		}
+	} while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY);
+
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
+		*fh = rrb->response.fh;
+	else {
+		pr_err("Set PCI FN failed with response: %x  cc: %d\n",
+			rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
+int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
+{
+	u32 fh = zdev->fh;
+	int rc;
+
+	rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
+	if (!rc)
+		/* Success -> store enabled handle in zdev */
+		zdev->fh = fh;
+	return rc;
+}
+
+int clp_disable_fh(struct zpci_dev *zdev)
+{
+	u32 fh = zdev->fh;
+	int rc;
+
+	if (!zdev_enabled(zdev))
+		return 0;
+
+	dev_info(&zdev->pdev->dev, "disabling fn handle: 0x%x\n", fh);
+	rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
+	if (!rc)
+		/* Success -> store disabled handle in zdev */
+		zdev->fh = fh;
+	else
+		dev_err(&zdev->pdev->dev,
+			"Failed to disable fn handle: 0x%x\n", fh);
+	return rc;
+}
+
+static void clp_check_pcifn_entry(struct clp_fh_list_entry *entry)
+{
+	int present, rc;
+
+	if (!entry->vendor_id)
+		return;
+
+	/* TODO: be a little bit more scalable */
+	present = zpci_fid_present(entry->fid);
+
+	if (present)
+		pr_debug("%s: device %x already present\n", __func__, entry->fid);
+
+	/* skip already used functions */
+	if (present && entry->config_state)
+		return;
+
+	/* aev 306: function moved to stand-by state */
+	if (present && !entry->config_state) {
+		/*
+		 * The handle is already disabled, that means no iota/irq freeing via
+		 * the firmware interfaces anymore. Need to free resources manually
+		 * (DMA memory, debug, sysfs)...
+		 */
+		zpci_stop_device(get_zdev_by_fid(entry->fid));
+		return;
+	}
+
+	rc = clp_add_pci_device(entry->fid, entry->fh, entry->config_state);
+	if (rc)
+		pr_err("Failed to add fid: 0x%x\n", entry->fid);
+}
+
+int clp_find_pci_devices(void)
+{
+	struct clp_req_rsp_list_pci *rrb;
+	u64 resume_token = 0;
+	int entries, i, rc;
+
+	rrb = clp_alloc_block();
+	if (!rrb)
+		return -ENOMEM;
+
+	do {
+		memset(rrb, 0, sizeof(*rrb));
+		rrb->request.hdr.len = sizeof(rrb->request);
+		rrb->request.hdr.cmd = CLP_LIST_PCI;
+		/* store as many entries as possible */
+		rrb->response.hdr.len = CLP_BLK_SIZE - LIST_PCI_HDR_LEN;
+		rrb->request.resume_token = resume_token;
+
+		/* Get PCI function handle list */
+		rc = clp_instr(rrb);
+		if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
+			pr_err("List PCI failed with response: 0x%x  cc: %d\n",
+				rrb->response.hdr.rsp, rc);
+			rc = -EIO;
+			goto out;
+		}
+
+		WARN_ON_ONCE(rrb->response.entry_size !=
+			sizeof(struct clp_fh_list_entry));
+
+		entries = (rrb->response.hdr.len - LIST_PCI_HDR_LEN) /
+			rrb->response.entry_size;
+		pr_info("Detected number of PCI functions: %u\n", entries);
+
+		/* Store the returned resume token as input for the next call */
+		resume_token = rrb->response.resume_token;
+
+		for (i = 0; i < entries; i++)
+			clp_check_pcifn_entry(&rrb->response.fh_list[i]);
+	} while (resume_token);
+
+	pr_debug("Maximum number of supported PCI functions: %u\n",
+		rrb->response.max_fn);
+out:
+	clp_free_block(rrb);
+	return rc;
+}

arch/s390/pci/pci_dma.c

@@ -0,0 +1,506 @@
+/*
+ * 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;
+	int rtx;
+
+	if (!zdev || !zdev->dma_table)
+		return;
+
+	table = zdev->dma_table;
+	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);

arch/s390/pci/pci_event.c

@@ -0,0 +1,93 @@
+/*
+ *  Copyright IBM Corp. 2012
+ *
+ *  Author(s):
+ *    Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+
+/* Content Code Description for PCI Function Error */
+struct zpci_ccdf_err {
+	u32 reserved1;
+	u32 fh;				/* function handle */
+	u32 fid;			/* function id */
+	u32 ett		:  4;		/* expected table type */
+	u32 mvn		: 12;		/* MSI vector number */
+	u32 dmaas	:  8;		/* DMA address space */
+	u32		:  6;
+	u32 q		:  1;		/* event qualifier */
+	u32 rw		:  1;		/* read/write */
+	u64 faddr;			/* failing address */
+	u32 reserved3;
+	u16 reserved4;
+	u16 pec;			/* PCI event code */
+} __packed;
+
+/* Content Code Description for PCI Function Availability */
+struct zpci_ccdf_avail {
+	u32 reserved1;
+	u32 fh;				/* function handle */
+	u32 fid;			/* function id */
+	u32 reserved2;
+	u32 reserved3;
+	u32 reserved4;
+	u32 reserved5;
+	u16 reserved6;
+	u16 pec;			/* PCI event code */
+} __packed;
+
+static void zpci_event_log_err(struct zpci_ccdf_err *ccdf)
+{
+	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+
+	dev_err(&zdev->pdev->dev, "event code: 0x%x\n", ccdf->pec);
+}
+
+static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf)
+{
+	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+
+	pr_err("%s%s: availability event: fh: 0x%x  fid: 0x%x  event code: 0x%x  reason:",
+		(zdev) ? dev_driver_string(&zdev->pdev->dev) : "?",
+		(zdev) ? dev_name(&zdev->pdev->dev) : "?",
+		ccdf->fh, ccdf->fid, ccdf->pec);
+	print_hex_dump(KERN_CONT, "ccdf", DUMP_PREFIX_OFFSET,
+		       16, 1, ccdf, sizeof(*ccdf), false);
+
+	switch (ccdf->pec) {
+	case 0x0301:
+		zpci_enable_device(zdev);
+		break;
+	case 0x0302:
+		clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
+		break;
+	case 0x0306:
+		clp_find_pci_devices();
+		break;
+	default:
+		break;
+	}
+}
+
+void zpci_event_error(void *data)
+{
+	struct zpci_ccdf_err *ccdf = data;
+	struct zpci_dev *zdev;
+
+	zpci_event_log_err(ccdf);
+	zdev = get_zdev_by_fid(ccdf->fid);
+	if (!zdev) {
+		pr_err("Error event for unknown fid: %x", ccdf->fid);
+		return;
+	}
+}
+
+void zpci_event_availability(void *data)
+{
+	zpci_event_log_avail(data);
+}

arch/s390/pci/pci_msi.c

@@ -0,0 +1,141 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/rculist.h>
+#include <linux/hash.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <asm/hw_irq.h>
+
+/* mapping of irq numbers to msi_desc */
+static struct hlist_head *msi_hash;
+static unsigned int msihash_shift = 6;
+#define msi_hashfn(nr)	hash_long(nr, msihash_shift)
+
+static DEFINE_SPINLOCK(msi_map_lock);
+
+struct msi_desc *__irq_get_msi_desc(unsigned int irq)
+{
+	struct hlist_node *entry;
+	struct msi_map *map;
+
+	hlist_for_each_entry_rcu(map, entry,
+			&msi_hash[msi_hashfn(irq)], msi_chain)
+		if (map->irq == irq)
+			return map->msi;
+	return NULL;
+}
+
+int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
+{
+	if (msi->msi_attrib.is_msix) {
+		int offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+			PCI_MSIX_ENTRY_VECTOR_CTRL;
+		msi->masked = readl(msi->mask_base + offset);
+		writel(flag, msi->mask_base + offset);
+	} else {
+		if (msi->msi_attrib.maskbit) {
+			int pos;
+			u32 mask_bits;
+
+			pos = (long) msi->mask_base;
+			pci_read_config_dword(msi->dev, pos, &mask_bits);
+			mask_bits &= ~(mask);
+			mask_bits |= flag & mask;
+			pci_write_config_dword(msi->dev, pos, mask_bits);
+		} else {
+			return 0;
+		}
+	}
+
+	msi->msi_attrib.maskbit = !!flag;
+	return 1;
+}
+
+int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi,
+			unsigned int nr, int offset)
+{
+	struct msi_map *map;
+	struct msi_msg msg;
+	int rc;
+
+	map = kmalloc(sizeof(*map), GFP_KERNEL);
+	if (map == NULL)
+		return -ENOMEM;
+
+	map->irq = nr;
+	map->msi = msi;
+	zdev->msi_map[nr & ZPCI_MSI_MASK] = map;
+
+	pr_debug("%s hashing irq: %u  to bucket nr: %llu\n",
+		__func__, nr, msi_hashfn(nr));
+	hlist_add_head_rcu(&map->msi_chain, &msi_hash[msi_hashfn(nr)]);
+
+	spin_lock(&msi_map_lock);
+	rc = irq_set_msi_desc(nr, msi);
+	if (rc) {
+		spin_unlock(&msi_map_lock);
+		hlist_del_rcu(&map->msi_chain);
+		kfree(map);
+		zdev->msi_map[nr & ZPCI_MSI_MASK] = NULL;
+		return rc;
+	}
+	spin_unlock(&msi_map_lock);
+
+	msg.data = nr - offset;
+	msg.address_lo = zdev->msi_addr & 0xffffffff;
+	msg.address_hi = zdev->msi_addr >> 32;
+	write_msi_msg(nr, &msg);
+	return 0;
+}
+
+void zpci_teardown_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi)
+{
+	int irq = msi->irq & ZPCI_MSI_MASK;
+	struct msi_map *map;
+
+	msi->msg.address_lo = 0;
+	msi->msg.address_hi = 0;
+	msi->msg.data = 0;
+	msi->irq = 0;
+	zpci_msi_set_mask_bits(msi, 1, 1);
+
+	spin_lock(&msi_map_lock);
+	map = zdev->msi_map[irq];
+	hlist_del_rcu(&map->msi_chain);
+	kfree(map);
+	zdev->msi_map[irq] = NULL;
+	spin_unlock(&msi_map_lock);
+}
+
+/*
+ * The msi hash table has 256 entries which is good for 4..20
+ * devices (a typical device allocates 10 + CPUs MSI's). Maybe make
+ * the hash table size adjustable later.
+ */
+int __init zpci_msihash_init(void)
+{
+	unsigned int i;
+
+	msi_hash = kmalloc(256 * sizeof(*msi_hash), GFP_KERNEL);
+	if (!msi_hash)
+		return -ENOMEM;
+
+	for (i = 0; i < (1U << msihash_shift); i++)
+		INIT_HLIST_HEAD(&msi_hash[i]);
+	return 0;
+}
+
+void __init zpci_msihash_exit(void)
+{
+	kfree(msi_hash);
+}

