Automatic merge of /spare/repo/linux-2.6/.git branch HEAD

Documentation/cpu-freq/cpufreq-stats.txt

@@ -0,0 +1,128 @@
+
+     CPU frequency and voltage scaling statictics in the Linux(TM) kernel
+
+
+             L i n u x    c p u f r e q - s t a t s   d r i v e r
+
+                       - information for users -
+
+
+             Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+
+Contents
+1. Introduction
+2. Statistics Provided (with example)
+3. Configuring cpufreq-stats
+
+
+1. Introduction
+
+cpufreq-stats is a driver that provices CPU frequency statistics for each CPU.
+This statistics is provided in /sysfs as a bunch of read_only interfaces. This
+interface (when configured) will appear in a seperate directory under cpufreq
+in /sysfs (<sysfs root>/devices/system/cpu/cpuX/cpufreq/stats/) for each CPU.
+Various statistics will form read_only files under this directory.
+
+This driver is designed to be independent of any particular cpufreq_driver
+that may be running on your CPU. So, it will work with any cpufreq_driver.
+
+
+2. Statistics Provided (with example)
+
+cpufreq stats provides following statistics (explained in detail below).
+-  time_in_state
+-  total_trans
+-  trans_table
+
+All the statistics will be from the time the stats driver has been inserted 
+to the time when a read of a particular statistic is done. Obviously, stats 
+driver will not have any information about the the frequcny transitions before
+the stats driver insertion.
+
+--------------------------------------------------------------------------------
+<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # ls -l
+total 0
+drwxr-xr-x  2 root root    0 May 14 16:06 .
+drwxr-xr-x  3 root root    0 May 14 15:58 ..
+-r--r--r--  1 root root 4096 May 14 16:06 time_in_state
+-r--r--r--  1 root root 4096 May 14 16:06 total_trans
+-r--r--r--  1 root root 4096 May 14 16:06 trans_table
+--------------------------------------------------------------------------------
+
+-  time_in_state
+This gives the amount of time spent in each of the frequencies supported by
+this CPU. The cat output will have "<frequency> <time>" pair in each line, which
+will mean this CPU spent <time> usertime units of time at <frequency>. Output
+will have one line for each of the supported freuencies. usertime units here 
+is 10mS (similar to other time exported in /proc).
+
+--------------------------------------------------------------------------------
+<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat time_in_state 
+3600000 2089
+3400000 136
+3200000 34
+3000000 67
+2800000 172488
+--------------------------------------------------------------------------------
+
+
+-  total_trans
+This gives the total number of frequency transitions on this CPU. The cat 
+output will have a single count which is the total number of frequency
+transitions.
+
+--------------------------------------------------------------------------------
+<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat total_trans
+20
+--------------------------------------------------------------------------------
+
+-  trans_table
+This will give a fine grained information about all the CPU frequency
+transitions. The cat output here is a two dimensional matrix, where an entry
+<i,j> (row i, column j) represents the count of number of transitions from 
+Freq_i to Freq_j. Freq_i is in descending order with increasing rows and 
+Freq_j is in descending order with increasing columns. The output here also 
+contains the actual freq values for each row and column for better readability.
+
+--------------------------------------------------------------------------------
+<mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # cat trans_table
+   From  :    To
+         :   3600000   3400000   3200000   3000000   2800000 
+  3600000:         0         5         0         0         0 
+  3400000:         4         0         2         0         0 
+  3200000:         0         1         0         2         0 
+  3000000:         0         0         1         0         3 
+  2800000:         0         0         0         2         0 
+--------------------------------------------------------------------------------
+
+
+3. Configuring cpufreq-stats
+
+To configure cpufreq-stats in your kernel
+Config Main Menu
+	Power management options (ACPI, APM)  --->
+		CPU Frequency scaling  --->
+			[*] CPU Frequency scaling
+			<*>   CPU frequency translation statistics 
+			[*]     CPU frequency translation statistics details
+
+
+"CPU Frequency scaling" (CONFIG_CPU_FREQ) should be enabled to configure
+cpufreq-stats.
+
+"CPU frequency translation statistics" (CONFIG_CPU_FREQ_STAT) provides the
+basic statistics which includes time_in_state and total_trans.
+
+"CPU frequency translation statistics details" (CONFIG_CPU_FREQ_STAT_DETAILS)
+provides fine grained cpufreq stats by trans_table. The reason for having a
+seperate config option for trans_table is:
+- trans_table goes against the traditional /sysfs rule of one value per
+  interface. It provides a whole bunch of value in a 2 dimensional matrix
+  form.
+
+Once these two options are enabled and your CPU supports cpufrequency, you
+will be able to see the CPU frequency statistics in /sysfs.
+
+
+
+

MAINTAINERS

@@ -239,6 +239,12 @@ L:	linux-usb-devel@lists.sourceforge.net
 W:	http://www.linux-usb.org/SpeedTouch/
 S:	Maintained
 
+ALI1563 I2C DRIVER
+P:	Rudolf Marek
+M:	r.marek@sh.cvut.cz
+L:	sensors@stimpy.netroedge.com
+S:	Maintained
+
 ALPHA PORT
 P:	Richard Henderson
 M:	rth@twiddle.net
@@ -1023,8 +1029,8 @@ W:	http://www.ia64-linux.org/
 S:	Maintained
 
 SN-IA64 (Itanium) SUB-PLATFORM
-P:	Jesse Barnes
-M:	jbarnes@sgi.com
+P:	Greg Edwards
+M:	edwardsg@sgi.com
 L:	linux-altix@sgi.com
 L:	linux-ia64@vger.kernel.org
 W:	http://www.sgi.com/altix

arch/h8300/kernel/process.c

@@ -54,7 +54,7 @@ asmlinkage void ret_from_fork(void);
 void default_idle(void)
 {
 	while(1) {
-		if (need_resched()) {
+		if (!need_resched()) {
 			local_irq_enable();
 			__asm__("sleep");
 			local_irq_disable();

arch/i386/kernel/cpu/cpufreq/Kconfig

@@ -23,7 +23,7 @@ config X86_ACPI_CPUFREQ
 	  If in doubt, say N.
 
 config ELAN_CPUFREQ
-	tristate "AMD Elan"
+	tristate "AMD Elan SC400 and SC410"
 	select CPU_FREQ_TABLE
 	depends on X86_ELAN
 	---help---
@@ -38,6 +38,18 @@ config ELAN_CPUFREQ
 
 	  If in doubt, say N.
 
+config SC520_CPUFREQ
+	tristate "AMD Elan SC520"
+	select CPU_FREQ_TABLE
+	depends on X86_ELAN
+	---help---
+	  This adds the CPUFreq driver for AMD Elan SC520 processor.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+
 config X86_POWERNOW_K6
 	tristate "AMD Mobile K6-2/K6-3 PowerNow!"
 	select CPU_FREQ_TABLE

arch/i386/kernel/cpu/cpufreq/Makefile

@@ -3,6 +3,7 @@ obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
 obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
 obj-$(CONFIG_ELAN_CPUFREQ)		+= elanfreq.o
+obj-$(CONFIG_SC520_CPUFREQ)		+= sc520_freq.o
 obj-$(CONFIG_X86_LONGRUN)		+= longrun.o  
 obj-$(CONFIG_X86_GX_SUSPMOD)		+= gx-suspmod.o
 obj-$(CONFIG_X86_SPEEDSTEP_ICH)		+= speedstep-ich.o

arch/i386/kernel/cpu/cpufreq/longhaul.c

@@ -29,6 +29,7 @@
 #include <linux/cpufreq.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/pci.h>
 
 #include <asm/msr.h>
 #include <asm/timex.h>
@@ -119,7 +120,13 @@ static int longhaul_get_cpu_mult(void)
 static void do_powersaver(union msr_longhaul *longhaul,
 			unsigned int clock_ratio_index)
 {
+	struct pci_dev *dev;
+	unsigned long flags;
+	unsigned int tmp_mask;
 	int version;
+	int i;
+	u16 pci_cmd;
+	u16 cmd_state[64];
 
 	switch (cpu_model) {
 	case CPU_EZRA_T:
@@ -137,17 +144,58 @@ static void do_powersaver(union msr_longhaul *longhaul,
 	longhaul->bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
 	longhaul->bits.EnableSoftBusRatio = 1;
 	longhaul->bits.RevisionKey = 0;
-	local_irq_disable();
-	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
+
+	preempt_disable();
+	local_irq_save(flags);
+
+	/*
+	 * get current pci bus master state for all devices
+	 * and clear bus master bit
+	 */
+	dev = NULL;
+	i = 0;
+	do {
+		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
+		if (dev != NULL) {
+			pci_read_config_word(dev, PCI_COMMAND, &pci_cmd);
+			cmd_state[i++] = pci_cmd;
+			pci_cmd &= ~PCI_COMMAND_MASTER;
+			pci_write_config_word(dev, PCI_COMMAND, pci_cmd);
+		}
+	} while (dev != NULL);
+
+	tmp_mask=inb(0x21);	/* works on C3. save mask. */
+	outb(0xFE,0x21);	/* TMR0 only */
+	outb(0xFF,0x80);	/* delay */
+
 	local_irq_enable();
+
+	__hlt();
+	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
 	__hlt();
 
+	local_irq_disable();
+
+	outb(tmp_mask,0x21);	/* restore mask */
+
+	/* restore pci bus master state for all devices */
+	dev = NULL;
+	i = 0;
+	do {
+		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
+		if (dev != NULL) {
+			pci_cmd = cmd_state[i++];
+			pci_write_config_byte(dev, PCI_COMMAND, pci_cmd);
+		}
+	} while (dev != NULL);
+	local_irq_restore(flags);
+	preempt_enable();
+
+	/* disable bus ratio bit */
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul->val);
 	longhaul->bits.EnableSoftBusRatio = 0;
 	longhaul->bits.RevisionKey = version;
-	local_irq_disable();
 	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
-	local_irq_enable();
 }
 
 /**
@@ -578,7 +626,7 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		longhaul_setup_voltagescaling();
 
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+	policy->cpuinfo.transition_latency = 200000;	/* nsec */
 	policy->cur = calc_speed(longhaul_get_cpu_mult());
 
 	ret = cpufreq_frequency_table_cpuinfo(policy, longhaul_table);

arch/i386/kernel/cpu/cpufreq/powernow-k7.c

@@ -23,6 +23,7 @@
 #include <linux/dmi.h>
 
 #include <asm/msr.h>
+#include <asm/timer.h>
 #include <asm/timex.h>
 #include <asm/io.h>
 #include <asm/system.h>
@@ -586,13 +587,17 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy)
 
 	rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val);
 
-	/* A K7 with powernow technology is set to max frequency by BIOS */
-	fsb = (10 * cpu_khz) / fid_codes[fidvidstatus.bits.MFID];
+	/* recalibrate cpu_khz */
+	result = recalibrate_cpu_khz();
+	if (result)
+		return result;
+
+	fsb = (10 * cpu_khz) / fid_codes[fidvidstatus.bits.CFID];
 	if (!fsb) {
 		printk(KERN_WARNING PFX "can not determine bus frequency\n");
 		return -EINVAL;
 	}
-	dprintk("FSB: %3d.%03d MHz\n", fsb/1000, fsb%1000);
+	dprintk("FSB: %3dMHz\n", fsb/1000);
 
 	if (dmi_check_system(powernow_dmi_table) || acpi_force) {
 		printk (KERN_INFO PFX "PSB/PST known to be broken.  Trying ACPI instead\n");

arch/i386/kernel/cpu/cpufreq/powernow-k8.c

@@ -4,7 +4,7 @@
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
  *
- *  Support : paul.devriendt@amd.com
+ *  Support : mark.langsdorf@amd.com
  *
  *  Based on the powernow-k7.c module written by Dave Jones.
  *  (C) 2003 Dave Jones <davej@codemonkey.org.uk> on behalf of SuSE Labs
@@ -15,12 +15,13 @@
  *
  *  Valuable input gratefully received from Dave Jones, Pavel Machek,
  *  Dominik Brodowski, and others.
+ *  Originally developed by Paul Devriendt.
  *  Processor information obtained from Chapter 9 (Power and Thermal Management)
  *  of the "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD
  *  Opteron Processors" available for download from www.amd.com
  *
  *  Tables for specific CPUs can be infrerred from
- *	http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/30430.pdf
+ *     http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/30430.pdf
  */
 
