Merge with rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git

Documentation/DocBook/libata.tmpl

@@ -14,7 +14,7 @@
   </authorgroup>
 
   <copyright>
-   <year>2003</year>
+   <year>2003-2005</year>
    <holder>Jeff Garzik</holder>
   </copyright>
 
@@ -44,30 +44,38 @@
 
 <toc></toc>
 
-  <chapter id="libataThanks">
-     <title>Thanks</title>
+  <chapter id="libataIntroduction">
+     <title>Introduction</title>
   <para>
-  The bulk of the ATA knowledge comes thanks to long conversations with
-  Andre Hedrick (www.linux-ide.org).
+  libATA is a library used inside the Linux kernel to support ATA host
+  controllers and devices.  libATA provides an ATA driver API, class
+  transports for ATA and ATAPI devices, and SCSI&lt;-&gt;ATA translation
+  for ATA devices according to the T10 SAT specification.
   </para>
   <para>
-  Thanks to Alan Cox for pointing out similarities 
-  between SATA and SCSI, and in general for motivation to hack on
-  libata.
-  </para>
-  <para>
-  libata's device detection
-  method, ata_pio_devchk, and in general all the early probing was
-  based on extensive study of Hale Landis's probe/reset code in his
-  ATADRVR driver (www.ata-atapi.com).
+  This Guide documents the libATA driver API, library functions, library
+  internals, and a couple sample ATA low-level drivers.
   </para>
   </chapter>
 
   <chapter id="libataDriverApi">
      <title>libata Driver API</title>
+     <para>
+     struct ata_port_operations is defined for every low-level libata
+     hardware driver, and it controls how the low-level driver
+     interfaces with the ATA and SCSI layers.
+     </para>
+     <para>
+     FIS-based drivers will hook into the system with ->qc_prep() and
+     ->qc_issue() high-level hooks.  Hardware which behaves in a manner
+     similar to PCI IDE hardware may utilize several generic helpers,
+     defining at a bare minimum the bus I/O addresses of the ATA shadow
+     register blocks.
+     </para>
      <sect1>
         <title>struct ata_port_operations</title>
 
+	<sect2><title>Disable ATA port</title>
 	<programlisting>
 void (*port_disable) (struct ata_port *);
 	</programlisting>
@@ -78,6 +86,9 @@ void (*port_disable) (struct ata_port *);
 	unplug).
 	</para>
 
+	</sect2>
+
+	<sect2><title>Post-IDENTIFY device configuration</title>
 	<programlisting>
 void (*dev_config) (struct ata_port *, struct ata_device *);
 	</programlisting>
@@ -88,6 +99,9 @@ void (*dev_config) (struct ata_port *, struct ata_device *);
 	issue of SET FEATURES - XFER MODE, and prior to operation.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Set PIO/DMA mode</title>
 	<programlisting>
 void (*set_piomode) (struct ata_port *, struct ata_device *);
 void (*set_dmamode) (struct ata_port *, struct ata_device *);
@@ -108,6 +122,9 @@ void (*post_set_mode) (struct ata_port *ap);
 	->set_dma_mode() is only called if DMA is possible.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Taskfile read/write</title>
 	<programlisting>
 void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
 void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
@@ -120,6 +137,9 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
 	taskfile register values.
 	</para>
 
+	</sect2>
+
+	<sect2><title>ATA command execute</title>
 	<programlisting>
 void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
 	</programlisting>
@@ -129,17 +149,37 @@ void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
 	->tf_load(), to be initiated in hardware.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Per-cmd ATAPI DMA capabilities filter</title>
+	<programlisting>
+int (*check_atapi_dma) (struct ata_queued_cmd *qc);
+	</programlisting>
+
+	<para>
+Allow low-level driver to filter ATA PACKET commands, returning a status
+indicating whether or not it is OK to use DMA for the supplied PACKET
+command.
+	</para>
+
+	</sect2>
+
+	<sect2><title>Read specific ATA shadow registers</title>
 	<programlisting>
 u8   (*check_status)(struct ata_port *ap);
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*check_err)(struct ata_port *ap);
 	</programlisting>
 
 	<para>
-	Reads the Status ATA shadow register from hardware.  On some
-	hardware, this has the side effect of clearing the interrupt
-	condition.
+	Reads the Status/AltStatus/Error ATA shadow register from
+	hardware.  On some hardware, reading the Status register has
+	the side effect of clearing the interrupt condition.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Select ATA device on bus</title>
 	<programlisting>
 void (*dev_select)(struct ata_port *ap, unsigned int device);
 	</programlisting>
@@ -147,9 +187,13 @@ void (*dev_select)(struct ata_port *ap, unsigned int device);
 	<para>
 	Issues the low-level hardware command(s) that causes one of N
 	hardware devices to be considered 'selected' (active and
-	available for use) on the ATA bus.
+	available for use) on the ATA bus.  This generally has no
+meaning on FIS-based devices.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Reset ATA bus</title>
 	<programlisting>
 void (*phy_reset) (struct ata_port *ap);
 	</programlisting>
@@ -162,17 +206,31 @@ void (*phy_reset) (struct ata_port *ap);
 	functions ata_bus_reset() or sata_phy_reset() for this hook.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Control PCI IDE BMDMA engine</title>
 	<programlisting>
 void (*bmdma_setup) (struct ata_queued_cmd *qc);
 void (*bmdma_start) (struct ata_queued_cmd *qc);
+void (*bmdma_stop) (struct ata_port *ap);
+u8   (*bmdma_status) (struct ata_port *ap);
 	</programlisting>
 
