Merge tag 's390-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Alexander Gordeev:

 - Factor out handle_write() function and simplify 3215 console write
   operation

 - When 3170 terminal emulator is connected to the 3215 console driver
   the boot time could be very long due to limited buffer space or
   missing operator input. Add con3215_drop command line parameter and
   con3215_drop sysfs attribute file to instruct the kernel drop console
   data when such conditions are met

 - Fix white space errors in 3215 console driver

 - Move enum paiext_mode definition to a header file and rename it to
   paievt_mode to indicate this is now used for several events. Rename
   PAI_MODE_COUNTER to PAI_MODE_COUNTING to make consistent with
   PAI_MODE_SAMPLING

 - Simplify the logic of PMU pai_crypto mapped buffer reference counter
   and make it consistent with PMU pai_ext

 - Rename PMU pai_crypto mapped buffer structure member users to
   active_events to make it consistent with PMU pai_ext

 - Enable HUGETLB_PAGE_OPTIMIZE_VMEMMAP configuration option. This
   results in saving of 12K per 1M hugetlb page (~1.2%) and 32764K per
   2G hugetlb page (~1.6%)

 - Use generic serial.h, bugs.h, shmparam.h and vga.h header files and
   scrap s390-specific versions

 - The generic percpu setup code does not expect the s390-like
   implementation and emits a warning. To get rid of that warning and
   provide sane CPU-to-node and CPU-to-CPU distance mappings implementat
   a minimal version of setup_per_cpu_areas()

 - Use kstrtobool() instead of strtobool() for re-IPL sysfs device
   attributes

 - Avoid unnecessary lookup of a pointer to MSI descriptor when setting
   IRQ affinity for a PCI device

 - Get rid of "an incompatible function type cast" warning by changing
   debug_sprintf_format_fn() function prototype so it matches the
   debug_format_proc_t function type

 - Remove unused info_blk_hdr__pcpus() and get_page_state() functions

 - Get rid of clang "unused unused insn cache ops function" warning by
   moving s390_insn definition to a private header

 - Get rid of clang "unused function" warning by making function
   raw3270_state_final() only available if CONFIG_TN3270_CONSOLE is
   enabled

 - Use kstrobool() to parse sclp_con_drop parameter to make it identical
   to the con3215_drop parameter and allow passing values like "yes" and
   "true"

 - Use sysfs_emit() for all SCLP sysfs show functions, which is the
   current standard way to generate output strings

 - Make SCLP con_drop sysfs attribute also writable and allow to change
   its value during runtime. This makes SCLP console drop handling
   consistent with the 3215 device driver

 - Virtual and physical addresses are indentical on s390. However, there
   is still a confusion when pointers are directly casted to physical
   addresses or vice versa. Use correct address converters
   virt_to_phys() and phys_to_virt() for s390 channel IO drivers

 - Support for power managemant has been removed from s390 since quite
   some time. Remove unused power managemant code from the appldata
   device driver

 - Allow memory tools like KASAN see memory accesses from the checksum
   code. Switch to GENERIC_CSUM if KASAN is enabled, just like x86 does

 - Add support of ECKD DASDs disks so it could be used as boot and dump
   devices

 - Follow checkpatch recommendations and use octal values instead of
   S_IRUGO and S_IWUSR for dump device attributes in sysfs

 - Changes to vx-insn.h do not cause a recompile of C files that use
   asm(".include \"asm/vx-insn.h\"\n") magic to access vector
   instruction macros from inline assemblies. Add wrapper include header
   file to avoid this problem

 - Use vector instruction macros instead of byte patterns to increase
   register validation routine readability

 - The current machine check register validation handling does not take
   into account various scenarios and might lead to killing a wrong user
   process or potentially ignore corrupted FPU registers. Simplify logic
   of the machine check handler and stop the whole machine if the
   previous context was kerenel mode. If the previous context was user
   mode, kill the current task