 #include <linux/kernel.h>
@@ -30,6 +31,7 @@
 #include <linux/cpufreq.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/cpumask.h>
 
 #include <asm/msr.h>
 #include <asm/io.h>
@@ -42,7 +44,7 @@
 
 #define PFX "powernow-k8: "
 #define BFX PFX "BIOS error: "
-#define VERSION "version 1.00.09e"
+#define VERSION "version 1.40.2"
 #include "powernow-k8.h"
 
 /* serialize freq changes  */
@@ -50,6 +52,10 @@ static DECLARE_MUTEX(fidvid_sem);
 
 static struct powernow_k8_data *powernow_data[NR_CPUS];
 
+#ifndef CONFIG_SMP
+static cpumask_t cpu_core_map[1];
+#endif
+
 /* Return a frequency in MHz, given an input fid */
 static u32 find_freq_from_fid(u32 fid)
 {
@@ -274,11 +280,18 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid
 {
 	u32 rvosteps = data->rvo;
 	u32 savefid = data->currfid;
+	u32 maxvid, lo;
 
 	dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, reqvid 0x%x, rvo 0x%x\n",
 		smp_processor_id(),
 		data->currfid, data->currvid, reqvid, data->rvo);
 
+	rdmsr(MSR_FIDVID_STATUS, lo, maxvid);
+	maxvid = 0x1f & (maxvid >> 16);
+	dprintk("ph1 maxvid=0x%x\n", maxvid);
+	if (reqvid < maxvid) /* lower numbers are higher voltages */
+		reqvid = maxvid;
+
 	while (data->currvid > reqvid) {
 		dprintk("ph1: curr 0x%x, req vid 0x%x\n",
 			data->currvid, reqvid);
@@ -286,8 +299,8 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid
 			return 1;
 	}
 
-	while ((rvosteps > 0)  && ((data->rvo + data->currvid) > reqvid)) {
-		if (data->currvid == 0) {
+	while ((rvosteps > 0) && ((data->rvo + data->currvid) > reqvid)) {
+		if (data->currvid == maxvid) {
 			rvosteps = 0;
 		} else {
 			dprintk("ph1: changing vid for rvo, req 0x%x\n",
@@ -671,7 +684,7 @@ static int find_psb_table(struct powernow_k8_data *data)
 	 * BIOS and Kernel Developer's Guide, which is available on
 	 * www.amd.com
 	 */
-	printk(KERN_ERR PFX "BIOS error - no PSB\n");
+	printk(KERN_INFO PFX "BIOS error - no PSB or ACPI _PSS objects\n");
 	return -ENODEV;
 }
 
@@ -695,7 +708,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	struct cpufreq_frequency_table *powernow_table;
 
 	if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
-		dprintk("register performance failed\n");
+		dprintk("register performance failed: bad ACPI data\n");
 		return -EIO;
 	}
 
@@ -746,22 +759,23 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 			continue;
 		}
 
- 		if (fid < HI_FID_TABLE_BOTTOM) {
- 			if (cntlofreq) {
- 				/* if both entries are the same, ignore this
- 				 * one... 
- 				 */
- 				if ((powernow_table[i].frequency != powernow_table[cntlofreq].frequency) ||
- 				    (powernow_table[i].index != powernow_table[cntlofreq].index)) {
- 					printk(KERN_ERR PFX "Too many lo freq table entries\n");
- 					goto err_out_mem;
- 				}
-				
- 				dprintk("double low frequency table entry, ignoring it.\n");
- 				powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID;
- 				continue;
- 			} else
- 				cntlofreq = i;
+		/* verify only 1 entry from the lo frequency table */
+		if (fid < HI_FID_TABLE_BOTTOM) {
+			if (cntlofreq) {
+				/* if both entries are the same, ignore this
+				 * one... 
+				 */
+				if ((powernow_table[i].frequency != powernow_table[cntlofreq].frequency) ||
+				    (powernow_table[i].index != powernow_table[cntlofreq].index)) {
+					printk(KERN_ERR PFX "Too many lo freq table entries\n");
+					goto err_out_mem;
+				}
+
+				dprintk("double low frequency table entry, ignoring it.\n");
+				powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID;
+				continue;
+			} else
+				cntlofreq = i;
 		}
 
 		if (powernow_table[i].frequency != (data->acpi_data.states[i].core_frequency * 1000)) {
@@ -816,7 +830,7 @@ static int transition_frequency(struct powernow_k8_data *data, unsigned int inde
 {
 	u32 fid;
 	u32 vid;
-	int res;
+	int res, i;
 	struct cpufreq_freqs freqs;
 
 	dprintk("cpu %d transition to index %u\n", smp_processor_id(), index);
@@ -841,7 +855,8 @@ static int transition_frequency(struct powernow_k8_data *data, unsigned int inde
 	}
 
 	if ((fid < HI_FID_TABLE_BOTTOM) && (data->currfid < HI_FID_TABLE_BOTTOM)) {
-		printk("ignoring illegal change in lo freq table-%x to 0x%x\n",
+		printk(KERN_ERR PFX
+		       "ignoring illegal change in lo freq table-%x to 0x%x\n",
 		       data->currfid, fid);
 		return 1;
 	}
@@ -850,18 +865,20 @@ static int transition_frequency(struct powernow_k8_data *data, unsigned int inde
 		smp_processor_id(), fid, vid);
 
 	freqs.cpu = data->cpu;
-
 	freqs.old = find_khz_freq_from_fid(data->currfid);
 	freqs.new = find_khz_freq_from_fid(fid);
-	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+	for_each_cpu_mask(i, cpu_core_map[data->cpu]) {
+		freqs.cpu = i;
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+	}
 
-	down(&fidvid_sem);
 	res = transition_fid_vid(data, fid, vid);
-	up(&fidvid_sem);
 
 	freqs.new = find_khz_freq_from_fid(data->currfid);
-	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
+	for_each_cpu_mask(i, cpu_core_map[data->cpu]) {
+		freqs.cpu = i;
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+        }
 	return res;
 }
 
@@ -874,6 +891,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 	u32 checkvid = data->currvid;
 	unsigned int newstate;
 	int ret = -EIO;
+	int i;
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
@@ -902,22 +920,41 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 		data->currfid, data->currvid);
 
 	if ((checkvid != data->currvid) || (checkfid != data->currfid)) {
-		printk(KERN_ERR PFX
-		       "error - out of sync, fid 0x%x 0x%x, vid 0x%x 0x%x\n",
-		       checkfid, data->currfid, checkvid, data->currvid);
+		printk(KERN_INFO PFX
+			"error - out of sync, fix 0x%x 0x%x, vid 0x%x 0x%x\n",
+			checkfid, data->currfid, checkvid, data->currvid);
 	}
 
 	if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate))
 		goto err_out;
 
+	down(&fidvid_sem);
+
+	for_each_cpu_mask(i, cpu_core_map[pol->cpu]) {
+		/* make sure the sibling is initialized */
+		if (!powernow_data[i]) {
+                        ret = 0;
+                        up(&fidvid_sem);
+                        goto err_out;
+                }
+	}
+
 	powernow_k8_acpi_pst_values(data, newstate);
 
 	if (transition_frequency(data, newstate)) {
 		printk(KERN_ERR PFX "transition frequency failed\n");
 		ret = 1;
+		up(&fidvid_sem);
 		goto err_out;
 	}
 
+	/* Update all the fid/vids of our siblings */
+	for_each_cpu_mask(i, cpu_core_map[pol->cpu]) {
+		powernow_data[i]->currvid = data->currvid;
+		powernow_data[i]->currfid = data->currfid;
+	}	
+	up(&fidvid_sem);
+
 	pol->cur = find_khz_freq_from_fid(data->currfid);
 	ret = 0;
 
@@ -962,7 +999,7 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol)
 		 */
 
 		if ((num_online_cpus() != 1) || (num_possible_cpus() != 1)) {
-			printk(KERN_INFO PFX "MP systems not supported by PSB BIOS structure\n");
+			printk(KERN_ERR PFX "MP systems not supported by PSB BIOS structure\n");
 			kfree(data);
 			return -ENODEV;
 		}
@@ -1003,6 +1040,7 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol)
 	schedule();
 
 	pol->governor = CPUFREQ_DEFAULT_GOVERNOR;
+	pol->cpus = cpu_core_map[pol->cpu];
 
 	/* Take a crude guess here. 
 	 * That guess was in microseconds, so multiply with 1000 */
@@ -1069,7 +1107,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
 		return 0;
 	}
 	preempt_disable();
-
+	
 	if (query_current_values_with_pending_wait(data))
 		goto out;
 
@@ -1127,9 +1165,10 @@ static void __exit powernowk8_exit(void)
 	cpufreq_unregister_driver(&cpufreq_amd64_driver);
 }
 
-MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com>");
+MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and Mark Langsdorf <mark.langsdorf@amd.com.");
 MODULE_DESCRIPTION("AMD Athlon 64 and Opteron processor frequency driver.");
 MODULE_LICENSE("GPL");
 
 late_initcall(powernowk8_init);
 module_exit(powernowk8_exit);
+

arch/i386/kernel/cpu/cpufreq/powernow-k8.h

@@ -174,3 +174,18 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi
 static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid);
 
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index);
+
+#ifndef for_each_cpu_mask
+#define for_each_cpu_mask(i,mask) for (i=0;i<1;i++)
+#endif
+                                                                                
+#ifdef CONFIG_SMP
+static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[])
+{
+}
+#else
+static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[])
+{
+	cpu_set(0, cpu_sharedcore_mask[0]);
+}
+#endif

