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

+#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

+#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

-/*
- *  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

+#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

 #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

+#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

+#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

+#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

+#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

+#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

+/*
+ *    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 @@ static inline int do_exception(struct pt_regs *regs, int access)
 			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

+#
+# 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_clp.c

+/*
+ * 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_event.c

+/*
+ *  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);
+}

drivers/gpu/vga/Kconfig

 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