Merge branch 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6

* 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6: (44 commits)
  [S390] hypfs crashes with invalid mount option.
  [S390] cio: subchannel evaluation function operates without lock
  [S390] cio: always query all paths on path verification.
  [S390] cio: update path groups on logical CHPID changes.
  [S390] cio: subchannels in no-path state.
  [S390] Replace nopav-message on VM.
  [S390] set modalias for ccw bus uevents.
  [S390] Get rid of DBG macro.
  [S390] Use alternative user-copy operations for new hardware.
  [S390] Make user-copy operations run-time configurable.
  [S390] Cleanup in signal handling code.
  [S390] Cleanup in page table related code.
  [S390] Linux API for writing z/VM APPLDATA Monitor records.
  [S390] xpram off by one error.
  [S390] Remove kexec experimental flag.
  [S390] cleanup appldata.
  [S390] fix typo in vmcp.
  [S390] Kernel stack overflow handling.
  [S390] qdio slsb processing state.
  [S390] Missing initialization in common i/o layer.
  ...

MAINTAINERS

@@ -2452,6 +2452,8 @@ S:      Maintained
 S390
 P:	Martin Schwidefsky
 M:	schwidefsky@de.ibm.com
+P:	Heiko Carstens
+M:	heiko.carstens@de.ibm.com
 M:	linux390@de.ibm.com
 L:	linux-390@vm.marist.edu
 W:	http://www.ibm.com/developerworks/linux/linux390/

arch/s390/Kconfig

@@ -460,8 +460,7 @@ config S390_HYPFS_FS
 	  information in an s390 hypervisor environment.
 
 config KEXEC
-	bool "kexec system call (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "kexec system call"
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot
@@ -487,8 +486,22 @@ source "drivers/net/Kconfig"
 
 source "fs/Kconfig"
 
+menu "Instrumentation Support"
+
 source "arch/s390/oprofile/Kconfig"
 
+config KPROBES
+	bool "Kprobes (EXPERIMENTAL)"
+	depends on EXPERIMENTAL && MODULES
+	help
+	  Kprobes allows you to trap at almost any kernel address and
+	  execute a callback function.	register_kprobe() establishes
+	  a probepoint and specifies the callback.  Kprobes is useful
+	  for kernel debugging, non-intrusive instrumentation and testing.
+	  If in doubt, say "N".
+
+endmenu
+
 source "arch/s390/Kconfig.debug"
 
 source "security/Kconfig"

arch/s390/appldata/appldata.h

@@ -29,22 +29,6 @@
 #define CTL_APPLDATA_NET_SUM	2125
 #define CTL_APPLDATA_PROC	2126
 
-#ifndef CONFIG_64BIT
-
-#define APPLDATA_START_INTERVAL_REC 0x00	/* Function codes for */
-#define APPLDATA_STOP_REC	    0x01	/* DIAG 0xDC	  */
-#define APPLDATA_GEN_EVENT_RECORD   0x02
-#define APPLDATA_START_CONFIG_REC   0x03
-
-#else
-
-#define APPLDATA_START_INTERVAL_REC 0x80
-#define APPLDATA_STOP_REC	    0x81
-#define APPLDATA_GEN_EVENT_RECORD   0x82
-#define APPLDATA_START_CONFIG_REC   0x83
-
-#endif /* CONFIG_64BIT */
-
 #define P_INFO(x...)	printk(KERN_INFO MY_PRINT_NAME " info: " x)
 #define P_ERROR(x...)	printk(KERN_ERR MY_PRINT_NAME " error: " x)
 #define P_WARNING(x...)	printk(KERN_WARNING MY_PRINT_NAME " status: " x)

arch/s390/appldata/appldata_base.c

@@ -14,20 +14,20 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/smp.h>
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/page-flags.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/sysctl.h>
-#include <asm/timer.h>
-//#include <linux/kernel_stat.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/workqueue.h>
+#include <asm/appldata.h>
+#include <asm/timer.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/smp.h>
 
 #include "appldata.h"
 
@@ -39,34 +39,6 @@
 
 #define TOD_MICRO	0x01000			/* nr. of TOD clock units
 						   for 1 microsecond */
-
-/*
- * Parameter list for DIAGNOSE X'DC'
- */
-#ifndef CONFIG_64BIT
-struct appldata_parameter_list {
-	u16 diag;		/* The DIAGNOSE code X'00DC'          */
-	u8  function;		/* The function code for the DIAGNOSE */
-	u8  parlist_length;	/* Length of the parameter list       */
-	u32 product_id_addr;	/* Address of the 16-byte product ID  */
-	u16 reserved;
-	u16 buffer_length;	/* Length of the application data buffer  */
-	u32 buffer_addr;	/* Address of the application data buffer */
-};
-#else
-struct appldata_parameter_list {
-	u16 diag;
-	u8  function;
-	u8  parlist_length;
-	u32 unused01;
-	u16 reserved;
-	u16 buffer_length;
-	u32 unused02;
-	u64 product_id_addr;
-	u64 buffer_addr;
-};
-#endif /* CONFIG_64BIT */
-
 /*
  * /proc entries (sysctl)
  */
@@ -181,46 +153,17 @@ static void appldata_work_fn(void *data)
 int appldata_diag(char record_nr, u16 function, unsigned long buffer,
 			u16 length, char *mod_lvl)
 {
-	unsigned long ry;
-	struct appldata_product_id {
-		char prod_nr[7];			/* product nr. */
-		char prod_fn[2];			/* product function */
-		char record_nr;				/* record nr. */
-		char version_nr[2];			/* version */
-		char release_nr[2];			/* release */
-		char mod_lvl[2];			/* modification lvl. */
-	} appldata_product_id = {
-	/* all strings are EBCDIC, record_nr is byte */
+	struct appldata_product_id id = {
 		.prod_nr    = {0xD3, 0xC9, 0xD5, 0xE4,
 			       0xE7, 0xD2, 0xD9},	/* "LINUXKR" */
-		.prod_fn    = {0xD5, 0xD3},		/* "NL" */
+		.prod_fn    = 0xD5D3,			/* "NL" */
 		.record_nr  = record_nr,
-		.version_nr = {0xF2, 0xF6},		/* "26" */
-		.release_nr = {0xF0, 0xF1},		/* "01" */
-		.mod_lvl    = {mod_lvl[0], mod_lvl[1]},
-	};
-	struct appldata_parameter_list appldata_parameter_list = {
-				.diag = 0xDC,
-				.function = function,
-				.parlist_length =
-					sizeof(appldata_parameter_list),
-				.buffer_length = length,
-				.product_id_addr =
-					(unsigned long) &appldata_product_id,
-				.buffer_addr = virt_to_phys((void *) buffer)
+		.version_nr = 0xF2F6,			/* "26" */
+		.release_nr = 0xF0F1,			/* "01" */
+		.mod_lvl    = (mod_lvl[0]) << 8 | mod_lvl[1],
 	};
 
-	if (!MACHINE_IS_VM)
-		return -ENOSYS;
-	ry = -1;
-	asm volatile(
-			"diag %1,%0,0xDC\n\t"
-			: "=d" (ry)
-			: "d" (&appldata_parameter_list),
-			  "m" (appldata_parameter_list),
-			  "m" (appldata_product_id)
-			: "cc");
-	return (int) ry;
+	return appldata_asm(&id, function, (void *) buffer, length);
 }
 /************************ timer, work, DIAG <END> ****************************/
 

arch/s390/appldata/appldata_os.c

@@ -16,6 +16,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/netdevice.h>
 #include <linux/sched.h>
+#include <asm/appldata.h>
 #include <asm/smp.h>
 
 #include "appldata.h"

arch/s390/defconfig

@@ -428,6 +428,7 @@ CONFIG_S390_TAPE_34XX=m
 # CONFIG_VMLOGRDR is not set
 # CONFIG_VMCP is not set
 # CONFIG_MONREADER is not set
+CONFIG_MONWRITER=m
 
 #
 # Cryptographic devices

arch/s390/hypfs/hypfs.h

 /*
- *  fs/hypfs/hypfs.h
+ *  arch/s390/hypfs/hypfs.h
  *    Hypervisor filesystem for Linux on s390.
  *
  *    Copyright (C) IBM Corp. 2006

arch/s390/hypfs/hypfs_diag.c

 /*
- *  fs/hypfs/hypfs_diag.c
+ *  arch/s390/hypfs/hypfs_diag.c
  *    Hypervisor filesystem for Linux on s390. Diag 204 and 224
  *    implementation.
  *
@@ -432,12 +432,14 @@ static int diag204_probe(void)
 
 	buf = diag204_get_buffer(INFO_EXT, &pages);
 	if (!IS_ERR(buf)) {
-		if (diag204(SUBC_STIB7 | INFO_EXT, pages, buf) >= 0) {
+		if (diag204((unsigned long)SUBC_STIB7 |
+			    (unsigned long)INFO_EXT, pages, buf) >= 0) {
 			diag204_store_sc = SUBC_STIB7;
 			diag204_info_type = INFO_EXT;
 			goto out;
 		}
-		if (diag204(SUBC_STIB6 | INFO_EXT, pages, buf) >= 0) {
+		if (diag204((unsigned long)SUBC_STIB6 |
+			    (unsigned long)INFO_EXT, pages, buf) >= 0) {
 			diag204_store_sc = SUBC_STIB7;
 			diag204_info_type = INFO_EXT;
 			goto out;
@@ -452,7 +454,8 @@ static int diag204_probe(void)
 		rc = PTR_ERR(buf);
 		goto fail_alloc;
 	}
-	if (diag204(SUBC_STIB4 | INFO_SIMPLE, pages, buf) >= 0) {
+	if (diag204((unsigned long)SUBC_STIB4 |
+		    (unsigned long)INFO_SIMPLE, pages, buf) >= 0) {
 		diag204_store_sc = SUBC_STIB4;
 		diag204_info_type = INFO_SIMPLE;
 		goto out;
@@ -476,7 +479,8 @@ static void *diag204_store(void)
 	buf = diag204_get_buffer(diag204_info_type, &pages);
 	if (IS_ERR(buf))
 		goto out;
-	if (diag204(diag204_store_sc | diag204_info_type, pages, buf) < 0)
+	if (diag204((unsigned long)diag204_store_sc |
+		    (unsigned long)diag204_info_type, pages, buf) < 0)
 		return ERR_PTR(-ENOSYS);
 out:
 	return buf;
@@ -531,7 +535,7 @@ __init int hypfs_diag_init(void)
 	return rc;
 }
 
-__exit void hypfs_diag_exit(void)
+void hypfs_diag_exit(void)
 {
 	diag224_delete_name_table();
 	diag204_free_buffer();

arch/s390/hypfs/hypfs_diag.h

 /*
- *  fs/hypfs/hypfs_diag.h
+ *  arch/s390/hypfs_diag.h
  *    Hypervisor filesystem for Linux on s390.
  *
  *    Copyright (C) IBM Corp. 2006

arch/s390/hypfs/inode.c

 /*
- *  fs/hypfs/inode.c
+ *  arch/s390/hypfs/inode.c
  *    Hypervisor filesystem for Linux on s390.
  *
  *    Copyright (C) IBM Corp. 2006
@@ -312,10 +312,12 @@ static void hypfs_kill_super(struct super_block *sb)
 {
 	struct hypfs_sb_info *sb_info = sb->s_fs_info;
 
+	if (sb->s_root) {
 		hypfs_delete_tree(sb->s_root);
 		hypfs_remove(sb_info->update_file);
 		kfree(sb->s_fs_info);
 		sb->s_fs_info = NULL;
+	}
 	kill_litter_super(sb);
 }
 

arch/s390/kernel/Makefile

@@ -6,7 +6,7 @@ EXTRA_AFLAGS	:= -traditional
 
 obj-y	:=  bitmap.o traps.o time.o process.o \
             setup.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
-            semaphore.o s390_ext.o debug.o profile.o irq.o reipl_diag.o
+	    semaphore.o s390_ext.o debug.o profile.o irq.o ipl.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
@@ -24,6 +24,7 @@ obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o \
 
 obj-$(CONFIG_VIRT_TIMER)	+= vtime.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
 
 # Kexec part
 S390_KEXEC_OBJS := machine_kexec.o crash.o

arch/s390/kernel/entry.S

@@ -505,6 +505,8 @@ pgm_no_vtime2:
 	mvc	__THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS
 	mvc	__THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID
 	oi	__TI_flags+3(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
+	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
+	bz	BASED(kernel_per)
 	l	%r3,__LC_PGM_ILC	 # load program interruption code
 	la	%r8,0x7f
 	nr	%r8,%r3                  # clear per-event-bit and ilc
@@ -536,6 +538,16 @@ pgm_no_vtime3:
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	b	BASED(sysc_do_svc)
 
+#
+# per was called from kernel, must be kprobes
+#
+kernel_per:
+	mvi	SP_TRAP+1(%r15),0x28	# set trap indication to pgm check
+	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	l	%r1,BASED(.Lhandle_per)	# load adr. of per handler
+	la	%r14,BASED(sysc_leave)	# load adr. of system return
+	br	%r1			# branch to do_single_step
+
 /*
  * IO interrupt handler routine
  */

arch/s390/kernel/entry64.S

@@ -518,6 +518,8 @@ pgm_no_vtime2:
 #endif
 	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
 	lg	%r1,__TI_task(%r9)
+	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
+	jz	kernel_per
 	mvc	__THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID
 	mvc	__THREAD_per+__PER_address(8,%r1),__LC_PER_ADDRESS
 	mvc	__THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID
@@ -553,6 +555,16 @@ pgm_no_vtime3:
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	j	sysc_do_svc
 
+#
+# per was called from kernel, must be kprobes
+#
+kernel_per:
+	lhi	%r0,__LC_PGM_OLD_PSW
+	sth	%r0,SP_TRAP(%r15)	# set trap indication to pgm check
+	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	larl	%r14,sysc_leave		# load adr. of system ret, no work
+	jg	do_single_step		# branch to do_single_step
+
 /*
  * IO interrupt handler routine
  */
@@ -815,7 +827,7 @@ restart_go:
  */
 stack_overflow:
 	lg	%r15,__LC_PANIC_STACK	# change to panic stack
-	aghi	%r1,-SP_SIZE
+	aghi	%r15,-SP_SIZE
 	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
 	stmg	%r0,%r11,SP_R0(%r15)	# store gprs %r0-%r11 to kernel stack
 	la	%r1,__LC_SAVE_AREA
@@ -823,7 +835,7 @@ stack_overflow:
 	je	0f
 	chi	%r12,__LC_PGM_OLD_PSW
 	je	0f
-	la	%r1,__LC_SAVE_AREA+16
+	la	%r1,__LC_SAVE_AREA+32
 0:	mvc	SP_R12(32,%r15),0(%r1)  # move %r12-%r15 to stack
         xc      __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # clear back chain
         la      %r2,SP_PTREGS(%r15)	# load pt_regs

arch/s390/kernel/head.S

@@ -272,7 +272,7 @@ iplstart:
 # load parameter file from ipl device
 #
 .Lagain1:
- 	l     %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # ramdisk loc. is temp
+	l     %r2,.Linitrd		       # ramdisk loc. is temp
         bas   %r14,.Lloader                    # load parameter file
         ltr   %r2,%r2                          # got anything ?
         bz    .Lnopf
@@ -280,7 +280,7 @@ iplstart:
 	bnh   .Lnotrunc
 	la    %r2,895
 .Lnotrunc:
-	l     %r4,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
+	l     %r4,.Linitrd
 	clc   0(3,%r4),.L_hdr		       # if it is HDRx
 	bz    .Lagain1			       # skip dataset header
 	clc   0(3,%r4),.L_eof		       # if it is EOFx
@@ -323,14 +323,15 @@ iplstart:
 # load ramdisk from ipl device
 #	
 .Lagain2:
- 	l     %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # addr of ramdisk
+	l     %r2,.Linitrd		       # addr of ramdisk
+	st    %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
         bas   %r14,.Lloader                    # load ramdisk
  	st    %r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of ramdisk
         ltr   %r2,%r2
         bnz   .Lrdcont
         st    %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
 .Lrdcont:
-	l     %r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
+	l     %r2,.Linitrd
 
 	clc   0(3,%r2),.L_hdr		       # skip HDRx and EOFx 
 	bz    .Lagain2
@@ -379,6 +380,7 @@ iplstart:
         l     %r1,.Lstartup
         br    %r1
 