arch/i386/kernel/cpu/cpufreq/sc520_freq.c

@@ -0,0 +1,186 @@
+/*
+ *	sc520_freq.c: cpufreq driver for the AMD Elan sc520
+ *
+ *	Copyright (C) 2005 Sean Young <sean@mess.org>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	Based on elanfreq.c
+ *
+ *	2005-03-30: - initial revision
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/delay.h>
+#include <linux/cpufreq.h>
+
+#include <asm/msr.h>
+#include <asm/timex.h>
+#include <asm/io.h>
+
+#define MMCR_BASE	0xfffef000	/* The default base address */
+#define OFFS_CPUCTL	0x2   /* CPU Control Register */
+
+static __u8 __iomem *cpuctl;
+
+#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "sc520_freq", msg)
+
+static struct cpufreq_frequency_table sc520_freq_table[] = {
+	{0x01,	100000},
+	{0x02,	133000},
+	{0,	CPUFREQ_TABLE_END},
+};
+
+static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)
+{
+	u8 clockspeed_reg = *cpuctl;
+
+	switch (clockspeed_reg & 0x03) {
+	default:
+		printk(KERN_ERR "sc520_freq: error: cpuctl register has unexpected value %02x\n", clockspeed_reg);
+	case 0x01:
+		return 100000;
+	case 0x02:
+		return 133000;
+	}
+}
+
+static void sc520_freq_set_cpu_state (unsigned int state)
+{
+
+	struct cpufreq_freqs	freqs;
+	u8 clockspeed_reg;
+
+	freqs.old = sc520_freq_get_cpu_frequency(0);
+	freqs.new = sc520_freq_table[state].frequency;
+	freqs.cpu = 0; /* AMD Elan is UP */
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	dprintk("attempting to set frequency to %i kHz\n",
+			sc520_freq_table[state].frequency);
+
+	local_irq_disable();
+
+	clockspeed_reg = *cpuctl & ~0x03;
+	*cpuctl = clockspeed_reg | sc520_freq_table[state].index;
+
+	local_irq_enable();
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+};
+
+static int sc520_freq_verify (struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, &sc520_freq_table[0]);
+}
+
+static int sc520_freq_target (struct cpufreq_policy *policy,
+			    unsigned int target_freq,
+			    unsigned int relation)
+{
+	unsigned int newstate = 0;
+
+	if (cpufreq_frequency_table_target(policy, sc520_freq_table, target_freq, relation, &newstate))
+		return -EINVAL;
+
+	sc520_freq_set_cpu_state(newstate);
+
+	return 0;
+}
+
+
+/*
+ *	Module init and exit code
+ */
+
+static int sc520_freq_cpu_init(struct cpufreq_policy *policy)
+{
+	struct cpuinfo_x86 *c = cpu_data;
+	int result;
+
+	/* capability check */
+	if (c->x86_vendor != X86_VENDOR_AMD ||
+	    c->x86 != 4 || c->x86_model != 9)
+		return -ENODEV;
+
+	/* cpuinfo and default policy values */
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+	policy->cpuinfo.transition_latency = 1000000; /* 1ms */
+	policy->cur = sc520_freq_get_cpu_frequency(0);
+
+	result = cpufreq_frequency_table_cpuinfo(policy, sc520_freq_table);
+	if (result)
+		return (result);
+
+	cpufreq_frequency_table_get_attr(sc520_freq_table, policy->cpu);
+
+	return 0;
+}
+
+
+static int sc520_freq_cpu_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
+
+static struct freq_attr* sc520_freq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+
+static struct cpufreq_driver sc520_freq_driver = {
+	.get	= sc520_freq_get_cpu_frequency,
+	.verify	= sc520_freq_verify,
+	.target	= sc520_freq_target,
+	.init	= sc520_freq_cpu_init,
+	.exit	= sc520_freq_cpu_exit,
+	.name	= "sc520_freq",
+	.owner	= THIS_MODULE,
+	.attr	= sc520_freq_attr,
+};
+
+
+static int __init sc520_freq_init(void)
+{
+	struct cpuinfo_x86 *c = cpu_data;
+
+	/* Test if we have the right hardware */
+	if(c->x86_vendor != X86_VENDOR_AMD ||
+				c->x86 != 4 || c->x86_model != 9) {
+		dprintk("no Elan SC520 processor found!\n");
+		return -ENODEV;
+	}
+	cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1);
+	if(!cpuctl) {
+		printk(KERN_ERR "sc520_freq: error: failed to remap memory\n");
+		return -ENOMEM;
+	}
+
+	return cpufreq_register_driver(&sc520_freq_driver);
+}
+
+
+static void __exit sc520_freq_exit(void)
+{
+	cpufreq_unregister_driver(&sc520_freq_driver);
+	iounmap(cpuctl);
+}
+
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sean Young <sean@mess.org>");
+MODULE_DESCRIPTION("cpufreq driver for AMD's Elan sc520 CPU");
+
+module_init(sc520_freq_init);
+module_exit(sc520_freq_exit);
+

arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c

@@ -54,6 +54,8 @@ enum {
 	CPU_DOTHAN_A1,
 	CPU_DOTHAN_A2,
 	CPU_DOTHAN_B0,
+	CPU_MP4HT_D0,
+	CPU_MP4HT_E0,
 };
 
 static const struct cpu_id cpu_ids[] = {
@@ -61,6 +63,8 @@ static const struct cpu_id cpu_ids[] = {
 	[CPU_DOTHAN_A1]	= { 6, 13, 1 },
 	[CPU_DOTHAN_A2]	= { 6, 13, 2 },
 	[CPU_DOTHAN_B0]	= { 6, 13, 6 },
+	[CPU_MP4HT_D0]	= {15,  3, 4 },
+	[CPU_MP4HT_E0]	= {15,  4, 1 },
 };
 #define N_IDS	(sizeof(cpu_ids)/sizeof(cpu_ids[0]))
 
@@ -226,6 +230,8 @@ static struct cpu_model models[] =
 	{ &cpu_ids[CPU_DOTHAN_A1], NULL, 0, NULL },
 	{ &cpu_ids[CPU_DOTHAN_A2], NULL, 0, NULL },
 	{ &cpu_ids[CPU_DOTHAN_B0], NULL, 0, NULL },
+	{ &cpu_ids[CPU_MP4HT_D0], NULL, 0, NULL },
+	{ &cpu_ids[CPU_MP4HT_E0], NULL, 0, NULL },
 
 	{ NULL, }
 };

arch/i386/kernel/cpu/cpufreq/speedstep-lib.c

@@ -336,7 +336,7 @@ unsigned int speedstep_get_freqs(unsigned int processor,
 	if (!prev_speed)
 		return -EIO;
 
-	dprintk("previous seped is %u\n", prev_speed);
+	dprintk("previous speed is %u\n", prev_speed);
 	
 	local_irq_save(flags);
 
@@ -348,7 +348,7 @@ unsigned int speedstep_get_freqs(unsigned int processor,
 		goto out;
 	}
 
-	dprintk("low seped is %u\n", *low_speed);
+	dprintk("low speed is %u\n", *low_speed);
 
 	/* switch to high state */
 	set_state(SPEEDSTEP_HIGH);
@@ -358,7 +358,7 @@ unsigned int speedstep_get_freqs(unsigned int processor,
 		goto out;
 	}
 
-	dprintk("high seped is %u\n", *high_speed);
+	dprintk("high speed is %u\n", *high_speed);
 
 	if (*low_speed == *high_speed) {
 		ret = -ENODEV;

arch/i386/kernel/cpu/cpufreq/speedstep-smi.c

@@ -357,6 +357,9 @@ static int __init speedstep_init(void)
 	case SPEEDSTEP_PROCESSOR_PIII_C:
 	case SPEEDSTEP_PROCESSOR_PIII_C_EARLY:
 		break;
+	case SPEEDSTEP_PROCESSOR_P4M:
+		printk(KERN_INFO "speedstep-smi: you're trying to use this cpufreq driver on a Pentium 4-based CPU. Most likely it will not work.\n");
+		break;
 	default:
 		speedstep_processor = 0;
 	}

arch/i386/kernel/cpu/intel_cacheinfo.c

@@ -118,7 +118,7 @@ struct _cpuid4_info {
 };
 
 #define MAX_CACHE_LEAVES		4
-static unsigned short __devinitdata	num_cache_leaves;
+static unsigned short			num_cache_leaves;
 
 static int __devinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
 {

arch/i386/kernel/setup.c

@@ -1502,11 +1502,13 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled)
 		efi_map_memmap();
 
+#ifdef CONFIG_ACPI_BOOT
 	/*
 	 * Parse the ACPI tables for possible boot-time SMP configuration.
 	 */
 	acpi_boot_table_init();
 	acpi_boot_init();
+#endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (smp_found_config)

arch/i386/kernel/smpboot.c

@@ -1074,8 +1074,10 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 			cpu_set(cpu, cpu_sibling_map[cpu]);
 		}
 
-		if (siblings != smp_num_siblings)
+		if (siblings != smp_num_siblings) {
 			printk(KERN_WARNING "WARNING: %d siblings found for CPU%d, should be %d\n", siblings, cpu, smp_num_siblings);
+			smp_num_siblings = siblings;
+		}
 
 		if (c->x86_num_cores > 1) {
 			for (i = 0; i < NR_CPUS; i++) {

arch/i386/kernel/timers/common.c

@@ -6,6 +6,7 @@
 #include <linux/timex.h>
 #include <linux/errno.h>
 #include <linux/jiffies.h>
+#include <linux/module.h>
 
 #include <asm/io.h>
 #include <asm/timer.h>
@@ -24,7 +25,7 @@
 
 #define CALIBRATE_TIME	(5 * 1000020/HZ)
 
-unsigned long __init calibrate_tsc(void)
+unsigned long calibrate_tsc(void)
 {
 	mach_prepare_counter();
 
@@ -139,7 +140,7 @@ bad_calibration:
 #endif
 
 /* calculate cpu_khz */
-void __init init_cpu_khz(void)
+void init_cpu_khz(void)
 {
 	if (cpu_has_tsc) {
 		unsigned long tsc_quotient = calibrate_tsc();
@@ -158,3 +159,4 @@ void __init init_cpu_khz(void)
 		}
 	}
 }
+

arch/i386/kernel/timers/timer_tsc.c

@@ -320,6 +320,26 @@ core_initcall(cpufreq_tsc);
 static inline void cpufreq_delayed_get(void) { return; }
 #endif 
 
+int recalibrate_cpu_khz(void)
+{
+#ifndef CONFIG_SMP
+	unsigned long cpu_khz_old = cpu_khz;
+
+	if (cpu_has_tsc) {
+		init_cpu_khz();
+		cpu_data[0].loops_per_jiffy =
+		    cpufreq_scale(cpu_data[0].loops_per_jiffy,
+			          cpu_khz_old,
+				  cpu_khz);
+		return 0;
+	} else
+		return -ENODEV;
+#else
+	return -ENODEV;
+#endif
+}
+EXPORT_SYMBOL(recalibrate_cpu_khz);
+
 static void mark_offset_tsc(void)
 {
 	unsigned long lost,delay;

arch/ia64/ia32/sys_ia32.c

@@ -2427,7 +2427,7 @@ sys32_epoll_wait(int epfd, struct epoll_event32 __user * events, int maxevents,
 {
 	struct epoll_event *events64 = NULL;
 	mm_segment_t old_fs = get_fs();
-	int error, numevents, size;
+	int numevents, size;
 	int evt_idx;
 	int do_free_pages = 0;
 

arch/ia64/kernel/entry.S

@@ -1182,7 +1182,7 @@ ENTRY(notify_resume_user)
 	;;
 (pNonSys) mov out2=0				// out2==0 => not a syscall
 	.fframe 16
-	.spillpsp ar.unat, 16			// (note that offset is relative to psp+0x10!)
+	.spillsp ar.unat, 16
 	st8 [sp]=r9,-16				// allocate space for ar.unat and save it
 	st8 [out1]=loc1,-8			// save ar.pfs, out1=&sigscratch
 	.body
@@ -1208,7 +1208,7 @@ GLOBAL_ENTRY(sys_rt_sigsuspend)
 	adds out2=8,sp				// out2=&sigscratch->ar_pfs
 	;;
 	.fframe 16
-	.spillpsp ar.unat, 16			// (note that offset is relative to psp+0x10!)
+	.spillsp ar.unat, 16
 	st8 [sp]=r9,-16				// allocate space for ar.unat and save it
 	st8 [out2]=loc1,-8			// save ar.pfs, out2=&sigscratch
 	.body

arch/ia64/kernel/mca.c

@@ -1103,8 +1103,6 @@ ia64_mca_cpe_int_caller(int cpe_irq, void *arg, struct pt_regs *ptregs)
 	return IRQ_HANDLED;
 }
 
-#endif /* CONFIG_ACPI */
-
 /*
  *  ia64_mca_cpe_poll
  *
@@ -1122,6 +1120,8 @@ ia64_mca_cpe_poll (unsigned long dummy)
 	platform_send_ipi(first_cpu(cpu_online_map), IA64_CPEP_VECTOR, IA64_IPI_DM_INT, 0);
 }
 