 	<para>
-	When setting up an IDE BMDMA transaction, these hooks arm
-	(->bmdma_setup) and fire (->bmdma_start) the hardware's DMA
-	engine.
+When setting up an IDE BMDMA transaction, these hooks arm
+(->bmdma_setup), fire (->bmdma_start), and halt (->bmdma_stop)
+the hardware's DMA engine.  ->bmdma_status is used to read the standard
+PCI IDE DMA Status register.
 	</para>
 
+	<para>
+These hooks are typically either no-ops, or simply not implemented, in
+FIS-based drivers.
+	</para>
+
+	</sect2>
+
+	<sect2><title>High-level taskfile hooks</title>
 	<programlisting>
 void (*qc_prep) (struct ata_queued_cmd *qc);
 int (*qc_issue) (struct ata_queued_cmd *qc);
@@ -190,20 +248,26 @@ int (*qc_issue) (struct ata_queued_cmd *qc);
 	->qc_issue is used to make a command active, once the hardware
 	and S/G tables have been prepared.  IDE BMDMA drivers use the
 	helper function ata_qc_issue_prot() for taskfile protocol-based
-	dispatch.  More advanced drivers roll their own ->qc_issue
-	implementation, using this as the "issue new ATA command to
-	hardware" hook.
+	dispatch.  More advanced drivers implement their own ->qc_issue.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Timeout (error) handling</title>
 	<programlisting>
 void (*eng_timeout) (struct ata_port *ap);
 	</programlisting>
 
 	<para>
-	This is a high level error handling function, called from the
-	error handling thread, when a command times out.
+This is a high level error handling function, called from the
+error handling thread, when a command times out.  Most newer
+hardware will implement its own error handling code here.  IDE BMDMA
+drivers may use the helper function ata_eng_timeout().
 	</para>
 
+	</sect2>
+
+	<sect2><title>Hardware interrupt handling</title>
 	<programlisting>
 irqreturn_t (*irq_handler)(int, void *, struct pt_regs *);
 void (*irq_clear) (struct ata_port *);
@@ -216,6 +280,9 @@ void (*irq_clear) (struct ata_port *);
 	is quiet.
 	</para>
 
+	</sect2>
+
+	<sect2><title>SATA phy read/write</title>
 	<programlisting>
 u32 (*scr_read) (struct ata_port *ap, unsigned int sc_reg);
 void (*scr_write) (struct ata_port *ap, unsigned int sc_reg,
@@ -227,6 +294,9 @@ void (*scr_write) (struct ata_port *ap, unsigned int sc_reg,
 	if ->phy_reset hook called the sata_phy_reset() helper function.
 	</para>
 
+	</sect2>
+
+	<sect2><title>Init and shutdown</title>
 	<programlisting>
 int (*port_start) (struct ata_port *ap);
 void (*port_stop) (struct ata_port *ap);
@@ -240,15 +310,17 @@ void (*host_stop) (struct ata_host_set *host_set);
 	tasks.  
 	</para>
 	<para>
-	->host_stop() is called when the rmmod or hot unplug process
-	begins.  The hook must stop all hardware interrupts, DMA
-	engines, etc.
-	</para>
-	<para>
 	->port_stop() is called after ->host_stop().  It's sole function
 	is to release DMA/memory resources, now that they are no longer
 	actively being used.
 	</para>
+	<para>
+	->host_stop() is called after all ->port_stop() calls
+have completed.  The hook must finalize hardware shutdown, release DMA
+and other resources, etc.
+	</para>
+
+	</sect2>
 
      </sect1>
   </chapter>
@@ -279,4 +351,24 @@ void (*host_stop) (struct ata_host_set *host_set);
 !Idrivers/scsi/sata_sil.c
   </chapter>
 
+  <chapter id="libataThanks">
+     <title>Thanks</title>
+  <para>
+  The bulk of the ATA knowledge comes thanks to long conversations with
+  Andre Hedrick (www.linux-ide.org), and long hours pondering the ATA
+  and SCSI specifications.
+  </para>
+  <para>
+  Thanks to Alan Cox for pointing out similarities 
+  between SATA and SCSI, and in general for motivation to hack on
+  libata.
+  </para>
+  <para>
+  libata's device detection
+  method, ata_pio_devchk, and in general all the early probing was
+  based on extensive study of Hale Landis's probe/reset code in his
+  ATADRVR driver (www.ata-atapi.com).
+  </para>
+  </chapter>
+
 </book>