+.Linitrd:.long _end + 0x400000		       # default address of initrd
 .Lparm:	.long  PARMAREA
 .Lstartup: .long startup
 .Lcvtab:.long  _ebcasc                         # ebcdic to ascii table
@@ -479,65 +481,6 @@ start:
 	.byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7 
 	.byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff
 
-.macro GET_IPL_DEVICE
-.Lget_ipl_device:
-	l     %r1,0xb8			# get sid
-	sll   %r1,15			# test if subchannel is enabled
-	srl   %r1,31
-	ltr   %r1,%r1
-	bz    2f-.LPG1(%r13)		# subchannel disabled
-	l     %r1,0xb8
-	la    %r5,.Lipl_schib-.LPG1(%r13)
-	stsch 0(%r5)		        # get schib of subchannel
-	bnz   2f-.LPG1(%r13)		# schib not available
-	tm    5(%r5),0x01		# devno valid?
-	bno   2f-.LPG1(%r13)
-	la    %r6,ipl_parameter_flags-.LPG1(%r13)
-	oi    3(%r6),0x01		# set flag
-	la    %r2,ipl_devno-.LPG1(%r13)
-	mvc   0(2,%r2),6(%r5)		# store devno
-	tm    4(%r5),0x80		# qdio capable device?
-	bno   2f-.LPG1(%r13)
-	oi    3(%r6),0x02		# set flag
-
-	# copy ipl parameters
-
-	lhi   %r0,4096
-	l     %r2,20(%r0)		# get address of parameter list
-	lhi   %r3,IPL_PARMBLOCK_ORIGIN
-	st    %r3,20(%r0)
-	lhi   %r4,1
-	cr    %r2,%r3			# start parameters < destination ?
-	jl    0f
-	lhi   %r1,1			# copy direction is upwards
-	j     1f
-0:	lhi   %r1,-1			# copy direction is downwards
-	ar    %r2,%r0
-	ar    %r3,%r0
-	ar    %r2,%r1
-	ar    %r3,%r1
-1:	mvc   0(1,%r3),0(%r2)		# finally copy ipl parameters
-	ar    %r3,%r1
-	ar    %r2,%r1
-	sr    %r0,%r4
-	jne   1b
-	b     2f-.LPG1(%r13)
-
-	.align 4
-.Lipl_schib:
-	.rept 13
-	.long 0
-	.endr
-
-	.globl ipl_parameter_flags
-ipl_parameter_flags:
-	.long 0
-	.globl ipl_devno
-ipl_devno:
-	.word 0
-2:
-.endm
-
 #ifdef CONFIG_64BIT
 #include "head64.S"
 #else

arch/s390/kernel/head31.S

@@ -26,8 +26,8 @@ startup:basr	%r13,0			# get base
 #
 	.org	PARMAREA
 	.long	0,0			# IPL_DEVICE
-	.long	0,RAMDISK_ORIGIN	# INITRD_START
-	.long	0,RAMDISK_SIZE		# INITRD_SIZE
+	.long	0,0			# INITRD_START
+	.long	0,0			# INITRD_SIZE
 
 	.org	COMMAND_LINE
 	.byte	"root=/dev/ram0 ro"
@@ -37,12 +37,23 @@ startup:basr	%r13,0			# get base
 
 startup_continue:
 	basr	%r13,0			# get base
-.LPG1:	GET_IPL_DEVICE
+.LPG1:	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
 	lctl	%c0,%c15,.Lctl-.LPG1(%r13) # load control registers
 	l	%r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area
 					# move IPL device to lowcore
 	mvc	__LC_IPLDEV(4),IPL_DEVICE-PARMAREA(%r12)
+#
+# Setup stack
+#
+	l	%r15,.Linittu-.LPG1(%r13)
+	mvc	__LC_CURRENT(4),__TI_task(%r15)
+	ahi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE
+	st	%r15,__LC_KERNEL_STACK	# set end of kernel stack
+	ahi	%r15,-96
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear backchain
 
+	l	%r14,.Lipl_save_parameters-.LPG1(%r13)
+	basr	%r14,%r14
 #
 # clear bss memory
 #
@@ -114,6 +125,10 @@ startup_continue:
 	b	.Lfchunk-.LPG1(%r13)
 
 	.align 4
+.Lipl_save_parameters:
+	.long	ipl_save_parameters
+.Linittu:
+	.long	init_thread_union
 .Lpmask:
 	.byte	0
 .align 8
@@ -273,7 +288,23 @@ startup_continue:
 .Lbss_end:  .long _end
 .Lparmaddr: .long PARMAREA
 .Lsccbaddr: .long .Lsccb
+
+	.globl ipl_schib
+ipl_schib:
+	.rept 13
+	.long 0
+	.endr
+
+	.globl ipl_flags
+ipl_flags:
+	.long 0
+	.globl ipl_devno
+ipl_devno:
+	.word 0
+
 	.org	0x12000
+.globl s390_readinfo_sccb
+s390_readinfo_sccb:
 .Lsccb:
 	.hword	0x1000			# length, one page
 	.byte	0x00,0x00,0x00
@@ -302,16 +333,6 @@ startup_continue:
 	.globl	_stext
 _stext:	basr	%r13,0			# get base
 .LPG3:
-#
-# Setup stack
-#
-	l	%r15,.Linittu-.LPG3(%r13)
-	mvc	__LC_CURRENT(4),__TI_task(%r15)
-	ahi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE
-	st	%r15,__LC_KERNEL_STACK	# set end of kernel stack
-	ahi	%r15,-96
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear backchain
-
 # check control registers
 	stctl	%c0,%c15,0(%r15)
 	oi	2(%r15),0x40		# enable sigp emergency signal
@@ -330,6 +351,5 @@ _stext:	basr	%r13,0			# get base
 #
 	.align	8
 .Ldw:	.long	0x000a0000,0x00000000
-.Linittu:.long	init_thread_union
 .Lstart:.long	start_kernel
 .Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0

arch/s390/kernel/head64.S

@@ -26,8 +26,8 @@ startup:basr  %r13,0			 # get base
 #
 	.org   PARMAREA
 	.quad  0			# IPL_DEVICE
-	.quad  RAMDISK_ORIGIN		# INITRD_START
-	.quad  RAMDISK_SIZE		# INITRD_SIZE
+	.quad  0			# INITRD_START
+	.quad  0			# INITRD_SIZE
 
 	.org   COMMAND_LINE
 	.byte  "root=/dev/ram0 ro"
@@ -39,8 +39,8 @@ startup_continue:
 	basr  %r13,0			 # get base
 .LPG1:  sll   %r13,1                     # remove high order bit
         srl   %r13,1
-	GET_IPL_DEVICE
         lhi   %r1,1                      # mode 1 = esame
+	mvi   __LC_AR_MODE_ID,1		 # set esame flag
         slr   %r0,%r0                    # set cpuid to zero
         sigp  %r1,%r0,0x12               # switch to esame mode
 	sam64				 # switch to 64 bit mode
@@ -48,7 +48,18 @@ startup_continue:
 	lg    %r12,.Lparmaddr-.LPG1(%r13)# pointer to parameter area
 					 # move IPL device to lowcore
         mvc   __LC_IPLDEV(4),IPL_DEVICE+4-PARMAREA(%r12)
+#
+# Setup stack
+#
+	larl  %r15,init_thread_union
+	lg    %r14,__TI_task(%r15)	# cache current in lowcore
+	stg   %r14,__LC_CURRENT
+	aghi  %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE
+	stg   %r15,__LC_KERNEL_STACK	# set end of kernel stack
+	aghi  %r15,-160
+	xc    __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear backchain
 
+	brasl %r14,ipl_save_parameters
 #
 # clear bss memory
 #
@@ -239,6 +250,19 @@ startup_continue:
 	oi	7(%r12),0x80		# set IDTE flag
 0:
 
+#
+# find out if we have the MVCOS instruction
+#
+	la	%r1,0f-.LPG1(%r13)	# set program check address
+	stg	%r1,__LC_PGM_NEW_PSW+8
+	.short	0xc800			# mvcos 0(%r0),0(%r0),%r0
+	.short	0x0000
+	.short	0x0000
+0:	tm	0x8f,0x13		# special-operation exception?
+	bno	1f-.LPG1(%r13)		# if yes, MVCOS is present
+	oi	6(%r12),2		# set MVCOS flag
+1:
+
         lpswe .Lentry-.LPG1(13)         # jump to _stext in primary-space,
                                         # virtual and never return ...
         .align 16
@@ -268,7 +292,22 @@ startup_continue:
 .Lparmaddr:
 	.quad	PARMAREA
 
+	.globl ipl_schib
+ipl_schib:
+	.rept 13
+	.long 0
+	.endr
+
+	.globl ipl_flags
+ipl_flags:
+	.long 0
+	.globl ipl_devno
+ipl_devno:
+	.word 0
+
 	.org	0x12000
+.globl s390_readinfo_sccb
+s390_readinfo_sccb:
 .Lsccb:
 	.hword 0x1000			# length, one page
 	.byte 0x00,0x00,0x00
@@ -297,24 +336,12 @@ startup_continue:
         .globl _stext
 _stext:	basr  %r13,0                    # get base
 .LPG3:
-#
-# Setup stack
-#
-	larl  %r15,init_thread_union
-	lg    %r14,__TI_task(%r15)      # cache current in lowcore
-	stg   %r14,__LC_CURRENT
-        aghi  %r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE
-        stg   %r15,__LC_KERNEL_STACK    # set end of kernel stack
-        aghi  %r15,-160
-        xc    __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear backchain
-
 # check control registers
         stctg  %c0,%c15,0(%r15)
 	oi     6(%r15),0x40             # enable sigp emergency signal
 	oi     4(%r15),0x10             # switch on low address proctection
         lctlg  %c0,%c15,0(%r15)
 
-#
         lam    0,15,.Laregs-.LPG3(%r13) # load access regs needed by uaccess
         brasl  %r14,start_kernel        # go to C code
 #
@@ -322,7 +349,7 @@ _stext:	basr  %r13,0                    # get base
 #
         basr  %r13,0
 	lpswe .Ldw-.(%r13)           # load disabled wait psw
-#
+
             .align 8
 .Ldw:       .quad  0x0002000180000000,0x0000000000000000
 .Laregs:    .long  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0

arch/s390/kernel/reipl.S

@@ -8,13 +8,30 @@
 
 #include <asm/lowcore.h>
 
-		.globl	do_reipl
-do_reipl:	basr	%r13,0
+		.globl	do_reipl_asm
+do_reipl_asm:	basr	%r13,0
 .Lpg0:		lpsw	.Lnewpsw-.Lpg0(%r13)
-.Lpg1:		lctl	%c6,%c6,.Lall-.Lpg0(%r13)
-                stctl   %c0,%c0,.Lctlsave-.Lpg0(%r13)
-                ni      .Lctlsave-.Lpg0(%r13),0xef
-                lctl    %c0,%c0,.Lctlsave-.Lpg0(%r13)
+
+		# switch off lowcore protection
+
+.Lpg1:		stctl	%c0,%c0,.Lctlsave1-.Lpg0(%r13)
+		stctl	%c0,%c0,.Lctlsave2-.Lpg0(%r13)
+		ni	.Lctlsave1-.Lpg0(%r13),0xef
+		lctl	%c0,%c0,.Lctlsave1-.Lpg0(%r13)
+
+		# do store status of all registers
+
+		stm	%r0,%r15,__LC_GPREGS_SAVE_AREA
+		stctl	%c0,%c15,__LC_CREGS_SAVE_AREA
+		mvc	__LC_CREGS_SAVE_AREA(4),.Lctlsave2-.Lpg0(%r13)
+		stam	%a0,%a15,__LC_AREGS_SAVE_AREA
+		stpx	__LC_PREFIX_SAVE_AREA
+		stckc	.Lclkcmp-.Lpg0(%r13)
+		mvc	__LC_CLOCK_COMP_SAVE_AREA(8),.Lclkcmp-.Lpg0(%r13)
+		stpt	__LC_CPU_TIMER_SAVE_AREA
+		st	%r13, __LC_PSW_SAVE_AREA+4
+
+		lctl	%c6,%c6,.Lall-.Lpg0(%r13)
                 lr      %r1,%r2
         	mvc     __LC_PGM_NEW_PSW(8),.Lpcnew-.Lpg0(%r13)
                 stsch   .Lschib-.Lpg0(%r13)                                    
@@ -46,9 +63,11 @@ do_reipl:	basr	%r13,0
 .Ldisab:	st      %r14,.Ldispsw+4-.Lpg0(%r13)
 		lpsw	.Ldispsw-.Lpg0(%r13)
                 .align 	8
+.Lclkcmp:	.quad	0x0000000000000000
 .Lall:		.long	0xff000000
 .Lnull:		.long   0x00000000
-.Lctlsave:      .long   0x00000000
+.Lctlsave1:	.long	0x00000000
+.Lctlsave2:	.long	0x00000000
                 .align 	8
 .Lnewpsw:	.long   0x00080000,0x80000000+.Lpg1
 .Lpcnew:  	.long   0x00080000,0x80000000+.Lecs

arch/s390/kernel/reipl64.S

@@ -8,13 +8,30 @@
  */
 
 #include <asm/lowcore.h>
-		.globl	do_reipl
-do_reipl:	basr	%r13,0
-.Lpg0:		lpswe   .Lnewpsw-.Lpg0(%r13)
+		.globl	do_reipl_asm
+do_reipl_asm:	basr	%r13,0
+
+		# do store status of all registers
+
+.Lpg0:		stg	%r1,.Lregsave-.Lpg0(%r13)
+		lghi	%r1,0x1000
+		stmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-0x1000(%r1)
+		lg	%r0,.Lregsave-.Lpg0(%r13)
+		stg	%r0,__LC_GPREGS_SAVE_AREA-0x1000+8(%r1)
+		stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-0x1000(%r1)
+		stam	%a0,%a15,__LC_AREGS_SAVE_AREA-0x1000(%r1)
+		stpx	__LC_PREFIX_SAVE_AREA-0x1000(%r1)
+		stfpc	__LC_FP_CREG_SAVE_AREA-0x1000(%r1)
+		stckc	.Lclkcmp-.Lpg0(%r13)
+		mvc	__LC_CLOCK_COMP_SAVE_AREA-0x1000(8,%r1),.Lclkcmp-.Lpg0(%r13)
+		stpt	__LC_CPU_TIMER_SAVE_AREA-0x1000(%r1)
+		stg	%r13, __LC_PSW_SAVE_AREA-0x1000+8(%r1)
+
+		lpswe	.Lnewpsw-.Lpg0(%r13)
 .Lpg1:		lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
-                stctg   %c0,%c0,.Lctlsave-.Lpg0(%r13)
-                ni      .Lctlsave+4-.Lpg0(%r13),0xef
-                lctlg   %c0,%c0,.Lctlsave-.Lpg0(%r13)
+		stctg	%c0,%c0,.Lregsave-.Lpg0(%r13)
+		ni	.Lregsave+4-.Lpg0(%r13),0xef
+		lctlg	%c0,%c0,.Lregsave-.Lpg0(%r13)
                 lgr     %r1,%r2
         	mvc     __LC_PGM_NEW_PSW(16),.Lpcnew-.Lpg0(%r13)
                 stsch   .Lschib-.Lpg0(%r13)                                    
@@ -50,8 +67,9 @@ do_reipl:	basr	%r13,0
 		st     %r14,.Ldispsw+12-.Lpg0(%r13)
 		lpswe	.Ldispsw-.Lpg0(%r13)
                 .align 	8
+.Lclkcmp:	.quad	0x0000000000000000
 .Lall:		.quad	0x00000000ff000000
-.Lctlsave:      .quad   0x0000000000000000
+.Lregsave:	.quad	0x0000000000000000
 .Lnull:		.long   0x0000000000000000
                 .align 	16
 /*
@@ -92,5 +110,3 @@ do_reipl:	basr	%r13,0
 		.long	0x00000000,0x00000000
 		.long	0x00000000,0x00000000
 	