+#endif /* CONFIG_ACPI */
+
 /*
  * C portion of the OS INIT handler
  *
@@ -1390,8 +1390,7 @@ ia64_mca_init(void)
 	register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, &mca_wkup_irqaction);
 
 #ifdef CONFIG_ACPI
-	/* Setup the CPEI/P vector and handler */
-	cpe_vector = acpi_request_vector(ACPI_INTERRUPT_CPEI);
+	/* Setup the CPEI/P handler */
 	register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction);
 #endif
 
@@ -1436,6 +1435,7 @@ ia64_mca_late_init(void)
 
 #ifdef CONFIG_ACPI
 	/* Setup the CPEI/P vector and handler */
+	cpe_vector = acpi_request_vector(ACPI_INTERRUPT_CPEI);
 	init_timer(&cpe_poll_timer);
 	cpe_poll_timer.function = ia64_mca_cpe_poll;
 

arch/ia64/kernel/minstate.h

@@ -41,7 +41,7 @@
 (pKStk) addl r3=THIS_CPU(ia64_mca_data),r3;;							\
 (pKStk) ld8 r3 = [r3];;										\
 (pKStk) addl r3=IA64_MCA_CPU_INIT_STACK_OFFSET,r3;;						\
-(pKStk) addl sp=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r3;						\
+(pKStk) addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r3;						\
 (pUStk)	mov ar.rsc=0;		/* set enforced lazy mode, pl 0, little-endian, loadrs=0 */	\
 (pUStk)	addl r22=IA64_RBS_OFFSET,r1;		/* compute base of register backing store */	\
 	;;											\
@@ -50,7 +50,6 @@
 (pUStk)	mov r23=ar.bspstore;				/* save ar.bspstore */			\
 (pUStk)	dep r22=-1,r22,61,3;			/* compute kernel virtual addr of RBS */	\
 	;;											\
-(pKStk) addl r1=-IA64_PT_REGS_SIZE,r1;		/* if in kernel mode, use sp (r12) */		\
 (pUStk)	mov ar.bspstore=r22;			/* switch to kernel RBS */			\
 	;;											\
 (pUStk)	mov r18=ar.bsp;										\

arch/ia64/kernel/perfmon.c

@@ -11,7 +11,7 @@
  * Version Perfmon-2.x is a rewrite of perfmon-1.x
  * by Stephane Eranian, Hewlett Packard Co.
  *
- * Copyright (C) 1999-2003, 2005  Hewlett Packard Co
+ * Copyright (C) 1999-2005  Hewlett Packard Co
  *               Stephane Eranian <eranian@hpl.hp.com>
  *               David Mosberger-Tang <davidm@hpl.hp.com>
  *
@@ -497,6 +497,9 @@ typedef struct {
 static pfm_stats_t		pfm_stats[NR_CPUS];
 static pfm_session_t		pfm_sessions;	/* global sessions information */
 
+static spinlock_t pfm_alt_install_check = SPIN_LOCK_UNLOCKED;
+static pfm_intr_handler_desc_t  *pfm_alt_intr_handler;
+
 static struct proc_dir_entry 	*perfmon_dir;
 static pfm_uuid_t		pfm_null_uuid = {0,};
 
@@ -606,6 +609,7 @@ DEFINE_PER_CPU(unsigned long, pfm_syst_info);
 DEFINE_PER_CPU(struct task_struct *, pmu_owner);
 DEFINE_PER_CPU(pfm_context_t  *, pmu_ctx);
 DEFINE_PER_CPU(unsigned long, pmu_activation_number);
+EXPORT_PER_CPU_SYMBOL_GPL(pfm_syst_info);
 
 
 /* forward declaration */
@@ -1325,7 +1329,7 @@ pfm_reserve_session(struct task_struct *task, int is_syswide, unsigned int cpu)
 error_conflict:
 	DPRINT(("system wide not possible, conflicting session [%d] on CPU%d\n",
   		pfm_sessions.pfs_sys_session[cpu]->pid,
-		smp_processor_id()));
+		cpu));
 abort:
 	UNLOCK_PFS(flags);
 
@@ -5555,26 +5559,32 @@ pfm_interrupt_handler(int irq, void *arg, struct pt_regs *regs)
 	int ret;
 
 	this_cpu = get_cpu();
-	min      = pfm_stats[this_cpu].pfm_ovfl_intr_cycles_min;
-	max      = pfm_stats[this_cpu].pfm_ovfl_intr_cycles_max;
+	if (likely(!pfm_alt_intr_handler)) {
+		min = pfm_stats[this_cpu].pfm_ovfl_intr_cycles_min;
+		max = pfm_stats[this_cpu].pfm_ovfl_intr_cycles_max;
 
-	start_cycles = ia64_get_itc();
+		start_cycles = ia64_get_itc();
 
-	ret = pfm_do_interrupt_handler(irq, arg, regs);
+		ret = pfm_do_interrupt_handler(irq, arg, regs);
 
-	total_cycles = ia64_get_itc();
+		total_cycles = ia64_get_itc();
 
-	/*
-	 * don't measure spurious interrupts
-	 */
-	if (likely(ret == 0)) {
-		total_cycles -= start_cycles;
+		/*
+		 * don't measure spurious interrupts
+		 */
+		if (likely(ret == 0)) {
+			total_cycles -= start_cycles;
 
-		if (total_cycles < min) pfm_stats[this_cpu].pfm_ovfl_intr_cycles_min = total_cycles;
-		if (total_cycles > max) pfm_stats[this_cpu].pfm_ovfl_intr_cycles_max = total_cycles;
+			if (total_cycles < min) pfm_stats[this_cpu].pfm_ovfl_intr_cycles_min = total_cycles;
+			if (total_cycles > max) pfm_stats[this_cpu].pfm_ovfl_intr_cycles_max = total_cycles;
 
-		pfm_stats[this_cpu].pfm_ovfl_intr_cycles += total_cycles;
+			pfm_stats[this_cpu].pfm_ovfl_intr_cycles += total_cycles;
+		}
+	}
+	else {
+		(*pfm_alt_intr_handler->handler)(irq, arg, regs);
 	}
+
 	put_cpu_no_resched();
 	return IRQ_HANDLED;
 }
@@ -6425,6 +6435,141 @@ static struct irqaction perfmon_irqaction = {
 	.name    = "perfmon"
 };
 
+static void
+pfm_alt_save_pmu_state(void *data)
+{
+	struct pt_regs *regs;
+
+	regs = ia64_task_regs(current);
+
+	DPRINT(("called\n"));
+
+	/*
+	 * should not be necessary but
+	 * let's take not risk
+	 */
+	pfm_clear_psr_up();
+	pfm_clear_psr_pp();
+	ia64_psr(regs)->pp = 0;
+
+	/*
+	 * This call is required
+	 * May cause a spurious interrupt on some processors
+	 */
+	pfm_freeze_pmu();
+
+	ia64_srlz_d();
+}
+
+void
+pfm_alt_restore_pmu_state(void *data)
+{
+	struct pt_regs *regs;
+
+	regs = ia64_task_regs(current);
+
+	DPRINT(("called\n"));
+
+	/*
+	 * put PMU back in state expected
+	 * by perfmon
+	 */
+	pfm_clear_psr_up();
+	pfm_clear_psr_pp();
+	ia64_psr(regs)->pp = 0;
+
+	/*
+	 * perfmon runs with PMU unfrozen at all times
+	 */
+	pfm_unfreeze_pmu();
+
+	ia64_srlz_d();
+}
+
+int
+pfm_install_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl)
+{
+	int ret, i;
+	int reserve_cpu;
+
+	/* some sanity checks */
+	if (hdl == NULL || hdl->handler == NULL) return -EINVAL;
+
+	/* do the easy test first */
+	if (pfm_alt_intr_handler) return -EBUSY;
+
+	/* one at a time in the install or remove, just fail the others */
+	if (!spin_trylock(&pfm_alt_install_check)) {
+		return -EBUSY;
+	}
+
+	/* reserve our session */
+	for_each_online_cpu(reserve_cpu) {
+		ret = pfm_reserve_session(NULL, 1, reserve_cpu);
+		if (ret) goto cleanup_reserve;
+	}
+
+	/* save the current system wide pmu states */
+	ret = on_each_cpu(pfm_alt_save_pmu_state, NULL, 0, 1);
+	if (ret) {
+		DPRINT(("on_each_cpu() failed: %d\n", ret));
+		goto cleanup_reserve;
+	}
+
+	/* officially change to the alternate interrupt handler */
+	pfm_alt_intr_handler = hdl;
+
+	spin_unlock(&pfm_alt_install_check);
+
+	return 0;
+
+cleanup_reserve:
+	for_each_online_cpu(i) {
+		/* don't unreserve more than we reserved */
+		if (i >= reserve_cpu) break;
+
+		pfm_unreserve_session(NULL, 1, i);
+	}
+
+	spin_unlock(&pfm_alt_install_check);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pfm_install_alt_pmu_interrupt);
+
+int
+pfm_remove_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl)
+{
+	int i;
+	int ret;
+
+	if (hdl == NULL) return -EINVAL;
+
+	/* cannot remove someone else's handler! */
+	if (pfm_alt_intr_handler != hdl) return -EINVAL;
+
+	/* one at a time in the install or remove, just fail the others */
+	if (!spin_trylock(&pfm_alt_install_check)) {
+		return -EBUSY;
+	}
+
+	pfm_alt_intr_handler = NULL;
+
+	ret = on_each_cpu(pfm_alt_restore_pmu_state, NULL, 0, 1);
+	if (ret) {
+		DPRINT(("on_each_cpu() failed: %d\n", ret));
+	}
+
+	for_each_online_cpu(i) {
+		pfm_unreserve_session(NULL, 1, i);
+	}
+
+	spin_unlock(&pfm_alt_install_check);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pfm_remove_alt_pmu_interrupt);
+
 /*
  * perfmon initialization routine, called from the initcall() table
  */

arch/ia64/kernel/ptrace.c

@@ -692,16 +692,30 @@ convert_to_non_syscall (struct task_struct *child, struct pt_regs  *pt,
 			unsigned long cfm)
 {
 	struct unw_frame_info info, prev_info;
-	unsigned long ip, pr;
+	unsigned long ip, sp, pr;
 
 	unw_init_from_blocked_task(&info, child);
 	while (1) {
 		prev_info = info;
 		if (unw_unwind(&info) < 0)
 			return;
-		if (unw_get_rp(&info, &ip) < 0)
+
+		unw_get_sp(&info, &sp);
+		if ((long)((unsigned long)child + IA64_STK_OFFSET - sp)
+		    < IA64_PT_REGS_SIZE) {
+			dprintk("ptrace.%s: ran off the top of the kernel "
+				"stack\n", __FUNCTION__);
+			return;
+		}
+		if (unw_get_pr (&prev_info, &pr) < 0) {
+			unw_get_rp(&prev_info, &ip);
+			dprintk("ptrace.%s: failed to read "
+				"predicate register (ip=0x%lx)\n",
+				__FUNCTION__, ip);
 			return;
-		if (ip < FIXADDR_USER_END)
+		}
+		if (unw_is_intr_frame(&info)
+		    && (pr & (1UL << PRED_USER_STACK)))
 			break;
 	}
 

arch/ia64/kernel/smpboot.c

@@ -624,7 +624,7 @@ static struct {
 	__u16   thread_id;
 	__u16   proc_fixed_addr;
 	__u8    valid;
-}mt_info[NR_CPUS] __devinit;
+} mt_info[NR_CPUS] __devinitdata;
 