Makefile

 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 12
-EXTRAVERSION =-rc5
+EXTRAVERSION =-rc6
 NAME=Woozy Numbat
 
 # *DOCUMENTATION*

arch/m68knommu/kernel/process.c

@@ -45,11 +45,13 @@ asmlinkage void ret_from_fork(void);
  */
 void default_idle(void)
 {
-	while(1) {
-		if (need_resched())
-			__asm__("stop #0x2000" : : : "cc");
-		schedule();
+	local_irq_disable();
+ 	while (!need_resched()) {
+		/* This stop will re-enable interrupts */
+ 		__asm__("stop #0x2000" : : : "cc");
+		local_irq_disable();
 	}
+	local_irq_enable();
 }
 
 void (*idle)(void) = default_idle;
@@ -63,7 +65,12 @@ void (*idle)(void) = default_idle;
 void cpu_idle(void)
 {
 	/* endless idle loop with no priority at all */
-	idle();
+	while (1) {
+		idle();
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
+	}
 }
 
 void machine_restart(char * __unused)

arch/ppc64/kernel/entry.S

@@ -436,15 +436,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	REST_8GPRS(14, r1)
 	REST_10GPRS(22, r1)
 
-#ifdef CONFIG_PPC_ISERIES
-	clrrdi	r7,r1,THREAD_SHIFT	/* get current_thread_info() */
-	ld	r7,TI_FLAGS(r7)		/* Get run light flag */
-	mfspr	r9,CTRLF
-	srdi	r7,r7,TIF_RUN_LIGHT
-	insrdi	r9,r7,1,63		/* Insert run light into CTRL */
-	mtspr	CTRLT,r9
-#endif
-
 	/* convert old thread to its task_struct for return value */
 	addi	r3,r3,-THREAD
 	ld	r7,_NIP(r1)	/* Return to _switch caller in new task */

arch/ppc64/kernel/head.S

@@ -626,10 +626,10 @@ system_reset_iSeries:
 	lhz	r24,PACAPACAINDEX(r13)	/* Get processor # */
 	cmpwi	0,r24,0			/* Are we processor 0? */
 	beq	.__start_initialization_iSeries	/* Start up the first processor */
-	mfspr	r4,CTRLF
-	li	r5,RUNLATCH		/* Turn off the run light */
+	mfspr	r4,SPRN_CTRLF
+	li	r5,CTRL_RUNLATCH	/* Turn off the run light */
 	andc	r4,r4,r5
-	mtspr	CTRLT,r4
+	mtspr	SPRN_CTRLT,r4
 
 1:
 	HMT_LOW
@@ -2082,9 +2082,9 @@ _GLOBAL(hmt_start_secondary)
 	mfspr	r4, HID0
 	ori	r4, r4, 0x1
 	mtspr	HID0, r4
-	mfspr	r4, CTRLF
+	mfspr	r4, SPRN_CTRLF
 	oris	r4, r4, 0x40
-	mtspr	CTRLT, r4
+	mtspr	SPRN_CTRLT, r4
 	blr
 #endif
 

arch/ppc64/kernel/iSeries_setup.c

@@ -852,6 +852,28 @@ static int __init iSeries_src_init(void)
 
 late_initcall(iSeries_src_init);
 
+static int set_spread_lpevents(char *str)
+{
+	unsigned long i;
+	unsigned long val = simple_strtoul(str, NULL, 0);
+
+	/*
+	 * The parameter is the number of processors to share in processing
+	 * lp events.
+	 */
+	if (( val > 0) && (val <= NR_CPUS)) {
+		for (i = 1; i < val; ++i)
+			paca[i].lpqueue_ptr = paca[0].lpqueue_ptr;
+
+		printk("lpevent processing spread over %ld processors\n", val);
+	} else {
+		printk("invalid spread_lpevents %ld\n", val);
+	}
+
+	return 1;
+}
+__setup("spread_lpevents=", set_spread_lpevents);
+
 void __init iSeries_early_setup(void)
 {
 	iSeries_fixup_klimit();

arch/ppc64/kernel/idle.c

@@ -75,13 +75,9 @@ static int iSeries_idle(void)
 {
 	struct paca_struct *lpaca;
 	long oldval;
-	unsigned long CTRL;
 
 	/* ensure iSeries run light will be out when idle */
-	clear_thread_flag(TIF_RUN_LIGHT);
-	CTRL = mfspr(CTRLF);
-	CTRL &= ~RUNLATCH;
-	mtspr(CTRLT, CTRL);
+	ppc64_runlatch_off();
 
 	lpaca = get_paca();
 
