[patch 00/10] 2.6.24-rc s390 patch queue

[patch 00/10] 2.6.24-rc s390 patch queue

[Martin Schwidefsky]

These are the s390 patches in the queue for 2.6.24-rc. I plan to send
a please pull sometime next week. The shortlog:

Christian Borntraeger (2):
      [S390] magic sysrq: check for in_atomic before doing an console_unblank
      [S390] Optimize storage key handling for anonymous pages

Christoph Lameter (1):
      [S390] Explicitly code allocpercpu calls in iucv

Heiko Carstens (6):
      [S390] Fix irq tracing and lockdep_sys_exit calls.
      [S390] cmm: remove unused binary sysctls.
      [S390] appldata: remove unused binary sysctls.
      [S390] Fix kernel preemption.
      [S390] Dont overwrite lowcores on smp_send_stop().
      [S390] Fix memory detection.

Peter Oberparleiter (1):
      [S390] cio: change device sense procedure to work with pav aliases

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 01/10] cio: change device sense procedure to work with pav aliases

[Martin Schwidefsky]

[-- Attachment #1: 001-cio-sense.diff --]
[-- Type: text/plain, Size: 3178 bytes --]

From: Peter Oberparleiter <peter.oberparleiter@de.ibm.com>

Modify the sense id channel program to allow device sensing of pav
alias devices which belong to a base device with ungrouped paths.

Signed-off-by: Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 drivers/s390/cio/device_id.c |   45 ++++++++-----------------------------------
 1 file changed, 9 insertions(+), 36 deletions(-)

diff -urpN linux-2.6/drivers/s390/cio/device_id.c linux-2.6-patched/drivers/s390/cio/device_id.c
--- linux-2.6/drivers/s390/cio/device_id.c	2007-10-09 22:31:38.000000000 +0200
+++ linux-2.6-patched/drivers/s390/cio/device_id.c	2007-11-16 14:27:37.000000000 +0100
@@ -113,19 +113,10 @@ __ccw_device_sense_id_start(struct ccw_d
 {
 	struct subchannel *sch;
 	struct ccw1 *ccw;
-	int ret;
 
 	sch = to_subchannel(cdev->dev.parent);
 	/* Setup sense channel program. */
 	ccw = cdev->private->iccws;
-	if (sch->schib.pmcw.pim != 0x80) {
-		/* more than one path installed. */
-		ccw->cmd_code = CCW_CMD_SUSPEND_RECONN;
-		ccw->cda = 0;
-		ccw->count = 0;
-		ccw->flags = CCW_FLAG_SLI | CCW_FLAG_CC;
-		ccw++;
-	}
 	ccw->cmd_code = CCW_CMD_SENSE_ID;
 	ccw->cda = (__u32) __pa (&cdev->private->senseid);
 	ccw->count = sizeof (struct senseid);
@@ -133,25 +124,9 @@ __ccw_device_sense_id_start(struct ccw_d
 
 	/* Reset device status. */
 	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	cdev->private->flags.intretry = 0;
 
-	/* Try on every path. */
-	ret = -ENODEV;
-	while (cdev->private->imask != 0) {
-		if ((sch->opm & cdev->private->imask) != 0 &&
-		    cdev->private->iretry > 0) {
-			cdev->private->iretry--;
-			/* Reset internal retry indication. */
-			cdev->private->flags.intretry = 0;
-			ret = cio_start (sch, cdev->private->iccws,
-					 cdev->private->imask);
-			/* ret is 0, -EBUSY, -EACCES or -ENODEV */
-			if (ret != -EACCES)
-				return ret;
-		}
-		cdev->private->imask >>= 1;
-		cdev->private->iretry = 5;
-	}
-	return ret;
+	return cio_start(sch, ccw, LPM_ANYPATH);
 }
 
 void
@@ -161,8 +136,7 @@ ccw_device_sense_id_start(struct ccw_dev
 
 	memset (&cdev->private->senseid, 0, sizeof (struct senseid));
 	cdev->private->senseid.cu_type = 0xFFFF;
-	cdev->private->imask = 0x80;
-	cdev->private->iretry = 5;
+	cdev->private->iretry = 3;
 	ret = __ccw_device_sense_id_start(cdev);
 	if (ret && ret != -EBUSY)
 		ccw_device_sense_id_done(cdev, ret);
@@ -278,14 +252,13 @@ ccw_device_sense_id_irq(struct ccw_devic
 		ccw_device_sense_id_done(cdev, ret);
 		break;
 	case -EACCES:		/* channel is not operational. */
-		sch->lpm &= ~cdev->private->imask;
-		cdev->private->imask >>= 1;
-		cdev->private->iretry = 5;
-		/* fall through. */
 	case -EAGAIN:		/* try again. */
-		ret = __ccw_device_sense_id_start(cdev);
-		if (ret == 0 || ret == -EBUSY)
-			break;
+		cdev->private->iretry--;
+		if (cdev->private->iretry > 0) {
+			ret = __ccw_device_sense_id_start(cdev);
+			if (ret == 0 || ret == -EBUSY)
+				break;
+		}
 		/* fall through. */
 	default:		/* Sense ID failed. Try asking VM. */
 		if (MACHINE_IS_VM) {

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 02/10] magic sysrq: check for in_atomic before doing an console_unblank

[Martin Schwidefsky]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: 002-console-unblank.diff --]
[-- Type: text/plain, Size: 2310 bytes --]

From: Christian Borntraeger <borntraeger@de.ibm.com>

When doing an magic sysrq reboot on s390 the following bug message
appears:

SysRq : Resetting
BUG: sleeping function called from invalid context at include/asm/semaphore.h:61

in_atomic():1, irqs_disabled():0
07000000004002a8 000000000fe6bc48 0000000000000002 0000000000000000
       000000000fe6bce8 000000000fe6bc60 000000000fe6bc60 000000000012a79a
       0000000000000000 07000000004002a8 0000000000000006 0000000000000000
       0000000000000000 000000000fe6bc48 000000000000000d 000000000fe6bcb8
       00000000004000c8 0000000000103234 000000000fe6bc48 000000000fe6bc90
Call Trace:
(¬<00000000001031b2>| show_trace+0x12e/0x148)
 ¬<000000000011ffca>| __might_sleep+0x10a/0x118
 ¬<0000000000129fba>| acquire_console_sem+0x92/0xf4
 ¬<000000000012a2ca>| console_unblank+0xc2/0xc8
 ¬<0000000000107bb4>| machine_restart+0x54/0x6c
 ¬<000000000028e806>| sysrq_handle_reboot+0x26/0x30
 ¬<000000000028e52a>| __handle_sysrq+0xa6/0x180
 ¬<0000000000140134>| run_workqueue+0xcc/0x18c
 ¬<000000000014029a>| worker_thread+0xa6/0x108
 ¬<00000000001458e4>| kthread+0x64/0x9c
 ¬<0000000000106f0e>| kernel_thread_starter+0x6/0xc
 ¬<0000000000106f08>| kernel_thread_starter+0x0/0xc

The only reason for doing a console_unblank on s390 is to flush the
log buffer. We have to check for in_atomic before doing a
console_unblank as the console is otherwise filled with an unrelated
bug message.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/kernel/setup.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff -urpN linux-2.6/arch/s390/kernel/setup.c linux-2.6-patched/arch/s390/kernel/setup.c
--- linux-2.6/arch/s390/kernel/setup.c	2007-10-09 22:31:38.000000000 +0200
+++ linux-2.6-patched/arch/s390/kernel/setup.c	2007-11-16 14:27:37.000000000 +0100
@@ -347,7 +347,7 @@ void (*_machine_power_off)(void) = do_ma
 
 void machine_restart(char *command)
 {
-	if (!in_interrupt() || oops_in_progress)
+	if ((!in_interrupt() && !in_atomic()) || oops_in_progress)
 		/*
 		 * Only unblank the console if we are called in enabled
 		 * context or a bust_spinlocks cleared the way for us.

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 03/10] Fix irq tracing and lockdep_sys_exit calls.