 #ifdef CONFIG_HOTPLUG_CPU
 static inline void

arch/ia64/kernel/sys_ia64.c

@@ -182,13 +182,6 @@ do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, un
 		}
 	}
 
-	/*
-	 * A zero mmap always succeeds in Linux, independent of whether or not the
-	 * remaining arguments are valid.
-	 */
-	if (len == 0)
-		goto out;
-
 	/* Careful about overflows.. */
 	len = PAGE_ALIGN(len);
 	if (!len || len > TASK_SIZE) {

arch/ia64/sn/kernel/setup.c

@@ -271,6 +271,8 @@ void __init sn_setup(char **cmdline_p)
 	int major = sn_sal_rev_major(), minor = sn_sal_rev_minor();
 	extern void sn_cpu_init(void);
 
+	ia64_sn_plat_set_error_handling_features();
+
 	/*
 	 * If the generic code has enabled vga console support - lets
 	 * get rid of it again. This is a kludge for the fact that ACPI

arch/ppc/Kconfig

@@ -1143,12 +1143,12 @@ config PCI_QSPAN
 
 config PCI_8260
 	bool
-	depends on PCI && 8260 && !8272
+	depends on PCI && 8260
 	default y
 
 config 8260_PCI9
 	bool "  Enable workaround for MPC826x erratum PCI 9"
-	depends on PCI_8260
+	depends on PCI_8260 && !ADS8272
 	default y
 
 choice

arch/ppc/boot/images/Makefile

@@ -22,7 +22,8 @@ targets += uImage
 $(obj)/uImage: $(obj)/vmlinux.gz
 	$(Q)rm -f $@
 	$(call if_changed,uimage)
-	@echo '  Image: $@' $(if $(wildcard $@),'is ready','not made')
+	@echo -n '  Image: $@ '
+	@if [ -f $@ ]; then echo 'is ready' ; else echo 'not made'; fi
 
 # Files generated that shall be removed upon make clean
 clean-files	:= sImage vmapus vmlinux* miboot* zImage* uImage

arch/ppc/configs/mpc8555_cds_defconfig

@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.11-rc1
-# Thu Jan 20 01:25:35 2005
+# Linux kernel version: 2.6.12-rc4
+# Tue May 17 11:56:01 2005
 #
 CONFIG_MMU=y
 CONFIG_GENERIC_HARDIRQS=y
@@ -11,6 +11,7 @@ CONFIG_HAVE_DEC_LOCK=y
 CONFIG_PPC=y
 CONFIG_PPC32=y
 CONFIG_GENERIC_NVRAM=y
+CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
 
 #
 # Code maturity level options
@@ -18,6 +19,7 @@ CONFIG_GENERIC_NVRAM=y
 CONFIG_EXPERIMENTAL=y
 CONFIG_CLEAN_COMPILE=y
 CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
 
 #
 # General setup
@@ -29,12 +31,14 @@ CONFIG_SYSVIPC=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 CONFIG_SYSCTL=y
 # CONFIG_AUDIT is not set
-CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_HOTPLUG is not set
 CONFIG_KOBJECT_UEVENT=y
 # CONFIG_IKCONFIG is not set
 CONFIG_EMBEDDED=y
 # CONFIG_KALLSYMS is not set
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
 # CONFIG_EPOLL is not set
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
@@ -44,6 +48,7 @@ CONFIG_CC_ALIGN_LABELS=0
 CONFIG_CC_ALIGN_LOOPS=0
 CONFIG_CC_ALIGN_JUMPS=0
 # CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
 
 #
 # Loadable module support
@@ -62,10 +67,12 @@ CONFIG_CC_ALIGN_JUMPS=0
 CONFIG_E500=y
 CONFIG_BOOKE=y
 CONFIG_FSL_BOOKE=y
+# CONFIG_PHYS_64BIT is not set
 CONFIG_SPE=y
 CONFIG_MATH_EMULATION=y
 # CONFIG_CPU_FREQ is not set
 CONFIG_PPC_GEN550=y
+# CONFIG_PM is not set
 CONFIG_85xx=y
 CONFIG_PPC_INDIRECT_PCI_BE=y
 
@@ -76,6 +83,7 @@ CONFIG_PPC_INDIRECT_PCI_BE=y
 CONFIG_MPC8555_CDS=y
 # CONFIG_MPC8560_ADS is not set
 # CONFIG_SBC8560 is not set
+# CONFIG_STX_GP3 is not set
 CONFIG_MPC8555=y
 CONFIG_85xx_PCI2=y
 
@@ -90,6 +98,7 @@ CONFIG_CPM2=y
 CONFIG_BINFMT_ELF=y
 # CONFIG_BINFMT_MISC is not set
 # CONFIG_CMDLINE_BOOL is not set
+CONFIG_ISA_DMA_API=y
 
 #
 # Bus options
@@ -104,10 +113,6 @@ CONFIG_PCI_NAMES=y
 #
 # CONFIG_PCCARD is not set
 
-#
-# PC-card bridges
-#
-
 #
 # Advanced setup
 #
@@ -180,7 +185,59 @@ CONFIG_IOSCHED_CFQ=y
 #
 # ATA/ATAPI/MFM/RLL support
 #
-# CONFIG_IDE is not set
+CONFIG_IDE=y
+CONFIG_BLK_DEV_IDE=y
+
+#
+# Please see Documentation/ide.txt for help/info on IDE drives
+#
+# CONFIG_BLK_DEV_IDE_SATA is not set
+CONFIG_BLK_DEV_IDEDISK=y
+# CONFIG_IDEDISK_MULTI_MODE is not set
+# CONFIG_BLK_DEV_IDECD is not set
+# CONFIG_BLK_DEV_IDETAPE is not set
+# CONFIG_BLK_DEV_IDEFLOPPY is not set
+# CONFIG_IDE_TASK_IOCTL is not set
+
+#
+# IDE chipset support/bugfixes
+#
+CONFIG_IDE_GENERIC=y
+CONFIG_BLK_DEV_IDEPCI=y
+CONFIG_IDEPCI_SHARE_IRQ=y
+# CONFIG_BLK_DEV_OFFBOARD is not set
+CONFIG_BLK_DEV_GENERIC=y
+# CONFIG_BLK_DEV_OPTI621 is not set
+# CONFIG_BLK_DEV_SL82C105 is not set
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+CONFIG_IDEDMA_PCI_AUTO=y
+# CONFIG_IDEDMA_ONLYDISK is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+# CONFIG_BLK_DEV_CMD64X is not set
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CY82C693 is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_HPT34X is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+CONFIG_BLK_DEV_VIA82CXXX=y
+# CONFIG_IDE_ARM is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_IVB is not set
+CONFIG_IDEDMA_AUTO=y
+# CONFIG_BLK_DEV_HD is not set
 
 #
 # SCSI device support
@@ -220,7 +277,6 @@ CONFIG_NET=y
 #
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
-# CONFIG_NETLINK_DEV is not set
 CONFIG_UNIX=y
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
@@ -369,14 +425,6 @@ CONFIG_INPUT=y
 # CONFIG_INPUT_EVDEV is not set
 # CONFIG_INPUT_EVBUG is not set
 
-#
-# Input I/O drivers
-#
-# CONFIG_GAMEPORT is not set
-CONFIG_SOUND_GAMEPORT=y
-# CONFIG_SERIO is not set
-# CONFIG_SERIO_I8042 is not set
-
 #
 # Input Device Drivers
 #
@@ -386,6 +434,13 @@ CONFIG_SOUND_GAMEPORT=y
 # CONFIG_INPUT_TOUCHSCREEN is not set
 # CONFIG_INPUT_MISC is not set
 
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+CONFIG_SOUND_GAMEPORT=y
+
 #
 # Character devices
 #
@@ -406,6 +461,7 @@ CONFIG_SERIAL_8250_NR_UARTS=4
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_CPM is not set
+# CONFIG_SERIAL_JSM is not set
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
@@ -433,6 +489,11 @@ CONFIG_GEN_RTC=y
 # CONFIG_DRM is not set
 # CONFIG_RAW_DRIVER is not set
 
+#
+# TPM devices
+#
+# CONFIG_TCG_TPM is not set
+
 #
 # I2C support
 #
@@ -456,11 +517,11 @@ CONFIG_I2C_CHARDEV=y
 # CONFIG_I2C_AMD8111 is not set
 # CONFIG_I2C_I801 is not set
 # CONFIG_I2C_I810 is not set
+# CONFIG_I2C_PIIX4 is not set
 # CONFIG_I2C_ISA is not set
 CONFIG_I2C_MPC=y
 # CONFIG_I2C_NFORCE2 is not set
 # CONFIG_I2C_PARPORT_LIGHT is not set
-# CONFIG_I2C_PIIX4 is not set
 # CONFIG_I2C_PROSAVAGE is not set
 # CONFIG_I2C_SAVAGE4 is not set
 # CONFIG_SCx200_ACB is not set
@@ -483,7 +544,9 @@ CONFIG_I2C_MPC=y
 # CONFIG_SENSORS_ASB100 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_FSCHER is not set
+# CONFIG_SENSORS_FSCPOS is not set
 # CONFIG_SENSORS_GL518SM is not set
+# CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_IT87 is not set
 # CONFIG_SENSORS_LM63 is not set
 # CONFIG_SENSORS_LM75 is not set
@@ -494,9 +557,11 @@ CONFIG_I2C_MPC=y
 # CONFIG_SENSORS_LM85 is not set
 # CONFIG_SENSORS_LM87 is not set
 # CONFIG_SENSORS_LM90 is not set
+# CONFIG_SENSORS_LM92 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_SMSC47B397 is not set
+# CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
 # CONFIG_SENSORS_VIA686A is not set
 # CONFIG_SENSORS_W83781D is not set
@@ -506,10 +571,12 @@ CONFIG_I2C_MPC=y
 #
 # Other I2C Chip support
 #
+# CONFIG_SENSORS_DS1337 is not set
 # CONFIG_SENSORS_EEPROM is not set
 # CONFIG_SENSORS_PCF8574 is not set
 # CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_RTC8564 is not set
+# CONFIG_SENSORS_M41T00 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
 # CONFIG_I2C_DEBUG_ALGO is not set
 # CONFIG_I2C_DEBUG_BUS is not set
@@ -538,7 +605,6 @@ CONFIG_I2C_MPC=y
 # Graphics support
 #
 # CONFIG_FB is not set
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
 
 #
 # Sound
@@ -548,13 +614,9 @@ CONFIG_I2C_MPC=y
 #
 # USB support
 #
-# CONFIG_USB is not set
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
-
-#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information
-#
+# CONFIG_USB is not set
 
 #
 # USB Gadget Support
@@ -585,6 +647,10 @@ CONFIG_JBD=y
 CONFIG_FS_MBCACHE=y
 # CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
+
+#
+# XFS support
+#
 # CONFIG_XFS_FS is not set
 # CONFIG_MINIX_FS is not set
 # CONFIG_ROMFS_FS is not set
@@ -646,7 +712,6 @@ CONFIG_NFS_FS=y
 # CONFIG_NFSD is not set
 CONFIG_ROOT_NFS=y
 CONFIG_LOCKD=y
-# CONFIG_EXPORTFS is not set
 CONFIG_SUNRPC=y
 # CONFIG_RPCSEC_GSS_KRB5 is not set
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
@@ -698,7 +763,9 @@ CONFIG_CRC32=y
 #
 # Kernel hacking
 #
+# CONFIG_PRINTK_TIME is not set
 # CONFIG_DEBUG_KERNEL is not set
+CONFIG_LOG_BUF_SHIFT=14
 # CONFIG_KGDB_CONSOLE is not set
 # CONFIG_SERIAL_TEXT_DEBUG is not set
 

arch/ppc/kernel/head_fsl_booke.S

@@ -232,7 +232,8 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	tlbwe
 
 /* 7. Jump to KERNELBASE mapping */
-	li	r7,0
+	lis	r7,MSR_KERNEL@h
+	ori	r7,r7,MSR_KERNEL@l
 	bl	1f			/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
@@ -293,6 +294,18 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mtspr	SPRN_HID0, r2
 #endif
 