 - Introduce sclp_emergency_printk() function which can be used to emit
   a message in emergency cases. It is supposed to be used in cases
   where regular console device drivers may not work anymore, e.g.
   unrecoverable machine checks

   Keep the early Service-Call Control Block so it can also be used
   after initdata has been freed to allow sclp_emergency_printk()
   implementation

 - In case a system will be stopped because of an unrecoverable machine
   check error print the machine check interruption code to give a hint
   of what went wrong

 - Move storage error checking from the assembly entry code to C in
   order to simplify machine check handling. Enter the handler with DAT
   turned on, which simplifies the entry code even more

 - The machine check extended save areas are allocated using a private
   "nmi_save_areas" slab cache which guarantees a required power-of-two
   alignment. Get rid of that cache in favour of kmalloc()

* tag 's390-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (38 commits)
  s390/nmi: get rid of private slab cache
  s390/nmi: move storage error checking back to C, enter with DAT on
  s390/nmi: print machine check interruption code before stopping system
  s390/sclp: introduce sclp_emergency_printk()
  s390/sclp: keep sclp_early_sccb
  s390/nmi: rework register validation handling
  s390/nmi: use vector instruction macros instead of byte patterns
  s390/vx: add vx-insn.h wrapper include file
  s390/ipl: use octal values instead of S_* macros
  s390/ipl: add eckd dump support
  s390/ipl: add eckd support
  vfio/ccw: identify CCW data addresses as physical
  vfio/ccw: sort out physical vs virtual pointers usage
  s390/checksum: support GENERIC_CSUM, enable it for KASAN
  s390/appldata: remove power management callbacks
  s390/cio: sort out physical vs virtual pointers usage
  s390/sclp: allow to change sclp_console_drop during runtime
  s390/sclp: convert to use sysfs_emit()
  s390/sclp: use kstrobool() to parse sclp_con_drop parameter
  s390/3270: make raw3270_state_final() depend on CONFIG_TN3270_CONSOLE
  ...

28 files changed, 1309 insertions, 1037 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 48a11deb502c..7fd08755a1f9 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -26,6 +26,10 @@ config GENERIC_BUG
 config GENERIC_BUG_RELATIVE_POINTERS
 	def_bool y
 
+config GENERIC_CSUM
+	bool
+	default y if KASAN
+
 config GENERIC_LOCKBREAK
 	def_bool y if PREEMPTION
 
@@ -122,6 +126,7 @@ config S390
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_IPC_PARSE_VERSION
+	select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
 	select DMA_OPS if PCI
@@ -197,6 +202,7 @@ config S390
 	select HAVE_RSEQ
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+	select HAVE_SETUP_PER_CPU_AREA
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
@@ -208,6 +214,7 @@ config S390
 	select MMU_GATHER_MERGE_VMAS
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE	if PCI
+	select NEED_PER_CPU_EMBED_FIRST_CHUNK
 	select NEED_SG_DMA_LENGTH	if PCI
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index d74a4c7d5df6..c0fd29133f27 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -26,8 +26,6 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/workqueue.h>
-#include <linux/suspend.h>
-#include <linux/platform_device.h>
 #include <asm/appldata.h>
 #include <asm/vtimer.h>
 #include <linux/uaccess.h>
@@ -44,8 +42,6 @@
 #define TOD_MICRO	0x01000			/* nr. of TOD clock units
 						   for 1 microsecond */
 
-static struct platform_device *appldata_pdev;
-
 /*
  * /proc entries (sysctl)
  */
@@ -88,7 +84,6 @@ static struct vtimer_list appldata_timer;
 static DEFINE_SPINLOCK(appldata_timer_lock);
 static int appldata_interval = APPLDATA_CPU_INTERVAL;
 static int appldata_timer_active;
-static int appldata_timer_suspended = 0;
 
 /*
  * Work queue
@@ -412,88 +407,6 @@ void appldata_unregister_ops(struct appldata_ops *ops)
 /********************** module-ops management <END> **************************/
 