arch/s390/pci/pci_sysfs.c

@@ -0,0 +1,86 @@
+/*
+ * Copyright IBM Corp. 2012
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define COMPONENT "zPCI"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/stat.h>
+#include <linux/pci.h>
+
+static ssize_t show_fid(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev));
+
+	sprintf(buf, "0x%08x\n", zdev->fid);
+	return strlen(buf);
+}
+static DEVICE_ATTR(function_id, S_IRUGO, show_fid, NULL);
+
+static ssize_t show_fh(struct device *dev, struct device_attribute *attr,
+		       char *buf)
+{
+	struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev));
+
+	sprintf(buf, "0x%08x\n", zdev->fh);
+	return strlen(buf);
+}
+static DEVICE_ATTR(function_handle, S_IRUGO, show_fh, NULL);
+
+static ssize_t show_pchid(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev));
+
+	sprintf(buf, "0x%04x\n", zdev->pchid);
+	return strlen(buf);
+}
+static DEVICE_ATTR(pchid, S_IRUGO, show_pchid, NULL);
+
+static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct zpci_dev *zdev = get_zdev(container_of(dev, struct pci_dev, dev));
+
+	sprintf(buf, "0x%02x\n", zdev->pfgid);
+	return strlen(buf);
+}
+static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL);
+
+static struct device_attribute *zpci_dev_attrs[] = {
+	&dev_attr_function_id,
+	&dev_attr_function_handle,
+	&dev_attr_pchid,
+	&dev_attr_pfgid,
+	NULL,
+};
+
+int zpci_sysfs_add_device(struct device *dev)
+{
+	int i, rc = 0;
+
+	for (i = 0; zpci_dev_attrs[i]; i++) {
+		rc = device_create_file(dev, zpci_dev_attrs[i]);
+		if (rc)
+			goto error;
+	}
+	return 0;
+
+error:
+	while (--i >= 0)
+		device_remove_file(dev, zpci_dev_attrs[i]);
+	return rc;
+}
+
+void zpci_sysfs_remove_device(struct device *dev)
+{
+	int i;
+
+	for (i = 0; zpci_dev_attrs[i]; i++)
+		device_remove_file(dev, zpci_dev_attrs[i]);
+}

drivers/gpu/vga/Kconfig

@@ -1,7 +1,7 @@
 config VGA_ARB
 	bool "VGA Arbitration" if EXPERT
 	default y
-	depends on PCI
+	depends on (PCI && !S390)
 	help
 	  Some "legacy" VGA devices implemented on PCI typically have the same
 	  hard-decoded addresses as they did on ISA. When multiple PCI devices

drivers/pci/hotplug/Kconfig

@@ -151,4 +151,15 @@ config HOTPLUG_PCI_SGI
 
 	  When in doubt, say N.
 
+config HOTPLUG_PCI_S390
+	tristate "System z PCI Hotplug Support"
+	depends on S390 && 64BIT
+	help
+	  Say Y here if you want to use the System z PCI Hotplug
+	  driver for PCI devices. Without this driver it is not
+	  possible to access stand-by PCI functions nor to deconfigure
+	  PCI functions.
+
+	  When in doubt, say Y.
+
 endif # HOTPLUG_PCI

drivers/pci/hotplug/Makefile

@@ -18,6 +18,7 @@ obj-$(CONFIG_HOTPLUG_PCI_RPA)		+= rpaphp.o
 obj-$(CONFIG_HOTPLUG_PCI_RPA_DLPAR)	+= rpadlpar_io.o
 obj-$(CONFIG_HOTPLUG_PCI_SGI)		+= sgi_hotplug.o
 obj-$(CONFIG_HOTPLUG_PCI_ACPI)		+= acpiphp.o
+obj-$(CONFIG_HOTPLUG_PCI_S390)		+= s390_pci_hpc.o
 
 # acpiphp_ibm extends acpiphp, so should be linked afterwards.
 

drivers/pci/hotplug/s390_pci_hpc.c

@@ -0,0 +1,252 @@
+/*
+ * PCI Hot Plug Controller Driver for System z
+ *
+ * Copyright 2012 IBM Corp.
+ *
+ * Author(s):
+ *   Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#define COMPONENT "zPCI hpc"
+#define pr_fmt(fmt) COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <linux/init.h>
+#include <asm/sclp.h>
+
+#define SLOT_NAME_SIZE	10
+static LIST_HEAD(s390_hotplug_slot_list);
+
+MODULE_AUTHOR("Jan Glauber <jang@linux.vnet.ibm.com");
+MODULE_DESCRIPTION("Hot Plug PCI Controller for System z");
+MODULE_LICENSE("GPL");
+
+static int zpci_fn_configured(enum zpci_state state)
+{
+	return state == ZPCI_FN_STATE_CONFIGURED ||
+	       state == ZPCI_FN_STATE_ONLINE;
+}
+
+/*
+ * struct slot - slot information for each *physical* slot
+ */
+struct slot {
+	struct list_head slot_list;
+	struct hotplug_slot *hotplug_slot;
+	struct zpci_dev *zdev;
+};
+
+static int enable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int rc;
+
+	if (slot->zdev->state != ZPCI_FN_STATE_STANDBY)
+		return -EIO;
+
+	rc = sclp_pci_configure(slot->zdev->fid);
+	if (!rc) {
+		slot->zdev->state = ZPCI_FN_STATE_CONFIGURED;
+		/* automatically scan the device after is was configured */
+		zpci_enable_device(slot->zdev);
+		zpci_scan_device(slot->zdev);
+	}
+	return rc;
+}
+
+static int disable_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+	int rc;
+
+	if (!zpci_fn_configured(slot->zdev->state))
+		return -EIO;
+
+	/* TODO: we rely on the user to unbind/remove the device, is that plausible
+	 *	 or do we need to trigger that here?
+	 */
+	rc = sclp_pci_deconfigure(slot->zdev->fid);
+	if (!rc) {
+		/* Fixme: better call List-PCI to find the disabled FH
+		   for the FID since the FH should be opaque... */
+		slot->zdev->fh &= 0x7fffffff;
+		slot->zdev->state = ZPCI_FN_STATE_STANDBY;
+	}
+	return rc;
+}
+
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	switch (slot->zdev->state) {
+	case ZPCI_FN_STATE_STANDBY:
+		*value = 0;
+		break;
+	default:
+		*value = 1;
+		break;
+	}
+	return 0;
+}
+
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
+{
+	/* if the slot exits it always contains a function */
+	*value = 1;
+	return 0;
+}
+
+static void release_slot(struct hotplug_slot *hotplug_slot)
+{
+	struct slot *slot = hotplug_slot->private;
+
+	pr_debug("%s - physical_slot = %s\n", __func__, hotplug_slot_name(hotplug_slot));
+	kfree(slot->hotplug_slot->info);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
+}
+
+static struct hotplug_slot_ops s390_hotplug_slot_ops = {
+	.enable_slot =		enable_slot,
+	.disable_slot =		disable_slot,
+	.get_power_status =	get_power_status,
+	.get_adapter_status =	get_adapter_status,
+};
+
+static int init_pci_slot(struct zpci_dev *zdev)
+{
+	struct hotplug_slot *hotplug_slot;
+	struct hotplug_slot_info *info;
+	char name[SLOT_NAME_SIZE];
+	struct slot *slot;
+	int rc;
+
+	if (!zdev)
+		return 0;
+
+	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
+	if (!slot)
+		goto error;
+
+	hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL);
+	if (!hotplug_slot)
+		goto error_hp;
+	hotplug_slot->private = slot;
+
+	slot->hotplug_slot = hotplug_slot;
+	slot->zdev = zdev;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		goto error_info;
+	hotplug_slot->info = info;
+
+	hotplug_slot->ops = &s390_hotplug_slot_ops;
+	hotplug_slot->release = &release_slot;
+
+	get_power_status(hotplug_slot, &info->power_status);
+	get_adapter_status(hotplug_slot, &info->adapter_status);
+
+	snprintf(name, SLOT_NAME_SIZE, "%08x", zdev->fid);
+	rc = pci_hp_register(slot->hotplug_slot, zdev->bus,
+			     ZPCI_DEVFN, name);
+	if (rc) {
+		pr_err("pci_hp_register failed with error %d\n", rc);
+		goto error_reg;
+	}
+	list_add(&slot->slot_list, &s390_hotplug_slot_list);
+	return 0;
+
+error_reg:
+	kfree(info);
+error_info:
+	kfree(hotplug_slot);
+error_hp:
+	kfree(slot);
+error:
+	return -ENOMEM;
+}
+
+static int __init init_pci_slots(void)
+{
+	struct zpci_dev *zdev;
+	int device = 0;
+
+	/*
+	 * Create a structure for each slot, and register that slot
+	 * with the pci_hotplug subsystem.
+	 */
+	mutex_lock(&zpci_list_lock);
+	list_for_each_entry(zdev, &zpci_list, entry) {
+		init_pci_slot(zdev);
+		device++;
+	}
+
+	mutex_unlock(&zpci_list_lock);
+	return (device) ? 0 : -ENODEV;
+}
+
+static void exit_pci_slot(struct zpci_dev *zdev)
+{
+	struct list_head *tmp, *n;
+	struct slot *slot;
+
+	list_for_each_safe(tmp, n, &s390_hotplug_slot_list) {
+		slot = list_entry(tmp, struct slot, slot_list);
+		if (slot->zdev != zdev)
+			continue;
+		list_del(&slot->slot_list);
+		pci_hp_deregister(slot->hotplug_slot);
+	}
+}
+
+static void __exit exit_pci_slots(void)
+{
+	struct list_head *tmp, *n;
+	struct slot *slot;
+
+	/*
+	 * Unregister all of our slots with the pci_hotplug subsystem.
+	 * Memory will be freed in release_slot() callback after slot's
+	 * lifespan is finished.
+	 */
+	list_for_each_safe(tmp, n, &s390_hotplug_slot_list) {
+		slot = list_entry(tmp, struct slot, slot_list);
+		list_del(&slot->slot_list);
+		pci_hp_deregister(slot->hotplug_slot);
+	}
+}
+
+static int __init pci_hotplug_s390_init(void)
+{
+	/*
+	 * Do specific initialization stuff for your driver here
+	 * like initializing your controller hardware (if any) and
+	 * determining the number of slots you have in the system
+	 * right now.
+	 */
+
+	if (!pci_probe)
+		return -EOPNOTSUPP;
+
+	/* register callbacks for slot handling from arch code */
+	mutex_lock(&zpci_list_lock);
+	hotplug_ops.create_slot = init_pci_slot;
+	hotplug_ops.remove_slot = exit_pci_slot;
+	mutex_unlock(&zpci_list_lock);
+	pr_info("registered hotplug slot callbacks\n");
+	return init_pci_slots();
+}
+
+static void __exit pci_hotplug_s390_exit(void)
+{
+	exit_pci_slots();
+}
+
+module_init(pci_hotplug_s390_init);
+module_exit(pci_hotplug_s390_exit);

drivers/pci/msi.c

@@ -207,6 +207,8 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 	desc->masked = __msix_mask_irq(desc, flag);
 }
 