[Martin Schwidefsky]

[-- Attachment #1: 003-lockdep.diff --]
[-- Type: text/plain, Size: 19554 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Current support for TRACE_IRQFLAGS and lockdep_sys_exit is broken.
IRQ flag tracing is broken for program checks. Even worse is that
the newly introduced calls to lockdep_sys_exit are in the critical
section code which is not supposed to call any C functions. In
addition the checks if locks are still held are also done when
returning to kernel code which is broken as well.
Fix all this by disabling interrupts and machine checks at the
exit paths and then do the appropriate checks and calls.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/kernel/entry.S   |  109 +++++++++++++++++++++++++++++++--------------
 arch/s390/kernel/entry64.S |  106 ++++++++++++++++++++++++++++++-------------
 arch/s390/kernel/setup.c   |    4 +
 include/asm-s390/system.h  |    5 ++
 4 files changed, 158 insertions(+), 66 deletions(-)

diff -urpN linux-2.6/arch/s390/kernel/entry64.S linux-2.6-patched/arch/s390/kernel/entry64.S
--- linux-2.6/arch/s390/kernel/entry64.S	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/entry64.S	2007-11-16 14:27:38.000000000 +0100
@@ -67,12 +67,28 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_
 	 brasl	%r14,trace_hardirqs_off
 	.endm
 
-	.macro	LOCKDEP_SYS_EXIT
-	 brasl	%r14,lockdep_sys_exit
+	.macro TRACE_IRQS_CHECK
+	tm	SP_PSW(%r15),0x03	# irqs enabled?
+	jz	0f
+	brasl	%r14,trace_hardirqs_on
+	j	1f
+0:	brasl	%r14,trace_hardirqs_off
+1:
 	.endm
 #else
 #define TRACE_IRQS_ON
 #define TRACE_IRQS_OFF
+#define TRACE_IRQS_CHECK
+#endif
+
+#ifdef CONFIG_LOCKDEP
+	.macro	LOCKDEP_SYS_EXIT
+	tm	SP_PSW+1(%r15),0x01	# returning to user ?
+	jz	0f
+	brasl	%r14,lockdep_sys_exit
+0:
+	.endm
+#else
 #define LOCKDEP_SYS_EXIT
 #endif
 
@@ -222,8 +238,6 @@ sysc_saveall:
 	llgh	%r7,__LC_SVC_INT_CODE	# get svc number from lowcore
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 sysc_vtime:
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	sysc_do_svc
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 sysc_stime:
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
@@ -257,19 +271,34 @@ sysc_noemu:
 
 sysc_return:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	jno	sysc_leave
+	jno	sysc_restore
 	tm	__TI_flags+7(%r9),_TIF_WORK_SVC
 	jnz	sysc_work	# there is work to do (signals etc.)
+sysc_restore:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	larl	%r1,sysc_restore_trace_psw
+	lpswe	0(%r1)
+sysc_restore_trace:
+	TRACE_IRQS_CHECK
 	LOCKDEP_SYS_EXIT
+#endif
 sysc_leave:
 	RESTORE_ALL __LC_RETURN_PSW,1
+sysc_done:
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	.align	8
+	.globl sysc_restore_trace_psw
+sysc_restore_trace_psw:
+	.quad	0, sysc_restore_trace
+#endif
 
 #
 # recheck if there is more work to do
 #
 sysc_work_loop:
 	tm	__TI_flags+7(%r9),_TIF_WORK_SVC
-	jz	sysc_leave	  # there is no work to do
+	jz	sysc_restore	  # there is no work to do
 #
 # One of the work bits is on. Find out which one.
 #
@@ -284,8 +313,8 @@ sysc_work:
 	jo	sysc_restart
 	tm	__TI_flags+7(%r9),_TIF_SINGLE_STEP
 	jo	sysc_singlestep
-	LOCKDEP_SYS_EXIT
-	j	sysc_leave
+	j	sysc_restore
+sysc_work_done:
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
@@ -445,6 +474,7 @@ pgm_check_handler:
 pgm_no_vtime:
 #endif
 	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	TRACE_IRQS_OFF
 	lgf	%r3,__LC_PGM_ILC	# load program interruption code
 	lghi	%r8,0x7f
 	ngr	%r8,%r3
@@ -484,6 +514,7 @@ pgm_per_std:
 pgm_no_vtime2:
 #endif
 	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	TRACE_IRQS_OFF
 	lg	%r1,__TI_task(%r9)
 	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
 	jz	kernel_per
@@ -504,12 +535,9 @@ pgm_svcper:
 	SAVE_ALL_SYNC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
 	CREATE_STACK_FRAME __LC_SVC_OLD_PSW,__LC_SAVE_AREA
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	pgm_no_vtime3
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-pgm_no_vtime3:
 #endif
 	llgh	%r7,__LC_SVC_INT_CODE	# get svc number from lowcore
 	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
@@ -529,7 +557,7 @@ 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
+	larl	%r14,sysc_restore	# load adr. of system ret, no work
 	jg	do_single_step		# branch to do_single_step
 
 /*
@@ -554,26 +582,38 @@ io_no_vtime:
 	TRACE_IRQS_OFF
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	brasl	%r14,do_IRQ		# call standard irq handler
-	TRACE_IRQS_ON
-
 io_return:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
 #ifdef CONFIG_PREEMPT
 	jno	io_preempt		# no -> check for preemptive scheduling
 #else
-	jno	io_leave		# no-> skip resched & signal
+	jno	io_restore		# no-> skip resched & signal
 #endif
 	tm	__TI_flags+7(%r9),_TIF_WORK_INT
 	jnz	io_work 		# there is work to do (signals etc.)
+io_restore:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	larl	%r1,io_restore_trace_psw
+	lpswe	0(%r1)
+io_restore_trace:
+	TRACE_IRQS_CHECK
 	LOCKDEP_SYS_EXIT
+#endif
 io_leave:
 	RESTORE_ALL __LC_RETURN_PSW,0
 io_done:
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	.align	8
+	.globl io_restore_trace_psw
+io_restore_trace_psw:
+	.quad	0, io_restore_trace
+#endif
+
 #ifdef CONFIG_PREEMPT
 io_preempt:
 	icm	%r0,15,__TI_precount(%r9)
-	jnz	io_leave
+	jnz	io_restore
 	# switch to kernel stack
 	lg	%r1,SP_R15(%r15)
 	aghi	%r1,-SP_SIZE
@@ -582,12 +622,14 @@ io_preempt:
 	lgr	%r15,%r1
 io_resume_loop:
 	tm	__TI_flags+7(%r9),_TIF_NEED_RESCHED
-	jno	io_leave
+	jno	io_restore
 	larl	%r1,.Lc_pactive
 	mvc	__TI_precount(4,%r9),0(%r1)
+	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	brasl	%r14,schedule		# call schedule
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
 	xc	__TI_precount(4,%r9),__TI_precount(%r9)
 	j	io_resume_loop
 #endif
@@ -613,37 +655,39 @@ io_work_loop:
 	jo	io_reschedule
 	tm	__TI_flags+7(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)
 	jnz	io_sigpending
-	LOCKDEP_SYS_EXIT
-	j	io_leave
+	j	io_restore
+io_work_done:
 
 #
 # _TIF_MCCK_PENDING is set, call handler
 #
 io_mcck_pending:
-	TRACE_IRQS_OFF
 	brasl	%r14,s390_handle_mcck	# TIF bit will be cleared by handler
-	TRACE_IRQS_ON
 	j	io_work_loop
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
 #
 io_reschedule:
+	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	brasl	%r14,schedule		# call scheduler
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
 	tm	__TI_flags+7(%r9),_TIF_WORK_INT
-	jz	io_leave		# there is no work to do
+	jz	io_restore		# there is no work to do
 	j	io_work_loop
 
 #
 # _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal
 #
 io_sigpending:
+	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	brasl	%r14,do_signal		# call do_signal
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
 	j	io_work_loop
 
 /*
@@ -669,7 +713,6 @@ ext_no_vtime:
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	llgh	%r3,__LC_EXT_INT_CODE	# get interruption code
 	brasl	%r14,do_extint
-	TRACE_IRQS_ON
 	j	io_return
 