 
-/**************************** suspend / resume *******************************/
-static int appldata_freeze(struct device *dev)
-{
-	struct appldata_ops *ops;
-	int rc;
-	struct list_head *lh;
-
-	spin_lock(&appldata_timer_lock);
-	if (appldata_timer_active) {
-		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
-		appldata_timer_suspended = 1;
-	}
-	spin_unlock(&appldata_timer_lock);
-
-	mutex_lock(&appldata_ops_mutex);
-	list_for_each(lh, &appldata_ops_list) {
-		ops = list_entry(lh, struct appldata_ops, list);
-		if (ops->active == 1) {
-			rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
-					(unsigned long) ops->data, ops->size,
-					ops->mod_lvl);
-			if (rc != 0)
-				pr_err("Stopping the data collection for %s "
-				       "failed with rc=%d\n", ops->name, rc);
-		}
-	}
-	mutex_unlock(&appldata_ops_mutex);
-	return 0;
-}
-
-static int appldata_restore(struct device *dev)
-{
-	struct appldata_ops *ops;
-	int rc;
-	struct list_head *lh;
-
-	spin_lock(&appldata_timer_lock);
-	if (appldata_timer_suspended) {
-		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
-		appldata_timer_suspended = 0;
-	}
-	spin_unlock(&appldata_timer_lock);
-
-	mutex_lock(&appldata_ops_mutex);
-	list_for_each(lh, &appldata_ops_list) {
-		ops = list_entry(lh, struct appldata_ops, list);
-		if (ops->active == 1) {
-			ops->callback(ops->data);	// init record
-			rc = appldata_diag(ops->record_nr,
-					APPLDATA_START_INTERVAL_REC,
-					(unsigned long) ops->data, ops->size,
-					ops->mod_lvl);
-			if (rc != 0) {
-				pr_err("Starting the data collection for %s "
-				       "failed with rc=%d\n", ops->name, rc);
-			}
-		}
-	}
-	mutex_unlock(&appldata_ops_mutex);
-	return 0;
-}
-
-static int appldata_thaw(struct device *dev)
-{
-	return appldata_restore(dev);
-}
-
-static const struct dev_pm_ops appldata_pm_ops = {
-	.freeze		= appldata_freeze,
-	.thaw		= appldata_thaw,
-	.restore	= appldata_restore,
-};
-
-static struct platform_driver appldata_pdrv = {
-	.driver = {
-		.name	= "appldata",
-		.pm	= &appldata_pm_ops,
-	},
-};
-/************************* suspend / resume <END> ****************************/
-
-
 /******************************* init / exit *********************************/
 
 /*
@@ -503,36 +416,14 @@ static struct platform_driver appldata_pdrv = {
  */
 static int __init appldata_init(void)
 {
-	int rc;
-
 	init_virt_timer(&appldata_timer);
 	appldata_timer.function = appldata_timer_function;
 	appldata_timer.data = (unsigned long) &appldata_work;
-
-	rc = platform_driver_register(&appldata_pdrv);
-	if (rc)
-		return rc;
-
-	appldata_pdev = platform_device_register_simple("appldata", -1, NULL,
-							0);
-	if (IS_ERR(appldata_pdev)) {
-		rc = PTR_ERR(appldata_pdev);
-		goto out_driver;
-	}
 	appldata_wq = alloc_ordered_workqueue("appldata", 0);
-	if (!appldata_wq) {
-		rc = -ENOMEM;
-		goto out_device;
-	}
-
+	if (!appldata_wq)
+		return -ENOMEM;
 	appldata_sysctl_header = register_sysctl_table(appldata_dir_table);
 	return 0;
-
-out_device:
-	platform_device_unregister(appldata_pdev);
-out_driver:
-	platform_driver_unregister(&appldata_pdrv);
-	return rc;
 }
 