+#ifdef CONFIG_GENERIC_HARDIRQS
+
 static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 {
 	struct msi_desc *desc = irq_data_get_msi(data);
@@ -230,6 +232,8 @@ void unmask_msi_irq(struct irq_data *data)
 	msi_set_mask_bit(data, 0);
 }
 
+#endif /* CONFIG_GENERIC_HARDIRQS */
+
 void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
 	BUG_ON(entry->dev->current_state != PCI_D0);
@@ -337,8 +341,10 @@ static void free_msi_irqs(struct pci_dev *dev)
 		if (!entry->irq)
 			continue;
 		nvec = 1 << entry->msi_attrib.multiple;
+#ifdef CONFIG_GENERIC_HARDIRQS
 		for (i = 0; i < nvec; i++)
 			BUG_ON(irq_has_action(entry->irq + i));
+#endif
 	}
 
 	arch_teardown_msi_irqs(dev);

drivers/s390/block/dasd.c

@@ -349,6 +349,16 @@ static int dasd_state_basic_to_ready(struct dasd_device *device)
 	return rc;
 }
 
+static inline
+int _wait_for_empty_queues(struct dasd_device *device)
+{
+	if (device->block)
+		return list_empty(&device->ccw_queue) &&
+			list_empty(&device->block->ccw_queue);
+	else
+		return list_empty(&device->ccw_queue);
+}
+
 /*
  * Remove device from block device layer. Destroy dirty buffers.
  * Forget format information. Check if the target level is basic
@@ -1841,6 +1851,13 @@ static void __dasd_device_check_expire(struct dasd_device *device)
 	cqr = list_entry(device->ccw_queue.next, struct dasd_ccw_req, devlist);
 	if ((cqr->status == DASD_CQR_IN_IO && cqr->expires != 0) &&
 	    (time_after_eq(jiffies, cqr->expires + cqr->starttime))) {
+		if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+			/*
+			 * IO in safe offline processing should not
+			 * run out of retries
+			 */
+			cqr->retries++;
+		}
 		if (device->discipline->term_IO(cqr) != 0) {
 			/* Hmpf, try again in 5 sec */
 			dev_err(&device->cdev->dev,
@@ -3024,11 +3041,11 @@ void dasd_generic_remove(struct ccw_device *cdev)
 
 	cdev->handler = NULL;
 
-	dasd_remove_sysfs_files(cdev);
 	device = dasd_device_from_cdev(cdev);
 	if (IS_ERR(device))
 		return;
-	if (test_and_set_bit(DASD_FLAG_OFFLINE, &device->flags)) {
+	if (test_and_set_bit(DASD_FLAG_OFFLINE, &device->flags) &&
+	    !test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
 		/* Already doing offline processing */
 		dasd_put_device(device);
 		return;
@@ -3048,6 +3065,8 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	 */
 	if (block)
 		dasd_free_block(block);
+
+	dasd_remove_sysfs_files(cdev);
 }
 
 /*
@@ -3126,16 +3145,13 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 {
 	struct dasd_device *device;
 	struct dasd_block *block;
-	int max_count, open_count;
+	int max_count, open_count, rc;
 
+	rc = 0;
 	device = dasd_device_from_cdev(cdev);
 	if (IS_ERR(device))
 		return PTR_ERR(device);
-	if (test_and_set_bit(DASD_FLAG_OFFLINE, &device->flags)) {
-		/* Already doing offline processing */
-		dasd_put_device(device);
-		return 0;
-	}
+
 	/*
 	 * We must make sure that this device is currently not in use.
 	 * The open_count is increased for every opener, that includes
@@ -3159,6 +3175,54 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 			return -EBUSY;
 		}
 	}
+
+	if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+		/*
+		 * safe offline allready running
+		 * could only be called by normal offline so safe_offline flag
+		 * needs to be removed to run normal offline and kill all I/O
+		 */
+		if (test_and_set_bit(DASD_FLAG_OFFLINE, &device->flags)) {
+			/* Already doing normal offline processing */
+			dasd_put_device(device);
+			return -EBUSY;
+		} else
+			clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags);
+
+	} else
+		if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) {
+			/* Already doing offline processing */
+			dasd_put_device(device);
+			return -EBUSY;
+		}
+
+	/*
+	 * if safe_offline called set safe_offline_running flag and
+	 * clear safe_offline so that a call to normal offline
+	 * can overrun safe_offline processing
+	 */
+	if (test_and_clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags) &&
+	    !test_and_set_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+		/*
+		 * If we want to set the device safe offline all IO operations
+		 * should be finished before continuing the offline process
+		 * so sync bdev first and then wait for our queues to become
+		 * empty
+		 */
+		/* sync blockdev and partitions */
+		rc = fsync_bdev(device->block->bdev);
+		if (rc != 0)
+			goto interrupted;
+
+		/* schedule device tasklet and wait for completion */
+		dasd_schedule_device_bh(device);
+		rc = wait_event_interruptible(shutdown_waitq,
+					      _wait_for_empty_queues(device));
+		if (rc != 0)
+			goto interrupted;
+	}
+
+	set_bit(DASD_FLAG_OFFLINE, &device->flags);
 	dasd_set_target_state(device, DASD_STATE_NEW);
 	/* dasd_delete_device destroys the device reference. */
 	block = device->block;
@@ -3170,6 +3234,14 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 	if (block)
 		dasd_free_block(block);
 	return 0;
+
+interrupted:
+	/* interrupted by signal */
+	clear_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags);
+	clear_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags);
+	clear_bit(DASD_FLAG_OFFLINE, &device->flags);
+	dasd_put_device(device);
+	return rc;
 }
 
 int dasd_generic_last_path_gone(struct dasd_device *device)
@@ -3489,15 +3561,6 @@ char *dasd_get_sense(struct irb *irb)
 }
 EXPORT_SYMBOL_GPL(dasd_get_sense);
 
-static inline int _wait_for_empty_queues(struct dasd_device *device)
-{
-	if (device->block)
-		return list_empty(&device->ccw_queue) &&
-			list_empty(&device->block->ccw_queue);
-	else
-		return list_empty(&device->ccw_queue);
-}
-
 void dasd_generic_shutdown(struct ccw_device *cdev)
 {
 	struct dasd_device *device;

drivers/s390/block/dasd_devmap.c

@@ -951,6 +951,39 @@ dasd_use_raw_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(raw_track_access, 0644, dasd_use_raw_show,
 		   dasd_use_raw_store);
 
+static ssize_t
+dasd_safe_offline_store(struct device *dev, struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	struct ccw_device *cdev = to_ccwdev(dev);
+	struct dasd_device *device;
+	int rc;
+
+	device = dasd_device_from_cdev(cdev);
+	if (IS_ERR(device)) {
+		rc = PTR_ERR(device);
+		goto out;
+	}
+
+	if (test_bit(DASD_FLAG_OFFLINE, &device->flags) ||
+	    test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
+		/* Already doing offline processing */
+		dasd_put_device(device);
+		rc = -EBUSY;
+		goto out;
+	}
+
+	set_bit(DASD_FLAG_SAFE_OFFLINE, &device->flags);
+	dasd_put_device(device);
+
+	rc = ccw_device_set_offline(cdev);
+
+out:
+	return rc ? rc : count;
+}
+
+static DEVICE_ATTR(safe_offline, 0200, NULL, dasd_safe_offline_store);
+
 static ssize_t
 dasd_discipline_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
@@ -1320,6 +1353,7 @@ static struct attribute * dasd_attrs[] = {
 	&dev_attr_expires.attr,
 	&dev_attr_reservation_policy.attr,
 	&dev_attr_last_known_reservation_state.attr,
+	&dev_attr_safe_offline.attr,
 	NULL,
 };
 

drivers/s390/block/dasd_eckd.c

@@ -1026,7 +1026,7 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 {
 	void *conf_data;
 	int conf_len, conf_data_saved;
-	int rc;
+	int rc, path_err;
 	__u8 lpm, opm;
 	struct dasd_eckd_private *private, path_private;
 	struct dasd_path *path_data;
@@ -1037,6 +1037,7 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 	path_data = &device->path_data;
 	opm = ccw_device_get_path_mask(device->cdev);
 	conf_data_saved = 0;
+	path_err = 0;
 	/* get configuration data per operational path */
 	for (lpm = 0x80; lpm; lpm>>= 1) {
 		if (!(lpm & opm))
@@ -1122,7 +1123,8 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 					"the same device, path %02X leads to "
 					"device %s instead of %s\n", lpm,
 					print_path_uid, print_device_uid);
-				return -EINVAL;
+				path_err = -EINVAL;
+				continue;
 			}
 
 			path_private.conf_data = NULL;
@@ -1142,7 +1144,7 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 			kfree(conf_data);
 	}
 
-	return 0;
+	return path_err;
 }
 
 static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm)
@@ -3847,7 +3849,7 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page)
 
 	len = 0;
 	while (from <= to) {
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " CCW %p: %08X %08X DAT:",
 			       from, ((int *) from)[0], ((int *) from)[1]);
 
@@ -3908,23 +3910,23 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		return;
 	}
 	/* dump the sense data */
-	len = sprintf(page,  KERN_ERR PRINTK_HEADER
+	len = sprintf(page, PRINTK_HEADER
 		      " I/O status report for device %s:\n",
 		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+	len += sprintf(page + len, PRINTK_HEADER
 		       " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
 		       "CS:%02X RC:%d\n",
 		       req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw),
 		       scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw),
 		       scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw),
 		       req ? req->intrc : 0);
-	len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+	len += sprintf(page + len, PRINTK_HEADER
 		       " device %s: Failing CCW: %p\n",
 		       dev_name(&device->cdev->dev),
 		       (void *) (addr_t) irb->scsw.cmd.cpa);
 	if (irb->esw.esw0.erw.cons) {
 		for (sl = 0; sl < 4; sl++) {
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 				       " Sense(hex) %2d-%2d:",
 				       (8 * sl), ((8 * sl) + 7));
 