@@ -111,7 +107,9 @@ static int iSeries_idle(void)
 			}
 		}
 
+		ppc64_runlatch_on();
 		schedule();
+		ppc64_runlatch_off();
 	}
 
 	return 0;

arch/ppc64/kernel/process.c

@@ -378,9 +378,6 @@ copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
 		p->thread.regs = NULL;	/* no user register state */
 		clear_ti_thread_flag(p->thread_info, TIF_32BIT);
-#ifdef CONFIG_PPC_ISERIES
-		set_ti_thread_flag(p->thread_info, TIF_RUN_LIGHT);
-#endif
 	} else {
 		childregs->gpr[1] = usp;
 		p->thread.regs = childregs;

arch/ppc64/kernel/prom_init.c

@@ -1370,7 +1370,7 @@ static int __init prom_find_machine_type(void)
 	}
 	/* Default to pSeries. We need to know if we are running LPAR */
 	rtas = call_prom("finddevice", 1, 1, ADDR("/rtas"));
-	if (!PHANDLE_VALID(rtas)) {
+	if (PHANDLE_VALID(rtas)) {
 		int x = prom_getproplen(rtas, "ibm,hypertas-functions");
 		if (x != PROM_ERROR) {
 			prom_printf("Hypertas detected, assuming LPAR !\n");

arch/ppc64/kernel/setup.c

@@ -103,11 +103,6 @@ extern void unflatten_device_tree(void);
 
 extern void smp_release_cpus(void);
 
-unsigned long decr_overclock = 1;
-unsigned long decr_overclock_proc0 = 1;
-unsigned long decr_overclock_set = 0;
-unsigned long decr_overclock_proc0_set = 0;
-
 int have_of = 1;
 int boot_cpuid = 0;
 int boot_cpuid_phys = 0;
@@ -1120,64 +1115,15 @@ void ppc64_dump_msg(unsigned int src, const char *msg)
 	printk("[dump]%04x %s\n", src, msg);
 }
 
-int set_spread_lpevents( char * str )
-{
-	/* The parameter is the number of processors to share in processing lp events */
-	unsigned long i;
-	unsigned long val = simple_strtoul( str, NULL, 0 );
-	if ( ( val > 0 ) && ( val <= NR_CPUS ) ) {
-		for ( i=1; i<val; ++i )
-			paca[i].lpqueue_ptr = paca[0].lpqueue_ptr;
-		printk("lpevent processing spread over %ld processors\n", val);
-	}
-	else
-		printk("invalid spreaqd_lpevents %ld\n", val);
-	return 1;
-}	
-
 /* This should only be called on processor 0 during calibrate decr */
 void setup_default_decr(void)
 {
 	struct paca_struct *lpaca = get_paca();
 
-	if ( decr_overclock_set && !decr_overclock_proc0_set )
-		decr_overclock_proc0 = decr_overclock;
-
-	lpaca->default_decr = tb_ticks_per_jiffy / decr_overclock_proc0;	
+	lpaca->default_decr = tb_ticks_per_jiffy;
 	lpaca->next_jiffy_update_tb = get_tb() + tb_ticks_per_jiffy;
 }
 
-int set_decr_overclock_proc0( char * str )
-{
-	unsigned long val = simple_strtoul( str, NULL, 0 );
-	if ( ( val >= 1 ) && ( val <= 48 ) ) {
-		decr_overclock_proc0_set = 1;
-		decr_overclock_proc0 = val;
-		printk("proc 0 decrementer overclock factor of %ld\n", val);
-	}
-	else
-		printk("invalid proc 0 decrementer overclock factor of %ld\n", val);
-	return 1;
-}
-
-int set_decr_overclock( char * str )
-{
-	unsigned long val = simple_strtoul( str, NULL, 0 );
-	if ( ( val >= 1 ) && ( val <= 48 ) ) {
-		decr_overclock_set = 1;
-		decr_overclock = val;
-		printk("decrementer overclock factor of %ld\n", val);
-	}
-	else
-		printk("invalid decrementer overclock factor of %ld\n", val);
-	return 1;
-
-}
-
-__setup("spread_lpevents=", set_spread_lpevents );
-__setup("decr_overclock_proc0=", set_decr_overclock_proc0 );
-__setup("decr_overclock=", set_decr_overclock );
-
 #ifndef CONFIG_PPC_ISERIES
 /*
  * This function can be used by platforms to "find" legacy serial ports.

arch/ppc64/kernel/smp.c

@@ -334,7 +334,6 @@ void smp_call_function_interrupt(void)
 	}
 }
 
-extern unsigned long decr_overclock;
 extern struct gettimeofday_struct do_gtod;
 
 struct thread_info *current_set[NR_CPUS];
@@ -491,7 +490,7 @@ int __devinit __cpu_up(unsigned int cpu)
 	if (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu))
 		return -EINVAL;
 
-	paca[cpu].default_decr = tb_ticks_per_jiffy / decr_overclock;
+	paca[cpu].default_decr = tb_ticks_per_jiffy;
 
 	if (!cpu_has_feature(CPU_FTR_SLB)) {
 		void *tmp;

arch/ppc64/kernel/sysfs.c

@@ -113,7 +113,6 @@ void ppc64_enable_pmcs(void)
 #ifdef CONFIG_PPC_PSERIES
 	unsigned long set, reset;
 	int ret;
-	unsigned int ctrl;
 #endif /* CONFIG_PPC_PSERIES */
 