-
-	

arch/s390/kernel/reipl_diag.c

-/*
- * This file contains the implementation of the
- * Linux re-IPL support
- *
- * (C) Copyright IBM Corp. 2005
- *
- * Author(s): Volker Sameske (sameske@de.ibm.com)
- *
- */
-
-#include <linux/kernel.h>
-
-static unsigned int reipl_diag_rc1;
-static unsigned int reipl_diag_rc2;
-
-/*
- * re-IPL the system using the last used IPL parameters
- */
-void reipl_diag(void)
-{
-        asm volatile (
-		"   la   %%r4,0\n"
-		"   la   %%r5,0\n"
-                "   diag %%r4,%2,0x308\n"
-                "0:\n"
-		"   st   %%r4,%0\n"
-		"   st   %%r5,%1\n"
-                ".section __ex_table,\"a\"\n"
-#ifdef CONFIG_64BIT
-                "   .align 8\n"
-                "   .quad 0b, 0b\n"
-#else
-                "   .align 4\n"
-                "   .long 0b, 0b\n"
-#endif
-                ".previous\n"
-                : "=m" (reipl_diag_rc1), "=m" (reipl_diag_rc2)
-		: "d" (3) : "cc", "4", "5" );
-}

arch/s390/kernel/s390_ksyms.c

@@ -25,12 +25,6 @@ EXPORT_SYMBOL(_oi_bitmap);
 EXPORT_SYMBOL(_ni_bitmap);
 EXPORT_SYMBOL(_zb_findmap);
 EXPORT_SYMBOL(_sb_findmap);
-EXPORT_SYMBOL(__copy_from_user_asm);
-EXPORT_SYMBOL(__copy_to_user_asm);
-EXPORT_SYMBOL(__copy_in_user_asm);
-EXPORT_SYMBOL(__clear_user_asm);
-EXPORT_SYMBOL(__strncpy_from_user_asm);
-EXPORT_SYMBOL(__strnlen_user_asm);
 EXPORT_SYMBOL(diag10);
 
 /*

arch/s390/kernel/setup.c

@@ -37,6 +37,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
+#include <linux/pfn.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -49,6 +50,12 @@
 #include <asm/ptrace.h>
 #include <asm/sections.h>
 
+/*
+ * User copy operations.
+ */
+struct uaccess_ops uaccess;
+EXPORT_SYMBOL_GPL(uaccess);
+
 /*
  * Machine setup..
  */
@@ -284,16 +291,9 @@ void (*_machine_power_off)(void) = machine_power_off_smp;
 /*
  * Reboot, halt and power_off routines for non SMP.
  */
-extern void reipl(unsigned long devno);
-extern void reipl_diag(void);
 static void do_machine_restart_nonsmp(char * __unused)
 {
-	reipl_diag();
-
-	if (MACHINE_IS_VM)
-		cpcmd ("IPL", NULL, 0, NULL);
-	else
-		reipl (0x10000 | S390_lowcore.ipl_device);
+	do_reipl();
 }
 
 static void do_machine_halt_nonsmp(void)
@@ -501,13 +501,47 @@ setup_memory(void)
 	 * partially used pages are not usable - thus
 	 * we are rounding upwards:
 	 */
-	start_pfn = (__pa(&_end) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	end_pfn = max_pfn = memory_end >> PAGE_SHIFT;
+	start_pfn = PFN_UP(__pa(&_end));
+	end_pfn = max_pfn = PFN_DOWN(memory_end);
 
 	/* Initialize storage key for kernel pages */
 	for (init_pfn = 0 ; init_pfn < start_pfn; init_pfn++)
 		page_set_storage_key(init_pfn << PAGE_SHIFT, PAGE_DEFAULT_KEY);
 
+#ifdef CONFIG_BLK_DEV_INITRD
+	/*
+	 * Move the initrd in case the bitmap of the bootmem allocater
+	 * would overwrite it.
+	 */
+
+	if (INITRD_START && INITRD_SIZE) {
+		unsigned long bmap_size;
+		unsigned long start;
+
+		bmap_size = bootmem_bootmap_pages(end_pfn - start_pfn + 1);
+		bmap_size = PFN_PHYS(bmap_size);
+
+		if (PFN_PHYS(start_pfn) + bmap_size > INITRD_START) {
+			start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE;
+
+			if (start + INITRD_SIZE > memory_end) {
+				printk("initrd extends beyond end of memory "
+				       "(0x%08lx > 0x%08lx)\n"
+				       "disabling initrd\n",
+				       start + INITRD_SIZE, memory_end);
+				INITRD_START = INITRD_SIZE = 0;
+			} else {
+				printk("Moving initrd (0x%08lx -> 0x%08lx, "
+				       "size: %ld)\n",
+				       INITRD_START, start, INITRD_SIZE);
+				memmove((void *) start, (void *) INITRD_START,
+					INITRD_SIZE);
+				INITRD_START = start;
+			}
+		}
+	}
+#endif
+
 	/*
 	 * Initialize the boot-time allocator (with low memory only):
 	 */
@@ -559,7 +593,7 @@ setup_memory(void)
 	reserve_bootmem(start_pfn << PAGE_SHIFT, bootmap_size);
 
 #ifdef CONFIG_BLK_DEV_INITRD
-	if (INITRD_START) {
+	if (INITRD_START && INITRD_SIZE) {
 		if (INITRD_START + INITRD_SIZE <= memory_end) {
 			reserve_bootmem(INITRD_START, INITRD_SIZE);
 			initrd_start = INITRD_START;
@@ -613,6 +647,11 @@ setup_arch(char **cmdline_p)
 
 	memory_end = memory_size;
 
+	if (MACHINE_HAS_MVCOS)
+		memcpy(&uaccess, &uaccess_mvcos, sizeof(uaccess));
+	else
+		memcpy(&uaccess, &uaccess_std, sizeof(uaccess));
+
 	parse_early_param();
 
 #ifndef CONFIG_64BIT
@@ -720,214 +759,3 @@ struct seq_operations cpuinfo_op = {
 	.show	= show_cpuinfo,
 };
 
-#define DEFINE_IPL_ATTR(_name, _format, _value)			\
-static ssize_t ipl_##_name##_show(struct subsystem *subsys,	\
-		char *page)					\
-{								\
-	return sprintf(page, _format, _value);			\
-}								\
-static struct subsys_attribute ipl_##_name##_attr =		\
-	__ATTR(_name, S_IRUGO, ipl_##_name##_show, NULL);
-
-DEFINE_IPL_ATTR(wwpn, "0x%016llx\n", (unsigned long long)
-		IPL_PARMBLOCK_START->fcp.wwpn);
-DEFINE_IPL_ATTR(lun, "0x%016llx\n", (unsigned long long)
-		IPL_PARMBLOCK_START->fcp.lun);
-DEFINE_IPL_ATTR(bootprog, "%lld\n", (unsigned long long)
-		IPL_PARMBLOCK_START->fcp.bootprog);
-DEFINE_IPL_ATTR(br_lba, "%lld\n", (unsigned long long)
-		IPL_PARMBLOCK_START->fcp.br_lba);
-
-enum ipl_type_type {
-	ipl_type_unknown,
-	ipl_type_ccw,
-	ipl_type_fcp,
-};
-
-static enum ipl_type_type
-get_ipl_type(void)
-{
-	struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START;
-
-	if (!IPL_DEVNO_VALID)
-		return ipl_type_unknown;
-	if (!IPL_PARMBLOCK_VALID)
-		return ipl_type_ccw;
-	if (ipl->hdr.header.version > IPL_MAX_SUPPORTED_VERSION)
-		return ipl_type_unknown;
-	if (ipl->fcp.pbt != IPL_TYPE_FCP)
-		return ipl_type_unknown;
-	return ipl_type_fcp;
-}
-
-static ssize_t
-ipl_type_show(struct subsystem *subsys, char *page)
-{
-	switch (get_ipl_type()) {
-	case ipl_type_ccw:
-		return sprintf(page, "ccw\n");
-	case ipl_type_fcp:
-		return sprintf(page, "fcp\n");
-	default:
-		return sprintf(page, "unknown\n");
-	}
-}
-
-static struct subsys_attribute ipl_type_attr = __ATTR_RO(ipl_type);
-
-static ssize_t
-ipl_device_show(struct subsystem *subsys, char *page)
-{
-	struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START;
-
-	switch (get_ipl_type()) {
-	case ipl_type_ccw:
-		return sprintf(page, "0.0.%04x\n", ipl_devno);
-	case ipl_type_fcp:
-		return sprintf(page, "0.0.%04x\n", ipl->fcp.devno);
-	default:
-		return 0;
-	}
-}
-
-static struct subsys_attribute ipl_device_attr =
-	__ATTR(device, S_IRUGO, ipl_device_show, NULL);
-
-static struct attribute *ipl_fcp_attrs[] = {
-	&ipl_type_attr.attr,
-	&ipl_device_attr.attr,
-	&ipl_wwpn_attr.attr,
-	&ipl_lun_attr.attr,
-	&ipl_bootprog_attr.attr,
-	&ipl_br_lba_attr.attr,
-	NULL,
-};
-
-static struct attribute_group ipl_fcp_attr_group = {
-	.attrs = ipl_fcp_attrs,
-};
-
-static struct attribute *ipl_ccw_attrs[] = {
-	&ipl_type_attr.attr,
-	&ipl_device_attr.attr,
-	NULL,
-};
-
-static struct attribute_group ipl_ccw_attr_group = {
-	.attrs = ipl_ccw_attrs,
-};
-
-static struct attribute *ipl_unknown_attrs[] = {
-	&ipl_type_attr.attr,
-	NULL,
-};
-
-static struct attribute_group ipl_unknown_attr_group = {
-	.attrs = ipl_unknown_attrs,
-};
-
-static ssize_t
-ipl_parameter_read(struct kobject *kobj, char *buf, loff_t off, size_t count)
-{
-	unsigned int size = IPL_PARMBLOCK_SIZE;
-
-	if (off > size)
-		return 0;
-	if (off + count > size)
-		count = size - off;
-
-	memcpy(buf, (void *) IPL_PARMBLOCK_START + off, count);
-	return count;
-}
-
-static struct bin_attribute ipl_parameter_attr = {
-	.attr = {
-		.name = "binary_parameter",
-		.mode = S_IRUGO,
-		.owner = THIS_MODULE,
-	},
-	.size = PAGE_SIZE,
-	.read = &ipl_parameter_read,
-};
-
-static ssize_t
-ipl_scp_data_read(struct kobject *kobj, char *buf, loff_t off, size_t count)
-{
-	unsigned int size =  IPL_PARMBLOCK_START->fcp.scp_data_len;
-	void *scp_data = &IPL_PARMBLOCK_START->fcp.scp_data;
-
-	if (off > size)
-		return 0;
-	if (off + count > size)
-		count = size - off;
-
-	memcpy(buf, scp_data + off, count);
-	return count;
-}
-
-static struct bin_attribute ipl_scp_data_attr = {
-	.attr = {
-		.name = "scp_data",
-		.mode = S_IRUGO,
-		.owner = THIS_MODULE,
-	},
-	.size = PAGE_SIZE,
-	.read = &ipl_scp_data_read,
-};
-
-static decl_subsys(ipl, NULL, NULL);
-
-static int ipl_register_fcp_files(void)
-{
-	int rc;
-
-	rc = sysfs_create_group(&ipl_subsys.kset.kobj,
-				&ipl_fcp_attr_group);
-	if (rc)
-		goto out;
-	rc = sysfs_create_bin_file(&ipl_subsys.kset.kobj,
-				   &ipl_parameter_attr);
-	if (rc)
-		goto out_ipl_parm;
-	rc = sysfs_create_bin_file(&ipl_subsys.kset.kobj,
-				   &ipl_scp_data_attr);
-	if (!rc)
-		goto out;
-
-	sysfs_remove_bin_file(&ipl_subsys.kset.kobj, &ipl_parameter_attr);
-
-out_ipl_parm:
-	sysfs_remove_group(&ipl_subsys.kset.kobj, &ipl_fcp_attr_group);
-out:
-	return rc;
-}
-
-static int __init
-ipl_device_sysfs_register(void) {
-	int rc;
-
-	rc = firmware_register(&ipl_subsys);
-	if (rc)
-		goto out;
-
-	switch (get_ipl_type()) {
-	case ipl_type_ccw:
-		rc = sysfs_create_group(&ipl_subsys.kset.kobj,
-					&ipl_ccw_attr_group);
-		break;
-	case ipl_type_fcp:
-		rc = ipl_register_fcp_files();
-		break;
-	default:
-		rc = sysfs_create_group(&ipl_subsys.kset.kobj,
-					&ipl_unknown_attr_group);
-		break;
-	}
-
-	if (rc)
-		firmware_unregister(&ipl_subsys);
-out:
-	return rc;
-}
-
-__initcall(ipl_device_sysfs_register);

arch/s390/kernel/signal.c

@@ -114,29 +114,26 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 {
 	unsigned long old_mask = regs->psw.mask;
-	int err;
+	_sigregs user_sregs;
 
 	save_access_regs(current->thread.acrs);
 
 	/* Copy a 'clean' PSW mask to the user to avoid leaking
 	   information about whether PER is currently on.  */
 	regs->psw.mask = PSW_MASK_MERGE(PSW_USER_BITS, regs->psw.mask);
-	err = __copy_to_user(&sregs->regs.psw, &regs->psw,
-			     sizeof(sregs->regs.psw)+sizeof(sregs->regs.gprs));
+	memcpy(&user_sregs.regs.psw, &regs->psw, sizeof(sregs->regs.psw) +
+	       sizeof(sregs->regs.gprs));
 	regs->psw.mask = old_mask;
-	if (err != 0)
-		return err;
-	err = __copy_to_user(&sregs->regs.acrs, current->thread.acrs,
+	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(sregs->regs.acrs));
-	if (err != 0)
-		return err;
 	/* 
 	 * We have to store the fp registers to current->thread.fp_regs
 	 * to merge them with the emulated registers.
 	 */
 	save_fp_regs(&current->thread.fp_regs);
-	return __copy_to_user(&sregs->fpregs, &current->thread.fp_regs,
+	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(s390_fp_regs));
+	return __copy_to_user(sregs, &user_sregs, sizeof(_sigregs));
 }
 
 /* Returns positive number on error */
@@ -144,27 +141,25 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 {
 	unsigned long old_mask = regs->psw.mask;
 	int err;
+	_sigregs user_sregs;
 
 	/* Alwys make any pending restarted system call return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-	err = __copy_from_user(&regs->psw, &sregs->regs.psw,
-			       sizeof(sregs->regs.psw)+sizeof(sregs->regs.gprs));
+	err = __copy_from_user(&user_sregs, sregs, sizeof(_sigregs));
 	regs->psw.mask = PSW_MASK_MERGE(old_mask, regs->psw.mask);
 	regs->psw.addr |= PSW_ADDR_AMODE;
 	if (err)
 		return err;
-	err = __copy_from_user(&current->thread.acrs, &sregs->regs.acrs,
+	memcpy(&regs->psw, &user_sregs.regs.psw, sizeof(sregs->regs.psw) +
+	       sizeof(sregs->regs.gprs));
+	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(sregs->regs.acrs));
-	if (err)
-		return err;
 	restore_access_regs(current->thread.acrs);
 
-	err = __copy_from_user(&current->thread.fp_regs, &sregs->fpregs,
+	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(s390_fp_regs));
 	current->thread.fp_regs.fpc &= FPC_VALID_MASK;
-	if (err)
-		return err;
 
 	restore_fp_regs(&current->thread.fp_regs);
 	regs->trap = -1;	/* disable syscall checks */
@@ -457,6 +452,7 @@ void do_signal(struct pt_regs *regs)
 		case -ERESTART_RESTARTBLOCK:
 			regs->gprs[2] = -EINTR;
 		}
+		regs->trap = -1;	/* Don't deal with this again. */
 	}
 
 	/* Get signal to deliver.  When running under ptrace, at this point

arch/s390/kernel/smp.c

@@ -59,9 +59,6 @@ static struct task_struct *current_set[NR_CPUS];
 extern char vmhalt_cmd[];
 extern char vmpoff_cmd[];
 
-extern void reipl(unsigned long devno);
-extern void reipl_diag(void);
-
 static void smp_ext_bitcall(int, ec_bit_sig);
 static void smp_ext_bitcall_others(ec_bit_sig);
 