@@ -3937,23 +3939,23 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 
 		if (irb->ecw[27] & DASD_SENSE_BIT_0) {
 			/* 24 Byte Sense Data */
-			sprintf(page + len, KERN_ERR PRINTK_HEADER
+			sprintf(page + len, PRINTK_HEADER
 				" 24 Byte: %x MSG %x, "
 				"%s MSGb to SYSOP\n",
 				irb->ecw[7] >> 4, irb->ecw[7] & 0x0f,
 				irb->ecw[1] & 0x10 ? "" : "no");
 		} else {
 			/* 32 Byte Sense Data */
-			sprintf(page + len, KERN_ERR PRINTK_HEADER
+			sprintf(page + len, PRINTK_HEADER
 				" 32 Byte: Format: %x "
 				"Exception class %x\n",
 				irb->ecw[6] & 0x0f, irb->ecw[22] >> 4);
 		}
 	} else {
-		sprintf(page + len, KERN_ERR PRINTK_HEADER
+		sprintf(page + len, PRINTK_HEADER
 			" SORRY - NO VALID SENSE AVAILABLE\n");
 	}
-	printk("%s", page);
+	printk(KERN_ERR "%s", page);
 
 	if (req) {
 		/* req == NULL for unsolicited interrupts */
@@ -3962,10 +3964,10 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		first = req->cpaddr;
 		for (last = first; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
 		to = min(first + 6, last);
-		len = sprintf(page,  KERN_ERR PRINTK_HEADER
+		len = sprintf(page, PRINTK_HEADER
 			      " Related CP in req: %p\n", req);
 		dasd_eckd_dump_ccw_range(first, to, page + len);
-		printk("%s", page);
+		printk(KERN_ERR "%s", page);
 
 		/* print failing CCW area (maximum 4) */
 		/* scsw->cda is either valid or zero  */
@@ -3975,7 +3977,7 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 				irb->scsw.cmd.cpa; /* failing CCW */
 		if (from <  fail - 2) {
 			from = fail - 2;     /* there is a gap - print header */
-			len += sprintf(page, KERN_ERR PRINTK_HEADER "......\n");
+			len += sprintf(page, PRINTK_HEADER "......\n");
 		}
 		to = min(fail + 1, last);
 		len += dasd_eckd_dump_ccw_range(from, to, page + len);
@@ -3984,11 +3986,11 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		from = max(from, ++to);
 		if (from < last - 1) {
 			from = last - 1;     /* there is a gap - print header */
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER "......\n");
+			len += sprintf(page + len, PRINTK_HEADER "......\n");
 		}
 		len += dasd_eckd_dump_ccw_range(from, last, page + len);
 		if (len > 0)
-			printk("%s", page);
+			printk(KERN_ERR "%s", page);
 	}
 	free_page((unsigned long) page);
 }
@@ -4012,10 +4014,10 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		return;
 	}
 	/* dump the sense data */
-	len = sprintf(page,  KERN_ERR PRINTK_HEADER
+	len = sprintf(page, PRINTK_HEADER
 		      " I/O status report for device %s:\n",
 		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+	len += sprintf(page + len, PRINTK_HEADER
 		       " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
 		       "CS:%02X fcxs:%02X schxs:%02X RC:%d\n",
 		       req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw),
@@ -4023,7 +4025,7 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		       scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw),
 		       irb->scsw.tm.fcxs, irb->scsw.tm.schxs,
 		       req ? req->intrc : 0);
-	len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+	len += sprintf(page + len, PRINTK_HEADER
 		       " device %s: Failing TCW: %p\n",
 		       dev_name(&device->cdev->dev),
 		       (void *) (addr_t) irb->scsw.tm.tcw);
@@ -4035,43 +4037,42 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 			(struct tcw *)(unsigned long)irb->scsw.tm.tcw);
 
 	if (tsb) {
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->length %d\n", tsb->length);
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->flags %x\n", tsb->flags);
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->dcw_offset %d\n", tsb->dcw_offset);
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->count %d\n", tsb->count);
 		residual = tsb->count - 28;
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " residual %d\n", residual);
 
 		switch (tsb->flags & 0x07) {
 		case 1:	/* tsa_iostat */
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->tsa.iostat.dev_time %d\n",
 				       tsb->tsa.iostat.dev_time);
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->tsa.iostat.def_time %d\n",
 				       tsb->tsa.iostat.def_time);
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->tsa.iostat.queue_time %d\n",
 				       tsb->tsa.iostat.queue_time);
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->tsa.iostat.dev_busy_time %d\n",
 				       tsb->tsa.iostat.dev_busy_time);
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->tsa.iostat.dev_act_time %d\n",
 				       tsb->tsa.iostat.dev_act_time);
 			sense = tsb->tsa.iostat.sense;
 			break;
 		case 2: /* ts_ddpc */
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 			       " tsb->tsa.ddpc.rc %d\n", tsb->tsa.ddpc.rc);
 			for (sl = 0; sl < 2; sl++) {
-				len += sprintf(page + len,
-					       KERN_ERR PRINTK_HEADER
+				len += sprintf(page + len, PRINTK_HEADER
 					       " tsb->tsa.ddpc.rcq %2d-%2d: ",
 					       (8 * sl), ((8 * sl) + 7));
 				rcq = tsb->tsa.ddpc.rcq;
@@ -4084,15 +4085,14 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 			sense = tsb->tsa.ddpc.sense;
 			break;
 		case 3: /* tsa_intrg */
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
-				      " tsb->tsa.intrg.: not supportet yet \n");
+			len += sprintf(page + len, PRINTK_HEADER
+				      " tsb->tsa.intrg.: not supportet yet\n");
 			break;
 		}
 
 		if (sense) {
 			for (sl = 0; sl < 4; sl++) {
-				len += sprintf(page + len,
-					       KERN_ERR PRINTK_HEADER
+				len += sprintf(page + len, PRINTK_HEADER
 					       " Sense(hex) %2d-%2d:",
 					       (8 * sl), ((8 * sl) + 7));
 				for (sct = 0; sct < 8; sct++) {
@@ -4104,27 +4104,27 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 
 			if (sense[27] & DASD_SENSE_BIT_0) {
 				/* 24 Byte Sense Data */
-				sprintf(page + len, KERN_ERR PRINTK_HEADER
+				sprintf(page + len, PRINTK_HEADER
 					" 24 Byte: %x MSG %x, "
 					"%s MSGb to SYSOP\n",
 					sense[7] >> 4, sense[7] & 0x0f,
 					sense[1] & 0x10 ? "" : "no");
 			} else {
 				/* 32 Byte Sense Data */
-				sprintf(page + len, KERN_ERR PRINTK_HEADER
+				sprintf(page + len, PRINTK_HEADER
 					" 32 Byte: Format: %x "
 					"Exception class %x\n",
 					sense[6] & 0x0f, sense[22] >> 4);
 			}
 		} else {
-			sprintf(page + len, KERN_ERR PRINTK_HEADER
+			sprintf(page + len, PRINTK_HEADER
 				" SORRY - NO VALID SENSE AVAILABLE\n");
 		}
 	} else {
-		sprintf(page + len, KERN_ERR PRINTK_HEADER
+		sprintf(page + len, PRINTK_HEADER
 			" SORRY - NO TSB DATA AVAILABLE\n");
 	}
-	printk("%s", page);
+	printk(KERN_ERR "%s", page);
 	free_page((unsigned long) page);
 }
 
@@ -4161,9 +4161,7 @@ static int dasd_eckd_restore_device(struct dasd_device *device)
 	private = (struct dasd_eckd_private *) device->private;
 
 	/* Read Configuration Data */
-	rc = dasd_eckd_read_conf(device);
-	if (rc)
-		goto out_err;
+	dasd_eckd_read_conf(device);
 
 	dasd_eckd_get_uid(device, &temp_uid);
 	/* Generate device unique id */
@@ -4183,9 +4181,7 @@ static int dasd_eckd_restore_device(struct dasd_device *device)
 	dasd_eckd_validate_server(device, DASD_CQR_FLAGS_FAILFAST);
 
 	/* RE-Read Configuration Data */
-	rc = dasd_eckd_read_conf(device);
-	if (rc)
-		goto out_err;
+	dasd_eckd_read_conf(device);
 
 	/* Read Feature Codes */
 	dasd_eckd_read_features(device);

drivers/s390/block/dasd_fba.c

@@ -479,19 +479,19 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 			    "No memory to dump sense data");
 		return;
 	}
-	len = sprintf(page, KERN_ERR PRINTK_HEADER
+	len = sprintf(page, PRINTK_HEADER
 		      " I/O status report for device %s:\n",
 		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+	len += sprintf(page + len, PRINTK_HEADER
 		       " in req: %p CS: 0x%02X DS: 0x%02X\n", req,
 		       irb->scsw.cmd.cstat, irb->scsw.cmd.dstat);
-	len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+	len += sprintf(page + len, PRINTK_HEADER
 		       " device %s: Failing CCW: %p\n",
 		       dev_name(&device->cdev->dev),
 		       (void *) (addr_t) irb->scsw.cmd.cpa);
 	if (irb->esw.esw0.erw.cons) {
 		for (sl = 0; sl < 4; sl++) {
-			len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+			len += sprintf(page + len, PRINTK_HEADER
 				       " Sense(hex) %2d-%2d:",
 				       (8 * sl), ((8 * sl) + 7));
 
@@ -502,7 +502,7 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 			len += sprintf(page + len, "\n");
 		}
 	} else {
-	        len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " SORRY - NO VALID SENSE AVAILABLE\n");
 	}
 	printk(KERN_ERR "%s", page);
@@ -512,10 +512,9 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 	act = req->cpaddr;
         for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
 	end = min(act + 8, last);
-	len = sprintf(page, KERN_ERR PRINTK_HEADER
-		      " Related CP in req: %p\n", req);
+	len = sprintf(page, PRINTK_HEADER " Related CP in req: %p\n", req);
 	while (act <= end) {
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " CCW %p: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
@@ -533,11 +532,11 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 	len = 0;
 	if (act <  ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2) {
 		act = ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2;
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER "......\n");
+		len += sprintf(page + len, PRINTK_HEADER "......\n");
 	}
 	end = min((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa + 2, last);
 	while (act <= end) {
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " CCW %p: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
@@ -552,10 +551,10 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 	/* print last CCWs */
 	if (act <  last - 2) {
 		act = last - 2;
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER "......\n");
+		len += sprintf(page + len, PRINTK_HEADER "......\n");
 	}
 	while (act <= last) {
-		len += sprintf(page + len, KERN_ERR PRINTK_HEADER
+		len += sprintf(page + len, PRINTK_HEADER
 			       " CCW %p: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;

drivers/s390/block/dasd_int.h

@@ -516,6 +516,8 @@ struct dasd_block {
 #define DASD_FLAG_IS_RESERVED	7	/* The device is reserved */
 #define DASD_FLAG_LOCK_STOLEN	8	/* The device lock was stolen */
 #define DASD_FLAG_SUSPENDED	9	/* The device was suspended */
+#define DASD_FLAG_SAFE_OFFLINE	10	/* safe offline processing requested*/
+#define DASD_FLAG_SAFE_OFFLINE_RUNNING	11	/* safe offline running */
 
 
 void dasd_put_device_wake(struct dasd_device *);

drivers/s390/block/dasd_ioctl.c

@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 #include <asm/compat.h>
 #include <asm/ccwdev.h>
+#include <asm/schid.h>
 #include <asm/cmb.h>
 #include <asm/uaccess.h>
 