 	/* Only need to enable them once */
@@ -167,11 +166,8 @@ void ppc64_enable_pmcs(void)
 	 * On SMT machines we have to set the run latch in the ctrl register
 	 * in order to make PMC6 spin.
 	 */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		ctrl = mfspr(CTRLF);
-		ctrl |= RUNLATCH;
-		mtspr(CTRLT, ctrl);
-	}
+	if (cpu_has_feature(CPU_FTR_SMT))
+		ppc64_runlatch_on();
 #endif /* CONFIG_PPC_PSERIES */
 }
 

arch/s390/appldata/appldata_base.c

@@ -28,6 +28,7 @@
 //#include <linux/kernel_stat.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
+#include <linux/workqueue.h>
 
 #include "appldata.h"
 
@@ -133,9 +134,12 @@ static int appldata_interval = APPLDATA_CPU_INTERVAL;
 static int appldata_timer_active;
 
 /*
- * Tasklet
+ * Work queue
  */
-static struct tasklet_struct appldata_tasklet_struct;
+static struct workqueue_struct *appldata_wq;
+static void appldata_work_fn(void *data);
+static DECLARE_WORK(appldata_work, appldata_work_fn, NULL);
+
 
 /*
  * Ops list
@@ -144,11 +148,11 @@ static DEFINE_SPINLOCK(appldata_ops_lock);
 static LIST_HEAD(appldata_ops_list);
 
 
-/************************* timer, tasklet, DIAG ******************************/
+/*************************** timer, work, DIAG *******************************/
 /*
  * appldata_timer_function()
  *
- * schedule tasklet and reschedule timer
+ * schedule work and reschedule timer
  */
 static void appldata_timer_function(unsigned long data, struct pt_regs *regs)
 {
@@ -157,22 +161,22 @@ static void appldata_timer_function(unsigned long data, struct pt_regs *regs)
 		atomic_read(&appldata_expire_count));
 	if (atomic_dec_and_test(&appldata_expire_count)) {
 		atomic_set(&appldata_expire_count, num_online_cpus());
-		tasklet_schedule((struct tasklet_struct *) data);
+		queue_work(appldata_wq, (struct work_struct *) data);
 	}
 }
 
 /*
- * appldata_tasklet_function()
+ * appldata_work_fn()
  *
  * call data gathering function for each (active) module
  */
-static void appldata_tasklet_function(unsigned long data)
+static void appldata_work_fn(void *data)
 {
 	struct list_head *lh;
 	struct appldata_ops *ops;
 	int i;
 
-	P_DEBUG("  -= Tasklet =-\n");
+	P_DEBUG("  -= Work Queue =-\n");
 	i = 0;
 	spin_lock(&appldata_ops_lock);
 	list_for_each(lh, &appldata_ops_list) {
@@ -231,7 +235,7 @@ static int appldata_diag(char record_nr, u16 function, unsigned long buffer,
 			: "=d" (ry) : "d" (&(appldata_parameter_list)) : "cc");
 	return (int) ry;
 }
-/********************** timer, tasklet, DIAG <END> ***************************/
+/************************ timer, work, DIAG <END> ****************************/
 
 
 /****************************** /proc stuff **********************************/
@@ -411,7 +415,7 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp,
 	struct list_head *lh;
 
 	found = 0;
-	spin_lock_bh(&appldata_ops_lock);
+	spin_lock(&appldata_ops_lock);
 	list_for_each(lh, &appldata_ops_list) {
 		tmp_ops = list_entry(lh, struct appldata_ops, list);
 		if (&tmp_ops->ctl_table[2] == ctl) {
@@ -419,15 +423,15 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp,
 		}
 	}
 	if (!found) {
-		spin_unlock_bh(&appldata_ops_lock);
+		spin_unlock(&appldata_ops_lock);
 		return -ENODEV;
 	}
 	ops = ctl->data;
 	if (!try_module_get(ops->owner)) {	// protect this function
-		spin_unlock_bh(&appldata_ops_lock);
+		spin_unlock(&appldata_ops_lock);
 		return -ENODEV;
 	}
-	spin_unlock_bh(&appldata_ops_lock);
+	spin_unlock(&appldata_ops_lock);
 
 	if (!*lenp || *ppos) {
 		*lenp = 0;
@@ -451,10 +455,11 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp,
 		return -EFAULT;
 	}
 