@@ -279,12 +276,7 @@ static void do_machine_restart(void * __unused)
 	 * interrupted by an external interrupt and s390irq
 	 * locks are always held disabled).
 	 */
-	reipl_diag();
-
-	if (MACHINE_IS_VM)
-		cpcmd ("IPL", NULL, 0, NULL);
-	else
-		reipl (0x10000 | S390_lowcore.ipl_device);
+	do_reipl();
 }
 
 void machine_restart_smp(char * __unused) 

arch/s390/kernel/traps.c

@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/reboot.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -39,6 +40,7 @@
 #include <asm/s390_ext.h>
 #include <asm/lowcore.h>
 #include <asm/debug.h>
+#include <asm/kdebug.h>
 
 /* Called from entry.S only */
 extern void handle_per_exception(struct pt_regs *regs);
@@ -74,6 +76,20 @@ static int kstack_depth_to_print = 12;
 static int kstack_depth_to_print = 20;
 #endif /* CONFIG_64BIT */
 
+ATOMIC_NOTIFIER_HEAD(s390die_chain);
+
+int register_die_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&s390die_chain, nb);
+}
+EXPORT_SYMBOL(register_die_notifier);
+
+int unregister_die_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&s390die_chain, nb);
+}
+EXPORT_SYMBOL(unregister_die_notifier);
+
 /*
  * For show_trace we have tree different stack to consider:
  *   - the panic stack which is used if the kernel stack has overflown
@@ -305,8 +321,9 @@ report_user_fault(long interruption_code, struct pt_regs *regs)
 #endif
 }
 
-static void inline do_trap(long interruption_code, int signr, char *str,
-                           struct pt_regs *regs, siginfo_t *info)
+static void __kprobes inline do_trap(long interruption_code, int signr,
+					char *str, struct pt_regs *regs,
+					siginfo_t *info)
 {
 	/*
 	 * We got all needed information from the lowcore and can
@@ -315,6 +332,10 @@ static void inline do_trap(long interruption_code, int signr, char *str,
         if (regs->psw.mask & PSW_MASK_PSTATE)
 		local_irq_enable();
 
+	if (notify_die(DIE_TRAP, str, regs, interruption_code,
+				interruption_code, signr) == NOTIFY_STOP)
+		return;
+
         if (regs->psw.mask & PSW_MASK_PSTATE) {
                 struct task_struct *tsk = current;
 
@@ -336,8 +357,12 @@ static inline void __user *get_check_address(struct pt_regs *regs)
 	return (void __user *)((regs->psw.addr-S390_lowcore.pgm_ilc) & PSW_ADDR_INSN);
 }
 
-void do_single_step(struct pt_regs *regs)
+void __kprobes do_single_step(struct pt_regs *regs)
 {
+	if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0,
+					SIGTRAP) == NOTIFY_STOP){
+		return;
+	}
 	if ((current->ptrace & PT_PTRACED) != 0)
 		force_sig(SIGTRAP, current);
 }

arch/s390/kernel/vmlinux.lds.S

@@ -24,6 +24,7 @@ SECTIONS
 	*(.text)
 	SCHED_TEXT
 	LOCK_TEXT
+	KPROBES_TEXT
 	*(.fixup)
 	*(.gnu.warning)
 	} = 0x0700
@@ -117,7 +118,7 @@ SECTIONS
 
   /* Sections to be discarded */
   /DISCARD/ : {
-	*(.exitcall.exit)
+	*(.exit.text) *(.exit.data) *(.exitcall.exit)
 	}
 
   /* Stabs debugging sections.  */

arch/s390/lib/Makefile

@@ -4,6 +4,6 @@
 
 EXTRA_AFLAGS := -traditional
 
-lib-y += delay.o string.o
-lib-y += $(if $(CONFIG_64BIT),uaccess64.o,uaccess.o)
+lib-y += delay.o string.o uaccess_std.o
+lib-$(CONFIG_64BIT) += uaccess_mvcos.o
 lib-$(CONFIG_SMP) += spinlock.o

arch/s390/lib/uaccess.S

-/*
- *  arch/s390/lib/uaccess.S
- *    __copy_{from|to}_user functions.
- *
- *  s390
- *    Copyright (C) 2000,2002 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Authors(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- *  These functions have standard call interface
- */
-
-#include <linux/errno.h>
-#include <asm/lowcore.h>
-#include <asm/asm-offsets.h>
-
-        .text
-        .align 4
-        .globl __copy_from_user_asm
-	# %r2 = to, %r3 = n, %r4 = from
-__copy_from_user_asm:
-	slr	%r0,%r0
-0:	mvcp	0(%r3,%r2),0(%r4),%r0
-	jnz	1f
-	slr	%r2,%r2
-	br	%r14
-1:	la	%r2,256(%r2)
-	la	%r4,256(%r4)
-	ahi	%r3,-256
-2:	mvcp	0(%r3,%r2),0(%r4),%r0
-	jnz	1b
-3:	slr	%r2,%r2
-	br	%r14
-4:	lhi	%r0,-4096
-	lr	%r5,%r4
-	slr	%r5,%r0
-	nr	%r5,%r0		# %r5 = (%r4 + 4096) & -4096
-	slr	%r5,%r4		# %r5 = #bytes to next user page boundary
-	clr	%r3,%r5		# copy crosses next page boundary ?
-	jnh	6f		# no, the current page faulted
-	# move with the reduced length which is < 256
-5:	mvcp	0(%r5,%r2),0(%r4),%r0
-	slr	%r3,%r5
-6:	lr	%r2,%r3
-	br	%r14
-        .section __ex_table,"a"
-	.long	0b,4b
-	.long	2b,4b
-	.long	5b,6b
-        .previous
-
-        .align 4
-        .text
-        .globl __copy_to_user_asm
-	# %r2 = from, %r3 = n, %r4 = to
-__copy_to_user_asm:
-	slr	%r0,%r0
-0:	mvcs	0(%r3,%r4),0(%r2),%r0
-	jnz	1f
-	slr	%r2,%r2
-	br	%r14
-1:	la	%r2,256(%r2)
-	la	%r4,256(%r4)
-	ahi	%r3,-256
-2:	mvcs	0(%r3,%r4),0(%r2),%r0
-	jnz	1b
-3:	slr	%r2,%r2
-	br	%r14
-4:	lhi	%r0,-4096
-	lr	%r5,%r4
-	slr	%r5,%r0
-	nr	%r5,%r0		# %r5 = (%r4 + 4096) & -4096
-	slr	%r5,%r4		# %r5 = #bytes to next user page boundary
-	clr	%r3,%r5		# copy crosses next page boundary ?
-	jnh	6f		# no, the current page faulted
-	# move with the reduced length which is < 256
-5:	mvcs	0(%r5,%r4),0(%r2),%r0
-	slr	%r3,%r5
-6:	lr	%r2,%r3
-	br	%r14
-        .section __ex_table,"a"
-	.long	0b,4b
-	.long	2b,4b
-	.long	5b,6b
-        .previous
-
-        .align 4
-        .text
-        .globl __copy_in_user_asm
-	# %r2 = from, %r3 = n, %r4 = to
-__copy_in_user_asm:
-	ahi	%r3,-1
-	jo	6f
-	sacf	256
-	bras	%r1,4f
-0:	ahi	%r3,257
-1:	mvc	0(1,%r4),0(%r2)
-	la	%r2,1(%r2)
-	la	%r4,1(%r4)
-	ahi	%r3,-1
-	jnz	1b
-2:	lr	%r2,%r3
-	br	%r14
-3:	mvc	0(256,%r4),0(%r2)
-	la	%r2,256(%r2)
-	la	%r4,256(%r4)
-4:	ahi	%r3,-256
-	jnm	3b
-5:	ex	%r3,4(%r1)
-	sacf	0
-6:	slr	%r2,%r2
-	br	%r14
-        .section __ex_table,"a"
-	.long	1b,2b
-	.long	3b,0b
-	.long	5b,0b
-        .previous
-
-        .align 4
-        .text
-        .globl __clear_user_asm
-	# %r2 = to, %r3 = n
-__clear_user_asm:
-	bras	%r5,0f
-	.long	empty_zero_page
-0:	l	%r5,0(%r5)
-	slr	%r0,%r0
-1:	mvcs	0(%r3,%r2),0(%r5),%r0
-	jnz	2f
-	slr	%r2,%r2
-	br	%r14
-2:	la	%r2,256(%r2)
-	ahi	%r3,-256
-3:	mvcs	0(%r3,%r2),0(%r5),%r0
-	jnz	2b
-4:	slr	%r2,%r2
-	br	%r14
-5:	lhi	%r0,-4096
-	lr	%r4,%r2
-	slr	%r4,%r0
-	nr	%r4,%r0		# %r4 = (%r2 + 4096) & -4096
-	slr	%r4,%r2		# %r4 = #bytes to next user page boundary
-	clr	%r3,%r4		# clear crosses next page boundary ?
-	jnh	7f		# no, the current page faulted
-	# clear with the reduced length which is < 256
-6:	mvcs	0(%r4,%r2),0(%r5),%r0
-	slr	%r3,%r4
-7:	lr	%r2,%r3
-	br	%r14
-        .section __ex_table,"a"
-	.long	1b,5b
-	.long	3b,5b
-	.long	6b,7b
-        .previous
-
-        .align 4
-        .text
-        .globl __strncpy_from_user_asm
-	# %r2 = count, %r3 = dst, %r4 = src
-__strncpy_from_user_asm:
-	lhi	%r0,0
-	lr	%r1,%r4
-	la	%r4,0(%r4)	# clear high order bit from %r4
-	la	%r2,0(%r2,%r4)	# %r2 points to first byte after string
-	sacf	256
-0:	srst	%r2,%r1
-	jo	0b
-	sacf	0
-	lr	%r1,%r2
-	jh	1f		# \0 found in string ?
-	ahi	%r1,1		# include \0 in copy
-1:	slr	%r1,%r4		# %r1 = copy length (without \0)
-	slr	%r2,%r4		# %r2 = return length (including \0)
-2:	mvcp	0(%r1,%r3),0(%r4),%r0
-	jnz	3f
-	br	%r14
-3:	la	%r3,256(%r3)
-	la	%r4,256(%r4)
-	ahi	%r1,-256
-	mvcp	0(%r1,%r3),0(%r4),%r0
-	jnz	3b
-	br	%r14
-4:	sacf	0
-	lhi	%r2,-EFAULT
-	br	%r14
-	.section __ex_table,"a"
-	.long	0b,4b
-	.previous
-
-        .align 4
-        .text
-        .globl __strnlen_user_asm
-	# %r2 = count, %r3 = src
-__strnlen_user_asm:
-	lhi	%r0,0
-	lr	%r1,%r3
-	la	%r3,0(%r3)	# clear high order bit from %r4
-	la	%r2,0(%r2,%r3)	# %r2 points to first byte after string
-	sacf	256
-0:	srst	%r2,%r1
-	jo	0b
-	sacf	0
-	ahi	%r2,1		# strnlen_user result includes the \0
-				# or return count+1 if \0 not found
-	slr	%r2,%r3
-	br	%r14
-2:	sacf	0
-	slr	%r2,%r2		# return 0 on exception
-	br	%r14
-	.section __ex_table,"a"
-	.long	0b,2b
-	.previous

arch/s390/lib/uaccess64.S

-/*
- *  arch/s390x/lib/uaccess.S
- *    __copy_{from|to}_user functions.
- *
- *  s390
- *    Copyright (C) 2000,2002 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Authors(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
- *
- *  These functions have standard call interface
- */
-
-#include <linux/errno.h>
-#include <asm/lowcore.h>
-#include <asm/asm-offsets.h>
-
-        .text
-        .align 4
-        .globl __copy_from_user_asm
-	# %r2 = to, %r3 = n, %r4 = from
-__copy_from_user_asm:
-	slgr	%r0,%r0
-0:	mvcp	0(%r3,%r2),0(%r4),%r0
-	jnz	1f
-	slgr	%r2,%r2
-	br	%r14
-1:	la	%r2,256(%r2)
-	la	%r4,256(%r4)
-	aghi	%r3,-256
-2:	mvcp	0(%r3,%r2),0(%r4),%r0
-	jnz	1b
-3:	slgr	%r2,%r2
-	br	%r14
-4:	lghi	%r0,-4096
-	lgr	%r5,%r4
-	slgr	%r5,%r0
-	ngr	%r5,%r0		# %r5 = (%r4 + 4096) & -4096
-	slgr	%r5,%r4		# %r5 = #bytes to next user page boundary
-	clgr	%r3,%r5		# copy crosses next page boundary ?
-	jnh	6f		# no, the current page faulted
-	# move with the reduced length which is < 256
-5:	mvcp	0(%r5,%r2),0(%r4),%r0
-	slgr	%r3,%r5
-6:	lgr	%r2,%r3
-	br	%r14
-        .section __ex_table,"a"
-	.quad	0b,4b
-	.quad	2b,4b
-	.quad	5b,6b
-        .previous
-
-        .align 4
-        .text
-        .globl __copy_to_user_asm
-	# %r2 = from, %r3 = n, %r4 = to
-__copy_to_user_asm:
-	slgr	%r0,%r0
-0:	mvcs	0(%r3,%r4),0(%r2),%r0
-	jnz	1f
-	slgr	%r2,%r2
-	br	%r14
-1:	la	%r2,256(%r2)
-	la	%r4,256(%r4)
-	aghi	%r3,-256
-2:	mvcs	0(%r3,%r4),0(%r2),%r0
-	jnz	1b
-3:	slgr	%r2,%r2
-	br	%r14
-4:	lghi	%r0,-4096
-	lgr	%r5,%r4
-	slgr	%r5,%r0
-	ngr	%r5,%r0		# %r5 = (%r4 + 4096) & -4096
-	slgr	%r5,%r4		# %r5 = #bytes to next user page boundary
-	clgr	%r3,%r5		# copy crosses next page boundary ?
-	jnh	6f		# no, the current page faulted
-	# move with the reduced length which is < 256
-5:	mvcs	0(%r5,%r4),0(%r2),%r0
-	slgr	%r3,%r5
-6:	lgr	%r2,%r3
-	br	%r14
-        .section __ex_table,"a"
-	.quad	0b,4b
-	.quad	2b,4b
-	.quad	5b,6b
-        .previous
-
-        .align 4
-        .text
-        .globl __copy_in_user_asm
-	# %r2 = from, %r3 = n, %r4 = to
-__copy_in_user_asm:
-	aghi	%r3,-1
-	jo	6f
-	sacf	256
-	bras	%r1,4f
-0:	aghi	%r3,257
-1:	mvc	0(1,%r4),0(%r2)
-	la	%r2,1(%r2)
-	la	%r4,1(%r4)
-	aghi	%r3,-1
-	jnz	1b
-2:	lgr	%r2,%r3
-	br	%r14
-3:	mvc	0(256,%r4),0(%r2)
-	la	%r2,256(%r2)
-	la	%r4,256(%r4)
-4:	aghi	%r3,-256
-	jnm	3b
-5:	ex	%r3,4(%r1)
-	sacf	0
-6:	slgr	%r2,%r2
-	br	14
-        .section __ex_table,"a"
-	.quad	1b,2b
-	.quad	3b,0b
-	.quad	5b,0b
-        .previous
-
-        .align 4
-        .text
-        .globl __clear_user_asm
-	# %r2 = to, %r3 = n
-__clear_user_asm:
-	slgr	%r0,%r0
-	larl	%r5,empty_zero_page
-1:	mvcs	0(%r3,%r2),0(%r5),%r0
-	jnz	2f
-	slgr	%r2,%r2
-	br	%r14
-2:	la	%r2,256(%r2)
-	aghi	%r3,-256
-3:	mvcs	0(%r3,%r2),0(%r5),%r0
-	jnz	2b
-4:	slgr	%r2,%r2
-	br	%r14
-5:	lghi	%r0,-4096
-	lgr	%r4,%r2
-	slgr	%r4,%r0
-	ngr	%r4,%r0		# %r4 = (%r2 + 4096) & -4096
-	slgr	%r4,%r2		# %r4 = #bytes to next user page boundary
-	clgr	%r3,%r4		# clear crosses next page boundary ?
-	jnh	7f		# no, the current page faulted
-	# clear with the reduced length which is < 256
-6:	mvcs	0(%r4,%r2),0(%r5),%r0
-	slgr	%r3,%r4
-7:	lgr	%r2,%r3
-	br	%r14
-        .section __ex_table,"a"
-	.quad	1b,5b
-	.quad	3b,5b
-	.quad	6b,7b
-        .previous
-
-        .align 4
-        .text
-        .globl __strncpy_from_user_asm
-	# %r2 = count, %r3 = dst, %r4 = src
-__strncpy_from_user_asm:
-	lghi	%r0,0
-	lgr	%r1,%r4
-	la	%r2,0(%r2,%r4)	# %r2 points to first byte after string
-	sacf	256
-0:	srst	%r2,%r1
-	jo	0b
-	sacf	0
-	lgr	%r1,%r2
-	jh	1f		# \0 found in string ?
-	aghi	%r1,1		# include \0 in copy
-1:	slgr	%r1,%r4		# %r1 = copy length (without \0)
-	slgr	%r2,%r4		# %r2 = return length (including \0)
-2:	mvcp	0(%r1,%r3),0(%r4),%r0
-	jnz	3f
-	br	%r14
-3:	la	%r3,256(%r3)
-	la	%r4,256(%r4)
-	aghi	%r1,-256
-	mvcp	0(%r1,%r3),0(%r4),%r0
-	jnz	3b
-	br	%r14
-4:	sacf	0
-	lghi	%r2,-EFAULT
-	br	%r14
-	.section __ex_table,"a"
-	.quad	0b,4b
-	.previous
-
-        .align 4
-        .text
-        .globl __strnlen_user_asm
-	# %r2 = count, %r3 = src
-__strnlen_user_asm:
-	lghi	%r0,0
-	lgr	%r1,%r3
-	la	%r2,0(%r2,%r3)	# %r2 points to first byte after string
-	sacf	256
-0:	srst	%r2,%r1
-	jo	0b
-	sacf	0
-	aghi	%r2,1		# strnlen_user result includes the \0
-				# or return count+1 if \0 not found
-	slgr	%r2,%r3
-	br	%r14
-2:	sacf	0
-	slgr	%r2,%r2		# return 0 on exception
-	br	%r14
-	.section __ex_table,"a"
-	.quad	0b,2b
-	.previous