@@ -308,11 +309,12 @@ static int dasd_ioctl_information(struct dasd_block *block,
 				  unsigned int cmd, void __user *argp)
 {
 	struct dasd_information2_t *dasd_info;
-	unsigned long flags;
-	int rc;
+	struct subchannel_id sch_id;
+	struct ccw_dev_id dev_id;
 	struct dasd_device *base;
 	struct ccw_device *cdev;
-	struct ccw_dev_id dev_id;
+	unsigned long flags;
+	int rc;
 
 	base = block->base;
 	if (!base->discipline || !base->discipline->fill_info)
@@ -330,9 +332,10 @@ static int dasd_ioctl_information(struct dasd_block *block,
 
 	cdev = base->cdev;
 	ccw_device_get_id(cdev, &dev_id);
+	ccw_device_get_schid(cdev, &sch_id);
 
 	dasd_info->devno = dev_id.devno;
-	dasd_info->schid = _ccw_device_get_subchannel_number(base->cdev);
+	dasd_info->schid = sch_id.sch_no;
 	dasd_info->cu_type = cdev->id.cu_type;
 	dasd_info->cu_model = cdev->id.cu_model;
 	dasd_info->dev_type = cdev->id.dev_type;

drivers/s390/char/sclp.h

@@ -1,5 +1,5 @@
 /*
- * Copyright IBM Corp. 1999, 2009
+ * Copyright IBM Corp. 1999,2012
  *
  * Author(s): Martin Peschke <mpeschke@de.ibm.com>
  *	      Martin Schwidefsky <schwidefsky@de.ibm.com>
@@ -103,6 +103,7 @@ extern u64 sclp_facilities;
 #define SCLP_HAS_CHP_RECONFIG	(sclp_facilities & 0x2000000000000000ULL)
 #define SCLP_HAS_CPU_INFO	(sclp_facilities & 0x0800000000000000ULL)
 #define SCLP_HAS_CPU_RECONFIG	(sclp_facilities & 0x0400000000000000ULL)
+#define SCLP_HAS_PCI_RECONFIG	(sclp_facilities & 0x0000000040000000ULL)
 
 
 struct gds_subvector {

drivers/s390/char/sclp_cmd.c

@@ -1,5 +1,5 @@
 /*
- * Copyright IBM Corp. 2007, 2009
+ * Copyright IBM Corp. 2007,2012
  *
  * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
  *	      Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/mm.h>
@@ -19,10 +20,11 @@
 #include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <asm/ctl_reg.h>
 #include <asm/chpid.h>
-#include <asm/sclp.h>
 #include <asm/setup.h>
-#include <asm/ctl_reg.h>
+#include <asm/page.h>
+#include <asm/sclp.h>
 
 #include "sclp.h"
 
@@ -400,17 +402,15 @@ out:
 
 static int sclp_assign_storage(u16 rn)
 {
-	unsigned long long start, address;
+	unsigned long long start;
 	int rc;
 
 	rc = do_assign_storage(0x000d0001, rn);
 	if (rc)
-		goto out;
-	start = address = rn2addr(rn);
-	for (; address < start + rzm; address += PAGE_SIZE)
-		page_set_storage_key(address, PAGE_DEFAULT_KEY, 0);
-out:
-	return rc;
+		return rc;
+	start = rn2addr(rn);
+	storage_key_init_range(start, start + rzm);
+	return 0;
 }
 
 static int sclp_unassign_storage(u16 rn)
@@ -701,6 +701,67 @@ __initcall(sclp_detect_standby_memory);
 
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+/*
+ * PCI I/O adapter configuration related functions.
+ */
+#define SCLP_CMDW_CONFIGURE_PCI			0x001a0001
+#define SCLP_CMDW_DECONFIGURE_PCI		0x001b0001
+
+#define SCLP_RECONFIG_PCI_ATPYE			2
+
+struct pci_cfg_sccb {
+	struct sccb_header header;
+	u8 atype;		/* adapter type */
+	u8 reserved1;
+	u16 reserved2;
+	u32 aid;		/* adapter identifier */
+} __packed;
+
+static int do_pci_configure(sclp_cmdw_t cmd, u32 fid)
+{
+	struct pci_cfg_sccb *sccb;
+	int rc;
+
+	if (!SCLP_HAS_PCI_RECONFIG)
+		return -EOPNOTSUPP;
+
+	sccb = (struct pci_cfg_sccb *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!sccb)
+		return -ENOMEM;
+
+	sccb->header.length = PAGE_SIZE;
+	sccb->atype = SCLP_RECONFIG_PCI_ATPYE;
+	sccb->aid = fid;
+	rc = do_sync_request(cmd, sccb);
+	if (rc)
+		goto out;
+	switch (sccb->header.response_code) {
+	case 0x0020:
+	case 0x0120:
+		break;
+	default:
+		pr_warn("configure PCI I/O adapter failed: cmd=0x%08x  response=0x%04x\n",
+			cmd, sccb->header.response_code);
+		rc = -EIO;
+		break;
+	}
+out:
+	free_page((unsigned long) sccb);
+	return rc;
+}
+
+int sclp_pci_configure(u32 fid)
+{
+	return do_pci_configure(SCLP_CMDW_CONFIGURE_PCI, fid);
+}
+EXPORT_SYMBOL(sclp_pci_configure);
+
+int sclp_pci_deconfigure(u32 fid)
+{
+	return do_pci_configure(SCLP_CMDW_DECONFIGURE_PCI, fid);
+}
+EXPORT_SYMBOL(sclp_pci_deconfigure);
+
 /*
  * Channel path configuration related functions.
  */

drivers/s390/cio/ccwgroup.c

@@ -65,10 +65,18 @@ static void __ccwgroup_remove_cdev_refs(struct ccwgroup_device *gdev)
 	}
 }
 
-static int ccwgroup_set_online(struct ccwgroup_device *gdev)
+/**
+ * ccwgroup_set_online() - enable a ccwgroup device
+ * @gdev: target ccwgroup device
+ *
+ * This function attempts to put the ccwgroup device into the online state.
+ * Returns:
+ *  %0 on success and a negative error value on failure.
+ */
+int ccwgroup_set_online(struct ccwgroup_device *gdev)
 {
 	struct ccwgroup_driver *gdrv = to_ccwgroupdrv(gdev->dev.driver);
-	int ret = 0;
+	int ret = -EINVAL;
 
 	if (atomic_cmpxchg(&gdev->onoff, 0, 1) != 0)
 		return -EAGAIN;
@@ -84,11 +92,20 @@ out:
 	atomic_set(&gdev->onoff, 0);
 	return ret;
 }
+EXPORT_SYMBOL(ccwgroup_set_online);
 
-static int ccwgroup_set_offline(struct ccwgroup_device *gdev)
+/**
+ * ccwgroup_set_offline() - disable a ccwgroup device
+ * @gdev: target ccwgroup device
+ *
+ * This function attempts to put the ccwgroup device into the offline state.
+ * Returns:
+ *  %0 on success and a negative error value on failure.
+ */
+int ccwgroup_set_offline(struct ccwgroup_device *gdev)
 {
 	struct ccwgroup_driver *gdrv = to_ccwgroupdrv(gdev->dev.driver);
-	int ret = 0;
+	int ret = -EINVAL;
 
 	if (atomic_cmpxchg(&gdev->onoff, 0, 1) != 0)
 		return -EAGAIN;
@@ -104,6 +121,7 @@ out:
 	atomic_set(&gdev->onoff, 0);
 	return ret;
 }
+EXPORT_SYMBOL(ccwgroup_set_offline);
 
 static ssize_t ccwgroup_online_store(struct device *dev,
 				     struct device_attribute *attr,

drivers/s390/cio/chsc.c

@@ -1,7 +1,7 @@
 /*
  *   S/390 common I/O routines -- channel subsystem call
  *
- *    Copyright IBM Corp. 1999, 2010
+ *    Copyright IBM Corp. 1999,2012
  *    Author(s): Ingo Adlung (adlung@de.ibm.com)
  *		 Cornelia Huck (cornelia.huck@de.ibm.com)
  *		 Arnd Bergmann (arndb@de.ibm.com)
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/pci.h>
 
 #include <asm/cio.h>
 #include <asm/chpid.h>
@@ -260,26 +261,45 @@ __get_chpid_from_lir(void *data)
 	return (u16) (lir->indesc[0]&0x000000ff);
 }
 
-struct chsc_sei_area {
-	struct chsc_header request;
+struct chsc_sei_nt0_area {
+	u8  flags;
+	u8  vf;				/* validity flags */
+	u8  rs;				/* reporting source */
+	u8  cc;				/* content code */
+	u16 fla;			/* full link address */
+	u16 rsid;			/* reporting source id */
 	u32 reserved1;
 	u32 reserved2;
-	u32 reserved3;
-	struct chsc_header response;
-	u32 reserved4;
-	u8  flags;
-	u8  vf;		/* validity flags */
-	u8  rs;		/* reporting source */
-	u8  cc;		/* content code */
-	u16 fla;	/* full link address */
-	u16 rsid;	/* reporting source id */
-	u32 reserved5;
-	u32 reserved6;
-	u8 ccdf[4096 - 16 - 24];	/* content-code dependent field */
 	/* ccdf has to be big enough for a link-incident record */
-} __attribute__ ((packed));
-
-static void chsc_process_sei_link_incident(struct chsc_sei_area *sei_area)
+	u8  ccdf[PAGE_SIZE - 24 - 16];	/* content-code dependent field */
+} __packed;
+
+struct chsc_sei_nt2_area {
+	u8  flags;			/* p and v bit */
+	u8  reserved1;
+	u8  reserved2;
+	u8  cc;				/* content code */
+	u32 reserved3[13];
+	u8  ccdf[PAGE_SIZE - 24 - 56];	/* content-code dependent field */
+} __packed;
+
+#define CHSC_SEI_NT0	0ULL
+#define CHSC_SEI_NT2	(1ULL << 61)
+
+struct chsc_sei {
+	struct chsc_header request;
+	u32 reserved1;
+	u64 ntsm;			/* notification type mask */
+	struct chsc_header response;
+	u32 reserved2;
+	union {
+		struct chsc_sei_nt0_area nt0_area;
+		struct chsc_sei_nt2_area nt2_area;
+		u8 nt_area[PAGE_SIZE - 24];
+	} u;
+} __packed;
+
+static void chsc_process_sei_link_incident(struct chsc_sei_nt0_area *sei_area)
 {
 	struct chp_id chpid;
 	int id;
@@ -298,7 +318,7 @@ static void chsc_process_sei_link_incident(struct chsc_sei_area *sei_area)
 	}
 }
 