 __critical_end:
@@ -824,15 +867,15 @@ cleanup_table_system_call:
 cleanup_table_sysc_return:
 	.quad	sysc_return, sysc_leave
 cleanup_table_sysc_leave:
-	.quad	sysc_leave, sysc_work_loop
+	.quad	sysc_leave, sysc_done
 cleanup_table_sysc_work_loop:
-	.quad	sysc_work_loop, sysc_reschedule
+	.quad	sysc_work_loop, sysc_work_done
 cleanup_table_io_return:
 	.quad	io_return, io_leave
 cleanup_table_io_leave:
 	.quad	io_leave, io_done
 cleanup_table_io_work_loop:
-	.quad	io_work_loop, io_mcck_pending
+	.quad	io_work_loop, io_work_done
 
 cleanup_critical:
 	clc	8(8,%r12),BASED(cleanup_table_system_call)
@@ -901,8 +944,6 @@ cleanup_system_call:
 cleanup_vtime:
 	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+24)
 	jhe	cleanup_stime
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	cleanup_novtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 cleanup_stime:
 	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+32)
@@ -910,7 +951,6 @@ cleanup_stime:
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
 cleanup_update:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-cleanup_novtime:
 #endif
 	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_system_call+8)
 	la	%r12,__LC_RETURN_PSW
@@ -949,10 +989,10 @@ cleanup_sysc_leave:
 2:	la	%r12,__LC_RETURN_PSW
 	br	%r14
 cleanup_sysc_leave_insn:
+	.quad	sysc_done - 4
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	.quad	sysc_leave + 16
+	.quad	sysc_done - 8
 #endif
-	.quad	sysc_leave + 12
 
 cleanup_io_return:
 	mvc	__LC_RETURN_PSW(8),0(%r12)
@@ -979,10 +1019,10 @@ cleanup_io_leave:
 2:	la	%r12,__LC_RETURN_PSW
 	br	%r14
 cleanup_io_leave_insn:
+	.quad	io_done - 4
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	.quad	io_leave + 20
+	.quad	io_done - 8
 #endif
-	.quad	io_leave + 16
 
 /*
  * Integer constants
diff -urpN linux-2.6/arch/s390/kernel/entry.S linux-2.6-patched/arch/s390/kernel/entry.S
--- linux-2.6/arch/s390/kernel/entry.S	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/entry.S	2007-11-16 14:27:38.000000000 +0100
@@ -69,13 +69,31 @@ STACK_SIZE  = 1 << STACK_SHIFT
 	basr	%r14,%r1
 	.endm
 
-	.macro	LOCKDEP_SYS_EXIT
-	l	%r1,BASED(.Llockdep_sys_exit)
+	.macro	TRACE_IRQS_CHECK
+	tm	SP_PSW(%r15),0x03	# irqs enabled?
+	jz	0f
+	l	%r1,BASED(.Ltrace_irq_on)
+	basr	%r14,%r1
+	j	1f
+0:	l	%r1,BASED(.Ltrace_irq_off)
 	basr	%r14,%r1
+1:
 	.endm
 #else
 #define TRACE_IRQS_ON
 #define TRACE_IRQS_OFF
+#define TRACE_IRQS_CHECK
+#endif
+
+#ifdef CONFIG_LOCKDEP
+	.macro	LOCKDEP_SYS_EXIT
+	tm	SP_PSW+1(%r15),0x01	# returning to user ?
+	jz	0f
+	l	%r1,BASED(.Llockdep_sys_exit)
+	basr	%r14,%r1
+0:
+	.endm
+#else
 #define LOCKDEP_SYS_EXIT
 #endif
 
@@ -234,8 +252,6 @@ sysc_saveall:
 	lh	%r7,0x8a	  # get svc number from lowcore
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 sysc_vtime:
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(sysc_do_svc)
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 sysc_stime:
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
@@ -263,19 +279,34 @@ sysc_do_restart:
 
 sysc_return:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	bno	BASED(sysc_leave)
+	bno	BASED(sysc_restore)
 	tm	__TI_flags+3(%r9),_TIF_WORK_SVC
 	bnz	BASED(sysc_work)  # there is work to do (signals etc.)
+sysc_restore:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	la	%r1,BASED(sysc_restore_trace_psw)
+	lpsw	0(%r1)
+sysc_restore_trace:
+	TRACE_IRQS_CHECK
 	LOCKDEP_SYS_EXIT
+#endif
 sysc_leave:
 	RESTORE_ALL __LC_RETURN_PSW,1
+sysc_done:
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+	.align	8
+	.globl	sysc_restore_trace_psw
+sysc_restore_trace_psw:
+	.long	0, sysc_restore_trace + 0x80000000
+#endif
 
 #
 # recheck if there is more work to do
 #
 sysc_work_loop:
 	tm	__TI_flags+3(%r9),_TIF_WORK_SVC
-	bz	BASED(sysc_leave)	# there is no work to do
+	bz	BASED(sysc_restore)	# there is no work to do
 #
 # One of the work bits is on. Find out which one.
 #
@@ -290,8 +321,8 @@ sysc_work:
 	bo	BASED(sysc_restart)
 	tm	__TI_flags+3(%r9),_TIF_SINGLE_STEP
 	bo	BASED(sysc_singlestep)
-	LOCKDEP_SYS_EXIT
-	b	BASED(sysc_leave)
+	b	BASED(sysc_restore)
+sysc_work_done:
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
@@ -458,6 +489,7 @@ pgm_check_handler:
 pgm_no_vtime:
 #endif
 	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	TRACE_IRQS_OFF
 	l	%r3,__LC_PGM_ILC	# load program interruption code
 	la	%r8,0x7f
 	nr	%r8,%r3
@@ -497,6 +529,7 @@ pgm_per_std:
 pgm_no_vtime2:
 #endif
 	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	TRACE_IRQS_OFF
 	l	%r1,__TI_task(%r9)
 	mvc	__THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID
 	mvc	__THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS
@@ -517,15 +550,13 @@ pgm_svcper:
 	SAVE_ALL_SYNC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
 	CREATE_STACK_FRAME __LC_SVC_OLD_PSW,__LC_SAVE_AREA
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(pgm_no_vtime3)
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-pgm_no_vtime3:
 #endif
 	lh	%r7,0x8a		# get svc number from lowcore
 	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	TRACE_IRQS_OFF
 	l	%r1,__TI_task(%r9)
 	mvc	__THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID
 	mvc	__THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS
@@ -542,7 +573,7 @@ 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
+	la	%r14,BASED(sysc_restore)# load adr. of system return
 	br	%r1			# branch to do_single_step
 
 /*
@@ -569,26 +600,38 @@ io_no_vtime:
 	l	%r1,BASED(.Ldo_IRQ)	# load address of do_IRQ
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	basr	%r14,%r1		# branch to standard irq handler
-	TRACE_IRQS_ON
-
 io_return:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
 #ifdef CONFIG_PREEMPT
 	bno	BASED(io_preempt)	# no -> check for preemptive scheduling
 #else
-	bno	BASED(io_leave) 	# no-> skip resched & signal
+	bno	BASED(io_restore)	# no-> skip resched & signal
 #endif
 	tm	__TI_flags+3(%r9),_TIF_WORK_INT
 	bnz	BASED(io_work)		# there is work to do (signals etc.)
+io_restore:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	la	%r1,BASED(io_restore_trace_psw)
+	lpsw	0(%r1)
+io_restore_trace:
+	TRACE_IRQS_CHECK
 	LOCKDEP_SYS_EXIT
+#endif
 io_leave:
 	RESTORE_ALL __LC_RETURN_PSW,0
 io_done:
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+	.align	8
+	.globl	io_restore_trace_psw
+io_restore_trace_psw:
+	.long	0, io_restore_trace + 0x80000000
+#endif
+
 #ifdef CONFIG_PREEMPT
 io_preempt:
 	icm	%r0,15,__TI_precount(%r9)
-	bnz	BASED(io_leave)
+	bnz	BASED(io_restore)
 	l	%r1,SP_R15(%r15)
 	s	%r1,BASED(.Lc_spsize)
 	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
@@ -596,12 +639,14 @@ io_preempt:
 	lr	%r15,%r1
 io_resume_loop:
 	tm	__TI_flags+3(%r9),_TIF_NEED_RESCHED
-	bno	BASED(io_leave)
+	bno	BASED(io_restore)
 	mvc	__TI_precount(4,%r9),BASED(.Lc_pactive)
+	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03  # reenable interrupts
 	l	%r1,BASED(.Lschedule)
 	basr	%r14,%r1	       # call schedule
 	stnsm	__SF_EMPTY(%r15),0xfc  # disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
 	xc	__TI_precount(4,%r9),__TI_precount(%r9)
 	b	BASED(io_resume_loop)
 #endif
@@ -627,40 +672,42 @@ io_work_loop:
 	bo	BASED(io_reschedule)
 	tm	__TI_flags+3(%r9),(_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)
 	bnz	BASED(io_sigpending)
-	LOCKDEP_SYS_EXIT
-	b	BASED(io_leave)
+	b	BASED(io_restore)
+io_work_done:
 