 __initcall(appldata_init);
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index ca78d6162245..c1f8f7999fed 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -77,6 +77,9 @@ bool is_ipl_block_dump(void)
 	if (ipl_block.pb0_hdr.pbt == IPL_PBT_NVME &&
 	    ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP)
 		return true;
+	if (ipl_block.pb0_hdr.pbt == IPL_PBT_ECKD &&
+	    ipl_block.eckd.opt == IPL_PB0_ECKD_OPT_DUMP)
+		return true;
 	return false;
 }
 
@@ -108,6 +111,11 @@ static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size,
 		scp_data_len = ipb->nvme.scp_data_len;
 		scp_data = ipb->nvme.scp_data;
 		break;
+	case IPL_PBT_ECKD:
+		scp_data_len = ipb->eckd.scp_data_len;
+		scp_data = ipb->eckd.scp_data;
+		break;
+
 	default:
 		goto out;
 	}
@@ -153,6 +161,7 @@ static void append_ipl_block_parm(void)
 		break;
 	case IPL_PBT_FCP:
 	case IPL_PBT_NVME:
+	case IPL_PBT_ECKD:
 		rc = ipl_block_get_ascii_scpdata(
 			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 6511d15ace45..c3be533c4cd3 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -68,14 +68,6 @@ static inline __u8 info_blk_hdr__flags(enum diag204_format type, void *hdr)
 		return ((struct diag204_x_info_blk_hdr *)hdr)->flags;
 }
 
-static inline __u16 info_blk_hdr__pcpus(enum diag204_format type, void *hdr)
-{
-	if (type == DIAG204_INFO_SIMPLE)
-		return ((struct diag204_info_blk_hdr *)hdr)->phys_cpus;
-	else /* DIAG204_INFO_EXT */
-		return ((struct diag204_x_info_blk_hdr *)hdr)->phys_cpus;
-}
-
 /* Partition header */
 
 static inline int part_hdr__size(enum diag204_format type)
diff --git a/arch/s390/include/asm/bugs.h b/arch/s390/include/asm/bugs.h
deleted file mode 100644
index aa42a179be33..000000000000
--- a/arch/s390/include/asm/bugs.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- *  S390 version
- *    Copyright IBM Corp. 1999
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- *  Derived from "include/asm-i386/bugs.h"
- *    Copyright (C) 1994  Linus Torvalds
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *      void check_bugs(void);
- */
-
-static inline void check_bugs(void)
-{
-  /* s390 has no bugs ... */
-}
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index cdd19d326345..d977a3a2f619 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -12,6 +12,12 @@
 #ifndef _S390_CHECKSUM_H
 #define _S390_CHECKSUM_H
 
+#ifdef CONFIG_GENERIC_CSUM
+
+#include <asm-generic/checksum.h>
+
+#else /* CONFIG_GENERIC_CSUM */
+
 #include <linux/uaccess.h>
 #include <linux/in6.h>
 
@@ -129,4 +135,5 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold((__force __wsum)(sum >> 32));
 }
 
+#endif /* CONFIG_GENERIC_CSUM */
 #endif /* _S390_CHECKSUM_H */
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index a405b6bb89fb..b0d00032479d 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -22,6 +22,7 @@ struct ipl_parameter_block {
 		struct ipl_pb0_common common;
 		struct ipl_pb0_fcp fcp;
 		struct ipl_pb0_ccw ccw;
+		struct ipl_pb0_eckd eckd;
 		struct ipl_pb0_nvme nvme;
 		char raw[PAGE_SIZE - sizeof(struct ipl_pl_hdr)];
 	};
@@ -41,6 +42,10 @@ struct ipl_parameter_block {
 			      sizeof(struct ipl_pb0_ccw))
 #define IPL_BP0_CCW_LEN (sizeof(struct ipl_pb0_ccw))
 
+#define IPL_BP_ECKD_LEN (sizeof(struct ipl_pl_hdr) + \
+			      sizeof(struct ipl_pb0_eckd))
+#define IPL_BP0_ECKD_LEN (sizeof(struct ipl_pb0_eckd))
+
 #define IPL_MAX_SUPPORTED_VERSION (0)
 