-	spin_lock_bh(&appldata_ops_lock);
+	spin_lock(&appldata_ops_lock);
 	if ((buf[0] == '1') && (ops->active == 0)) {
-		if (!try_module_get(ops->owner)) {	// protect tasklet
-			spin_unlock_bh(&appldata_ops_lock);
+		// protect work queue callback
+		if (!try_module_get(ops->owner)) {
+			spin_unlock(&appldata_ops_lock);
 			module_put(ops->owner);
 			return -ENODEV;
 		}
@@ -485,7 +490,7 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp,
 		}
 		module_put(ops->owner);
 	}
-	spin_unlock_bh(&appldata_ops_lock);
+	spin_unlock(&appldata_ops_lock);
 out:
 	*lenp = len;
 	*ppos += len;
@@ -529,7 +534,7 @@ int appldata_register_ops(struct appldata_ops *ops)
 	}
 	memset(ops->ctl_table, 0, 4*sizeof(struct ctl_table));
 
-	spin_lock_bh(&appldata_ops_lock);
+	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",
@@ -541,18 +546,18 @@ int appldata_register_ops(struct appldata_ops *ops)
 				APPLDATA_PROC_NAME_LENGTH) == 0) {
 			P_ERROR("Name \"%s\" already registered!\n", ops->name);
 			kfree(ops->ctl_table);
-			spin_unlock_bh(&appldata_ops_lock);
+			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_bh(&appldata_ops_lock);
+			spin_unlock(&appldata_ops_lock);
 			return -EBUSY;
 		}
 	}
 	list_add(&ops->list, &appldata_ops_list);
-	spin_unlock_bh(&appldata_ops_lock);
+	spin_unlock(&appldata_ops_lock);
 
 	ops->ctl_table[0].ctl_name = CTL_APPLDATA;
 	ops->ctl_table[0].procname = appldata_proc_name;
@@ -583,12 +588,12 @@ int appldata_register_ops(struct appldata_ops *ops)
  */
 void appldata_unregister_ops(struct appldata_ops *ops)
 {
-	spin_lock_bh(&appldata_ops_lock);
+	spin_lock(&appldata_ops_lock);
 	unregister_sysctl_table(ops->sysctl_header);
 	list_del(&ops->list);
 	kfree(ops->ctl_table);
 	ops->ctl_table = NULL;
-	spin_unlock_bh(&appldata_ops_lock);
+	spin_unlock(&appldata_ops_lock);
 	P_INFO("%s-ops unregistered!\n", ops->name);
 }
 /********************** module-ops management <END> **************************/
@@ -602,7 +607,7 @@ appldata_online_cpu(int cpu)
 	init_virt_timer(&per_cpu(appldata_timer, cpu));
 	per_cpu(appldata_timer, cpu).function = appldata_timer_function;
 	per_cpu(appldata_timer, cpu).data = (unsigned long)
-		&appldata_tasklet_struct;
+		&appldata_work;
 	atomic_inc(&appldata_expire_count);
 	spin_lock(&appldata_timer_lock);
 	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
@@ -615,7 +620,7 @@ appldata_offline_cpu(int cpu)
 	del_virt_timer(&per_cpu(appldata_timer, cpu));
 	if (atomic_dec_and_test(&appldata_expire_count)) {
 		atomic_set(&appldata_expire_count, num_online_cpus());
-		tasklet_schedule(&appldata_tasklet_struct);
+		queue_work(appldata_wq, &appldata_work);
 	}
 	spin_lock(&appldata_timer_lock);
 	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
@@ -648,7 +653,7 @@ static struct notifier_block __devinitdata appldata_nb = {
 /*
  * appldata_init()
  *
- * init timer and tasklet, register /proc entries
+ * init timer, register /proc entries
  */
 static int __init appldata_init(void)
 {
@@ -657,6 +662,12 @@ static int __init appldata_init(void)
 	P_DEBUG("sizeof(parameter_list) = %lu\n",
 		sizeof(struct appldata_parameter_list));
 
+	appldata_wq = create_singlethread_workqueue("appldata");
+	if (!appldata_wq) {
+		P_ERROR("Could not create work queue\n");
+		return -ENOMEM;
+	}
+
 	for_each_online_cpu(i)
 		appldata_online_cpu(i);
 
@@ -670,7 +681,6 @@ static int __init appldata_init(void)
 	appldata_table[1].de->owner = THIS_MODULE;
 #endif
 
-	tasklet_init(&appldata_tasklet_struct, appldata_tasklet_function, 0);
 	P_DEBUG("Base interface initialized.\n");
 	return 0;
 }
@@ -678,7 +688,7 @@ static int __init appldata_init(void)
 /*
  * appldata_exit()
  *
- * stop timer and tasklet, unregister /proc entries
+ * stop timer, unregister /proc entries
  */
 static void __exit appldata_exit(void)
 {
@@ -690,7 +700,7 @@ static void __exit appldata_exit(void)
 	/*
 	 * ops list should be empty, but just in case something went wrong...
 	 */
-	spin_lock_bh(&appldata_ops_lock);
+	spin_lock(&appldata_ops_lock);
 	list_for_each(lh, &appldata_ops_list) {
 		ops = list_entry(lh, struct appldata_ops, list);
 		rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
@@ -700,7 +710,7 @@ static void __exit appldata_exit(void)
 				"return code: %d\n", ops->name, rc);
 		}
 	}
-	spin_unlock_bh(&appldata_ops_lock);
+	spin_unlock(&appldata_ops_lock);
 
 	for_each_online_cpu(i)
 		appldata_offline_cpu(i);
@@ -709,7 +719,7 @@ static void __exit appldata_exit(void)
 
 	unregister_sysctl_table(appldata_sysctl_header);
 