 #
 # _TIF_MCCK_PENDING is set, call handler
 #
 io_mcck_pending:
-	TRACE_IRQS_OFF
 	l	%r1,BASED(.Ls390_handle_mcck)
 	basr	%r14,%r1		# TIF bit will be cleared by handler
-	TRACE_IRQS_ON
 	b	BASED(io_work_loop)
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
 #
 io_reschedule:
+	TRACE_IRQS_ON
 	l	%r1,BASED(.Lschedule)
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	basr	%r14,%r1		# call scheduler
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
 	tm	__TI_flags+3(%r9),_TIF_WORK_INT
-	bz	BASED(io_leave) 	# there is no work to do
+	bz	BASED(io_restore)	# there is no work to do
 	b	BASED(io_work_loop)
 
 #
 # _TIF_SIGPENDING or _TIF_RESTORE_SIGMASK is set, call do_signal
 #
 io_sigpending:
+	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	l	%r1,BASED(.Ldo_signal)
 	basr	%r14,%r1		# call do_signal
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
 	b	BASED(io_work_loop)
 
 /*
@@ -688,7 +735,6 @@ ext_no_vtime:
 	lh	%r3,__LC_EXT_INT_CODE	# get interruption code
 	l	%r1,BASED(.Ldo_extint)
 	basr	%r14,%r1
-	TRACE_IRQS_ON
 	b	BASED(io_return)
 
 __critical_end:
@@ -853,15 +899,15 @@ cleanup_table_system_call:
 cleanup_table_sysc_return:
 	.long	sysc_return + 0x80000000, sysc_leave + 0x80000000
 cleanup_table_sysc_leave:
-	.long	sysc_leave + 0x80000000, sysc_work_loop + 0x80000000
+	.long	sysc_leave + 0x80000000, sysc_done + 0x80000000
 cleanup_table_sysc_work_loop:
-	.long	sysc_work_loop + 0x80000000, sysc_reschedule + 0x80000000
+	.long	sysc_work_loop + 0x80000000, sysc_work_done + 0x80000000
 cleanup_table_io_return:
 	.long	io_return + 0x80000000, io_leave + 0x80000000
 cleanup_table_io_leave:
 	.long	io_leave + 0x80000000, io_done + 0x80000000
 cleanup_table_io_work_loop:
-	.long	io_work_loop + 0x80000000, io_mcck_pending + 0x80000000
+	.long	io_work_loop + 0x80000000, io_work_done + 0x80000000
 
 cleanup_critical:
 	clc	4(4,%r12),BASED(cleanup_table_system_call)
@@ -930,8 +976,6 @@ cleanup_system_call:
 cleanup_vtime:
 	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+12)
 	bhe	BASED(cleanup_stime)
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(cleanup_novtime)
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 cleanup_stime:
 	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+16)
@@ -939,7 +983,6 @@ cleanup_stime:
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
 cleanup_update:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-cleanup_novtime:
 #endif
 	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_system_call+4)
 	la	%r12,__LC_RETURN_PSW
@@ -978,10 +1021,10 @@ cleanup_sysc_leave:
 2:	la	%r12,__LC_RETURN_PSW
 	br	%r14
 cleanup_sysc_leave_insn:
+	.long	sysc_done - 4 + 0x80000000
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	.long	sysc_leave + 14 + 0x80000000
+	.long	sysc_done - 8 + 0x80000000
 #endif
-	.long	sysc_leave + 10 + 0x80000000
 
 cleanup_io_return:
 	mvc	__LC_RETURN_PSW(4),0(%r12)
@@ -1008,10 +1051,10 @@ cleanup_io_leave:
 2:	la	%r12,__LC_RETURN_PSW
 	br	%r14
 cleanup_io_leave_insn:
+	.long	io_done - 4 + 0x80000000
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	.long	io_leave + 18 + 0x80000000
+	.long	io_done - 8 + 0x80000000
 #endif
-	.long	io_leave + 14 + 0x80000000
 
 /*
  * Integer constants
diff -urpN linux-2.6/arch/s390/kernel/setup.c linux-2.6-patched/arch/s390/kernel/setup.c
--- linux-2.6/arch/s390/kernel/setup.c	2007-11-16 14:27:38.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/setup.c	2007-11-16 14:27:38.000000000 +0100
@@ -492,6 +492,10 @@ static void setup_addressing_mode(void)
 		printk("S390 address spaces switched, ");
 		set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY);
 	}
+#ifdef CONFIG_TRACE_IRQFLAGS
+	sysc_restore_trace_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK;
+	io_restore_trace_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK;
+#endif
 }
 
 static void __init
diff -urpN linux-2.6/include/asm-s390/system.h linux-2.6-patched/include/asm-s390/system.h
--- linux-2.6/include/asm-s390/system.h	2007-11-16 14:27:34.000000000 +0100
+++ linux-2.6-patched/include/asm-s390/system.h	2007-11-16 14:27:38.000000000 +0100
@@ -388,6 +388,11 @@ extern void (*_machine_power_off)(void);
 
 #define arch_align_stack(x) (x)
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+extern psw_t sysc_restore_trace_psw;
+extern psw_t io_restore_trace_psw;
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 04/10] cmm: remove unused binary sysctls.

[Martin Schwidefsky]

[-- Attachment #1: 004-cmm.diff --]
[-- Type: text/plain, Size: 2436 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Remove binary sysctls that never worked due to missing strategy functions.

Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/mm/cmm.c     |    3 ---
 include/linux/sysctl.h |    5 -----
 kernel/sysctl_check.c  |    3 ---
 3 files changed, 11 deletions(-)

diff -urpN linux-2.6/arch/s390/mm/cmm.c linux-2.6-patched/arch/s390/mm/cmm.c
--- linux-2.6/arch/s390/mm/cmm.c	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/mm/cmm.c	2007-11-16 14:27:41.000000000 +0100
@@ -341,19 +341,16 @@ cmm_timeout_handler(ctl_table *ctl, int 
 
 static struct ctl_table cmm_table[] = {
 	{
-		.ctl_name	= VM_CMM_PAGES,
 		.procname	= "cmm_pages",
 		.mode		= 0644,
 		.proc_handler	= &cmm_pages_handler,
 	},
 	{
-		.ctl_name	= VM_CMM_TIMED_PAGES,
 		.procname	= "cmm_timed_pages",
 		.mode		= 0644,
 		.proc_handler	= &cmm_pages_handler,
 	},
 	{
-		.ctl_name	= VM_CMM_TIMEOUT,
 		.procname	= "cmm_timeout",
 		.mode		= 0644,
 		.proc_handler	= &cmm_timeout_handler,
diff -urpN linux-2.6/include/linux/sysctl.h linux-2.6-patched/include/linux/sysctl.h
--- linux-2.6/include/linux/sysctl.h	2007-11-16 14:27:34.000000000 +0100
+++ linux-2.6-patched/include/linux/sysctl.h	2007-11-16 14:27:41.000000000 +0100
@@ -207,11 +207,6 @@ enum
 	VM_PANIC_ON_OOM=33,	/* panic at out-of-memory */
 	VM_VDSO_ENABLED=34,	/* map VDSO into new processes? */
 	VM_MIN_SLAB=35,		 /* Percent pages ignored by zone reclaim */
-
-	/* s390 vm cmm sysctls */
-	VM_CMM_PAGES=1111,
-	VM_CMM_TIMED_PAGES=1112,
-	VM_CMM_TIMEOUT=1113,
 };
 
 
diff -urpN linux-2.6/kernel/sysctl_check.c linux-2.6-patched/kernel/sysctl_check.c
--- linux-2.6/kernel/sysctl_check.c	2007-11-16 14:27:35.000000000 +0100
+++ linux-2.6-patched/kernel/sysctl_check.c	2007-11-16 14:27:41.000000000 +0100
@@ -140,9 +140,6 @@ static struct trans_ctl_table trans_vm_t
 	{ VM_PANIC_ON_OOM,		"panic_on_oom" },
 	{ VM_VDSO_ENABLED,		"vdso_enabled" },
 	{ VM_MIN_SLAB,			"min_slab_ratio" },
-	{ VM_CMM_PAGES,			"cmm_pages" },
-	{ VM_CMM_TIMED_PAGES,		"cmm_timed_pages" },
-	{ VM_CMM_TIMEOUT,		"cmm_timeout" },
 
 	{}
 };

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 05/10] appldata: remove unused binary sysctls.