+#if !defined(CONFIG_BDI_SWITCH)
+	/*
+	 * The Abatron BDI JTAG debugger does not tolerate others
+	 * mucking with the debug registers.
+	 */
+	lis	r2,DBCR0_IDM@h
+	mtspr	SPRN_DBCR0,r2
+	/* clear any residual debug events */
+	li	r2,-1
+	mtspr	SPRN_DBSR,r2
+#endif
+
 	/*
 	 * This is where the main kernel code starts.
 	 */

arch/ppc/kernel/traps.c

@@ -408,12 +408,7 @@ static int emulate_string_inst(struct pt_regs *regs, u32 instword)
 
 	/* Early out if we are an invalid form of lswx */
 	if ((instword & INST_STRING_MASK) == INST_LSWX)
-		if ((rA >= rT) || (NB_RB >= rT) || (rT == rA) || (rT == NB_RB))
-			return -EINVAL;
-
-	/* Early out if we are an invalid form of lswi */
-	if ((instword & INST_STRING_MASK) == INST_LSWI)
-		if ((rA >= rT) || (rT == rA))
+		if ((rT == rA) || (rT == NB_RB))
 			return -EINVAL;
 
 	EA = (rA == 0) ? 0 : regs->gpr[rA];

arch/ppc/platforms/83xx/mpc834x_sys.c

@@ -127,7 +127,6 @@ mpc834x_sys_map_io(void)
 {
 	/* we steal the lowest ioremap addr for virt space */
 	io_block_mapping(VIRT_IMMRBAR, immrbar, 1024*1024, _PAGE_IO);
-	io_block_mapping(BCSR_VIRT_ADDR, BCSR_PHYS_ADDR, BCSR_SIZE, _PAGE_IO);
 }
 
 int

arch/ppc/platforms/83xx/mpc834x_sys.h

@@ -26,9 +26,14 @@
 #define VIRT_IMMRBAR		((uint)0xfe000000)
 
 #define BCSR_PHYS_ADDR		((uint)0xf8000000)
-#define BCSR_VIRT_ADDR		((uint)0xfe100000)
 #define BCSR_SIZE		((uint)(32 * 1024))
 
+#define BCSR_MISC_REG2_OFF	0x07
+#define BCSR_MISC_REG2_PORESET	0x01
+
+#define BCSR_MISC_REG3_OFF	0x08
+#define BCSR_MISC_REG3_CNFLOCK	0x80
+
 #ifdef CONFIG_PCI
 /* PCI interrupt controller */
 #define PIRQA        MPC83xx_IRQ_IRQ4

arch/ppc/platforms/85xx/mpc8540_ads.c

@@ -210,6 +210,9 @@ platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
 #if defined(CONFIG_SERIAL_8250) && defined(CONFIG_SERIAL_TEXT_DEBUG)
 	ppc_md.progress = gen550_progress;
 #endif	/* CONFIG_SERIAL_8250 && CONFIG_SERIAL_TEXT_DEBUG */
+#if defined(CONFIG_SERIAL_8250) && defined(CONFIG_KGDB)
+	ppc_md.early_serial_map = mpc85xx_early_serial_map;
+#endif	/* CONFIG_SERIAL_8250 && CONFIG_KGDB */
 
 	if (ppc_md.progress)
 		ppc_md.progress("mpc8540ads_init(): exit", 0);

arch/ppc/platforms/85xx/mpc85xx_cds_common.c

@@ -44,6 +44,7 @@
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/open_pic.h>
+#include <asm/i8259.h>
 #include <asm/bootinfo.h>
 #include <asm/pci-bridge.h>
 #include <asm/mpc85xx.h>
@@ -181,6 +182,7 @@ void __init
 mpc85xx_cds_init_IRQ(void)
 {
 	bd_t *binfo = (bd_t *) __res;
+	int i;
 
 	/* Determine the Physical Address of the OpenPIC regs */
 	phys_addr_t OpenPIC_PAddr = binfo->bi_immr_base + MPC85xx_OPENPIC_OFFSET;
@@ -198,6 +200,15 @@ mpc85xx_cds_init_IRQ(void)
 	 */
 	openpic_init(MPC85xx_OPENPIC_IRQ_OFFSET);
 
+#ifdef CONFIG_PCI
+	openpic_hookup_cascade(PIRQ0A, "82c59 cascade", i8259_irq);
+
+	for (i = 0; i < NUM_8259_INTERRUPTS; i++)
+		irq_desc[i].handler = &i8259_pic;
+
+	i8259_init(0);
+#endif
+
 #ifdef CONFIG_CPM2
 	/* Setup CPM2 PIC */
         cpm2_init_IRQ();
@@ -231,7 +242,7 @@ mpc85xx_map_irq(struct pci_dev *dev, unsigned char idsel, unsigned char pin)
 			 * interrupt on slot */
 		{
 			{ 0, 1, 2, 3 }, /* 16 - PMC */
-			{ 3, 0, 0, 0 }, /* 17 P2P (Tsi320) */
+			{ 0, 1, 2, 3 }, /* 17 P2P (Tsi320) */
 			{ 0, 1, 2, 3 }, /* 18 - Slot 1 */
 			{ 1, 2, 3, 0 }, /* 19 - Slot 2 */
 			{ 2, 3, 0, 1 }, /* 20 - Slot 3 */
@@ -280,13 +291,135 @@ mpc85xx_exclude_device(u_char bus, u_char devfn)
 			return PCIBIOS_DEVICE_NOT_FOUND;
 #endif
 	/* We explicitly do not go past the Tundra 320 Bridge */
-	if (bus == 1)
+	if ((bus == 1) && (PCI_SLOT(devfn) == ARCADIA_2ND_BRIDGE_IDSEL))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	if ((bus == 0) && (PCI_SLOT(devfn) == ARCADIA_2ND_BRIDGE_IDSEL))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	else
 		return PCIBIOS_SUCCESSFUL;
 }
+
+void __init
+mpc85xx_cds_enable_via(struct pci_controller *hose)
+{
+	u32 pci_class;
+	u16 vid, did;
+
+	early_read_config_dword(hose, 0, 0x88, PCI_CLASS_REVISION, &pci_class);
+	if ((pci_class >> 16) != PCI_CLASS_BRIDGE_PCI)
+		return;
+
+	/* Configure P2P so that we can reach bus 1 */
+	early_write_config_byte(hose, 0, 0x88, PCI_PRIMARY_BUS, 0);
+	early_write_config_byte(hose, 0, 0x88, PCI_SECONDARY_BUS, 1);
+	early_write_config_byte(hose, 0, 0x88, PCI_SUBORDINATE_BUS, 0xff);
+
+	early_read_config_word(hose, 1, 0x10, PCI_VENDOR_ID, &vid);
+	early_read_config_word(hose, 1, 0x10, PCI_DEVICE_ID, &did);
+
+	if ((vid != PCI_VENDOR_ID_VIA) ||
+			(did != PCI_DEVICE_ID_VIA_82C686))
+		return;
+
+	/* Enable USB and IDE functions */
+	early_write_config_byte(hose, 1, 0x10, 0x48, 0x08);
+}
+
+void __init
+mpc85xx_cds_fixup_via(struct pci_controller *hose)
+{
+	u32 pci_class;
+	u16 vid, did;
+
+	early_read_config_dword(hose, 0, 0x88, PCI_CLASS_REVISION, &pci_class);
+	if ((pci_class >> 16) != PCI_CLASS_BRIDGE_PCI)
+		return;
+
+	/*
+	 * Force the backplane P2P bridge to have a window
+	 * open from 0x00000000-0x00001fff in PCI I/O space.
+	 * This allows legacy I/O (i8259, etc) on the VIA
+	 * southbridge to be accessed.
+	 */
+	early_write_config_byte(hose, 0, 0x88, PCI_IO_BASE, 0x00);
+	early_write_config_word(hose, 0, 0x88, PCI_IO_BASE_UPPER16, 0x0000);
+	early_write_config_byte(hose, 0, 0x88, PCI_IO_LIMIT, 0x10);
+	early_write_config_word(hose, 0, 0x88, PCI_IO_LIMIT_UPPER16, 0x0000);
+
+	early_read_config_word(hose, 1, 0x10, PCI_VENDOR_ID, &vid);
+	early_read_config_word(hose, 1, 0x10, PCI_DEVICE_ID, &did);
+	if ((vid != PCI_VENDOR_ID_VIA) ||
+			(did != PCI_DEVICE_ID_VIA_82C686))
+		return;
+
+	/*
+	 * Since the P2P window was forced to cover the fixed
+	 * legacy I/O addresses, it is necessary to manually
+	 * place the base addresses for the IDE and USB functions
+	 * within this window.
+	 */
+	/* Function 1, IDE */
+	early_write_config_dword(hose, 1, 0x11, PCI_BASE_ADDRESS_0, 0x1ff8);
+	early_write_config_dword(hose, 1, 0x11, PCI_BASE_ADDRESS_1, 0x1ff4);
+	early_write_config_dword(hose, 1, 0x11, PCI_BASE_ADDRESS_2, 0x1fe8);
+	early_write_config_dword(hose, 1, 0x11, PCI_BASE_ADDRESS_3, 0x1fe4);
+	early_write_config_dword(hose, 1, 0x11, PCI_BASE_ADDRESS_4, 0x1fd0);
+
+	/* Function 2, USB ports 0-1 */
+	early_write_config_dword(hose, 1, 0x12, PCI_BASE_ADDRESS_4, 0x1fa0);
+
+	/* Function 3, USB ports 2-3 */
+	early_write_config_dword(hose, 1, 0x13, PCI_BASE_ADDRESS_4, 0x1f80);
+
+	/* Function 5, Power Management */
+	early_write_config_dword(hose, 1, 0x15, PCI_BASE_ADDRESS_0, 0x1e00);
+	early_write_config_dword(hose, 1, 0x15, PCI_BASE_ADDRESS_1, 0x1dfc);
+	early_write_config_dword(hose, 1, 0x15, PCI_BASE_ADDRESS_2, 0x1df8);
+
+	/* Function 6, AC97 Interface */
+	early_write_config_dword(hose, 1, 0x16, PCI_BASE_ADDRESS_0, 0x1c00);
+}
+
+void __init
+mpc85xx_cds_pcibios_fixup(void)
+{
+        struct pci_dev *dev = NULL;
+	u_char		c;
+
+        if ((dev = pci_find_device(PCI_VENDOR_ID_VIA,
+                                        PCI_DEVICE_ID_VIA_82C586_1, NULL))) {
+                /*
+                 * U-Boot does not set the enable bits
+                 * for the IDE device. Force them on here.
+                 */
+                pci_read_config_byte(dev, 0x40, &c);
+                c |= 0x03; /* IDE: Chip Enable Bits */
+                pci_write_config_byte(dev, 0x40, c);
+
+		/*
+		 * Since only primary interface works, force the
+		 * IDE function to standard primary IDE interrupt
+		 * w/ 8259 offset
+		 */
+                dev->irq = 14;
+                pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq);
+        }
+
+	/*
+	 * Force legacy USB interrupt routing
+	 */
+        if ((dev = pci_find_device(PCI_VENDOR_ID_VIA,
+                                        PCI_DEVICE_ID_VIA_82C586_2, NULL))) {
+                dev->irq = 10;
+                pci_write_config_byte(dev, PCI_INTERRUPT_LINE, 10);
+        }
+
+        if ((dev = pci_find_device(PCI_VENDOR_ID_VIA,
+                                        PCI_DEVICE_ID_VIA_82C586_2, dev))) {
+                dev->irq = 11;
+                pci_write_config_byte(dev, PCI_INTERRUPT_LINE, 11);
+        }
+}
 #endif /* CONFIG_PCI */
 