 #define IPL_RB_CERT_UNKNOWN ((unsigned short)-1)
@@ -68,6 +73,8 @@ enum ipl_type {
 	IPL_TYPE_NSS		= 16,
 	IPL_TYPE_NVME		= 32,
 	IPL_TYPE_NVME_DUMP	= 64,
+	IPL_TYPE_ECKD		= 128,
+	IPL_TYPE_ECKD_DUMP	= 256,
 };
 
 struct ipl_info
@@ -79,6 +86,9 @@ struct ipl_info
 		} ccw;
 		struct {
 			struct ccw_dev_id dev_id;
+		} eckd;
+		struct {
+			struct ccw_dev_id dev_id;
 			u64 wwpn;
 			u64 lun;
 		} fcp;
@@ -99,6 +109,7 @@ extern void set_os_info_reipl_block(void);
 static inline bool is_ipl_type_dump(void)
 {
 	return (ipl_info.type == IPL_TYPE_FCP_DUMP) ||
+		(ipl_info.type == IPL_TYPE_ECKD_DUMP) ||
 		(ipl_info.type == IPL_TYPE_NVME_DUMP);
 }
 
diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h
index 1a8a6b15d121..7d1888e3dee6 100644
--- a/arch/s390/include/asm/pai.h
+++ b/arch/s390/include/asm/pai.h
@@ -75,4 +75,10 @@ static __always_inline void pai_kernel_exit(struct pt_regs *regs)
 	WRITE_ONCE(S390_lowcore.ccd, S390_lowcore.ccd & ~PAI_CRYPTO_KERNEL_OFFSET);
 }
 
+enum paievt_mode {
+	PAI_MODE_NONE,
+	PAI_MODE_SAMPLING,
+	PAI_MODE_COUNTING,
+};
+
 #endif
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 9d4c7f71e070..dac7da88f61f 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -87,6 +87,7 @@ struct sclp_info {
 	unsigned char has_gisaf : 1;
 	unsigned char has_diag318 : 1;
 	unsigned char has_sipl : 1;
+	unsigned char has_sipl_eckd : 1;
 	unsigned char has_dirq : 1;
 	unsigned char has_iplcc : 1;
 	unsigned char has_zpci_lsi : 1;
@@ -131,6 +132,7 @@ void sclp_early_get_ipl_info(struct sclp_ipl_info *info);
 void sclp_early_detect(void);
 void sclp_early_printk(const char *s);
 void __sclp_early_printk(const char *s, unsigned int len);
+void sclp_emergency_printk(const char *s);
 