[Martin Schwidefsky]

[-- Attachment #1: 005-appldata.diff --]
[-- Type: text/plain, Size: 8946 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Remove binary sysctls that never worked due to missing strategy functions.

Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Gerald Schaefer <geraldsc@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/appldata/appldata.h         |    1 
 arch/s390/appldata/appldata_base.c    |   74 ++++++----------------------------
 arch/s390/appldata/appldata_mem.c     |    1 
 arch/s390/appldata/appldata_net_sum.c |    1 
 arch/s390/appldata/appldata_os.c      |    1 
 include/linux/sysctl.h                |    1 
 kernel/sysctl_check.c                 |   11 -----
 7 files changed, 15 insertions(+), 75 deletions(-)

diff -urpN linux-2.6/arch/s390/appldata/appldata_base.c linux-2.6-patched/arch/s390/appldata/appldata_base.c
--- linux-2.6/arch/s390/appldata/appldata_base.c	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/appldata/appldata_base.c	2007-11-16 14:27:42.000000000 +0100
@@ -53,29 +53,26 @@ static int appldata_interval_handler(ctl
 static struct ctl_table_header *appldata_sysctl_header;
 static struct ctl_table appldata_table[] = {
 	{
-		.ctl_name	= CTL_APPLDATA_TIMER,
 		.procname	= "timer",
 		.mode		= S_IRUGO | S_IWUSR,
 		.proc_handler	= &appldata_timer_handler,
 	},
 	{
-		.ctl_name	= CTL_APPLDATA_INTERVAL,
 		.procname	= "interval",
 		.mode		= S_IRUGO | S_IWUSR,
 		.proc_handler	= &appldata_interval_handler,
 	},
-	{ .ctl_name = 0 }
+	{ },
 };
 
 static struct ctl_table appldata_dir_table[] = {
 	{
-		.ctl_name	= CTL_APPLDATA,
 		.procname	= appldata_proc_name,
 		.maxlen		= 0,
 		.mode		= S_IRUGO | S_IXUGO,
 		.child		= appldata_table,
 	},
-	{ .ctl_name = 0 }
+	{ },
 };
 
 /*
@@ -441,75 +438,38 @@ out:
  */
 int appldata_register_ops(struct appldata_ops *ops)
 {
-	struct list_head *lh;
-	struct appldata_ops *tmp_ops;
-	int i;
-
-	i = 0;
+	if ((ops->size > APPLDATA_MAX_REC_SIZE) || (ops->size < 0))
+		return -EINVAL;
 
-	if ((ops->size > APPLDATA_MAX_REC_SIZE) ||
-		(ops->size < 0)){
-		P_ERROR("Invalid size of %s record = %i, maximum = %i!\n",
-			ops->name, ops->size, APPLDATA_MAX_REC_SIZE);
-		return -ENOMEM;
-	}
-	if ((ops->ctl_nr == CTL_APPLDATA) ||
-	    (ops->ctl_nr == CTL_APPLDATA_TIMER) ||
-	    (ops->ctl_nr == CTL_APPLDATA_INTERVAL)) {
-		P_ERROR("ctl_nr %i already in use!\n", ops->ctl_nr);
-		return -EBUSY;
-	}
-	ops->ctl_table = kzalloc(4*sizeof(struct ctl_table), GFP_KERNEL);
-	if (ops->ctl_table == NULL) {
-		P_ERROR("Not enough memory for %s ctl_table!\n", ops->name);
+	ops->ctl_table = kzalloc(4 * sizeof(struct ctl_table), GFP_KERNEL);
+	if (!ops->ctl_table)
 		return -ENOMEM;
-	}
 
 	spin_lock(&appldata_ops_lock);
-	list_for_each(lh, &appldata_ops_list) {
-		tmp_ops = list_entry(lh, struct appldata_ops, list);
-		P_DEBUG("register_ops loop: %i) name = %s, ctl = %i\n",
-			++i, tmp_ops->name, tmp_ops->ctl_nr);
-		P_DEBUG("Comparing %s (ctl %i) with %s (ctl %i)\n",
-			tmp_ops->name, tmp_ops->ctl_nr, ops->name,
-			ops->ctl_nr);
-		if (strncmp(tmp_ops->name, ops->name,
-				APPLDATA_PROC_NAME_LENGTH) == 0) {
-			P_ERROR("Name \"%s\" already registered!\n", ops->name);
-			kfree(ops->ctl_table);
-			spin_unlock(&appldata_ops_lock);
-			return -EBUSY;
-		}
-		if (tmp_ops->ctl_nr == ops->ctl_nr) {
-			P_ERROR("ctl_nr %i already registered!\n", ops->ctl_nr);
-			kfree(ops->ctl_table);
-			spin_unlock(&appldata_ops_lock);
-			return -EBUSY;
-		}
-	}
 	list_add(&ops->list, &appldata_ops_list);
 	spin_unlock(&appldata_ops_lock);
 
-	ops->ctl_table[0].ctl_name = CTL_APPLDATA;
 	ops->ctl_table[0].procname = appldata_proc_name;
 	ops->ctl_table[0].maxlen   = 0;
 	ops->ctl_table[0].mode     = S_IRUGO | S_IXUGO;
 	ops->ctl_table[0].child    = &ops->ctl_table[2];
 
-	ops->ctl_table[1].ctl_name = 0;
-
-	ops->ctl_table[2].ctl_name = ops->ctl_nr;
 	ops->ctl_table[2].procname = ops->name;
 	ops->ctl_table[2].mode     = S_IRUGO | S_IWUSR;
 	ops->ctl_table[2].proc_handler = appldata_generic_handler;
 	ops->ctl_table[2].data = ops;
 
-	ops->ctl_table[3].ctl_name = 0;
-
 	ops->sysctl_header = register_sysctl_table(ops->ctl_table);
-
+	if (!ops->sysctl_header)
+		goto out;
 	P_INFO("%s-ops registered!\n", ops->name);
 	return 0;
+out:
+	spin_lock(&appldata_ops_lock);
+	list_del(&ops->list);
+	spin_unlock(&appldata_ops_lock);
+	kfree(ops->ctl_table);
+	return -ENOMEM;
 }
 
 /*
@@ -519,15 +479,11 @@ int appldata_register_ops(struct appldat
  */
 void appldata_unregister_ops(struct appldata_ops *ops)
 {
-	void *table;
 	spin_lock(&appldata_ops_lock);
 	list_del(&ops->list);
-	/* at that point any incoming access will fail */
-	table = ops->ctl_table;
-	ops->ctl_table = NULL;
 	spin_unlock(&appldata_ops_lock);
 	unregister_sysctl_table(ops->sysctl_header);
-	kfree(table);
+	kfree(ops->ctl_table);
 	P_INFO("%s-ops unregistered!\n", ops->name);
 }
 /********************** module-ops management <END> **************************/
diff -urpN linux-2.6/arch/s390/appldata/appldata.h linux-2.6-patched/arch/s390/appldata/appldata.h
--- linux-2.6/arch/s390/appldata/appldata.h	2007-10-09 22:31:38.000000000 +0200
+++ linux-2.6-patched/arch/s390/appldata/appldata.h	2007-11-16 14:27:42.000000000 +0100
@@ -45,7 +45,6 @@ struct appldata_ops {
 	int    active;				/* monitoring status */
 