arch/s390/lib/uaccess_mvcos.c

+/*
+ *  arch/s390/lib/uaccess_mvcos.c
+ *
+ *  Optimized user space space access functions based on mvcos.
+ *
+ *    Copyright (C) IBM Corp. 2006
+ *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *		 Gerald Schaefer (gerald.schaefer@de.ibm.com)
+ */
+
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <asm/uaccess.h>
+#include <asm/futex.h>
+
+#ifndef __s390x__
+#define AHI	"ahi"
+#define ALR	"alr"
+#define CLR	"clr"
+#define LHI	"lhi"
+#define SLR	"slr"
+#else
+#define AHI	"aghi"
+#define ALR	"algr"
+#define CLR	"clgr"
+#define LHI	"lghi"
+#define SLR	"slgr"
+#endif
+
+size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
+{
+	register unsigned long reg0 asm("0") = 0x81UL;
+	unsigned long tmp1, tmp2;
+
+	tmp1 = -4096UL;
+	asm volatile(
+		"0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n"
+		"   jz    4f\n"
+		"1:"ALR"  %0,%3\n"
+		"  "SLR"  %1,%3\n"
+		"  "SLR"  %2,%3\n"
+		"   j     0b\n"
+		"2: la    %4,4095(%1)\n"/* %4 = ptr + 4095 */
+		"   nr    %4,%3\n"	/* %4 = (ptr + 4095) & -4096 */
+		"  "SLR"  %4,%1\n"
+		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
+		"   jnh   5f\n"
+		"3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n"
+		"  "SLR"  %0,%4\n"
+		"   j     5f\n"
+		"4:"SLR"  %0,%0\n"
+		"5: \n"
+		EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+		: "d" (reg0) : "cc", "memory");
+	return size;
+}
+
+size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
+{
+	register unsigned long reg0 asm("0") = 0x810000UL;
+	unsigned long tmp1, tmp2;
+
+	tmp1 = -4096UL;
+	asm volatile(
+		"0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
+		"   jz    4f\n"
+		"1:"ALR"  %0,%3\n"
+		"  "SLR"  %1,%3\n"
+		"  "SLR"  %2,%3\n"
+		"   j     0b\n"
+		"2: la    %4,4095(%1)\n"/* %4 = ptr + 4095 */
+		"   nr    %4,%3\n"	/* %4 = (ptr + 4095) & -4096 */
+		"  "SLR"  %4,%1\n"
+		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
+		"   jnh   5f\n"
+		"3: .insn ss,0xc80000000000,0(%4,%1),0(%2),0\n"
+		"  "SLR"  %0,%4\n"
+		"   j     5f\n"
+		"4:"SLR"  %0,%0\n"
+		"5: \n"
+		EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+		: "d" (reg0) : "cc", "memory");
+	return size;
+}
+
+size_t copy_in_user_mvcos(size_t size, void __user *to, const void __user *from)
+{
+	register unsigned long reg0 asm("0") = 0x810081UL;
+	unsigned long tmp1, tmp2;
+
+	tmp1 = -4096UL;
+	/* FIXME: copy with reduced length. */
+	asm volatile(
+		"0: .insn ss,0xc80000000000,0(%0,%1),0(%2),0\n"
+		"   jz    2f\n"
+		"1:"ALR"  %0,%3\n"
+		"  "SLR"  %1,%3\n"
+		"  "SLR"  %2,%3\n"
+		"   j     0b\n"
+		"2:"SLR"  %0,%0\n"
+		"3: \n"
+		EX_TABLE(0b,3b)
+		: "+a" (size), "+a" (to), "+a" (from), "+a" (tmp1), "=a" (tmp2)
+		: "d" (reg0) : "cc", "memory");
+	return size;
+}
+
+size_t clear_user_mvcos(size_t size, void __user *to)
+{
+	register unsigned long reg0 asm("0") = 0x810000UL;
+	unsigned long tmp1, tmp2;
+
+	tmp1 = -4096UL;
+	asm volatile(
+		"0: .insn ss,0xc80000000000,0(%0,%1),0(%4),0\n"
+		"   jz    4f\n"
+		"1:"ALR"  %0,%2\n"
+		"  "SLR"  %1,%2\n"
+		"   j     0b\n"
+		"2: la    %3,4095(%1)\n"/* %4 = to + 4095 */
+		"   nr    %3,%2\n"	/* %4 = (to + 4095) & -4096 */
+		"  "SLR"  %3,%1\n"
+		"  "CLR"  %0,%3\n"	/* copy crosses next page boundary? */
+		"   jnh   5f\n"
+		"3: .insn ss,0xc80000000000,0(%3,%1),0(%4),0\n"
+		"  "SLR"  %0,%3\n"
+		"   j     5f\n"
+		"4:"SLR"  %0,%0\n"
+		"5: \n"
+		EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+		: "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
+		: "a" (empty_zero_page), "d" (reg0) : "cc", "memory");
+	return size;
+}
+
+extern size_t copy_from_user_std_small(size_t, const void __user *, void *);
+extern size_t copy_to_user_std_small(size_t, void __user *, const void *);
+extern size_t strnlen_user_std(size_t, const char __user *);
+extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
+extern int futex_atomic_op(int, int __user *, int, int *);
+extern int futex_atomic_cmpxchg(int __user *, int, int);
+
+struct uaccess_ops uaccess_mvcos = {
+	.copy_from_user = copy_from_user_mvcos,
+	.copy_from_user_small = copy_from_user_std_small,
+	.copy_to_user = copy_to_user_mvcos,
+	.copy_to_user_small = copy_to_user_std_small,
+	.copy_in_user = copy_in_user_mvcos,
+	.clear_user = clear_user_mvcos,
+	.strnlen_user = strnlen_user_std,
+	.strncpy_from_user = strncpy_from_user_std,
+	.futex_atomic_op = futex_atomic_op,
+	.futex_atomic_cmpxchg = futex_atomic_cmpxchg,
+};

arch/s390/lib/uaccess_std.c

+/*
+ *  arch/s390/lib/uaccess_std.c
+ *
+ *  Standard user space access functions based on mvcp/mvcs and doing
+ *  interesting things in the secondary space mode.
+ *
+ *    Copyright (C) IBM Corp. 2006
+ *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *		 Gerald Schaefer (gerald.schaefer@de.ibm.com)
+ */
+
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <asm/uaccess.h>
+#include <asm/futex.h>
+
+#ifndef __s390x__
+#define AHI	"ahi"
+#define ALR	"alr"
+#define CLR	"clr"
+#define LHI	"lhi"
+#define SLR	"slr"
+#else
+#define AHI	"aghi"
+#define ALR	"algr"
+#define CLR	"clgr"
+#define LHI	"lghi"
+#define SLR	"slgr"
+#endif
+
+size_t copy_from_user_std(size_t size, const void __user *ptr, void *x)
+{
+	unsigned long tmp1, tmp2;
+
+	tmp1 = -256UL;
+	asm volatile(
+		"0: mvcp  0(%0,%2),0(%1),%3\n"
+		"   jz    5f\n"
+		"1:"ALR"  %0,%3\n"
+		"   la    %1,256(%1)\n"
+		"   la    %2,256(%2)\n"
+		"2: mvcp  0(%0,%2),0(%1),%3\n"
+		"   jnz   1b\n"
+		"   j     5f\n"
+		"3: la    %4,255(%1)\n"	/* %4 = ptr + 255 */
+		"  "LHI"  %3,-4096\n"
+		"   nr    %4,%3\n"	/* %4 = (ptr + 255) & -4096 */
+		"  "SLR"  %4,%1\n"
+		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
+		"   jnh   6f\n"
+		"4: mvcp  0(%4,%2),0(%1),%3\n"
+		"  "SLR"  %0,%4\n"
+		"   j     6f\n"
+		"5:"SLR"  %0,%0\n"
+		"6: \n"
+		EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,6b)
+		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+		: : "cc", "memory");
+	return size;
+}
+
+size_t copy_from_user_std_small(size_t size, const void __user *ptr, void *x)
+{
+	unsigned long tmp1, tmp2;
+
+	tmp1 = 0UL;
+	asm volatile(
+		"0: mvcp  0(%0,%2),0(%1),%3\n"
+		"  "SLR"  %0,%0\n"
+		"   j     3f\n"
+		"1: la    %4,255(%1)\n" /* %4 = ptr + 255 */
+		"  "LHI"  %3,-4096\n"
+		"   nr    %4,%3\n"	/* %4 = (ptr + 255) & -4096 */
+		"  "SLR"  %4,%1\n"
+		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
+		"   jnh   3f\n"
+		"2: mvcp  0(%4,%2),0(%1),%3\n"
+		"  "SLR"  %0,%4\n"
+		"3:\n"
+		EX_TABLE(0b,1b) EX_TABLE(2b,3b)
+		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+		: : "cc", "memory");
+	return size;
+}
+
+size_t copy_to_user_std(size_t size, void __user *ptr, const void *x)
+{
+	unsigned long tmp1, tmp2;
+
+	tmp1 = -256UL;
+	asm volatile(
+		"0: mvcs  0(%0,%1),0(%2),%3\n"
+		"   jz    5f\n"
+		"1:"ALR"  %0,%3\n"
+		"   la    %1,256(%1)\n"
+		"   la    %2,256(%2)\n"
+		"2: mvcs  0(%0,%1),0(%2),%3\n"
+		"   jnz   1b\n"
+		"   j     5f\n"
+		"3: la    %4,255(%1)\n" /* %4 = ptr + 255 */
+		"  "LHI"  %3,-4096\n"
+		"   nr    %4,%3\n"	/* %4 = (ptr + 255) & -4096 */
+		"  "SLR"  %4,%1\n"
+		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
+		"   jnh   6f\n"
+		"4: mvcs  0(%4,%1),0(%2),%3\n"
+		"  "SLR"  %0,%4\n"
+		"   j     6f\n"
+		"5:"SLR"  %0,%0\n"
+		"6: \n"
+		EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,6b)
+		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+		: : "cc", "memory");
+	return size;
+}
+
+size_t copy_to_user_std_small(size_t size, void __user *ptr, const void *x)
+{
+	unsigned long tmp1, tmp2;
+
+	tmp1 = 0UL;
+	asm volatile(
+		"0: mvcs  0(%0,%1),0(%2),%3\n"
+		"  "SLR"  %0,%0\n"
+		"   j     3f\n"
+		"1: la    %4,255(%1)\n" /* ptr + 255 */
+		"  "LHI"  %3,-4096\n"
+		"   nr    %4,%3\n"	/* (ptr + 255) & -4096UL */
+		"  "SLR"  %4,%1\n"
+		"  "CLR"  %0,%4\n"	/* copy crosses next page boundary? */
+		"   jnh   3f\n"
+		"2: mvcs  0(%4,%1),0(%2),%3\n"
+		"  "SLR"  %0,%4\n"
+		"3:\n"
+		EX_TABLE(0b,1b) EX_TABLE(2b,3b)
+		: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
+		: : "cc", "memory");
+	return size;
+}
+
+size_t copy_in_user_std(size_t size, void __user *to, const void __user *from)
+{
+	unsigned long tmp1;
+
+	asm volatile(
+		"  "AHI"  %0,-1\n"
+		"   jo    5f\n"
+		"   sacf  256\n"
+		"   bras  %3,3f\n"
+		"0:"AHI"  %0,257\n"
+		"1: mvc   0(1,%1),0(%2)\n"
+		"   la    %1,1(%1)\n"
+		"   la    %2,1(%2)\n"
+		"  "AHI"  %0,-1\n"
+		"   jnz   1b\n"
+		"   j     5f\n"
+		"2: mvc   0(256,%1),0(%2)\n"
+		"   la    %1,256(%1)\n"
+		"   la    %2,256(%2)\n"
+		"3:"AHI"  %0,-256\n"
+		"   jnm   2b\n"
+		"4: ex    %0,1b-0b(%3)\n"
+		"   sacf  0\n"
+		"5: "SLR"  %0,%0\n"
+		"6:\n"
+		EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
+		: "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1)
+		: : "cc", "memory");
+	return size;
+}
+
+size_t clear_user_std(size_t size, void __user *to)
+{
+	unsigned long tmp1, tmp2;
+
+	asm volatile(
+		"  "AHI"  %0,-1\n"
+		"   jo    5f\n"
+		"   sacf  256\n"
+		"   bras  %3,3f\n"
+		"   xc    0(1,%1),0(%1)\n"
+		"0:"AHI"  %0,257\n"
+		"   la    %2,255(%1)\n" /* %2 = ptr + 255 */
+		"   srl   %2,12\n"
+		"   sll   %2,12\n"	/* %2 = (ptr + 255) & -4096 */
+		"  "SLR"  %2,%1\n"
+		"  "CLR"  %0,%2\n"	/* clear crosses next page boundary? */
+		"   jnh   5f\n"
+		"  "AHI"  %2,-1\n"
+		"1: ex    %2,0(%3)\n"
+		"  "AHI"  %2,1\n"
+		"  "SLR"  %0,%2\n"
+		"   j     5f\n"
+		"2: xc    0(256,%1),0(%1)\n"
+		"   la    %1,256(%1)\n"
+		"3:"AHI"  %0,-256\n"
+		"   jnm   2b\n"
+		"4: ex    %0,0(%3)\n"
+		"   sacf  0\n"
+		"5: "SLR"  %0,%0\n"
+		"6:\n"
+		EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
+		: "+a" (size), "+a" (to), "=a" (tmp1), "=a" (tmp2)
+		: : "cc", "memory");
+	return size;
+}
+
+size_t strnlen_user_std(size_t size, const char __user *src)
+{
+	register unsigned long reg0 asm("0") = 0UL;
+	unsigned long tmp1, tmp2;
+
+	asm volatile(
+		"   la    %2,0(%1)\n"
+		"   la    %3,0(%0,%1)\n"
+		"  "SLR"  %0,%0\n"
+		"   sacf  256\n"
+		"0: srst  %3,%2\n"
+		"   jo    0b\n"
+		"   la    %0,1(%3)\n"	/* strnlen_user results includes \0 */
+		"  "SLR"  %0,%1\n"
+		"1: sacf  0\n"
+		EX_TABLE(0b,1b)
+		: "+a" (size), "+a" (src), "=a" (tmp1), "=a" (tmp2)
+		: "d" (reg0) : "cc", "memory");
+	return size;
+}
+
+size_t strncpy_from_user_std(size_t size, const char __user *src, char *dst)
+{
+	register unsigned long reg0 asm("0") = 0UL;
+	unsigned long tmp1, tmp2;
+
+	asm volatile(
+		"   la    %3,0(%1)\n"
+		"   la    %4,0(%0,%1)\n"
+		"   sacf  256\n"
+		"0: srst  %4,%3\n"
+		"   jo    0b\n"
+		"   sacf  0\n"
+		"   la    %0,0(%4)\n"
+		"   jh    1f\n"		/* found \0 in string ? */
+		"  "AHI"  %4,1\n"	/* include \0 in copy */
+		"1:"SLR"  %0,%1\n"	/* %0 = return length (without \0) */
+		"  "SLR"  %4,%1\n"	/* %4 = copy length (including \0) */
+		"2: mvcp  0(%4,%2),0(%1),%5\n"
+		"   jz    9f\n"
+		"3:"AHI"  %4,-256\n"
+		"   la    %1,256(%1)\n"
+		"   la    %2,256(%2)\n"
+		"4: mvcp  0(%4,%2),0(%1),%5\n"
+		"   jnz   3b\n"
+		"   j     9f\n"
+		"7: sacf  0\n"
+		"8:"LHI"  %0,%6\n"
+		"9:\n"
+		EX_TABLE(0b,7b) EX_TABLE(2b,8b) EX_TABLE(4b,8b)
+		: "+a" (size), "+a" (src), "+d" (dst), "=a" (tmp1), "=a" (tmp2)
+		: "d" (reg0), "K" (-EFAULT) : "cc", "memory");
+	return size;
+}
+
+#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg)	\
+	asm volatile(							\
+		"   sacf  256\n"					\
+		"0: l     %1,0(%6)\n"					\
+		"1:"insn						\
+		"2: cs    %1,%2,0(%6)\n"				\
+		"3: jl    1b\n"						\
+		"   lhi   %0,0\n"					\
+		"4: sacf  0\n"						\
+		EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b)		\
+		: "=d" (ret), "=&d" (oldval), "=&d" (newval),		\
+		  "=m" (*uaddr)						\
+		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
+		  "m" (*uaddr) : "cc");
+
+int futex_atomic_op(int op, int __user *uaddr, int oparg, int *old)
+{
+	int oldval = 0, newval, ret;
+
+	inc_preempt_count();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("lr %2,%5\n",
+				  ret, oldval, newval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("lr %2,%1\nar %2,%5\n",
+				  ret, oldval, newval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("lr %2,%1\nor %2,%5\n",
+				  ret, oldval, newval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("lr %2,%1\nnr %2,%5\n",
+				  ret, oldval, newval, uaddr, oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("lr %2,%1\nxr %2,%5\n",
+				  ret, oldval, newval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+	dec_preempt_count();
+	*old = oldval;
+	return ret;
+}
+
+int futex_atomic_cmpxchg(int __user *uaddr, int oldval, int newval)
+{
+	int ret;
+
+	asm volatile(
+		"   sacf 256\n"
+		"   cs   %1,%4,0(%5)\n"
+		"0: lr   %0,%1\n"
+		"1: sacf 0\n"
+		EX_TABLE(0b,1b)
+		: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
+		: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
+		: "cc", "memory" );
+	return ret;
+}
+
+struct uaccess_ops uaccess_std = {
+	.copy_from_user = copy_from_user_std,
+	.copy_from_user_small = copy_from_user_std_small,
+	.copy_to_user = copy_to_user_std,
+	.copy_to_user_small = copy_to_user_std_small,
+	.copy_in_user = copy_in_user_std,
+	.clear_user = clear_user_std,
+	.strnlen_user = strnlen_user_std,
+	.strncpy_from_user = strncpy_from_user_std,
+	.futex_atomic_op = futex_atomic_op,
+	.futex_atomic_cmpxchg = futex_atomic_cmpxchg,
+};