-	tasklet_kill(&appldata_tasklet_struct);
+	destroy_workqueue(appldata_wq);
 	P_DEBUG("... module unloaded!\n");
 }
 /**************************** init / exit <END> ******************************/

arch/s390/appldata/appldata_mem.c

@@ -68,7 +68,7 @@ struct appldata_mem_data {
 	u64 pgmajfault;		/* page faults (major only) */
 // <-- New in 2.6
 
-} appldata_mem_data;
+} __attribute__((packed)) appldata_mem_data;
 
 
 static inline void appldata_debug_print(struct appldata_mem_data *mem_data)

arch/s390/appldata/appldata_net_sum.c

@@ -57,7 +57,7 @@ struct appldata_net_sum_data {
 	u64 rx_dropped;		/* no space in linux buffers     */
 	u64 tx_dropped;		/* no space available in linux   */
 	u64 collisions;		/* collisions while transmitting */
-} appldata_net_sum_data;
+} __attribute__((packed)) appldata_net_sum_data;
 
 
 static inline void appldata_print_debug(struct appldata_net_sum_data *net_data)

arch/s390/appldata/appldata_os.c

@@ -49,7 +49,7 @@ struct appldata_os_per_cpu {
 	u32 per_cpu_softirq;	/* ... spent in softirqs            */
 	u32 per_cpu_iowait;	/* ... spent while waiting for I/O  */
 // <-- New in 2.6
-};
+} __attribute__((packed));
 
 struct appldata_os_data {
 	u64 timestamp;
@@ -75,7 +75,7 @@ struct appldata_os_data {
 
 	/* per cpu data */
 	struct appldata_os_per_cpu os_cpu[0];
-};
+} __attribute__((packed));
 
 static struct appldata_os_data *appldata_os_data;
 

arch/s390/kernel/ptrace.c

@@ -40,6 +40,7 @@
 #include <asm/pgalloc.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
+#include <asm/unistd.h>
 
 #ifdef CONFIG_S390_SUPPORT
 #include "compat_ptrace.h"
@@ -130,13 +131,19 @@ static int
 peek_user(struct task_struct *child, addr_t addr, addr_t data)
 {
 	struct user *dummy = NULL;
-	addr_t offset, tmp;
+	addr_t offset, tmp, mask;
 
 	/*
 	 * Stupid gdb peeks/pokes the access registers in 64 bit with
 	 * an alignment of 4. Programmers from hell...
 	 */
-	if ((addr & 3) || addr > sizeof(struct user) - __ADDR_MASK)
+	mask = __ADDR_MASK;
+#ifdef CONFIG_ARCH_S390X
+	if (addr >= (addr_t) &dummy->regs.acrs &&
+	    addr < (addr_t) &dummy->regs.orig_gpr2)
+		mask = 3;
+#endif
+	if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK)
 		return -EIO;
 
 	if (addr < (addr_t) &dummy->regs.acrs) {
@@ -153,6 +160,16 @@ peek_user(struct task_struct *child, addr_t addr, addr_t data)
 		 * access registers are stored in the thread structure
 		 */
 		offset = addr - (addr_t) &dummy->regs.acrs;
+#ifdef CONFIG_ARCH_S390X
+		/*
+		 * Very special case: old & broken 64 bit gdb reading
+		 * from acrs[15]. Result is a 64 bit value. Read the
+		 * 32 bit acrs[15] value and shift it by 32. Sick...
+		 */
+		if (addr == (addr_t) &dummy->regs.acrs[15])
+			tmp = ((unsigned long) child->thread.acrs[15]) << 32;
+		else
+#endif
 		tmp = *(addr_t *)((addr_t) &child->thread.acrs + offset);
 
 	} else if (addr == (addr_t) &dummy->regs.orig_gpr2) {
@@ -167,6 +184,9 @@ peek_user(struct task_struct *child, addr_t addr, addr_t data)
 		 */
 		offset = addr - (addr_t) &dummy->regs.fp_regs;
 		tmp = *(addr_t *)((addr_t) &child->thread.fp_regs + offset);
+		if (addr == (addr_t) &dummy->regs.fp_regs.fpc)
+			tmp &= (unsigned long) FPC_VALID_MASK
+				<< (BITS_PER_LONG - 32);
 
 	} else if (addr < (addr_t) (&dummy->regs.per_info + 1)) {
 		/*
@@ -191,13 +211,19 @@ static int
 poke_user(struct task_struct *child, addr_t addr, addr_t data)
 {
 	struct user *dummy = NULL;
-	addr_t offset;
+	addr_t offset, mask;
 