 	/* fill in from here */
-	unsigned int ctl_nr;			/* sysctl ID */
 	char name[APPLDATA_PROC_NAME_LENGTH];	/* name of /proc fs node */
 	unsigned char record_nr;		/* Record Nr. for Product ID */
 	void (*callback)(void *data);		/* callback function */
diff -urpN linux-2.6/arch/s390/appldata/appldata_mem.c linux-2.6-patched/arch/s390/appldata/appldata_mem.c
--- linux-2.6/arch/s390/appldata/appldata_mem.c	2007-10-09 22:31:38.000000000 +0200
+++ linux-2.6-patched/arch/s390/appldata/appldata_mem.c	2007-11-16 14:27:42.000000000 +0100
@@ -147,7 +147,6 @@ static void appldata_get_mem_data(void *
 
 
 static struct appldata_ops ops = {
-	.ctl_nr    = CTL_APPLDATA_MEM,
 	.name      = "mem",
 	.record_nr = APPLDATA_RECORD_MEM_ID,
 	.size	   = sizeof(struct appldata_mem_data),
diff -urpN linux-2.6/arch/s390/appldata/appldata_net_sum.c linux-2.6-patched/arch/s390/appldata/appldata_net_sum.c
--- linux-2.6/arch/s390/appldata/appldata_net_sum.c	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/appldata/appldata_net_sum.c	2007-11-16 14:27:42.000000000 +0100
@@ -142,7 +142,6 @@ static void appldata_get_net_sum_data(vo
 
 
 static struct appldata_ops ops = {
-	.ctl_nr    = CTL_APPLDATA_NET_SUM,
 	.name	   = "net_sum",
 	.record_nr = APPLDATA_RECORD_NET_SUM_ID,
 	.size	   = sizeof(struct appldata_net_sum_data),
diff -urpN linux-2.6/arch/s390/appldata/appldata_os.c linux-2.6-patched/arch/s390/appldata/appldata_os.c
--- linux-2.6/arch/s390/appldata/appldata_os.c	2007-10-09 22:31:38.000000000 +0200
+++ linux-2.6-patched/arch/s390/appldata/appldata_os.c	2007-11-16 14:27:42.000000000 +0100
@@ -82,7 +82,6 @@ struct appldata_os_data {
 static struct appldata_os_data *appldata_os_data;
 
 static struct appldata_ops ops = {
-	.ctl_nr    = CTL_APPLDATA_OS,
 	.name	   = "os",
 	.record_nr = APPLDATA_RECORD_OS_ID,
 	.owner	   = THIS_MODULE,
diff -urpN linux-2.6/include/linux/sysctl.h linux-2.6-patched/include/linux/sysctl.h
--- linux-2.6/include/linux/sysctl.h	2007-11-16 14:27:42.000000000 +0100
+++ linux-2.6-patched/include/linux/sysctl.h	2007-11-16 14:27:42.000000000 +0100
@@ -70,7 +70,6 @@ enum
 	CTL_ABI=9,		/* Binary emulation */
 	CTL_CPU=10,		/* CPU stuff (speed scaling, etc) */
 	CTL_ARLAN=254,		/* arlan wireless driver */
-	CTL_APPLDATA=2120,	/* s390 appldata */
 	CTL_S390DBF=5677,	/* s390 debug */
 	CTL_SUNRPC=7249,	/* sunrpc debug */
 	CTL_PM=9899,		/* frv power management */
diff -urpN linux-2.6/kernel/sysctl_check.c linux-2.6-patched/kernel/sysctl_check.c
--- linux-2.6/kernel/sysctl_check.c	2007-11-16 14:27:42.000000000 +0100
+++ linux-2.6-patched/kernel/sysctl_check.c	2007-11-16 14:27:42.000000000 +0100
@@ -1216,16 +1216,6 @@ static struct trans_ctl_table trans_arla
 	{}
 };
 
-static struct trans_ctl_table trans_appldata_table[] = {
-	{ CTL_APPLDATA_TIMER,		"timer" },
-	{ CTL_APPLDATA_INTERVAL,	"interval" },
-	{ CTL_APPLDATA_OS,		"os" },
-	{ CTL_APPLDATA_NET_SUM,		"net_sum" },
-	{ CTL_APPLDATA_MEM,		"mem" },
-	{}
-
-};
-
 static struct trans_ctl_table trans_s390dbf_table[] = {
 	{ 5678 /* CTL_S390DBF_STOPPABLE */,	"debug_stoppable" },
 	{ 5679 /* CTL_S390DBF_ACTIVE */,	"debug_active" },
@@ -1270,7 +1260,6 @@ static struct trans_ctl_table trans_root
 	{ CTL_ABI,	"abi" },
 	/* CTL_CPU not used */
 	{ CTL_ARLAN,	"arlan",	trans_arlan_table },
-	{ CTL_APPLDATA,	"appldata",	trans_appldata_table },
 	{ CTL_S390DBF,	"s390dbf",	trans_s390dbf_table },
 	{ CTL_SUNRPC,	"sunrpc",	trans_sunrpc_table },
 	{ CTL_PM,	"pm",		trans_pm_table },

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 06/10] Fix kernel preemption.

[Martin Schwidefsky]

[-- Attachment #1: 006-preemption.diff --]
[-- Type: text/plain, Size: 2901 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

When returning from IRQ handling and TIF_NEED_RESCHED is set we must
call preempt_schedule_irq() instead of schedule().
Otherwise the BKL might be unlocked in schedule() and therfore
everything that relies on the BKL is broken.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/kernel/entry.S   |   15 +++++----------
 arch/s390/kernel/entry64.S |   12 ++----------
 2 files changed, 7 insertions(+), 20 deletions(-)

diff -urpN linux-2.6/arch/s390/kernel/entry64.S linux-2.6-patched/arch/s390/kernel/entry64.S
--- linux-2.6/arch/s390/kernel/entry64.S	2007-11-16 14:27:41.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/entry64.S	2007-11-16 14:27:42.000000000 +0100
@@ -623,15 +623,8 @@ io_preempt:
 io_resume_loop:
 	tm	__TI_flags+7(%r9),_TIF_NEED_RESCHED
 	jno	io_restore
-	larl	%r1,.Lc_pactive
-	mvc	__TI_precount(4,%r9),0(%r1)
-	TRACE_IRQS_ON
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	brasl	%r14,schedule		# call schedule
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
-	TRACE_IRQS_OFF
-	xc	__TI_precount(4,%r9),__TI_precount(%r9)
-	j	io_resume_loop
+	larl	%r14,io_resume_loop
+	jg	preempt_schedule_irq
 #endif
 
 #
@@ -1029,7 +1022,6 @@ cleanup_io_leave_insn:
  */
 		.align	4
 .Lconst:
-.Lc_pactive:	.long	PREEMPT_ACTIVE
 .Lnr_syscalls:	.long	NR_syscalls
 .L0x0130:	.short	0x130
 .L0x0140:	.short	0x140
diff -urpN linux-2.6/arch/s390/kernel/entry.S linux-2.6-patched/arch/s390/kernel/entry.S
--- linux-2.6/arch/s390/kernel/entry.S	2007-11-16 14:27:41.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/entry.S	2007-11-16 14:27:42.000000000 +0100
@@ -640,15 +640,9 @@ io_preempt:
 io_resume_loop:
 	tm	__TI_flags+3(%r9),_TIF_NEED_RESCHED
 	bno	BASED(io_restore)
-	mvc	__TI_precount(4,%r9),BASED(.Lc_pactive)
-	TRACE_IRQS_ON
-	stosm	__SF_EMPTY(%r15),0x03  # reenable interrupts
-	l	%r1,BASED(.Lschedule)
-	basr	%r14,%r1	       # call schedule
-	stnsm	__SF_EMPTY(%r15),0xfc  # disable I/O and ext. interrupts
-	TRACE_IRQS_OFF
-	xc	__TI_precount(4,%r9),__TI_precount(%r9)
-	b	BASED(io_resume_loop)
+	l	%r1,BASED(.Lpreempt_schedule_irq)
+	la	%r14,BASED(io_resume_loop)
+	br	%r1			# call schedule
 #endif
 
 #
@@ -1062,7 +1056,6 @@ cleanup_io_leave_insn:
 		.align	4
 .Lc_spsize:	.long	SP_SIZE
 .Lc_overhead:	.long	STACK_FRAME_OVERHEAD
-.Lc_pactive:	.long	PREEMPT_ACTIVE
 .Lnr_syscalls:	.long	NR_syscalls
 .L0x018:	.short	0x018
 .L0x020:	.short	0x020
@@ -1086,6 +1079,8 @@ cleanup_io_leave_insn:
 .Lexecve_tail:	.long	execve_tail
 .Ljump_table:	.long	pgm_check_table
 .Lschedule:	.long	schedule
+.Lpreempt_schedule_irq:
+		.long	preempt_schedule_irq
 .Ltrace:	.long	syscall_trace
 .Lschedtail:	.long	schedule_tail
 .Lsysc_table:	.long	sys_call_table

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 07/10] Optimize storage key handling for anonymous pages

[Martin Schwidefsky]

[-- Attachment #1: 007-dirty-bit.diff --]
[-- Type: text/plain, Size: 1601 bytes --]

From: Christian Borntraeger <borntraeger@de.ibm.com>

page_mkclean used to call page_clear_dirty for every given page. This
is different to all other architectures, where the dirty bit in the
PTEs is only resetted, if page_mapping() returns a non-NULL pointer.
We can move the page_test_dirty/page_clear_dirty sequence into the 
2nd if to avoid unnecessary iske/sske sequences, which are expensive.