 int sclp_early_get_memsize(unsigned long *mem);
 int sclp_early_get_hsa_size(unsigned long *hsa_size);
diff --git a/arch/s390/include/asm/serial.h b/arch/s390/include/asm/serial.h
deleted file mode 100644
index aaf85a69061c..000000000000
--- a/arch/s390/include/asm/serial.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_S390_SERIAL_H
-#define _ASM_S390_SERIAL_H
-
-#define BASE_BAUD 0
-
-#endif /* _ASM_S390_SERIAL_H */
diff --git a/arch/s390/include/asm/shmparam.h b/arch/s390/include/asm/shmparam.h
deleted file mode 100644
index e75d45649c54..000000000000
--- a/arch/s390/include/asm/shmparam.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- *  S390 version
- *
- *  Derived from "include/asm-i386/shmparam.h"
- */
-#ifndef _ASM_S390_SHMPARAM_H
-#define _ASM_S390_SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE                 /* attach addr a multiple of this */
-
-#endif /* _ASM_S390_SHMPARAM_H */
diff --git a/arch/s390/include/asm/vga.h b/arch/s390/include/asm/vga.h
deleted file mode 100644
index 605dc46bac5e..000000000000
--- a/arch/s390/include/asm/vga.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_S390_VGA_H
-#define _ASM_S390_VGA_H
-
-/* Avoid compile errors due to missing asm/vga.h */
-
-#endif /* _ASM_S390_VGA_H */
diff --git a/arch/s390/include/asm/vx-insn-asm.h b/arch/s390/include/asm/vx-insn-asm.h
new file mode 100644
index 000000000000..360f8b36d962
--- /dev/null
+++ b/arch/s390/include/asm/vx-insn-asm.h
@@ -0,0 +1,681 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Support for Vector Instructions
+ *
+ * Assembler macros to generate .byte/.word code for particular
+ * vector instructions that are supported by recent binutils (>= 2.26) only.
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_S390_VX_INSN_INTERNAL_H
+#define __ASM_S390_VX_INSN_INTERNAL_H
+
+#ifndef __ASM_S390_VX_INSN_H
+#error only <asm/vx-insn.h> can be included directly
+#endif
+
+#ifdef __ASSEMBLY__
+
+/* Macros to generate vector instruction byte code */
+
+/* GR_NUM - Retrieve general-purpose register number
+ *
+ * @opd:	Operand to store register number
+ * @r64:	String designation register in the format "%rN"
+ */
+.macro	GR_NUM	opd gr
+	\opd = 255
+	.ifc \gr,%r0
+		\opd = 0
+	.endif
+	.ifc \gr,%r1
+		\opd = 1
+	.endif
+	.ifc \gr,%r2
+		\opd = 2
+	.endif
+	.ifc \gr,%r3
+		\opd = 3
+	.endif
+	.ifc \gr,%r4
+		\opd = 4
+	.endif
+	.ifc \gr,%r5
+		\opd = 5
+	.endif
+	.ifc \gr,%r6
+		\opd = 6
+	.endif
+	.ifc \gr,%r7
+		\opd = 7
+	.endif
+	.ifc \gr,%r8
+		\opd = 8
+	.endif
+	.ifc \gr,%r9
+		\opd = 9
+	.endif
+	.ifc \gr,%r10
+		\opd = 10
+	.endif
+	.ifc \gr,%r11
+		\opd = 11
+	.endif
+	.ifc \gr,%r12
+		\opd = 12
+	.endif
+	.ifc \gr,%r13
+		\opd = 13
+	.endif
+	.ifc \gr,%r14
+		\opd = 14
+	.endif
+	.ifc \gr,%r15
+		\opd = 15
+	.endif
+	.if \opd == 255
+		\opd = \gr
+	.endif
+.endm
+
+/* VX_NUM - Retrieve vector register number
+ *
+ * @opd:	Operand to store register number
+ * @vxr:	String designation register in the format "%vN"
+ *