 TODC_ALLOC();
@@ -328,6 +461,9 @@ mpc85xx_cds_setup_arch(void)
 	loops_per_jiffy = freq / HZ;
 
 #ifdef CONFIG_PCI
+	/* VIA IDE configuration */
+        ppc_md.pcibios_fixup = mpc85xx_cds_pcibios_fixup;
+
 	/* setup PCI host bridges */
 	mpc85xx_setup_hose();
 #endif
@@ -459,6 +595,9 @@ platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
 #if defined(CONFIG_SERIAL_8250) && defined(CONFIG_SERIAL_TEXT_DEBUG)
 	ppc_md.progress = gen550_progress;
 #endif /* CONFIG_SERIAL_8250 && CONFIG_SERIAL_TEXT_DEBUG */
+#if defined(CONFIG_SERIAL_8250) && defined(CONFIG_KGDB)
+	ppc_md.early_serial_map = mpc85xx_early_serial_map;
+#endif	/* CONFIG_SERIAL_8250 && CONFIG_KGDB */
 
 	if (ppc_md.progress)
 		ppc_md.progress("mpc85xx_cds_init(): exit", 0);

arch/ppc/platforms/85xx/mpc85xx_cds_common.h

@@ -77,4 +77,7 @@
 
 #define MPC85XX_PCI2_IO_SIZE         0x01000000
 
+#define NR_8259_INTS		     16
+#define CPM_IRQ_OFFSET		     NR_8259_INTS
+
 #endif /* __MACH_MPC85XX_CDS_H__ */

arch/ppc/platforms/85xx/sbc8560.c

@@ -221,6 +221,9 @@ platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
 #if defined(CONFIG_SERIAL_8250) && defined(CONFIG_SERIAL_TEXT_DEBUG)
 	ppc_md.progress = gen550_progress;
 #endif	/* CONFIG_SERIAL_8250 && CONFIG_SERIAL_TEXT_DEBUG */
+#if defined(CONFIG_SERIAL_8250) && defined(CONFIG_KGDB)
+	ppc_md.early_serial_map = sbc8560_early_serial_map;
+#endif	/* CONFIG_SERIAL_8250 && CONFIG_KGDB */
 
 	if (ppc_md.progress)
 		ppc_md.progress("sbc8560_init(): exit", 0);

arch/ppc/platforms/pmac_cpufreq.c

@@ -85,14 +85,11 @@ static int no_schedule;
 static int has_cpu_l2lve;
 
 
-#define PMAC_CPU_LOW_SPEED	1
-#define PMAC_CPU_HIGH_SPEED	0
-
 /* There are only two frequency states for each processor. Values
  * are in kHz for the time being.
  */
-#define CPUFREQ_HIGH                  PMAC_CPU_HIGH_SPEED
-#define CPUFREQ_LOW                   PMAC_CPU_LOW_SPEED
+#define CPUFREQ_HIGH                  0
+#define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table pmac_cpu_freqs[] = {
 	{CPUFREQ_HIGH, 		0},
@@ -100,6 +97,11 @@ static struct cpufreq_frequency_table pmac_cpu_freqs[] = {
 	{0,			CPUFREQ_TABLE_END},
 };
 
+static struct freq_attr* pmac_cpu_freqs_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
 static inline void local_delay(unsigned long ms)
 {
 	if (no_schedule)
@@ -269,6 +271,8 @@ static int __pmac pmu_set_cpu_speed(int low_speed)
 #ifdef DEBUG_FREQ
 	printk(KERN_DEBUG "HID1, before: %x\n", mfspr(SPRN_HID1));
 #endif
+	pmu_suspend();
+
 	/* Disable all interrupt sources on openpic */
  	pic_prio = openpic_get_priority();
 	openpic_set_priority(0xf);
@@ -343,6 +347,8 @@ static int __pmac pmu_set_cpu_speed(int low_speed)
 	debug_calc_bogomips();
 #endif
 
+	pmu_resume();
+
 	preempt_enable();
 
 	return 0;
@@ -355,7 +361,7 @@ static int __pmac do_set_cpu_speed(int speed_mode, int notify)
 	static unsigned long prev_l3cr;
 
 	freqs.old = cur_freq;
-	freqs.new = (speed_mode == PMAC_CPU_HIGH_SPEED) ? hi_freq : low_freq;
+	freqs.new = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq;
 	freqs.cpu = smp_processor_id();
 
 	if (freqs.old == freqs.new)
@@ -363,7 +369,7 @@ static int __pmac do_set_cpu_speed(int speed_mode, int notify)
 
 	if (notify)
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-	if (speed_mode == PMAC_CPU_LOW_SPEED &&
+	if (speed_mode == CPUFREQ_LOW &&
 	    cpu_has_feature(CPU_FTR_L3CR)) {
 		l3cr = _get_L3CR();
 		if (l3cr & L3CR_L3E) {
@@ -371,8 +377,8 @@ static int __pmac do_set_cpu_speed(int speed_mode, int notify)
 			_set_L3CR(0);
 		}
 	}
-	set_speed_proc(speed_mode == PMAC_CPU_LOW_SPEED);
-	if (speed_mode == PMAC_CPU_HIGH_SPEED &&
+	set_speed_proc(speed_mode == CPUFREQ_LOW);
+	if (speed_mode == CPUFREQ_HIGH &&
 	    cpu_has_feature(CPU_FTR_L3CR)) {
 		l3cr = _get_L3CR();
 		if ((prev_l3cr & L3CR_L3E) && l3cr != prev_l3cr)
@@ -380,7 +386,7 @@ static int __pmac do_set_cpu_speed(int speed_mode, int notify)
 	}
 	if (notify)
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-	cur_freq = (speed_mode == PMAC_CPU_HIGH_SPEED) ? hi_freq : low_freq;
+	cur_freq = (speed_mode == CPUFREQ_HIGH) ? hi_freq : low_freq;
 
 	return 0;
 }
@@ -423,7 +429,8 @@ static int __pmac pmac_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency	= CPUFREQ_ETERNAL;
 	policy->cur = cur_freq;
 
-	return cpufreq_frequency_table_cpuinfo(policy, &pmac_cpu_freqs[0]);
+	cpufreq_frequency_table_get_attr(pmac_cpu_freqs, policy->cpu);
+	return cpufreq_frequency_table_cpuinfo(policy, pmac_cpu_freqs);
 }
 
 static u32 __pmac read_gpio(struct device_node *np)
@@ -457,7 +464,7 @@ static int __pmac pmac_cpufreq_suspend(struct cpufreq_policy *policy, u32 state)
 	no_schedule = 1;
 	sleep_freq = cur_freq;
 	if (cur_freq == low_freq)
-		do_set_cpu_speed(PMAC_CPU_HIGH_SPEED, 0);
+		do_set_cpu_speed(CPUFREQ_HIGH, 0);
 	return 0;
 }
 
@@ -473,8 +480,8 @@ static int __pmac pmac_cpufreq_resume(struct cpufreq_policy *policy)
 	 * is that we force a switch to whatever it was, which is
 	 * probably high speed due to our suspend() routine
 	 */
-	do_set_cpu_speed(sleep_freq == low_freq ? PMAC_CPU_LOW_SPEED
-			 : PMAC_CPU_HIGH_SPEED, 0);
+	do_set_cpu_speed(sleep_freq == low_freq ?
+			 CPUFREQ_LOW : CPUFREQ_HIGH, 0);
 
 	no_schedule = 0;
 	return 0;
@@ -488,6 +495,7 @@ static struct cpufreq_driver pmac_cpufreq_driver = {
 	.suspend	= pmac_cpufreq_suspend,
 	.resume		= pmac_cpufreq_resume,
 	.flags		= CPUFREQ_PM_NO_WARN,
+	.attr		= pmac_cpu_freqs_attr,
 	.name		= "powermac",
 	.owner		= THIS_MODULE,
 };

arch/ppc/platforms/pq2ads.h

@@ -49,10 +49,10 @@
 /* PCI interrupt controller */
 #define PCI_INT_STAT_REG	0xF8200000
 #define PCI_INT_MASK_REG	0xF8200004
-#define PIRQA			(NR_SIU_INTS + 0)
-#define PIRQB			(NR_SIU_INTS + 1)
-#define PIRQC			(NR_SIU_INTS + 2)
-#define PIRQD			(NR_SIU_INTS + 3)
+#define PIRQA			(NR_CPM_INTS + 0)
+#define PIRQB			(NR_CPM_INTS + 1)
+#define PIRQC			(NR_CPM_INTS + 2)
+#define PIRQD			(NR_CPM_INTS + 3)
 
 /*
  * PCI memory map definitions for MPC8266ADS-PCI.
@@ -68,28 +68,23 @@
  *	0x00000000-0x1FFFFFFF	0x00000000-0x1FFFFFFF	MPC8266 local memory
  */
 
-/* window for a PCI master to access MPC8266 memory */
-#define PCI_SLV_MEM_LOCAL	0x00000000	/* Local base */
-#define PCI_SLV_MEM_BUS		0x00000000	/* PCI base */
+/* All the other PCI memory map definitions reside at syslib/m82xx_pci.h
+   Here we should redefine what is unique for this board */
+#define M82xx_PCI_SLAVE_MEM_LOCAL	0x00000000	/* Local base */
+#define M82xx_PCI_SLAVE_MEM_BUS		0x00000000	/* PCI base */
+#define M82xx_PCI_SLAVE_MEM_SIZE	0x10000000	/* 256 Mb */
 
-/* window for the processor to access PCI memory with prefetching */
-#define PCI_MSTR_MEM_LOCAL	0x80000000	/* Local base */
-#define PCI_MSTR_MEM_BUS	0x80000000	/* PCI base   */
-#define PCI_MSTR_MEM_SIZE	0x20000000	/* 512MB */
+#define M82xx_PCI_SLAVE_SEC_WND_SIZE	~(0x40000000 - 1U)	/* 2 x 512Mb  */
+#define M82xx_PCI_SLAVE_SEC_WND_BASE	0x80000000		/* PCI Memory base */
 
-/* window for the processor to access PCI memory without prefetching */
-#define PCI_MSTR_MEMIO_LOCAL	0xA0000000	/* Local base */
-#define PCI_MSTR_MEMIO_BUS	0xA0000000	/* PCI base   */
-#define PCI_MSTR_MEMIO_SIZE	0x20000000	/* 512MB */
+#if defined(CONFIG_ADS8272)
+#define PCI_INT_TO_SIU 	SIU_INT_IRQ2
+#elif defined(CONFIG_PQ2FADS)
+#define PCI_INT_TO_SIU 	SIU_INT_IRQ6
+#else
+#warning PCI Bridge will be without interrupts support
+#endif
 
-/* window for the processor to access PCI I/O */
-#define PCI_MSTR_IO_LOCAL	0xF4000000	/* Local base */
-#define PCI_MSTR_IO_BUS         0x00000000	/* PCI base   */
-#define PCI_MSTR_IO_SIZE        0x04000000	/* 64MB */
-
-#define _IO_BASE		PCI_MSTR_IO_LOCAL
-#define _ISA_MEM_BASE		PCI_MSTR_MEMIO_LOCAL
-#define PCI_DRAM_OFFSET		PCI_SLV_MEM_BUS
 #endif /* CONFIG_PCI */
 