-static void chsc_process_sei_res_acc(struct chsc_sei_area *sei_area)
+static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
 {
 	struct chp_link link;
 	struct chp_id chpid;
@@ -330,7 +350,7 @@ static void chsc_process_sei_res_acc(struct chsc_sei_area *sei_area)
 	s390_process_res_acc(&link);
 }
 
-static void chsc_process_sei_chp_avail(struct chsc_sei_area *sei_area)
+static void chsc_process_sei_chp_avail(struct chsc_sei_nt0_area *sei_area)
 {
 	struct channel_path *chp;
 	struct chp_id chpid;
@@ -366,7 +386,7 @@ struct chp_config_data {
 	u8 pc;
 };
 
-static void chsc_process_sei_chp_config(struct chsc_sei_area *sei_area)
+static void chsc_process_sei_chp_config(struct chsc_sei_nt0_area *sei_area)
 {
 	struct chp_config_data *data;
 	struct chp_id chpid;
@@ -398,7 +418,7 @@ static void chsc_process_sei_chp_config(struct chsc_sei_area *sei_area)
 	}
 }
 
-static void chsc_process_sei_scm_change(struct chsc_sei_area *sei_area)
+static void chsc_process_sei_scm_change(struct chsc_sei_nt0_area *sei_area)
 {
 	int ret;
 
@@ -412,13 +432,26 @@ static void chsc_process_sei_scm_change(struct chsc_sei_area *sei_area)
 			      " failed (rc=%d).\n", ret);
 }
 
-static void chsc_process_sei(struct chsc_sei_area *sei_area)
+static void chsc_process_sei_nt2(struct chsc_sei_nt2_area *sei_area)
 {
-	/* Check if we might have lost some information. */
-	if (sei_area->flags & 0x40) {
-		CIO_CRW_EVENT(2, "chsc: event overflow\n");
-		css_schedule_eval_all();
+#ifdef CONFIG_PCI
+	switch (sei_area->cc) {
+	case 1:
+		zpci_event_error(sei_area->ccdf);
+		break;
+	case 2:
+		zpci_event_availability(sei_area->ccdf);
+		break;
+	default:
+		CIO_CRW_EVENT(2, "chsc: unhandled sei content code %d\n",
+			      sei_area->cc);
+		break;
 	}
+#endif
+}
+
+static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
+{
 	/* which kind of information was stored? */
 	switch (sei_area->cc) {
 	case 1: /* link incident*/
@@ -443,9 +476,51 @@ static void chsc_process_sei(struct chsc_sei_area *sei_area)
 	}
 }
 
+static int __chsc_process_crw(struct chsc_sei *sei, u64 ntsm)
+{
+	do {
+		memset(sei, 0, sizeof(*sei));
+		sei->request.length = 0x0010;
+		sei->request.code = 0x000e;
+		sei->ntsm = ntsm;
+
+		if (chsc(sei))
+			break;
+
+		if (sei->response.code == 0x0001) {
+			CIO_CRW_EVENT(2, "chsc: sei successful\n");
+
+			/* Check if we might have lost some information. */
+			if (sei->u.nt0_area.flags & 0x40) {
+				CIO_CRW_EVENT(2, "chsc: event overflow\n");
+				css_schedule_eval_all();
+			}
+
+			switch (sei->ntsm) {
+			case CHSC_SEI_NT0:
+				chsc_process_sei_nt0(&sei->u.nt0_area);
+				return 1;
+			case CHSC_SEI_NT2:
+				chsc_process_sei_nt2(&sei->u.nt2_area);
+				return 1;
+			default:
+				CIO_CRW_EVENT(2, "chsc: unhandled nt (nt=%08Lx)\n",
+					      sei->ntsm);
+				return 0;
+			}
+		} else {
+			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
+				      sei->response.code);
+			break;
+		}
+	} while (sei->u.nt0_area.flags & 0x80);
+
+	return 0;
+}
+
 static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow)
 {
-	struct chsc_sei_area *sei_area;
+	struct chsc_sei *sei;
 
 	if (overflow) {
 		css_schedule_eval_all();
@@ -459,25 +534,18 @@ static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow)
 		return;
 	/* Access to sei_page is serialized through machine check handler
 	 * thread, so no need for locking. */
-	sei_area = sei_page;
+	sei = sei_page;
 
 	CIO_TRACE_EVENT(2, "prcss");
-	do {
-		memset(sei_area, 0, sizeof(*sei_area));
-		sei_area->request.length = 0x0010;
-		sei_area->request.code = 0x000e;
-		if (chsc(sei_area))
-			break;
 
-		if (sei_area->response.code == 0x0001) {
-			CIO_CRW_EVENT(4, "chsc: sei successful\n");
-			chsc_process_sei(sei_area);
-		} else {
-			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
-				      sei_area->response.code);
-			break;
-		}
-	} while (sei_area->flags & 0x80);
+	/*
+	 * The ntsm does not allow to select NT0 and NT2 together. We need to
+	 * first check for NT2, than additionally for NT0...
+	 */
+#ifdef CONFIG_PCI
+	if (!__chsc_process_crw(sei, CHSC_SEI_NT2))
+#endif
+		__chsc_process_crw(sei, CHSC_SEI_NT0);
 }
 
 void chsc_chp_online(struct chp_id chpid)

drivers/s390/cio/device.c

@@ -2036,16 +2036,6 @@ void ccw_driver_unregister(struct ccw_driver *cdriver)
 	driver_unregister(&cdriver->driver);
 }
 
-/* Helper func for qdio. */
-struct subchannel_id
-ccw_device_get_subchannel_id(struct ccw_device *cdev)
-{
-	struct subchannel *sch;
-
-	sch = to_subchannel(cdev->dev.parent);
-	return sch->schid;
-}
-
 static void ccw_device_todo(struct work_struct *work)
 {
 	struct ccw_device_private *priv;
@@ -2138,4 +2128,3 @@ EXPORT_SYMBOL(ccw_device_set_offline);
 EXPORT_SYMBOL(ccw_driver_register);
 EXPORT_SYMBOL(ccw_driver_unregister);
 EXPORT_SYMBOL(get_ccwdev_by_busid);
-EXPORT_SYMBOL_GPL(ccw_device_get_subchannel_id);

drivers/s390/cio/device.h

@@ -142,9 +142,7 @@ int ccw_device_notify(struct ccw_device *, int);
 void ccw_device_set_disconnected(struct ccw_device *cdev);
 void ccw_device_set_notoper(struct ccw_device *cdev);
 
-/* qdio needs this. */
 void ccw_device_set_timeout(struct ccw_device *, int);
-extern struct subchannel_id ccw_device_get_subchannel_id(struct ccw_device *);
 
 /* Channel measurement facility related */
 void retry_set_schib(struct ccw_device *cdev);

drivers/s390/cio/device_ops.c

@@ -755,14 +755,18 @@ int ccw_device_tm_intrg(struct ccw_device *cdev)
 }
 EXPORT_SYMBOL(ccw_device_tm_intrg);
 
-// FIXME: these have to go:
-
-int
-_ccw_device_get_subchannel_number(struct ccw_device *cdev)
+/**
+ * ccw_device_get_schid - obtain a subchannel id
+ * @cdev: device to obtain the id for
+ * @schid: where to fill in the values
+ */
+void ccw_device_get_schid(struct ccw_device *cdev, struct subchannel_id *schid)
 {
-	return cdev->private->schid.sch_no;
-}
+	struct subchannel *sch = to_subchannel(cdev->dev.parent);
 
+	*schid = sch->schid;
+}
+EXPORT_SYMBOL_GPL(ccw_device_get_schid);
 
 MODULE_LICENSE("GPL");
 EXPORT_SYMBOL(ccw_device_set_options_mask);
@@ -777,5 +781,4 @@ EXPORT_SYMBOL(ccw_device_start_timeout_key);
 EXPORT_SYMBOL(ccw_device_start_key);
 EXPORT_SYMBOL(ccw_device_get_ciw);
 EXPORT_SYMBOL(ccw_device_get_path_mask);
-EXPORT_SYMBOL(_ccw_device_get_subchannel_number);
 EXPORT_SYMBOL_GPL(ccw_device_get_chp_desc);

drivers/s390/cio/device_pgid.c

@@ -234,7 +234,7 @@ static int pgid_cmp(struct pgid *p1, struct pgid *p2)
  * Determine pathgroup state from PGID data.
  */
 static void pgid_analyze(struct ccw_device *cdev, struct pgid **p,
-			 int *mismatch, int *reserved, u8 *reset)
+			 int *mismatch, u8 *reserved, u8 *reset)
 {
 	struct pgid *pgid = &cdev->private->pgid[0];
 	struct pgid *first = NULL;
@@ -248,7 +248,7 @@ static void pgid_analyze(struct ccw_device *cdev, struct pgid **p,
 		if ((cdev->private->pgid_valid_mask & lpm) == 0)
 			continue;
 		if (pgid->inf.ps.state2 == SNID_STATE2_RESVD_ELSE)
-			*reserved = 1;
+			*reserved |= lpm;
 		if (pgid_is_reset(pgid)) {
 			*reset |= lpm;
 			continue;
@@ -316,14 +316,14 @@ static void snid_done(struct ccw_device *cdev, int rc)
 	struct subchannel *sch = to_subchannel(cdev->dev.parent);
 	struct pgid *pgid;
 	int mismatch = 0;
-	int reserved = 0;
+	u8 reserved = 0;
 	u8 reset = 0;
 	u8 donepm;
 
 	if (rc)
 		goto out;
 	pgid_analyze(cdev, &pgid, &mismatch, &reserved, &reset);
-	if (reserved)
+	if (reserved == cdev->private->pgid_valid_mask)
 		rc = -EUSERS;
 	else if (mismatch)
 		rc = -EOPNOTSUPP;
@@ -336,7 +336,7 @@ static void snid_done(struct ccw_device *cdev, int rc)
 	}
 out:
 	CIO_MSG_EVENT(2, "snid: device 0.%x.%04x: rc=%d pvm=%02x vpm=%02x "
-		      "todo=%02x mism=%d rsvd=%d reset=%02x\n", id->ssid,
+		      "todo=%02x mism=%d rsvd=%02x reset=%02x\n", id->ssid,
 		      id->devno, rc, cdev->private->pgid_valid_mask, sch->vpm,
 		      cdev->private->pgid_todo_mask, mismatch, reserved, reset);
 	switch (rc) {

drivers/s390/cio/qdio_main.c

@@ -129,7 +129,6 @@ static int qdio_do_eqbs(struct qdio_q *q, unsigned char *state,
 	int rc, tmp_count = count, tmp_start = start, nr = q->nr, retried = 0;
 	unsigned int ccq = 0;
 