+ * The vector register number is used for as input number to the
+ * instruction and, as well as, to compute the RXB field of the
+ * instruction.
+ */
+.macro	VX_NUM	opd vxr
+	\opd = 255
+	.ifc \vxr,%v0
+		\opd = 0
+	.endif
+	.ifc \vxr,%v1
+		\opd = 1
+	.endif
+	.ifc \vxr,%v2
+		\opd = 2
+	.endif
+	.ifc \vxr,%v3
+		\opd = 3
+	.endif
+	.ifc \vxr,%v4
+		\opd = 4
+	.endif
+	.ifc \vxr,%v5
+		\opd = 5
+	.endif
+	.ifc \vxr,%v6
+		\opd = 6
+	.endif
+	.ifc \vxr,%v7
+		\opd = 7
+	.endif
+	.ifc \vxr,%v8
+		\opd = 8
+	.endif
+	.ifc \vxr,%v9
+		\opd = 9
+	.endif
+	.ifc \vxr,%v10
+		\opd = 10
+	.endif
+	.ifc \vxr,%v11
+		\opd = 11
+	.endif
+	.ifc \vxr,%v12
+		\opd = 12
+	.endif
+	.ifc \vxr,%v13
+		\opd = 13
+	.endif
+	.ifc \vxr,%v14
+		\opd = 14
+	.endif
+	.ifc \vxr,%v15
+		\opd = 15
+	.endif
+	.ifc \vxr,%v16
+		\opd = 16
+	.endif
+	.ifc \vxr,%v17
+		\opd = 17
+	.endif
+	.ifc \vxr,%v18
+		\opd = 18
+	.endif
+	.ifc \vxr,%v19
+		\opd = 19
+	.endif
+	.ifc \vxr,%v20
+		\opd = 20
+	.endif
+	.ifc \vxr,%v21
+		\opd = 21
+	.endif
+	.ifc \vxr,%v22
+		\opd = 22
+	.endif
+	.ifc \vxr,%v23
+		\opd = 23
+	.endif
+	.ifc \vxr,%v24
+		\opd = 24
+	.endif
+	.ifc \vxr,%v25
+		\opd = 25
+	.endif
+	.ifc \vxr,%v26
+		\opd = 26
+	.endif
+	.ifc \vxr,%v27
+		\opd = 27
+	.endif
+	.ifc \vxr,%v28
+		\opd = 28
+	.endif
+	.ifc \vxr,%v29
+		\opd = 29
+	.endif
+	.ifc \vxr,%v30
+		\opd = 30
+	.endif
+	.ifc \vxr,%v31
+		\opd = 31
+	.endif
+	.if \opd == 255
+		\opd = \vxr
+	.endif
+.endm
+
+/* RXB - Compute most significant bit used vector registers
+ *
+ * @rxb:	Operand to store computed RXB value
+ * @v1:		First vector register designated operand
+ * @v2:		Second vector register designated operand
+ * @v3:		Third vector register designated operand
+ * @v4:		Fourth vector register designated operand
+ */
+.macro	RXB	rxb v1 v2=0 v3=0 v4=0
+	\rxb = 0
+	.if \v1 & 0x10
+		\rxb = \rxb | 0x08
+	.endif
+	.if \v2 & 0x10
+		\rxb = \rxb | 0x04
+	.endif
+	.if \v3 & 0x10
+		\rxb = \rxb | 0x02
+	.endif
+	.if \v4 & 0x10
+		\rxb = \rxb | 0x01
+	.endif
+.endm
+
+/* MRXB - Generate Element Size Control and RXB value
+ *
+ * @m:		Element size control
+ * @v1:		First vector register designated operand (for RXB)
+ * @v2:		Second vector register designated operand (for RXB)
+ * @v3:		Third vector register designated operand (for RXB)
+ * @v4:		Fourth vector register designated operand (for RXB)
+ */
+.macro	MRXB	m v1 v2=0 v3=0 v4=0
+	rxb = 0
+	RXB	rxb, \v1, \v2, \v3, \v4
+	.byte	(\m << 4) | rxb
+.endm
+
+/* MRXBOPC - Generate Element Size Control, RXB, and final Opcode fields
+ *
+ * @m:		Element size control
+ * @opc:	Opcode
+ * @v1:		First vector register designated operand (for RXB)
+ * @v2:		Second vector register designated operand (for RXB)
+ * @v3:		Third vector register designated operand (for RXB)
+ * @v4:		Fourth vector register designated operand (for RXB)
+ */
+.macro	MRXBOPC	m opc v1 v2=0 v3=0 v4=0
+	MRXB	\m, \v1, \v2, \v3, \v4
+	.byte	\opc
+.endm
+
+/* Vector support instructions */
+
+/* VECTOR GENERATE BYTE MASK */
+.macro	VGBM	vr imm2