 	/*
 	 * Stupid gdb peeks/pokes the access registers in 64 bit with
 	 * an alignment of 4. Programmers from hell indeed...
 	 */
-	if ((addr & 3) || addr > sizeof(struct user) - __ADDR_MASK)
+	mask = __ADDR_MASK;
+#ifdef CONFIG_ARCH_S390X
+	if (addr >= (addr_t) &dummy->regs.acrs &&
+	    addr < (addr_t) &dummy->regs.orig_gpr2)
+		mask = 3;
+#endif
+	if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK)
 		return -EIO;
 
 	if (addr < (addr_t) &dummy->regs.acrs) {
@@ -224,6 +250,17 @@ poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		 * access registers are stored in the thread structure
 		 */
 		offset = addr - (addr_t) &dummy->regs.acrs;
+#ifdef CONFIG_ARCH_S390X
+		/*
+		 * Very special case: old & broken 64 bit gdb writing
+		 * to acrs[15] with a 64 bit value. Ignore the lower
+		 * half of the value and write the upper 32 bit to
+		 * acrs[15]. Sick...
+		 */
+		if (addr == (addr_t) &dummy->regs.acrs[15])
+			child->thread.acrs[15] = (unsigned int) (data >> 32);
+		else
+#endif
 		*(addr_t *)((addr_t) &child->thread.acrs + offset) = data;
 
 	} else if (addr == (addr_t) &dummy->regs.orig_gpr2) {
@@ -237,7 +274,8 @@ poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		 * floating point regs. are stored in the thread structure
 		 */
 		if (addr == (addr_t) &dummy->regs.fp_regs.fpc &&
-		    (data & ~FPC_VALID_MASK) != 0)
+		    (data & ~((unsigned long) FPC_VALID_MASK
+			      << (BITS_PER_LONG - 32))) != 0)
 			return -EINVAL;
 		offset = addr - (addr_t) &dummy->regs.fp_regs;
 		*(addr_t *)((addr_t) &child->thread.fp_regs + offset) = data;
@@ -722,6 +760,13 @@ syscall_trace(struct pt_regs *regs, int entryexit)
 	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
 				 ? 0x80 : 0));
 
+	/*
+	 * If the debuffer has set an invalid system call number,
+	 * we prepare to skip the system call restart handling.
+	 */
+	if (!entryexit && regs->gprs[2] >= NR_syscalls)
+		regs->trap = -1;
+
 	/*
 	 * this isn't the same as continuing with a signal, but it will do
 	 * for normal use.  strace only continues with a signal if the

arch/s390/mm/fault.c

@@ -207,7 +207,7 @@ do_exception(struct pt_regs *regs, unsigned long error_code, int is_protection)
 	 * we are not in an interrupt and that there is a 
 	 * user context.
 	 */
-        if (user_address == 0 || in_interrupt() || !mm)
+        if (user_address == 0 || in_atomic() || !mm)
                 goto no_context;
 
 	/*

drivers/atm/Makefile

@@ -39,7 +39,8 @@ ifeq ($(CONFIG_ATM_FORE200E_PCA),y)
   fore_200e-objs		+= fore200e_pca_fw.o
   # guess the target endianess to choose the right PCA-200E firmware image
   ifeq ($(CONFIG_ATM_FORE200E_PCA_DEFAULT_FW),y)
-    CONFIG_ATM_FORE200E_PCA_FW = $(shell if test -n "`$(CC) -E -dM $(src)/../../include/asm/byteorder.h | grep ' __LITTLE_ENDIAN '`"; then echo $(obj)/pca200e.bin; else echo $(obj)/pca200e_ecd.bin2; fi)
+    byteorder.h			:= include$(if $(patsubst $(srctree),,$(objtree)),2)/asm/byteorder.h
+    CONFIG_ATM_FORE200E_PCA_FW	:= $(obj)/pca200e$(if $(shell $(CC) -E -dM $(byteorder.h) | grep ' __LITTLE_ENDIAN '),.bin,_ecd.bin2)
   endif
 endif
 

drivers/atm/fore200e.c

@@ -383,8 +383,7 @@ fore200e_shutdown(struct fore200e* fore200e)
     switch(fore200e->state) {
 
     case FORE200E_STATE_COMPLETE:
-	if (fore200e->stats)
-	    kfree(fore200e->stats);
+	kfree(fore200e->stats);
 
     case FORE200E_STATE_IRQ:
 	free_irq(fore200e->irq, fore200e->atm_dev);
@@ -963,8 +962,7 @@ fore200e_tx_irq(struct fore200e* fore200e)
 		entry, txq->tail, entry->vc_map, entry->skb);
 
 	/* free copy of misaligned data */
-	if (entry->data)
-	    kfree(entry->data);
+	kfree(entry->data);
 	
 	/* remove DMA mapping */
 	fore200e->bus->dma_unmap(fore200e, entry->tpd->tsd[ 0 ].buffer, entry->tpd->tsd[ 0 ].length,