This change also helps kvm for s390 as the host must transfer the 
dirty bit into the guest status bits. By moving the page_clear_dirty
operation into the 2nd if, the vm will only call page_clear_dirty
for pages where it walks the mapping anyway. There it calls
ptep_clear_flush for writable ptes, so we can transfer the dirty bit
to the guest. 

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 mm/rmap.c |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff -urpN linux-2.6/mm/rmap.c linux-2.6-patched/mm/rmap.c
--- linux-2.6/mm/rmap.c	2007-11-16 14:27:35.000000000 +0100
+++ linux-2.6-patched/mm/rmap.c	2007-11-16 14:27:43.000000000 +0100
@@ -471,11 +471,12 @@ int page_mkclean(struct page *page)
 
 	if (page_mapped(page)) {
 		struct address_space *mapping = page_mapping(page);
-		if (mapping)
+		if (mapping) {
 			ret = page_mkclean_file(mapping, page);
-		if (page_test_dirty(page)) {
-			page_clear_dirty(page);
-			ret = 1;
+			if (page_test_dirty(page)) {
+				page_clear_dirty(page);
+				ret = 1;
+			}
 		}
 	}
 

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 08/10] Dont overwrite lowcores on smp_send_stop().

[Martin Schwidefsky]

[-- Attachment #1: 008-lowcores.diff --]
[-- Type: text/plain, Size: 2706 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Don't perform a sigp store-status-at-address on smp_send_stop().
It will overwrite the lowcores of other cpus and destroys valueable
debug informations.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/kernel/smp.c |   56 ++++++-------------------------------------------
 1 file changed, 7 insertions(+), 49 deletions(-)

diff -urpN linux-2.6/arch/s390/kernel/smp.c linux-2.6-patched/arch/s390/kernel/smp.c
--- linux-2.6/arch/s390/kernel/smp.c	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/smp.c	2007-11-16 14:27:44.000000000 +0100
@@ -193,72 +193,30 @@ int smp_call_function_single(int cpu, vo
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-static void do_send_stop(void)
+void smp_send_stop(void)
 {
 	int cpu, rc;
 
-	/* stop all processors */
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		do {
-			rc = signal_processor(cpu, sigp_stop);
-		} while (rc == sigp_busy);
-	}
-}
+	/* Disable all interrupts/machine checks */
+	__load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK);
 
-static void do_store_status(void)
-{
-	int cpu, rc;
+	/* write magic number to zero page (absolute 0) */
+	lowcore_ptr[smp_processor_id()]->panic_magic = __PANIC_MAGIC;
 
-	/* store status of all processors in their lowcores (real 0) */
+	/* stop all processors */
 	for_each_online_cpu(cpu) {
 		if (cpu == smp_processor_id())
 			continue;
 		do {
-			rc = signal_processor_p(
-				(__u32)(unsigned long) lowcore_ptr[cpu], cpu,
-				sigp_store_status_at_address);
+			rc = signal_processor(cpu, sigp_stop);
 		} while (rc == sigp_busy);
-	}
-}
 
-static void do_wait_for_stop(void)
-{
-	int cpu;
-
-	/* Wait for all other cpus to enter stopped state */
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
 		while (!smp_cpu_not_running(cpu))
 			cpu_relax();
 	}
 }
 
 /*
- * this function sends a 'stop' sigp to all other CPUs in the system.
- * it goes straight through.
- */
-void smp_send_stop(void)
-{
-	/* Disable all interrupts/machine checks */
-	__load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK);
-
-	/* write magic number to zero page (absolute 0) */
-	lowcore_ptr[smp_processor_id()]->panic_magic = __PANIC_MAGIC;
-
-	/* stop other processors. */
-	do_send_stop();
-
-	/* wait until other processors are stopped */
-	do_wait_for_stop();
-
-	/* store status of other processors. */
-	do_store_status();
-}
-
-/*
  * Reboot, halt and power_off routines for SMP.
  */
 void machine_restart_smp(char *__unused)

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 09/10] Explicitly code allocpercpu calls in iucv

[Martin Schwidefsky]

[-- Attachment #1: 009-iucv.diff --]
[-- Type: text/plain, Size: 10184 bytes --]

From: Christoph Lameter <clameter@sgi.com>

The iucv is the only user of the various functions that are used to bring
parts of cpus up and down. Its the only allocpercpu user that will do
I/O on per cpu objects (which is difficult to do with virtually mapped memory).
And its the only use of allocpercpu where a GFP_DMA allocation is done.

Remove the allocpercpu calls from iucv and code the allocation and freeing
manually. After this patch it is possible to remove a large part of
the allocpercpu API.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 net/iucv/iucv.c |  107 +++++++++++++++++++++++++++++++-------------------------
 1 file changed, 61 insertions(+), 46 deletions(-)

diff -urpN linux-2.6/net/iucv/iucv.c linux-2.6-patched/net/iucv/iucv.c
--- linux-2.6/net/iucv/iucv.c	2007-11-16 14:27:35.000000000 +0100
+++ linux-2.6-patched/net/iucv/iucv.c	2007-11-16 14:27:44.000000000 +0100
@@ -97,7 +97,7 @@ struct iucv_irq_list {
 	struct iucv_irq_data data;
 };
 
-static struct iucv_irq_data *iucv_irq_data;
+static struct iucv_irq_data *iucv_irq_data[NR_CPUS];
 static cpumask_t iucv_buffer_cpumask = CPU_MASK_NONE;
 static cpumask_t iucv_irq_cpumask = CPU_MASK_NONE;
 
@@ -277,7 +277,7 @@ union iucv_param {
 /*
  * Anchor for per-cpu IUCV command parameter block.
  */
-static union iucv_param *iucv_param;
+static union iucv_param *iucv_param[NR_CPUS];
 
 /**
  * iucv_call_b2f0
@@ -356,7 +356,7 @@ static void iucv_allow_cpu(void *data)
 	 *	0x10 - Flag to allow priority message completion interrupts
 	 *	0x08 - Flag to allow IUCV control interrupts
 	 */
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[cpu];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->set_mask.ipmask = 0xf8;
 	iucv_call_b2f0(IUCV_SETMASK, parm);
@@ -377,7 +377,7 @@ static void iucv_block_cpu(void *data)
 	union iucv_param *parm;
 
 	/* Disable all iucv interrupts. */
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[cpu];
 	memset(parm, 0, sizeof(union iucv_param));
 	iucv_call_b2f0(IUCV_SETMASK, parm);
 
@@ -401,9 +401,9 @@ static void iucv_declare_cpu(void *data)
 		return;
 
 	/* Declare interrupt buffer. */
-	parm = percpu_ptr(iucv_param, cpu);
+	parm = iucv_param[cpu];
 	memset(parm, 0, sizeof(union iucv_param));
-	parm->db.ipbfadr1 = virt_to_phys(percpu_ptr(iucv_irq_data, cpu));
+	parm->db.ipbfadr1 = virt_to_phys(iucv_irq_data[cpu]);
 	rc = iucv_call_b2f0(IUCV_DECLARE_BUFFER, parm);
 	if (rc) {
 		char *err = "Unknown";
@@ -458,7 +458,7 @@ static void iucv_retrieve_cpu(void *data
 	iucv_block_cpu(NULL);
 
 	/* Retrieve interrupt buffer. */
-	parm = percpu_ptr(iucv_param, cpu);
+	parm = iucv_param[cpu];
 	iucv_call_b2f0(IUCV_RETRIEVE_BUFFER, parm);
 