arch/s390/mm/cmm.c

@@ -52,22 +52,6 @@ static struct timer_list cmm_timer;
 static void cmm_timer_fn(unsigned long);
 static void cmm_set_timer(void);
 
-static long
-cmm_strtoul(const char *cp, char **endp)
-{
-	unsigned int base = 10;
-
-	if (*cp == '0') {
-		base = 8;
-		cp++;
-		if ((*cp == 'x' || *cp == 'X') && isxdigit(cp[1])) {
-			base = 16;
-			cp++;
-		}
-	}
-	return simple_strtoul(cp, endp, base);
-}
-
 static long
 cmm_alloc_pages(long pages, long *counter, struct cmm_page_array **list)
 {
@@ -276,7 +260,7 @@ cmm_pages_handler(ctl_table *ctl, int write, struct file *filp,
 			return -EFAULT;
 		buf[sizeof(buf) - 1] = '\0';
 		cmm_skip_blanks(buf, &p);
-		pages = cmm_strtoul(p, &p);
+		pages = simple_strtoul(p, &p, 0);
 		if (ctl == &cmm_table[0])
 			cmm_set_pages(pages);
 		else
@@ -317,9 +301,9 @@ cmm_timeout_handler(ctl_table *ctl, int write, struct file *filp,
 			return -EFAULT;
 		buf[sizeof(buf) - 1] = '\0';
 		cmm_skip_blanks(buf, &p);
-		pages = cmm_strtoul(p, &p);
+		pages = simple_strtoul(p, &p, 0);
 		cmm_skip_blanks(p, &p);
-		seconds = cmm_strtoul(p, &p);
+		seconds = simple_strtoul(p, &p, 0);
 		cmm_set_timeout(pages, seconds);
 	} else {
 		len = sprintf(buf, "%ld %ld\n",
@@ -382,24 +366,24 @@ cmm_smsg_target(char *from, char *msg)
 	if (strncmp(msg, "SHRINK", 6) == 0) {
 		if (!cmm_skip_blanks(msg + 6, &msg))
 			return;
-		pages = cmm_strtoul(msg, &msg);
+		pages = simple_strtoul(msg, &msg, 0);
 		cmm_skip_blanks(msg, &msg);
 		if (*msg == '\0')
 			cmm_set_pages(pages);
 	} else if (strncmp(msg, "RELEASE", 7) == 0) {
 		if (!cmm_skip_blanks(msg + 7, &msg))
 			return;
-		pages = cmm_strtoul(msg, &msg);
+		pages = simple_strtoul(msg, &msg, 0);
 		cmm_skip_blanks(msg, &msg);
 		if (*msg == '\0')
 			cmm_add_timed_pages(pages);
 	} else if (strncmp(msg, "REUSE", 5) == 0) {
 		if (!cmm_skip_blanks(msg + 5, &msg))
 			return;
-		pages = cmm_strtoul(msg, &msg);
+		pages = simple_strtoul(msg, &msg, 0);
 		if (!cmm_skip_blanks(msg, &msg))
 			return;
-		seconds = cmm_strtoul(msg, &msg);
+		seconds = simple_strtoul(msg, &msg, 0);
 		cmm_skip_blanks(msg, &msg);
 		if (*msg == '\0')
 			cmm_set_timeout(pages, seconds);

arch/s390/mm/fault.c

@@ -25,10 +25,12 @@
 #include <linux/console.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
+#include <asm/kdebug.h>
 
 #ifndef CONFIG_64BIT
 #define __FAIL_ADDR_MASK 0x7ffff000
@@ -48,6 +50,38 @@ extern int sysctl_userprocess_debug;
 
 extern void die(const char *,struct pt_regs *,long);
 
+#ifdef CONFIG_KPROBES
+ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
+int register_page_fault_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
+}
+
+int unregister_page_fault_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
+}
+
+static inline int notify_page_fault(enum die_val val, const char *str,
+			struct pt_regs *regs, long err, int trap, int sig)
+{
+	struct die_args args = {
+		.regs = regs,
+		.str = str,
+		.err = err,
+		.trapnr = trap,
+		.signr = sig
+	};
+	return atomic_notifier_call_chain(&notify_page_fault_chain, val, &args);
+}
+#else
+static inline int notify_page_fault(enum die_val val, const char *str,
+			struct pt_regs *regs, long err, int trap, int sig)
+{
+	return NOTIFY_DONE;
+}
+#endif
+
 extern spinlock_t timerlist_lock;
 
 /*
@@ -159,7 +193,7 @@ static void do_sigsegv(struct pt_regs *regs, unsigned long error_code,
  *   11       Page translation     ->  Not present       (nullification)
  *   3b       Region third trans.  ->  Not present       (nullification)
  */
-static inline void
+static inline void __kprobes
 do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection)
 {
         struct task_struct *tsk;
@@ -173,6 +207,10 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection)
         tsk = current;
         mm = tsk->mm;
 	
+	if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+					SIGSEGV) == NOTIFY_STOP)
+		return;
+
 	/* 
          * Check for low-address protection.  This needs to be treated
 	 * as a special case because the translation exception code 

arch/s390/mm/init.c

@@ -108,16 +108,23 @@ void __init paging_init(void)
         unsigned long pgdir_k = (__pa(swapper_pg_dir) & PAGE_MASK) | _KERNSEG_TABLE;
         static const int ssm_mask = 0x04000000L;
 	unsigned long ro_start_pfn, ro_end_pfn;
+	unsigned long zones_size[MAX_NR_ZONES];
 
 	ro_start_pfn = PFN_DOWN((unsigned long)&__start_rodata);
 	ro_end_pfn = PFN_UP((unsigned long)&__end_rodata);
 
+	memset(zones_size, 0, sizeof(zones_size));
+	zones_size[ZONE_DMA] = max_low_pfn;
+	free_area_init_node(0, &contig_page_data, zones_size,
+			    __pa(PAGE_OFFSET) >> PAGE_SHIFT,
+			    zholes_size);
+
 	/* unmap whole virtual address space */
 	
         pg_dir = swapper_pg_dir;
 
-	for (i=0;i<KERNEL_PGD_PTRS;i++) 
-	        pmd_clear((pmd_t*)pg_dir++);
+	for (i = 0; i < PTRS_PER_PGD; i++)
+		pmd_clear((pmd_t *) pg_dir++);
 		
 	/*
 	 * map whole physical memory to virtual memory (identity mapping) 
@@ -131,10 +138,7 @@ void __init paging_init(void)
                  */
 		pg_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
 
-                pg_dir->pgd0 =  (_PAGE_TABLE | __pa(pg_table));
-                pg_dir->pgd1 =  (_PAGE_TABLE | (__pa(pg_table)+1024));
-                pg_dir->pgd2 =  (_PAGE_TABLE | (__pa(pg_table)+2048));
-                pg_dir->pgd3 =  (_PAGE_TABLE | (__pa(pg_table)+3072));
+		pmd_populate_kernel(&init_mm, (pmd_t *) pg_dir, pg_table);
                 pg_dir++;
 
                 for (tmp = 0 ; tmp < PTRS_PER_PTE ; tmp++,pg_table++) {
@@ -143,7 +147,7 @@ void __init paging_init(void)
 			else
 				pte = pfn_pte(pfn, PAGE_KERNEL);
                         if (pfn >= max_low_pfn)
-                                pte_clear(&init_mm, 0, &pte);
+				pte_val(pte) = _PAGE_TYPE_EMPTY;
 			set_pte(pg_table, pte);
                         pfn++;
                 }
@@ -159,16 +163,6 @@ void __init paging_init(void)
 			     : : "m" (pgdir_k), "m" (ssm_mask));
 
         local_flush_tlb();
-
-	{
-		unsigned long zones_size[MAX_NR_ZONES];
-
-		memset(zones_size, 0, sizeof(zones_size));
-		zones_size[ZONE_DMA] = max_low_pfn;
-		free_area_init_node(0, &contig_page_data, zones_size,
-				    __pa(PAGE_OFFSET) >> PAGE_SHIFT,
-				    zholes_size);
-	}
         return;
 }
 
@@ -236,10 +230,8 @@ void __init paging_init(void)
 					pte = pfn_pte(pfn, __pgprot(_PAGE_RO));
 				else
 					pte = pfn_pte(pfn, PAGE_KERNEL);
-                                if (pfn >= max_low_pfn) {
-                                        pte_clear(&init_mm, 0, &pte); 
-                                        continue;
-                                }
+				if (pfn >= max_low_pfn)
+					pte_val(pte) = _PAGE_TYPE_EMPTY;
                                 set_pte(pt_dir, pte);
                                 pfn++;
                         }

drivers/base/hypervisor.c

 /*
  * hypervisor.c - /sys/hypervisor subsystem.
  *
- * This file is released under the GPLv2
+ * Copyright (C) IBM Corp. 2006
  *
+ * This file is released under the GPLv2
  */
 
 #include <linux/kobject.h>

drivers/s390/Kconfig

@@ -213,17 +213,35 @@ config MONREADER
 	help
 	  Character device driver for reading z/VM monitor service records
 
+config MONWRITER
+	tristate "API for writing z/VM monitor service records"
+	default "m"
+	help
+	  Character device driver for writing z/VM monitor service records
+
 endmenu
 
 menu "Cryptographic devices"
 
-config Z90CRYPT
+config ZCRYPT
 	tristate "Support for PCI-attached cryptographic adapters"
+	select ZCRYPT_MONOLITHIC if ZCRYPT="y"
 	default "m"
 	help
 	  Select this option if you want to use a PCI-attached cryptographic
-	  adapter like the PCI Cryptographic Accelerator (PCICA) or the PCI
-	  Cryptographic Coprocessor (PCICC).  This option is also available
-	  as a module called z90crypt.ko.
+	  adapter like:
+	  + PCI Cryptographic Accelerator (PCICA)
+	  + PCI Cryptographic Coprocessor (PCICC)
+	  + PCI-X Cryptographic Coprocessor (PCIXCC)
+	  + Crypto Express2 Coprocessor (CEX2C)
+	  + Crypto Express2 Accelerator (CEX2A)
+
+config ZCRYPT_MONOLITHIC
+	bool "Monolithic zcrypt module"
+	depends on ZCRYPT="m"
+	help
+	  Select this option if you want to have a single module z90crypt.ko
+	  that contains all parts of the crypto device driver (ap bus,
+	  request router and all the card drivers).
 
 endmenu

drivers/s390/block/dasd.c

@@ -184,7 +184,7 @@ dasd_state_known_to_basic(struct dasd_device * device)
 	device->debug_area = debug_register(device->cdev->dev.bus_id, 1, 2,
 					    8 * sizeof (long));
 	debug_register_view(device->debug_area, &debug_sprintf_view);
-	debug_set_level(device->debug_area, DBF_EMERG);
+	debug_set_level(device->debug_area, DBF_WARNING);
 	DBF_DEV_EVENT(DBF_EMERG, device, "%s", "debug area created");
 
 	device->state = DASD_STATE_BASIC;
@@ -893,7 +893,7 @@ dasd_handle_killed_request(struct ccw_device *cdev, unsigned long intparm)
 
 	device = (struct dasd_device *) cqr->device;
 	if (device == NULL ||
-	    device != dasd_device_from_cdev(cdev) ||
+	    device != dasd_device_from_cdev_locked(cdev) ||
 	    strncmp(device->discipline->ebcname, (char *) &cqr->magic, 4)) {
 		MESSAGE(KERN_DEBUG, "invalid device in request: bus_id %s",
 			cdev->dev.bus_id);
@@ -970,7 +970,7 @@ dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
 	/* first of all check for state change pending interrupt */
 	mask = DEV_STAT_ATTENTION | DEV_STAT_DEV_END | DEV_STAT_UNIT_EXCEP;
 	if ((irb->scsw.dstat & mask) == mask) {
-		device = dasd_device_from_cdev(cdev);
+		device = dasd_device_from_cdev_locked(cdev);
 		if (!IS_ERR(device)) {
 			dasd_handle_state_change_pending(device);
 			dasd_put_device(device);
@@ -2169,7 +2169,7 @@ dasd_init(void)
 		goto failed;
 	}
 	debug_register_view(dasd_debug_area, &debug_sprintf_view);
-	debug_set_level(dasd_debug_area, DBF_EMERG);
+	debug_set_level(dasd_debug_area, DBF_WARNING);
 