-	BUG_ON(!q->irq_ptr->sch_token);
 	qperf_inc(q, eqbs);
 
 	if (!q->is_input_q)
@@ -147,7 +146,6 @@ again:
 	}
 
 	if (rc == 2) {
-		BUG_ON(tmp_count == count);
 		qperf_inc(q, eqbs_partial);
 		DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS part:%02x",
 			tmp_count);
@@ -189,8 +187,6 @@ static int qdio_do_sqbs(struct qdio_q *q, unsigned char state, int start,
 
 	if (!count)
 		return 0;
-
-	BUG_ON(!q->irq_ptr->sch_token);
 	qperf_inc(q, sqbs);
 
 	if (!q->is_input_q)
@@ -199,7 +195,7 @@ again:
 	ccq = do_sqbs(q->irq_ptr->sch_token, state, nr, &tmp_start, &tmp_count);
 	rc = qdio_check_ccq(q, ccq);
 	if (!rc) {
-		WARN_ON(tmp_count);
+		WARN_ON_ONCE(tmp_count);
 		return count - tmp_count;
 	}
 
@@ -224,9 +220,6 @@ static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
 	unsigned char __state = 0;
 	int i;
 
-	BUG_ON(bufnr > QDIO_MAX_BUFFERS_MASK);
-	BUG_ON(count > QDIO_MAX_BUFFERS_PER_Q);
-
 	if (is_qebsm(q))
 		return qdio_do_eqbs(q, state, bufnr, count, auto_ack);
 
@@ -258,9 +251,6 @@ static inline int set_buf_states(struct qdio_q *q, int bufnr,
 {
 	int i;
 
-	BUG_ON(bufnr > QDIO_MAX_BUFFERS_MASK);
-	BUG_ON(count > QDIO_MAX_BUFFERS_PER_Q);
-
 	if (is_qebsm(q))
 		return qdio_do_sqbs(q, state, bufnr, count);
 
@@ -345,7 +335,6 @@ again:
 
 	/* hipersocket busy condition */
 	if (unlikely(*busy_bit)) {
-		WARN_ON(queue_type(q) != QDIO_IQDIO_QFMT || cc != 2);
 		retries++;
 
 		if (!start_time) {
@@ -559,7 +548,7 @@ static int get_inbound_buffer_frontier(struct qdio_q *q)
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in nop");
 		break;
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 out:
 	return q->first_to_check;
@@ -678,12 +667,10 @@ static inline void qdio_handle_aobs(struct qdio_q *q, int start, int count)
 			if (aob == NULL)
 				continue;
 
-			BUG_ON(q->u.out.sbal_state == NULL);
 			q->u.out.sbal_state[b].flags |=
 				QDIO_OUTBUF_STATE_FLAG_PENDING;
 			q->u.out.aobs[b] = NULL;
 		} else if (state == SLSB_P_OUTPUT_EMPTY) {
-			BUG_ON(q->u.out.sbal_state == NULL);
 			q->u.out.sbal_state[b].aob = NULL;
 		}
 		b = next_buf(b);
@@ -703,12 +690,11 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 		q->aobs[bufnr] = aob;
 	}
 	if (q->aobs[bufnr]) {
-		BUG_ON(q->sbal_state == NULL);
 		q->sbal_state[bufnr].flags = QDIO_OUTBUF_STATE_FLAG_NONE;
 		q->sbal_state[bufnr].aob = q->aobs[bufnr];
 		q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
 		phys_aob = virt_to_phys(q->aobs[bufnr]);
-		BUG_ON(phys_aob & 0xFF);
+		WARN_ON_ONCE(phys_aob & 0xFF);
 	}
 
 out:
@@ -809,8 +795,6 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 		goto out;
 
 	switch (state) {
-	case SLSB_P_OUTPUT_PENDING:
-		BUG();
 	case SLSB_P_OUTPUT_EMPTY:
 		/* the adapter got it */
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr,
@@ -840,7 +824,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 	case SLSB_P_OUTPUT_HALTED:
 		break;
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 
 out:
@@ -912,7 +896,7 @@ retry:
 static void __qdio_outbound_processing(struct qdio_q *q)
 {
 	qperf_inc(q, tasklet_outbound);
-	BUG_ON(atomic_read(&q->nr_buf_used) < 0);
+	WARN_ON_ONCE(atomic_read(&q->nr_buf_used) < 0);
 
 	if (qdio_outbound_q_moved(q))
 		qdio_kick_handler(q);
@@ -1138,16 +1122,10 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 		irq_ptr->perf_stat.qdio_int++;
 
 	if (IS_ERR(irb)) {
-		switch (PTR_ERR(irb)) {
-		case -EIO:
-			DBF_ERROR("%4x IO error", irq_ptr->schid.sch_no);
-			qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR);
-			wake_up(&cdev->private->wait_q);
-			return;
-		default:
-			WARN_ON(1);
-			return;
-		}
+		DBF_ERROR("%4x IO error", irq_ptr->schid.sch_no);
+		qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR);
+		wake_up(&cdev->private->wait_q);
+		return;
 	}
 	qdio_irq_check_sense(irq_ptr, irb);
 	cstat = irb->scsw.cmd.cstat;
@@ -1173,7 +1151,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 	case QDIO_IRQ_STATE_STOPPED:
 		break;
 	default:
-		WARN_ON(1);
+		WARN_ON_ONCE(1);
 	}
 	wake_up(&cdev->private->wait_q);
 }
@@ -1227,7 +1205,7 @@ int qdio_shutdown(struct ccw_device *cdev, int how)
 	if (!irq_ptr)
 		return -ENODEV;
 
-	BUG_ON(irqs_disabled());
+	WARN_ON_ONCE(irqs_disabled());
 	DBF_EVENT("qshutdown:%4x", cdev->private->schid.sch_no);
 
 	mutex_lock(&irq_ptr->setup_mutex);
@@ -1358,7 +1336,6 @@ int qdio_allocate(struct qdio_initialize *init_data)
 	irq_ptr->qdr = (struct qdr *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 	if (!irq_ptr->qdr)
 		goto out_rel;
-	WARN_ON((unsigned long)irq_ptr->qdr & 0xfff);
 
 	if (qdio_allocate_qs(irq_ptr, init_data->no_input_qs,
 			     init_data->no_output_qs))
@@ -1597,9 +1574,7 @@ static int handle_inbound(struct qdio_q *q, unsigned int callflags,
 
 set:
 	count = set_buf_states(q, bufnr, SLSB_CU_INPUT_EMPTY, count);
-
 	used = atomic_add_return(count, &q->nr_buf_used) - count;
-	BUG_ON(used + count > QDIO_MAX_BUFFERS_PER_Q);
 
 	if (need_siga_in(q))
 		return qdio_siga_input(q);
@@ -1624,7 +1599,6 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags,
 
 	count = set_buf_states(q, bufnr, SLSB_CU_OUTPUT_PRIMED, count);
 	used = atomic_add_return(count, &q->nr_buf_used);
-	BUG_ON(used > QDIO_MAX_BUFFERS_PER_Q);
 
 	if (used == QDIO_MAX_BUFFERS_PER_Q)
 		qperf_inc(q, outbound_queue_full);
@@ -1678,7 +1652,6 @@ int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
 {
 	struct qdio_irq *irq_ptr;
 
-
 	if (bufnr >= QDIO_MAX_BUFFERS_PER_Q || count > QDIO_MAX_BUFFERS_PER_Q)
 		return -EINVAL;
 
@@ -1721,8 +1694,6 @@ int qdio_start_irq(struct ccw_device *cdev, int nr)
 		return -ENODEV;
 	q = irq_ptr->input_qs[nr];
 
-	WARN_ON(queue_irqs_enabled(q));
-
 	clear_nonshared_ind(irq_ptr);
 	qdio_stop_polling(q);
 	clear_bit(QDIO_QUEUE_IRQS_DISABLED, &q->u.in.queue_irq_state);
@@ -1769,7 +1740,6 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr,
 	if (!irq_ptr)
 		return -ENODEV;
 	q = irq_ptr->input_qs[nr];
-	WARN_ON(queue_irqs_enabled(q));
 
 	/*
 	 * Cannot rely on automatic sync after interrupt since queues may

drivers/s390/cio/qdio_setup.c

@@ -140,10 +140,8 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
 	q->sl = (struct sl *)((char *)q->slib + PAGE_SIZE / 2);
 
 	/* fill in sbal */
-	for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++) {
+	for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++)
 		q->sbal[j] = *sbals_array++;
-		BUG_ON((unsigned long)q->sbal[j] & 0xff);
-	}
 
 	/* fill in slib */
 	if (i > 0) {
@@ -434,9 +432,8 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 	irq_ptr->int_parm = init_data->int_parm;
 	irq_ptr->nr_input_qs = init_data->no_input_qs;
 	irq_ptr->nr_output_qs = init_data->no_output_qs;
-
-	irq_ptr->schid = ccw_device_get_subchannel_id(init_data->cdev);
 	irq_ptr->cdev = init_data->cdev;
+	ccw_device_get_schid(irq_ptr->cdev, &irq_ptr->schid);
 	setup_queues(irq_ptr, init_data);
 
 	setup_qib(irq_ptr, init_data);
@@ -483,7 +480,7 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
 	char s[80];
 
 	snprintf(s, 80, "qdio: %s %s on SC %x using "
-		 "AI:%d QEBSM:%d PCI:%d TDD:%d SIGA:%s%s%s%s%s\n",
+		 "AI:%d QEBSM:%d PRI:%d TDD:%d SIGA:%s%s%s%s%s\n",
 		 dev_name(&cdev->dev),
 		 (irq_ptr->qib.qfmt == QDIO_QETH_QFMT) ? "OSA" :
 			((irq_ptr->qib.qfmt == QDIO_ZFCP_QFMT) ? "ZFCP" : "HS"),

drivers/s390/cio/qdio_thinint.c

@@ -73,7 +73,6 @@ static void put_indicator(u32 *addr)
 void tiqdio_add_input_queues(struct qdio_irq *irq_ptr)
 {
 	mutex_lock(&tiq_list_lock);
-	BUG_ON(irq_ptr->nr_input_qs < 1);
 	list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list);
 	mutex_unlock(&tiq_list_lock);
 	xchg(irq_ptr->dsci, 1 << 7);
@@ -83,7 +82,6 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
 {
 	struct qdio_q *q;
 