 	/* Clear indication that an iucv buffer exists for this cpu. */
@@ -558,22 +558,23 @@ static int __cpuinit iucv_cpu_notify(str
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (!percpu_populate(iucv_irq_data,
-				     sizeof(struct iucv_irq_data),
-				     GFP_KERNEL|GFP_DMA, cpu))
+		iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data),
+					GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+		if (!iucv_irq_data[cpu])
 			return NOTIFY_BAD;
-		if (!percpu_populate(iucv_param, sizeof(union iucv_param),
-				     GFP_KERNEL|GFP_DMA, cpu)) {
-			percpu_depopulate(iucv_irq_data, cpu);
+		iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param),
+				     GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+		if (!iucv_param[cpu])
 			return NOTIFY_BAD;
-		}
 		break;
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		percpu_depopulate(iucv_param, cpu);
-		percpu_depopulate(iucv_irq_data, cpu);
+		kfree(iucv_param[cpu]);
+		iucv_param[cpu] = NULL;
+		kfree(iucv_irq_data[cpu]);
+		iucv_irq_data[cpu] = NULL;
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
@@ -612,7 +613,7 @@ static int iucv_sever_pathid(u16 pathid,
 {
 	union iucv_param *parm;
 
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (userdata)
 		memcpy(parm->ctrl.ipuser, userdata, sizeof(parm->ctrl.ipuser));
@@ -755,7 +756,7 @@ int iucv_path_accept(struct iucv_path *p
 
 	local_bh_disable();
 	/* Prepare parameter block. */
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->ctrl.ippathid = path->pathid;
 	parm->ctrl.ipmsglim = path->msglim;
@@ -799,7 +800,7 @@ int iucv_path_connect(struct iucv_path *
 	BUG_ON(in_atomic());
 	spin_lock_bh(&iucv_table_lock);
 	iucv_cleanup_queue();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->ctrl.ipmsglim = path->msglim;
 	parm->ctrl.ipflags1 = path->flags;
@@ -854,7 +855,7 @@ int iucv_path_quiesce(struct iucv_path *
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (userdata)
 		memcpy(parm->ctrl.ipuser, userdata, sizeof(parm->ctrl.ipuser));
@@ -881,7 +882,7 @@ int iucv_path_resume(struct iucv_path *p
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (userdata)
 		memcpy(parm->ctrl.ipuser, userdata, sizeof(parm->ctrl.ipuser));
@@ -936,7 +937,7 @@ int iucv_message_purge(struct iucv_path 
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->purge.ippathid = path->pathid;
 	parm->purge.ipmsgid = msg->id;
@@ -1003,7 +1004,7 @@ int iucv_message_receive(struct iucv_pat
 	}
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->db.ipbfadr1 = (u32)(addr_t) buffer;
 	parm->db.ipbfln1f = (u32) size;
@@ -1040,7 +1041,7 @@ int iucv_message_reject(struct iucv_path
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->db.ippathid = path->pathid;
 	parm->db.ipmsgid = msg->id;
@@ -1074,7 +1075,7 @@ int iucv_message_reply(struct iucv_path 
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (flags & IUCV_IPRMDATA) {
 		parm->dpl.ippathid = path->pathid;
@@ -1118,7 +1119,7 @@ int iucv_message_send(struct iucv_path *
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (flags & IUCV_IPRMDATA) {
 		/* Message of 8 bytes can be placed into the parameter list. */
@@ -1172,7 +1173,7 @@ int iucv_message_send2way(struct iucv_pa
 	int rc;
 
 	local_bh_disable();
-	parm = percpu_ptr(iucv_param, smp_processor_id());
+	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (flags & IUCV_IPRMDATA) {
 		parm->dpl.ippathid = path->pathid;
@@ -1559,7 +1560,7 @@ static void iucv_external_interrupt(u16 
 	struct iucv_irq_data *p;
 	struct iucv_irq_list *work;
 
-	p = percpu_ptr(iucv_irq_data, smp_processor_id());
+	p = iucv_irq_data[smp_processor_id()];
 	if (p->ippathid >= iucv_max_pathid) {
 		printk(KERN_WARNING "iucv_do_int: Got interrupt with "
 		       "pathid %d > max_connections (%ld)\n",
@@ -1598,6 +1599,7 @@ static void iucv_external_interrupt(u16 
 static int __init iucv_init(void)
 {
 	int rc;
+	int cpu;
 
 	if (!MACHINE_IS_VM) {
 		rc = -EPROTONOSUPPORT;
@@ -1617,19 +1619,23 @@ static int __init iucv_init(void)
 		rc = PTR_ERR(iucv_root);
 		goto out_bus;
 	}
-	/* Note: GFP_DMA used to get memory below 2G */
-	iucv_irq_data = percpu_alloc(sizeof(struct iucv_irq_data),
-				     GFP_KERNEL|GFP_DMA);
-	if (!iucv_irq_data) {
-		rc = -ENOMEM;
-		goto out_root;
-	}
-	/* Allocate parameter blocks. */
-	iucv_param = percpu_alloc(sizeof(union iucv_param),
-				  GFP_KERNEL|GFP_DMA);
-	if (!iucv_param) {
-		rc = -ENOMEM;
-		goto out_extint;
+
+	for_each_online_cpu(cpu) {
+		/* Note: GFP_DMA used to get memory below 2G */
+		iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data),
+				     GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+		if (!iucv_irq_data[cpu]) {
+			rc = -ENOMEM;
+			goto out_free;
+		}
+
+		/* Allocate parameter blocks. */
+		iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param),
+				  GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+		if (!iucv_param[cpu]) {
+			rc = -ENOMEM;
+			goto out_free;
+		}
 	}
 	register_hotcpu_notifier(&iucv_cpu_notifier);
 	ASCEBC(iucv_error_no_listener, 16);
@@ -1638,9 +1644,13 @@ static int __init iucv_init(void)
 	iucv_available = 1;
 	return 0;
 
-out_extint:
-	percpu_free(iucv_irq_data);
-out_root:
+out_free:
+	for_each_possible_cpu(cpu) {
+		kfree(iucv_param[cpu]);
+		iucv_param[cpu] = NULL;
+		kfree(iucv_irq_data[cpu]);
+		iucv_irq_data[cpu] = NULL;
+	}
 	s390_root_dev_unregister(iucv_root);
 out_bus:
 	bus_unregister(&iucv_bus);
@@ -1658,6 +1668,7 @@ out:
 static void __exit iucv_exit(void)
 {
 	struct iucv_irq_list *p, *n;
+	int cpu;
 
 	spin_lock_irq(&iucv_queue_lock);
 	list_for_each_entry_safe(p, n, &iucv_task_queue, list)
@@ -1666,8 +1677,12 @@ static void __exit iucv_exit(void)
 		kfree(p);
 	spin_unlock_irq(&iucv_queue_lock);
 	unregister_hotcpu_notifier(&iucv_cpu_notifier);
-	percpu_free(iucv_param);
-	percpu_free(iucv_irq_data);
+	for_each_possible_cpu(cpu) {
+		kfree(iucv_param[cpu]);
+		iucv_param[cpu] = NULL;
+		kfree(iucv_irq_data[cpu]);
+		iucv_irq_data[cpu] = NULL;
+	}
 	s390_root_dev_unregister(iucv_root);
 	bus_unregister(&iucv_bus);
 	unregister_external_interrupt(0x4000, iucv_external_interrupt);

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.

[patch 10/10] Fix memory detection.

[Martin Schwidefsky]

[-- Attachment #1: 010-memsize.diff --]
[-- Type: text/plain, Size: 1105 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Before we're getting short on memory detection fixes here is the next
one: if neither sclp nor diag260 report the storage size the detection
loop will return immediately without detecting anything. Fix this by
breaking the detection loop only if the memory end is known.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---

 arch/s390/kernel/early.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff -urpN linux-2.6/arch/s390/kernel/early.c linux-2.6-patched/arch/s390/kernel/early.c
--- linux-2.6/arch/s390/kernel/early.c	2007-11-16 14:27:30.000000000 +0100
+++ linux-2.6-patched/arch/s390/kernel/early.c	2007-11-16 14:27:45.000000000 +0100
@@ -200,7 +200,7 @@ static noinline __init void find_memory_
 		cc = __tprot(addr);
 		while (cc == old_cc) {
 			addr += CHUNK_INCR;
-			if (addr >= memsize)
+			if (memsize && addr >= memsize)
 				break;
 #ifndef CONFIG_64BIT
 			if (addr == ADDR2G)

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.