 	DBF_EVENT(DBF_EMERG, "%s", "debug area created");
 

drivers/s390/block/dasd_devmap.c

@@ -258,8 +258,12 @@ dasd_parse_keyword( char *parsestring ) {
                 return residual_str;
         }
 	if (strncmp("nopav", parsestring, length) == 0) {
+		if (MACHINE_IS_VM)
+			MESSAGE(KERN_INFO, "%s", "'nopav' not supported on VM");
+		else {
 			dasd_nopav = 1;
 			MESSAGE(KERN_INFO, "%s", "disable PAV mode");
+		}
 		return residual_str;
 	}
 	if (strncmp("fixedbuffers", parsestring, length) == 0) {
@@ -523,17 +527,17 @@ dasd_create_device(struct ccw_device *cdev)
 {
 	struct dasd_devmap *devmap;
 	struct dasd_device *device;
+	unsigned long flags;
 	int rc;
 
 	devmap = dasd_devmap_from_cdev(cdev);
 	if (IS_ERR(devmap))
 		return (void *) devmap;
-	cdev->dev.driver_data = devmap;
 
 	device = dasd_alloc_device();
 	if (IS_ERR(device))
 		return device;
-	atomic_set(&device->ref_count, 2);
+	atomic_set(&device->ref_count, 3);
 
 	spin_lock(&dasd_devmap_lock);
 	if (!devmap->device) {
@@ -552,6 +556,11 @@ dasd_create_device(struct ccw_device *cdev)
 		dasd_free_device(device);
 		return ERR_PTR(rc);
 	}
+
+	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+	cdev->dev.driver_data = device;
+	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+
 	return device;
 }
 
@@ -569,6 +578,7 @@ dasd_delete_device(struct dasd_device *device)
 {
 	struct ccw_device *cdev;
 	struct dasd_devmap *devmap;
+	unsigned long flags;
 
 	/* First remove device pointer from devmap. */
 	devmap = dasd_find_busid(device->cdev->dev.bus_id);
@@ -582,9 +592,16 @@ dasd_delete_device(struct dasd_device *device)
 	devmap->device = NULL;
 	spin_unlock(&dasd_devmap_lock);
 
-	/* Drop ref_count by 2, one for the devmap reference and
-	 * one for the passed reference. */
-	atomic_sub(2, &device->ref_count);
+	/* Disconnect dasd_device structure from ccw_device structure. */
+	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	device->cdev->dev.driver_data = NULL;
+	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+
+	/*
+	 * Drop ref_count by 3, one for the devmap reference, one for
+	 * the cdev reference and one for the passed reference.
+	 */
+	atomic_sub(3, &device->ref_count);
 
 	/* Wait for reference counter to drop to zero. */
 	wait_event(dasd_delete_wq, atomic_read(&device->ref_count) == 0);
@@ -593,9 +610,6 @@ dasd_delete_device(struct dasd_device *device)
 	cdev = device->cdev;
 	device->cdev = NULL;
 
-	/* Disconnect dasd_devmap structure from ccw_device structure. */
-	cdev->dev.driver_data = NULL;
-
 	/* Put ccw_device structure. */
 	put_device(&cdev->dev);
 
@@ -613,23 +627,34 @@ dasd_put_device_wake(struct dasd_device *device)
 	wake_up(&dasd_delete_wq);
 }
 
+/*
+ * Return dasd_device structure associated with cdev.
+ * This function needs to be called with the ccw device
+ * lock held. It can be used from interrupt context.
+ */
+struct dasd_device *
+dasd_device_from_cdev_locked(struct ccw_device *cdev)
+{
+	struct dasd_device *device = cdev->dev.driver_data;
+
+	if (!device)
+		return ERR_PTR(-ENODEV);
+	dasd_get_device(device);
+	return device;
+}
+
 /*
  * Return dasd_device structure associated with cdev.
  */
 struct dasd_device *
 dasd_device_from_cdev(struct ccw_device *cdev)
 {
-	struct dasd_devmap *devmap;
 	struct dasd_device *device;
+	unsigned long flags;
 
-	device = ERR_PTR(-ENODEV);
-	spin_lock(&dasd_devmap_lock);
-	devmap = cdev->dev.driver_data;
-	if (devmap && devmap->device) {
-		device = devmap->device;
-		dasd_get_device(device);
-	}
-	spin_unlock(&dasd_devmap_lock);
+	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+	device = dasd_device_from_cdev_locked(cdev);
+	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
 	return device;
 }
 
@@ -730,16 +755,17 @@ static ssize_t
 dasd_discipline_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
-	struct dasd_devmap *devmap;
-	char *dname;
+	struct dasd_device *device;
+	ssize_t len;
 
-	spin_lock(&dasd_devmap_lock);
-	dname = "none";
-	devmap = dev->driver_data;
-	if (devmap && devmap->device && devmap->device->discipline)
-		dname = devmap->device->discipline->name;
-	spin_unlock(&dasd_devmap_lock);
-	return snprintf(buf, PAGE_SIZE, "%s\n", dname);
+	device = dasd_device_from_cdev(to_ccwdev(dev));
+	if (!IS_ERR(device) && device->discipline) {
+		len = snprintf(buf, PAGE_SIZE, "%s\n",
+			       device->discipline->name);
+		dasd_put_device(device);
+	} else
+		len = snprintf(buf, PAGE_SIZE, "none\n");
+	return len;
 }
 
 static DEVICE_ATTR(discipline, 0444, dasd_discipline_show, NULL);

drivers/s390/block/dasd_eer.c

@@ -678,7 +678,7 @@ int __init dasd_eer_init(void)
 	return 0;
 }
 
-void __exit dasd_eer_exit(void)
+void dasd_eer_exit(void)
 {
 	WARN_ON(misc_deregister(&dasd_eer_dev) != 0);
 }

drivers/s390/block/dasd_int.h

@@ -534,6 +534,7 @@ int dasd_add_sysfs_files(struct ccw_device *);
 void dasd_remove_sysfs_files(struct ccw_device *);
 
 struct dasd_device *dasd_device_from_cdev(struct ccw_device *);
+struct dasd_device *dasd_device_from_cdev_locked(struct ccw_device *);
 struct dasd_device *dasd_device_from_devindex(int);
 
 int dasd_parse(void);

drivers/s390/block/xpram.c

@@ -453,7 +453,7 @@ static int __init xpram_init(void)
 		PRINT_WARN("No expanded memory available\n");
 		return -ENODEV;
 	}
-	xpram_pages = xpram_highest_page_index();
+	xpram_pages = xpram_highest_page_index() + 1;
 	PRINT_INFO("  %u pages expanded memory found (%lu KB).\n",
 		   xpram_pages, (unsigned long) xpram_pages*4);
 	rc = xpram_setup_sizes(xpram_pages);

drivers/s390/char/Makefile

@@ -28,3 +28,4 @@ obj-$(CONFIG_S390_TAPE) += tape.o tape_class.o
 obj-$(CONFIG_S390_TAPE_34XX) += tape_34xx.o
 obj-$(CONFIG_S390_TAPE_3590) += tape_3590.o
 obj-$(CONFIG_MONREADER) += monreader.o
+obj-$(CONFIG_MONWRITER) += monwriter.o

drivers/s390/char/monwriter.c

+/*
+ * drivers/s390/char/monwriter.c
+ *
+ * Character device driver for writing z/VM *MONITOR service records.
+ *
+ * Copyright (C) IBM Corp. 2006
+ *
+ * Author(s): Melissa Howland <Melissa.Howland@us.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/ctype.h>
+#include <linux/poll.h>
+#include <asm/uaccess.h>
+#include <asm/ebcdic.h>
+#include <asm/io.h>
+#include <asm/appldata.h>
+#include <asm/monwriter.h>
+
+#define MONWRITE_MAX_DATALEN	4024
+
+static int mon_max_bufs = 255;
+
+struct mon_buf {
+	struct list_head list;
+	struct monwrite_hdr hdr;
+	int diag_done;
+	char *data;
+};
+
+struct mon_private {
+	struct list_head list;
+	struct monwrite_hdr hdr;
+	size_t hdr_to_read;
+	size_t data_to_read;
+	struct mon_buf *current_buf;
+	int mon_buf_count;
+};
+
+/*
+ * helper functions
+ */
+
+static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
+{
+	struct appldata_product_id id;
+	int rc;
+
+	strcpy(id.prod_nr, "LNXAPPL");
+	id.prod_fn = myhdr->applid;
+	id.record_nr = myhdr->record_num;
+	id.version_nr = myhdr->version;
+	id.release_nr = myhdr->release;
+	id.mod_lvl = myhdr->mod_level;
+	rc = appldata_asm(&id, fcn, (void *) buffer, myhdr->datalen);
+	if (rc <= 0)
+		return rc;
+	if (rc == 5)
+		return -EPERM;
+	printk("DIAG X'DC' error with return code: %i\n", rc);
+	return -EINVAL;
+}
+
+static inline struct mon_buf *monwrite_find_hdr(struct mon_private *monpriv,
+						struct monwrite_hdr *monhdr)
+{
+	struct mon_buf *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &monpriv->list, list)
+		if (entry->hdr.applid == monhdr->applid &&
+		    entry->hdr.record_num == monhdr->record_num &&
+		    entry->hdr.version == monhdr->version &&
+		    entry->hdr.release == monhdr->release &&
+		    entry->hdr.mod_level == monhdr->mod_level)
+			return entry;
+	return NULL;
+}
+
+static int monwrite_new_hdr(struct mon_private *monpriv)
+{
+	struct monwrite_hdr *monhdr = &monpriv->hdr;
+	struct mon_buf *monbuf;
+	int rc;
+
+	if (monhdr->datalen > MONWRITE_MAX_DATALEN ||
+	    monhdr->mon_function > MONWRITE_START_CONFIG ||
+	    monhdr->hdrlen != sizeof(struct monwrite_hdr))
+		return -EINVAL;
+	monbuf = monwrite_find_hdr(monpriv, monhdr);
+	if (monbuf) {
+		if (monhdr->mon_function == MONWRITE_STOP_INTERVAL) {
+			monhdr->datalen = monbuf->hdr.datalen;
+			rc = monwrite_diag(monhdr, monbuf->data,
+					   APPLDATA_STOP_REC);
+			list_del(&monbuf->list);
+			monpriv->mon_buf_count--;
+			kfree(monbuf->data);
+			kfree(monbuf);
+			monbuf = NULL;
+		}
+	} else {
+		if (monpriv->mon_buf_count >= mon_max_bufs)
+			return -ENOSPC;
+		monbuf = kzalloc(sizeof(struct mon_buf), GFP_KERNEL);
+		if (!monbuf)
+			return -ENOMEM;
+		monbuf->data = kzalloc(monbuf->hdr.datalen,
+				       GFP_KERNEL | GFP_DMA);
+		if (!monbuf->data) {
+			kfree(monbuf);
+			return -ENOMEM;
+		}
+		monbuf->hdr = *monhdr;
+		list_add_tail(&monbuf->list, &monpriv->list);
+		monpriv->mon_buf_count++;
+	}
+	monpriv->current_buf = monbuf;
+	return 0;
+}
+
+static int monwrite_new_data(struct mon_private *monpriv)
+{
+	struct monwrite_hdr *monhdr = &monpriv->hdr;
+	struct mon_buf *monbuf = monpriv->current_buf;
+	int rc = 0;
+
+	switch (monhdr->mon_function) {
+	case MONWRITE_START_INTERVAL:
+		if (!monbuf->diag_done) {
+			rc = monwrite_diag(monhdr, monbuf->data,
+					   APPLDATA_START_INTERVAL_REC);
+			monbuf->diag_done = 1;
+		}
+		break;
+	case MONWRITE_START_CONFIG:
+		if (!monbuf->diag_done) {
+			rc = monwrite_diag(monhdr, monbuf->data,
+					   APPLDATA_START_CONFIG_REC);
+			monbuf->diag_done = 1;
+		}
+		break;
+	case MONWRITE_GEN_EVENT:
+		rc = monwrite_diag(monhdr, monbuf->data,
+				   APPLDATA_GEN_EVENT_REC);
+		list_del(&monpriv->current_buf->list);
+		kfree(monpriv->current_buf->data);
+		kfree(monpriv->current_buf);
+		monpriv->current_buf = NULL;
+		break;
+	default:
+		/* monhdr->mon_function is checked in monwrite_new_hdr */
+		BUG();
+	}
+	return rc;
+}
+
+/*
+ * file operations
+ */
+
+static int monwrite_open(struct inode *inode, struct file *filp)
+{
+	struct mon_private *monpriv;
+
+	monpriv = kzalloc(sizeof(struct mon_private), GFP_KERNEL);
+	if (!monpriv)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&monpriv->list);
+	monpriv->hdr_to_read = sizeof(monpriv->hdr);
+	filp->private_data = monpriv;
+	return nonseekable_open(inode, filp);
+}
+
+static int monwrite_close(struct inode *inode, struct file *filp)
+{
+	struct mon_private *monpriv = filp->private_data;
+	struct mon_buf *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &monpriv->list, list) {
+		if (entry->hdr.mon_function != MONWRITE_GEN_EVENT)
+			monwrite_diag(&entry->hdr, entry->data,
+				      APPLDATA_STOP_REC);
+		monpriv->mon_buf_count--;
+		list_del(&entry->list);
+		kfree(entry->data);
+		kfree(entry);
+	}
+	kfree(monpriv);
+	return 0;
+}
+
+static ssize_t monwrite_write(struct file *filp, const char __user *data,
+			      size_t count, loff_t *ppos)
+{
+	struct mon_private *monpriv = filp->private_data;
+	size_t len, written;
+	void *to;
+	int rc;
+
+	for (written = 0; written < count; ) {
+		if (monpriv->hdr_to_read) {
+			len = min(count - written, monpriv->hdr_to_read);
+			to = (char *) &monpriv->hdr +
+				sizeof(monpriv->hdr) - monpriv->hdr_to_read;
+			if (copy_from_user(to, data + written, len)) {
+				rc = -EFAULT;
+				goto out_error;
+			}
+			monpriv->hdr_to_read -= len;
+			written += len;
+			if (monpriv->hdr_to_read > 0)
+				continue;
+			rc = monwrite_new_hdr(monpriv);
+			if (rc)
+				goto out_error;
+			monpriv->data_to_read = monpriv->current_buf ?
+				monpriv->current_buf->hdr.datalen : 0;
+		}
+
+		if (monpriv->data_to_read) {
+			len = min(count - written, monpriv->data_to_read);
+			to = monpriv->current_buf->data +
+				monpriv->hdr.datalen - monpriv->data_to_read;
+			if (copy_from_user(to, data + written, len)) {
+				rc = -EFAULT;
+				goto out_error;
+			}
+			monpriv->data_to_read -= len;
+			written += len;
+			if (monpriv->data_to_read > 0)
+				continue;
+			rc = monwrite_new_data(monpriv);
+			if (rc)
+				goto out_error;
+		}
+		monpriv->hdr_to_read = sizeof(monpriv->hdr);
+	}
+	return written;
+
+out_error:
+	monpriv->data_to_read = 0;
+	monpriv->hdr_to_read = sizeof(struct monwrite_hdr);
+	return rc;
+}
+
+static struct file_operations monwrite_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = &monwrite_open,
+	.release = &monwrite_close,
+	.write	 = &monwrite_write,
+};
+
+static struct miscdevice mon_dev = {
+	.name	= "monwriter",
+	.fops	= &monwrite_fops,
+	.minor	= MISC_DYNAMIC_MINOR,
+};
+
+/*
+ * module init/exit
+ */
+
+static int __init mon_init(void)
+{
+	if (MACHINE_IS_VM)
+		return misc_register(&mon_dev);
+	else
+		return -ENODEV;
+}
+
+static void __exit mon_exit(void)
+{
+	WARN_ON(misc_deregister(&mon_dev) != 0);
+}
+
+module_init(mon_init);
+module_exit(mon_exit);
+
+module_param_named(max_bufs, mon_max_bufs, int, 0644);
+MODULE_PARM_DESC(max_bufs, "Maximum number of sample monitor data buffers"
+		 "that can be active at one time");
+
+MODULE_AUTHOR("Melissa Howland <Melissa.Howland@us.ibm.com>");
+MODULE_DESCRIPTION("Character device driver for writing z/VM "
+		   "APPLDATA monitor records.");
+MODULE_LICENSE("GPL");

drivers/s390/char/vmcp.c

 /*
  * Copyright (C) 2004,2005 IBM Corporation
- * Interface implementation for communication with the v/VM control program
+ * Interface implementation for communication with the z/VM control program
  * Author(s): Christian Borntraeger <cborntra@de.ibm.com>
  *
  *

drivers/s390/char/vmcp.h

 /*
  * Copyright (C) 2004, 2005 IBM Corporation
- * Interface implementation for communication with the v/VM control program
+ * Interface implementation for communication with the z/VM control program
  * Version 1.0
  * Author(s): Christian Borntraeger <cborntra@de.ibm.com>
  *

drivers/s390/cio/chsc.c

@@ -256,7 +256,7 @@ s390_subchannel_remove_chpid(struct device *dev, void *data)
 	/* trigger path verification. */
 	if (sch->driver && sch->driver->verify)
 		sch->driver->verify(&sch->dev);
-	else if (sch->vpm == mask)
+	else if (sch->lpm == mask)
 		goto out_unreg;
 out_unlock:
 	spin_unlock_irq(&sch->lock);
@@ -378,6 +378,7 @@ __s390_process_res_acc(struct subchannel_id schid, void *data)
 
 	if (chp_mask == 0) {
 		spin_unlock_irq(&sch->lock);
+		put_device(&sch->dev);
 		return 0;
 	}
 	old_lpm = sch->lpm;
@@ -392,7 +393,7 @@ __s390_process_res_acc(struct subchannel_id schid, void *data)
 
 	spin_unlock_irq(&sch->lock);
 	put_device(&sch->dev);
-	return (res_data->fla_mask == 0xffff) ? -ENODEV : 0;
+	return 0;
 }
 