-	BUG_ON(irq_ptr->nr_input_qs < 1);
 	q = irq_ptr->input_qs[0];
 	/* if establish triggered an error */
 	if (!q || !q->entry.prev || !q->entry.next)

drivers/s390/crypto/zcrypt_msgtype50.c

@@ -241,84 +241,70 @@ static int ICACRT_msg_to_type50CRT_msg(struct zcrypt_device *zdev,
 				       struct ap_message *ap_msg,
 				       struct ica_rsa_modexpo_crt *crt)
 {
-	int mod_len, short_len, long_len, long_offset, limit;
+	int mod_len, short_len;
 	unsigned char *p, *q, *dp, *dq, *u, *inp;
 
 	mod_len = crt->inputdatalength;
 	short_len = mod_len / 2;
-	long_len = mod_len / 2 + 8;
 
 	/*
-	 * CEX2A cannot handle p, dp, or U > 128 bytes.
-	 * If we have one of these, we need to do extra checking.
-	 * For CEX3A the limit is 256 bytes.
+	 * CEX2A and CEX3A w/o FW update can handle requests up to
+	 * 256 byte modulus (2k keys).
+	 * CEX3A with FW update and CEX4A cards are able to handle
+	 * 512 byte modulus (4k keys).
 	 */
-	if (zdev->max_mod_size == CEX3A_MAX_MOD_SIZE)
-		limit = 256;
-	else
-		limit = 128;
-
-	if (long_len > limit) {
-		/*
-		 * zcrypt_rsa_crt already checked for the leading
-		 * zeroes of np_prime, bp_key and u_mult_inc.
-		 */
-		long_offset = long_len - limit;
-		long_len = limit;
-	} else
-		long_offset = 0;
-
-	/*
-	 * Instead of doing extra work for p, dp, U > 64 bytes, we'll just use
-	 * the larger message structure.
-	 */
-	if (long_len <= 64) {
+	if (mod_len <= 128) {		/* up to 1024 bit key size */
 		struct type50_crb1_msg *crb1 = ap_msg->message;
 		memset(crb1, 0, sizeof(*crb1));
 		ap_msg->length = sizeof(*crb1);
 		crb1->header.msg_type_code = TYPE50_TYPE_CODE;
 		crb1->header.msg_len = sizeof(*crb1);
 		crb1->keyblock_type = TYPE50_CRB1_FMT;
-		p = crb1->p + sizeof(crb1->p) - long_len;
+		p = crb1->p + sizeof(crb1->p) - short_len;
 		q = crb1->q + sizeof(crb1->q) - short_len;
-		dp = crb1->dp + sizeof(crb1->dp) - long_len;
+		dp = crb1->dp + sizeof(crb1->dp) - short_len;
 		dq = crb1->dq + sizeof(crb1->dq) - short_len;
-		u = crb1->u + sizeof(crb1->u) - long_len;
+		u = crb1->u + sizeof(crb1->u) - short_len;
 		inp = crb1->message + sizeof(crb1->message) - mod_len;
-	} else if (long_len <= 128) {
+	} else if (mod_len <= 256) {	/* up to 2048 bit key size */
 		struct type50_crb2_msg *crb2 = ap_msg->message;
 		memset(crb2, 0, sizeof(*crb2));
 		ap_msg->length = sizeof(*crb2);
 		crb2->header.msg_type_code = TYPE50_TYPE_CODE;
 		crb2->header.msg_len = sizeof(*crb2);
 		crb2->keyblock_type = TYPE50_CRB2_FMT;
-		p = crb2->p + sizeof(crb2->p) - long_len;
+		p = crb2->p + sizeof(crb2->p) - short_len;
 		q = crb2->q + sizeof(crb2->q) - short_len;
-		dp = crb2->dp + sizeof(crb2->dp) - long_len;
+		dp = crb2->dp + sizeof(crb2->dp) - short_len;
 		dq = crb2->dq + sizeof(crb2->dq) - short_len;
-		u = crb2->u + sizeof(crb2->u) - long_len;
+		u = crb2->u + sizeof(crb2->u) - short_len;
 		inp = crb2->message + sizeof(crb2->message) - mod_len;
-	} else {
-		/* long_len >= 256 */
+	} else if ((mod_len <= 512) &&	/* up to 4096 bit key size */
+		   (zdev->max_mod_size == CEX3A_MAX_MOD_SIZE)) { /* >= CEX3A */
 		struct type50_crb3_msg *crb3 = ap_msg->message;
 		memset(crb3, 0, sizeof(*crb3));
 		ap_msg->length = sizeof(*crb3);
 		crb3->header.msg_type_code = TYPE50_TYPE_CODE;
 		crb3->header.msg_len = sizeof(*crb3);
 		crb3->keyblock_type = TYPE50_CRB3_FMT;
-		p = crb3->p + sizeof(crb3->p) - long_len;
+		p = crb3->p + sizeof(crb3->p) - short_len;
 		q = crb3->q + sizeof(crb3->q) - short_len;
-		dp = crb3->dp + sizeof(crb3->dp) - long_len;
+		dp = crb3->dp + sizeof(crb3->dp) - short_len;
 		dq = crb3->dq + sizeof(crb3->dq) - short_len;
-		u = crb3->u + sizeof(crb3->u) - long_len;
+		u = crb3->u + sizeof(crb3->u) - short_len;
 		inp = crb3->message + sizeof(crb3->message) - mod_len;
-	}
+	} else
+		return -EINVAL;
 
-	if (copy_from_user(p, crt->np_prime + long_offset, long_len) ||
+	/*
+	 * correct the offset of p, bp and mult_inv according zcrypt.h
+	 * block size right aligned (skip the first byte)
+	 */
+	if (copy_from_user(p, crt->np_prime + MSGTYPE_ADJUSTMENT, short_len) ||
 	    copy_from_user(q, crt->nq_prime, short_len) ||
-	    copy_from_user(dp, crt->bp_key + long_offset, long_len) ||
+	    copy_from_user(dp, crt->bp_key + MSGTYPE_ADJUSTMENT, short_len) ||
 	    copy_from_user(dq, crt->bq_key, short_len) ||
-	    copy_from_user(u, crt->u_mult_inv + long_offset, long_len) ||
+	    copy_from_user(u, crt->u_mult_inv + MSGTYPE_ADJUSTMENT, short_len) ||
 	    copy_from_user(inp, crt->inputdata, mod_len))
 		return -EFAULT;
 

drivers/s390/crypto/zcrypt_msgtype50.h

@@ -33,6 +33,8 @@
 #define MSGTYPE50_CRB2_MAX_MSG_SIZE	0x390 /*sizeof(struct type50_crb2_msg)*/
 #define MSGTYPE50_CRB3_MAX_MSG_SIZE	0x710 /*sizeof(struct type50_crb3_msg)*/
 
+#define MSGTYPE_ADJUSTMENT		0x08  /*type04 extension (not needed in type50)*/
+
 int zcrypt_msgtype50_init(void);
 void zcrypt_msgtype50_exit(void);
 

include/asm-generic/io.h

@@ -83,19 +83,25 @@ static inline void __raw_writel(u32 b, volatile void __iomem *addr)
 #define writel(b,addr) __raw_writel(__cpu_to_le32(b),addr)
 
 #ifdef CONFIG_64BIT
+#ifndef __raw_readq
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	return *(const volatile u64 __force *) addr;
 }
+#endif
+
 #define readq(addr) __le64_to_cpu(__raw_readq(addr))
 
+#ifndef __raw_writeq
 static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
 {
 	*(volatile u64 __force *) addr = b;
 }
-#define writeq(b,addr) __raw_writeq(__cpu_to_le64(b),addr)
 #endif
 
+#define writeq(b, addr) __raw_writeq(__cpu_to_le64(b), addr)
+#endif /* CONFIG_64BIT */
+
 #ifndef PCI_IOBASE
 #define PCI_IOBASE ((void __iomem *) 0)
 #endif
@@ -286,15 +292,20 @@ static inline void writesb(const void __iomem *addr, const void *buf, int len)
 
 #ifndef CONFIG_GENERIC_IOMAP
 struct pci_dev;
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+
+#ifndef pci_iounmap
 static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
 {
 }
+#endif
 #endif /* CONFIG_GENERIC_IOMAP */
 
 /*
  * Change virtual addresses to physical addresses and vv.
  * These are pretty trivial
  */
+#ifndef virt_to_phys
 static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return __pa((unsigned long)address);
@@ -304,6 +315,7 @@ static inline void *phys_to_virt(unsigned long address)
 {
 	return __va(address);
 }
+#endif
 
 /*
  * Change "struct page" to physical address.
@@ -363,9 +375,16 @@ static inline void *bus_to_virt(unsigned long address)
 }
 #endif
 
+#ifndef memset_io
 #define memset_io(a, b, c)	memset(__io_virt(a), (b), (c))
+#endif
+
+#ifndef memcpy_fromio
 #define memcpy_fromio(a, b, c)	memcpy((a), __io_virt(b), (c))
+#endif
+#ifndef memcpy_toio
 #define memcpy_toio(a, b, c)	memcpy(__io_virt(a), (b), (c))
+#endif
 
 #endif /* __KERNEL__ */
 

include/linux/irq.h

@@ -10,9 +10,6 @@
  */
 
 #include <linux/smp.h>
-
-#ifndef CONFIG_S390
-
 #include <linux/linkage.h>
 #include <linux/cache.h>
 #include <linux/spinlock.h>
@@ -746,8 +743,11 @@ static inline void irq_gc_lock(struct irq_chip_generic *gc) { }
 static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
 #endif
 
-#endif /* CONFIG_GENERIC_HARDIRQS */
+#else /* !CONFIG_GENERIC_HARDIRQS */
 
-#endif /* !CONFIG_S390 */
+extern struct msi_desc *irq_get_msi_desc(unsigned int irq);
+extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
+
+#endif /* CONFIG_GENERIC_HARDIRQS */
 
 #endif /* _LINUX_IRQ_H */