+	VX_NUM	v1, \vr
+	.word	(0xE700 | ((v1&15) << 4))
+	.word	\imm2
+	MRXBOPC	0, 0x44, v1
+.endm
+.macro	VZERO	vxr
+	VGBM	\vxr, 0
+.endm
+.macro	VONE	vxr
+	VGBM	\vxr, 0xFFFF
+.endm
+
+/* VECTOR LOAD VR ELEMENT FROM GR */
+.macro	VLVG	v, gr, disp, m
+	VX_NUM	v1, \v
+	GR_NUM	b2, "%r0"
+	GR_NUM	r3, \gr
+	.word	0xE700 | ((v1&15) << 4) | r3
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m, 0x22, v1
+.endm
+.macro	VLVGB	v, gr, index, base
+	VLVG	\v, \gr, \index, \base, 0
+.endm
+.macro	VLVGH	v, gr, index
+	VLVG	\v, \gr, \index, 1
+.endm
+.macro	VLVGF	v, gr, index
+	VLVG	\v, \gr, \index, 2
+.endm
+.macro	VLVGG	v, gr, index
+	VLVG	\v, \gr, \index, 3
+.endm
+
+/* VECTOR LOAD REGISTER */
+.macro	VLR	v1, v2
+	VX_NUM	v1, \v1
+	VX_NUM	v2, \v2
+	.word	0xE700 | ((v1&15) << 4) | (v2&15)
+	.word	0
+	MRXBOPC	0, 0x56, v1, v2
+.endm
+
+/* VECTOR LOAD */
+.macro	VL	v, disp, index="%r0", base
+	VX_NUM	v1, \v
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base
+	.word	0xE700 | ((v1&15) << 4) | x2
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC 0, 0x06, v1
+.endm
+
+/* VECTOR LOAD ELEMENT */
+.macro	VLEx	vr1, disp, index="%r0", base, m3, opc
+	VX_NUM	v1, \vr1
+	GR_NUM	x2, \index
+	GR_NUM	b2, \base
+	.word	0xE700 | ((v1&15) << 4) | x2
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m3, \opc, v1
+.endm
+.macro	VLEB	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x00
+.endm
+.macro	VLEH	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x01
+.endm
+.macro	VLEF	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x03
+.endm
+.macro	VLEG	vr1, disp, index="%r0", base, m3
+	VLEx	\vr1, \disp, \index, \base, \m3, 0x02
+.endm
+
+/* VECTOR LOAD ELEMENT IMMEDIATE */
+.macro	VLEIx	vr1, imm2, m3, opc
+	VX_NUM	v1, \vr1
+	.word	0xE700 | ((v1&15) << 4)
+	.word	\imm2
+	MRXBOPC	\m3, \opc, v1
+.endm
+.macro	VLEIB	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x40
+.endm
+.macro	VLEIH	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x41
+.endm
+.macro	VLEIF	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x43
+.endm
+.macro	VLEIG	vr1, imm2, index
+	VLEIx	\vr1, \imm2, \index, 0x42
+.endm
+
+/* VECTOR LOAD GR FROM VR ELEMENT */
+.macro	VLGV	gr, vr, disp, base="%r0", m
+	GR_NUM	r1, \gr
+	GR_NUM	b2, \base
+	VX_NUM	v3, \vr
+	.word	0xE700 | (r1 << 4) | (v3&15)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\m, 0x21, v3
+.endm
+.macro	VLGVB	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 0
+.endm
+.macro	VLGVH	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 1
+.endm
+.macro	VLGVF	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 2
+.endm
+.macro	VLGVG	gr, vr, disp, base="%r0"
+	VLGV	\gr, \vr, \disp, \base, 3
+.endm
+
+/* VECTOR LOAD MULTIPLE */
+.macro	VLM	vfrom, vto, disp, base, hint=3
+	VX_NUM	v1, \vfrom
+	VX_NUM	v3, \vto
+	GR_NUM	b2, \base
+	.word	0xE700 | ((v1&15) << 4) | (v3&15)
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC	\hint, 0x36, v1, v3
+.endm
+
+/* VECTOR STORE */
+.macro	VST	vr1, disp, index="%r0", base
+	VX_NUM	v1, \vr1