 

drivers/s390/cio/cio.c

@@ -16,11 +16,10 @@
 #include <linux/device.h>
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
-
 #include <asm/cio.h>
 #include <asm/delay.h>
 #include <asm/irq.h>
-
+#include <asm/setup.h>
 #include "airq.h"
 #include "cio.h"
 #include "css.h"
@@ -192,7 +191,7 @@ cio_start_key (struct subchannel *sch,	/* subchannel structure */
 	sch->orb.pfch = sch->options.prefetch == 0;
 	sch->orb.spnd = sch->options.suspend;
 	sch->orb.ssic = sch->options.suspend && sch->options.inter;
-	sch->orb.lpm = (lpm != 0) ? (lpm & sch->opm) : sch->lpm;
+	sch->orb.lpm = (lpm != 0) ? lpm : sch->lpm;
 #ifdef CONFIG_64BIT
 	/*
 	 * for 64 bit we always support 64 bit IDAWs with 4k page size only
@@ -570,10 +569,7 @@ cio_validate_subchannel (struct subchannel *sch, struct subchannel_id schid)
 	sch->opm = 0xff;
 	if (!cio_is_console(sch->schid))
 		chsc_validate_chpids(sch);
-	sch->lpm = sch->schib.pmcw.pim &
-		sch->schib.pmcw.pam &
-		sch->schib.pmcw.pom &
-		sch->opm;
+	sch->lpm = sch->schib.pmcw.pam & sch->opm;
 
 	CIO_DEBUG(KERN_INFO, 0,
 		  "Detected device %04x on subchannel 0.%x.%04X"
@@ -841,14 +837,26 @@ __clear_subchannel_easy(struct subchannel_id schid)
 	return -EBUSY;
 }
 
-extern void do_reipl(unsigned long devno);
-static int
-__shutdown_subchannel_easy(struct subchannel_id schid, void *data)
+struct sch_match_id {
+	struct subchannel_id schid;
+	struct ccw_dev_id devid;
+	int rc;
+};
+
+static int __shutdown_subchannel_easy_and_match(struct subchannel_id schid,
+	void *data)
 {
 	struct schib schib;
+	struct sch_match_id *match_id = data;
 
 	if (stsch_err(schid, &schib))
 		return -ENXIO;
+	if (match_id && schib.pmcw.dnv &&
+		(schib.pmcw.dev == match_id->devid.devno) &&
+		(schid.ssid == match_id->devid.ssid)) {
+		match_id->schid = schid;
+		match_id->rc = 0;
+	}
 	if (!schib.pmcw.ena)
 		return 0;
 	switch(__disable_subchannel_easy(schid, &schib)) {
@@ -864,18 +872,71 @@ __shutdown_subchannel_easy(struct subchannel_id schid, void *data)
 	return 0;
 }
 
-void
-clear_all_subchannels(void)
+static int clear_all_subchannels_and_match(struct ccw_dev_id *devid,
+	struct subchannel_id *schid)
 {
+	struct sch_match_id match_id;
+
+	match_id.devid = *devid;
+	match_id.rc = -ENODEV;
 	local_irq_disable();
-	for_each_subchannel(__shutdown_subchannel_easy, NULL);
+	for_each_subchannel(__shutdown_subchannel_easy_and_match, &match_id);
+	if (match_id.rc == 0)
+		*schid = match_id.schid;
+	return match_id.rc;
 }
 
+
+void clear_all_subchannels(void)
+{
+	local_irq_disable();
+	for_each_subchannel(__shutdown_subchannel_easy_and_match, NULL);
+}
+
+extern void do_reipl_asm(__u32 schid);
+
 /* Make sure all subchannels are quiet before we re-ipl an lpar. */
-void
-reipl(unsigned long devno)
+void reipl_ccw_dev(struct ccw_dev_id *devid)
 {
-	clear_all_subchannels();
+	struct subchannel_id schid;
+
+	if (clear_all_subchannels_and_match(devid, &schid))
+		panic("IPL Device not found\n");
 	cio_reset_channel_paths();
-	do_reipl(devno);
+	do_reipl_asm(*((__u32*)&schid));
+}
+
+extern struct schib ipl_schib;
+
+/*
+ * ipl_save_parameters gets called very early. It is not allowed to access
+ * anything in the bss section at all. The bss section is not cleared yet,
+ * but may contain some ipl parameters written by the firmware.
+ * These parameters (if present) are copied to 0x2000.
+ * To avoid corruption of the ipl parameters, all variables used by this
+ * function must reside on the stack or in the data section.
+ */
+void ipl_save_parameters(void)
+{
+	struct subchannel_id schid;
+	unsigned int *ipl_ptr;
+	void *src, *dst;
+
+	schid = *(struct subchannel_id *)__LC_SUBCHANNEL_ID;
+	if (!schid.one)
+		return;
+	if (stsch(schid, &ipl_schib))
+		return;
+	if (!ipl_schib.pmcw.dnv)
+		return;
+	ipl_devno = ipl_schib.pmcw.dev;
+	ipl_flags |= IPL_DEVNO_VALID;
+	if (!ipl_schib.pmcw.qf)
+		return;
+	ipl_flags |= IPL_PARMBLOCK_VALID;
+	ipl_ptr = (unsigned int *)__LC_IPL_PARMBLOCK_PTR;
+	src = (void *)(unsigned long)*ipl_ptr;
+	dst = (void *)IPL_PARMBLOCK_ORIGIN;
+	memmove(dst, src, PAGE_SIZE);
+	*ipl_ptr = IPL_PARMBLOCK_ORIGIN;
 }

drivers/s390/cio/css.c

@@ -182,136 +182,141 @@ get_subchannel_by_schid(struct subchannel_id schid)
 	return dev ? to_subchannel(dev) : NULL;
 }
 
-
-static inline int
-css_get_subchannel_status(struct subchannel *sch, struct subchannel_id schid)
+static inline int css_get_subchannel_status(struct subchannel *sch)
 {
 	struct schib schib;
-	int cc;
 
-	cc = stsch(schid, &schib);
-	if (cc)
-		return CIO_GONE;
-	if (!schib.pmcw.dnv)
+	if (stsch(sch->schid, &schib) || !schib.pmcw.dnv)
 		return CIO_GONE;
-	if (sch && sch->schib.pmcw.dnv &&
-	    (schib.pmcw.dev != sch->schib.pmcw.dev))
+	if (sch->schib.pmcw.dnv && (schib.pmcw.dev != sch->schib.pmcw.dev))
 		return CIO_REVALIDATE;
-	if (sch && !sch->lpm)
+	if (!sch->lpm)
 		return CIO_NO_PATH;
 	return CIO_OPER;
 }
 
-static int
-css_evaluate_subchannel(struct subchannel_id schid, int slow)
+static int css_evaluate_known_subchannel(struct subchannel *sch, int slow)
 {
 	int event, ret, disc;
-	struct subchannel *sch;
 	unsigned long flags;
+	enum { NONE, UNREGISTER, UNREGISTER_PROBE, REPROBE } action;
 
-	sch = get_subchannel_by_schid(schid);
-	disc = sch ? device_is_disconnected(sch) : 0;
+	spin_lock_irqsave(&sch->lock, flags);
+	disc = device_is_disconnected(sch);
 	if (disc && slow) {
-		if (sch)
-			put_device(&sch->dev);
-		return 0; /* Already processed. */
+		/* Disconnected devices are evaluated directly only.*/
+		spin_unlock_irqrestore(&sch->lock, flags);
+		return 0;
 	}
-	/*
-	 * We've got a machine check, so running I/O won't get an interrupt.
-	 * Kill any pending timers.
-	 */
-	if (sch)
+	/* No interrupt after machine check - kill pending timers. */
 	device_kill_pending_timer(sch);
 	if (!disc && !slow) {
-		if (sch)
-			put_device(&sch->dev);
-		return -EAGAIN; /* Will be done on the slow path. */
+		/* Non-disconnected devices are evaluated on the slow path. */
+		spin_unlock_irqrestore(&sch->lock, flags);
+		return -EAGAIN;
 	}
-	event = css_get_subchannel_status(sch, schid);
+	event = css_get_subchannel_status(sch);
 	CIO_MSG_EVENT(4, "Evaluating schid 0.%x.%04x, event %d, %s, %s path.\n",
-		      schid.ssid, schid.sch_no, event,
-		      sch?(disc?"disconnected":"normal"):"unknown",
-		      slow?"slow":"fast");
+		      sch->schid.ssid, sch->schid.sch_no, event,
+		      disc ? "disconnected" : "normal",
+		      slow ? "slow" : "fast");
+	/* Analyze subchannel status. */
+	action = NONE;
 	switch (event) {
 	case CIO_NO_PATH:
-	case CIO_GONE:
-		if (!sch) {
-			/* Never used this subchannel. Ignore. */
-			ret = 0;
-			break;
-		}
-		if (disc && (event == CIO_NO_PATH)) {
-			/*
-			 * Uargh, hack again. Because we don't get a machine
-			 * check on configure on, our path bookkeeping can
-			 * be out of date here (it's fine while we only do
-			 * logical varying or get chsc machine checks). We
-			 * need to force reprobing or we might miss devices
-			 * coming operational again. It won't do harm in real
-			 * no path situations.
-			 */
-			spin_lock_irqsave(&sch->lock, flags);
-			device_trigger_reprobe(sch);
-			spin_unlock_irqrestore(&sch->lock, flags);
-			ret = 0;
+		if (disc) {
+			/* Check if paths have become available. */
+			action = REPROBE;
 			break;
 		}
-		if (sch->driver && sch->driver->notify &&
-		    sch->driver->notify(&sch->dev, event)) {
+		/* fall through */
+	case CIO_GONE:
+		/* Prevent unwanted effects when opening lock. */
 		cio_disable_subchannel(sch);
 		device_set_disconnected(sch);
-			ret = 0;
-			break;
+		/* Ask driver what to do with device. */
+		action = UNREGISTER;
+		if (sch->driver && sch->driver->notify) {
+			spin_unlock_irqrestore(&sch->lock, flags);
+			ret = sch->driver->notify(&sch->dev, event);
+			spin_lock_irqsave(&sch->lock, flags);
+			if (ret)
+				action = NONE;
 		}
-		/*
-		 * Unregister subchannel.
-		 * The device will be killed automatically.
-		 */
-		cio_disable_subchannel(sch);
-		css_sch_device_unregister(sch);
-		/* Reset intparm to zeroes. */
-		sch->schib.pmcw.intparm = 0;
-		cio_modify(sch);
-		put_device(&sch->dev);
-		ret = 0;
 		break;
 	case CIO_REVALIDATE:
-		/* 
-		 * Revalidation machine check. Sick.
-		 * We don't notify the driver since we have to throw the device
-		 * away in any case.
-		 */
-		if (!disc) {
+		/* Device will be removed, so no notify necessary. */
+		if (disc)
+			/* Reprobe because immediate unregister might block. */
+			action = REPROBE;
+		else
+			action = UNREGISTER_PROBE;
+		break;
+	case CIO_OPER:
+		if (disc)
+			/* Get device operational again. */
+			action = REPROBE;
+		break;
+	}
+	/* Perform action. */
+	ret = 0;
+	switch (action) {
+	case UNREGISTER:
+	case UNREGISTER_PROBE:
+		/* Unregister device (will use subchannel lock). */
+		spin_unlock_irqrestore(&sch->lock, flags);
 		css_sch_device_unregister(sch);
+		spin_lock_irqsave(&sch->lock, flags);
+
 		/* Reset intparm to zeroes. */
 		sch->schib.pmcw.intparm = 0;
 		cio_modify(sch);
-			put_device(&sch->dev);
-			ret = css_probe_device(schid);
-		} else {
-			/*
-			 * We can't immediately deregister the disconnected
-			 * device since it might block.
-			 */
-			spin_lock_irqsave(&sch->lock, flags);
-			device_trigger_reprobe(sch);
-			spin_unlock_irqrestore(&sch->lock, flags);
-			ret = 0;
-		}
+
+		/* Probe if necessary. */
+		if (action == UNREGISTER_PROBE)
+			ret = css_probe_device(sch->schid);
 		break;
-	case CIO_OPER:
-		if (disc) {
-			spin_lock_irqsave(&sch->lock, flags);
-			/* Get device operational again. */
+	case REPROBE:
 		device_trigger_reprobe(sch);
-			spin_unlock_irqrestore(&sch->lock, flags);
-		}
-		ret = sch ? 0 : css_probe_device(schid);
 		break;
 	default:
-		BUG();
-		ret = 0;
+		break;
 	}
+	spin_unlock_irqrestore(&sch->lock, flags);
+
+	return ret;
+}
+
+static int css_evaluate_new_subchannel(struct subchannel_id schid, int slow)
+{
+	struct schib schib;
+
+	if (!slow) {
+		/* Will be done on the slow path. */
+		return -EAGAIN;
+	}
+	if (stsch(schid, &schib) || !schib.pmcw.dnv) {
+		/* Unusable - ignore. */
+		return 0;
+	}
+	CIO_MSG_EVENT(4, "Evaluating schid 0.%x.%04x, event %d, unknown, "
+			 "slow path.\n", schid.ssid, schid.sch_no, CIO_OPER);
+
+	return css_probe_device(schid);
+}
+
+static int css_evaluate_subchannel(struct subchannel_id schid, int slow)
+{
+	struct subchannel *sch;
+	int ret;
+
+	sch = get_subchannel_by_schid(schid);
+	if (sch) {
+		ret = css_evaluate_known_subchannel(sch, slow);
+		put_device(&sch->dev);
+	} else
+		ret = css_evaluate_new_subchannel(schid, slow);
+
 	return ret;
 }
 

drivers/s390/cio/qdio.c

@@ -115,7 +115,7 @@ qdio_min(int a,int b)
 static inline __u64 
 qdio_get_micros(void)
 {
-        return (get_clock() >> 10); /* time>>12 is microseconds */
+	return (get_clock() >> 12); /* time>>12 is microseconds */
 }
 
 /* 
@@ -1129,7 +1129,7 @@ qdio_get_inbound_buffer_frontier(struct qdio_q *q)
 
 #ifdef QDIO_USE_PROCESSING_STATE
 	if (last_position>=0)
-		set_slsb(q, &last_position, SLSB_P_INPUT_NOT_INIT, &count);
+		set_slsb(q, &last_position, SLSB_P_INPUT_PROCESSING, &count);
 #endif /* QDIO_USE_PROCESSING_STATE */
 
 	QDIO_DBF_HEX4(0,trace,&q->first_to_check,sizeof(int));