 #endif /* __MACH_ADS8260_DEFS */

arch/ppc/syslib/Makefile

@@ -81,7 +81,7 @@ obj-$(CONFIG_SBC82xx)		+= todc_time.o
 obj-$(CONFIG_SPRUCE)		+= cpc700_pic.o indirect_pci.o pci_auto.o \
 				   todc_time.o
 obj-$(CONFIG_8260)		+= m8260_setup.o
-obj-$(CONFIG_PCI_8260)		+= m8260_pci.o indirect_pci.o
+obj-$(CONFIG_PCI_8260)		+= m82xx_pci.o indirect_pci.o pci_auto.o
 obj-$(CONFIG_8260_PCI9)		+= m8260_pci_erratum9.o
 obj-$(CONFIG_CPM2)		+= cpm2_common.o cpm2_pic.o
 ifeq ($(CONFIG_PPC_GEN550),y)
@@ -97,7 +97,7 @@ obj-$(CONFIG_MPC10X_OPENPIC)	+= open_pic.o
 obj-$(CONFIG_40x)		+= dcr.o
 obj-$(CONFIG_BOOKE)		+= dcr.o
 obj-$(CONFIG_85xx)		+= open_pic.o ppc85xx_common.o ppc85xx_setup.o \
-					ppc_sys.o mpc85xx_sys.o \
+					ppc_sys.o i8259.o mpc85xx_sys.o \
 					mpc85xx_devices.o
 ifeq ($(CONFIG_85xx),y)
 obj-$(CONFIG_PCI)		+= indirect_pci.o pci_auto.o

arch/ppc/syslib/m8260_pci.c

@@ -1,193 +0,0 @@
-/*
- * (C) Copyright 2003
- * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
- *
- * (C) Copyright 2004 Red Hat, Inc.
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- * MA 02111-1307 USA
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-
-#include <asm/byteorder.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/uaccess.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/immap_cpm2.h>
-#include <asm/mpc8260.h>
-
-#include "m8260_pci.h"
-
-
-/* PCI bus configuration registers.
- */
-
-static void __init m8260_setup_pci(struct pci_controller *hose)
-{
-	volatile cpm2_map_t *immap = cpm2_immr;
-	unsigned long pocmr;
-	u16 tempShort;
-
-#ifndef CONFIG_ATC 	/* already done in U-Boot */
-	/* 
-	 * Setting required to enable IRQ1-IRQ7 (SIUMCR [DPPC]), 
-	 * and local bus for PCI (SIUMCR [LBPC]).
-	 */
-	immap->im_siu_conf.siu_82xx.sc_siumcr = 0x00640000;
-#endif
-
-	/* Make PCI lowest priority */
-	/* Each 4 bits is a device bus request  and the MS 4bits 
-	   is highest priority */
-	/* Bus               4bit value 
-	   ---               ----------
-	   CPM high          0b0000
-	   CPM middle        0b0001
-	   CPM low           0b0010
-	   PCI reguest       0b0011
-	   Reserved          0b0100
-	   Reserved          0b0101
-	   Internal Core     0b0110
-	   External Master 1 0b0111
-	   External Master 2 0b1000
-	   External Master 3 0b1001
-	   The rest are reserved */
-	immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x61207893;
-
-	/* Park bus on core while modifying PCI Bus accesses */
-	immap->im_siu_conf.siu_82xx.sc_ppc_acr = 0x6;
-
-	/* 
-	 * Set up master window that allows the CPU to access PCI space. This 
-	 * window is set up using the first SIU PCIBR registers.
-	 */
-	immap->im_memctl.memc_pcimsk0 = MPC826x_PCI_MASK;
-	immap->im_memctl.memc_pcibr0 =	MPC826x_PCI_BASE | PCIBR_ENABLE;
-
-	/* Disable machine check on no response or target abort */
-	immap->im_pci.pci_emr = cpu_to_le32(0x1fe7);
-	/* Release PCI RST (by default the PCI RST signal is held low)  */
-	immap->im_pci.pci_gcr = cpu_to_le32(PCIGCR_PCI_BUS_EN);
-
-	/* give it some time */
-	mdelay(1);
-
-	/* 
-	 * Set up master window that allows the CPU to access PCI Memory (prefetch) 
-	 * space. This window is set up using the first set of Outbound ATU registers.
-	 */
-	immap->im_pci.pci_potar0 = cpu_to_le32(MPC826x_PCI_LOWER_MEM >> 12);
-	immap->im_pci.pci_pobar0 = cpu_to_le32((MPC826x_PCI_LOWER_MEM - MPC826x_PCI_MEM_OFFSET) >> 12);
-	pocmr = ((MPC826x_PCI_UPPER_MEM - MPC826x_PCI_LOWER_MEM) >> 12) ^ 0xfffff;
-	immap->im_pci.pci_pocmr0 = cpu_to_le32(pocmr | POCMR_ENABLE | POCMR_PREFETCH_EN);
-
-	/* 
-	 * Set up master window that allows the CPU to access PCI Memory (non-prefetch) 
-	 * space. This window is set up using the second set of Outbound ATU registers.
-	 */
-	immap->im_pci.pci_potar1 = cpu_to_le32(MPC826x_PCI_LOWER_MMIO >> 12);
-	immap->im_pci.pci_pobar1 = cpu_to_le32((MPC826x_PCI_LOWER_MMIO - MPC826x_PCI_MMIO_OFFSET) >> 12);
-	pocmr = ((MPC826x_PCI_UPPER_MMIO - MPC826x_PCI_LOWER_MMIO) >> 12) ^ 0xfffff;
-	immap->im_pci.pci_pocmr1 = cpu_to_le32(pocmr | POCMR_ENABLE);
-
-	/* 
-	 * Set up master window that allows the CPU to access PCI IO space. This window
-	 * is set up using the third set of Outbound ATU registers.
-	 */
-	immap->im_pci.pci_potar2 = cpu_to_le32(MPC826x_PCI_IO_BASE >> 12);
-	immap->im_pci.pci_pobar2 = cpu_to_le32(MPC826x_PCI_LOWER_IO >> 12);
-	pocmr = ((MPC826x_PCI_UPPER_IO - MPC826x_PCI_LOWER_IO) >> 12) ^ 0xfffff;
-	immap->im_pci.pci_pocmr2 = cpu_to_le32(pocmr | POCMR_ENABLE | POCMR_PCI_IO);
-
-	/* 
-	 * Set up slave window that allows PCI masters to access MPC826x local memory. 
-	 * This window is set up using the first set of Inbound ATU registers
-	 */
-
-	immap->im_pci.pci_pitar0 = cpu_to_le32(MPC826x_PCI_SLAVE_MEM_LOCAL >> 12);
-	immap->im_pci.pci_pibar0 = cpu_to_le32(MPC826x_PCI_SLAVE_MEM_BUS >> 12);
-	pocmr = ((MPC826x_PCI_SLAVE_MEM_SIZE-1) >> 12) ^ 0xfffff;
-	immap->im_pci.pci_picmr0 = cpu_to_le32(pocmr | PICMR_ENABLE | PICMR_PREFETCH_EN);
-
-	/* See above for description - puts PCI request as highest priority */
-	immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x03124567;
-
-	/* Park the bus on the PCI */
-	immap->im_siu_conf.siu_82xx.sc_ppc_acr = PPC_ACR_BUS_PARK_PCI;
-
-	/* Host mode - specify the bridge as a host-PCI bridge */
-	early_write_config_word(hose, 0, 0, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_HOST);
-
-	/* Enable the host bridge to be a master on the PCI bus, and to act as a PCI memory target */
-	early_read_config_word(hose, 0, 0, PCI_COMMAND, &tempShort);
-	early_write_config_word(hose, 0, 0, PCI_COMMAND,
-				tempShort | PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY);
-}
-
-void __init m8260_find_bridges(void)
-{
-	extern int pci_assign_all_busses;
-	struct pci_controller * hose;
-
-	pci_assign_all_busses = 1;
-
-	hose = pcibios_alloc_controller();
-
-	if (!hose)
-		return;
-
-	ppc_md.pci_swizzle = common_swizzle;
-
-	hose->first_busno = 0;
-	hose->bus_offset = 0;
-	hose->last_busno = 0xff;
-
-	setup_m8260_indirect_pci(hose, 
-				 (unsigned long)&cpm2_immr->im_pci.pci_cfg_addr,
-				 (unsigned long)&cpm2_immr->im_pci.pci_cfg_data);
-
-	m8260_setup_pci(hose);
-        hose->pci_mem_offset = MPC826x_PCI_MEM_OFFSET;
-
-        hose->io_base_virt = ioremap(MPC826x_PCI_IO_BASE,
-                                        MPC826x_PCI_IO_SIZE);
-        isa_io_base = (unsigned long) hose->io_base_virt;
- 
-        /* setup resources */
-        pci_init_resource(&hose->mem_resources[0],
-			  MPC826x_PCI_LOWER_MEM,
-			  MPC826x_PCI_UPPER_MEM,
-			  IORESOURCE_MEM|IORESOURCE_PREFETCH, "PCI prefetchable memory");
-
-        pci_init_resource(&hose->mem_resources[1],
-			  MPC826x_PCI_LOWER_MMIO,
-			  MPC826x_PCI_UPPER_MMIO,
-			  IORESOURCE_MEM, "PCI memory");
-
-        pci_init_resource(&hose->io_resource,
-			  MPC826x_PCI_LOWER_IO,
-			  MPC826x_PCI_UPPER_IO,
-			  IORESOURCE_IO, "PCI I/O");
-}

arch/ppc/syslib/m8260_pci.h

@@ -1,76 +0,0 @@
-
-#ifndef _PPC_KERNEL_M8260_PCI_H
-#define _PPC_KERNEL_M8260_PCI_H
-
-#include <asm/m8260_pci.h>
-
-/*
- *   Local->PCI map (from CPU)                             controlled by
- *   MPC826x master window
- *
- *   0x80000000 - 0xBFFFFFFF    Total CPU2PCI space        PCIBR0
- *                       
- *   0x80000000 - 0x9FFFFFFF    PCI Mem with prefetch      (Outbound ATU #1)
- *   0xA0000000 - 0xAFFFFFFF    PCI Mem w/o  prefetch      (Outbound ATU #2)
- *   0xB0000000 - 0xB0FFFFFF    32-bit PCI IO              (Outbound ATU #3)
- *                      
- *   PCI->Local map (from PCI)
- *   MPC826x slave window                                  controlled by
- *
- *   0x00000000 - 0x07FFFFFF    MPC826x local memory       (Inbound ATU #1)
- */
-
-/* 
- * Slave window that allows PCI masters to access MPC826x local memory. 
- * This window is set up using the first set of Inbound ATU registers
- */
-
-#ifndef MPC826x_PCI_SLAVE_MEM_LOCAL
-#define MPC826x_PCI_SLAVE_MEM_LOCAL	(((struct bd_info *)__res)->bi_memstart)
-#define MPC826x_PCI_SLAVE_MEM_BUS	(((struct bd_info *)__res)->bi_memstart)
-#define MPC826x_PCI_SLAVE_MEM_SIZE	(((struct bd_info *)__res)->bi_memsize)
-#endif
-
-/* 
- * This is the window that allows the CPU to access PCI address space.
- * It will be setup with the SIU PCIBR0 register. All three PCI master
- * windows, which allow the CPU to access PCI prefetch, non prefetch,
- * and IO space (see below), must all fit within this window. 
- */
-#ifndef MPC826x_PCI_BASE
-#define MPC826x_PCI_BASE	0x80000000
-#define MPC826x_PCI_MASK	0xc0000000
-#endif
-
-#ifndef MPC826x_PCI_LOWER_MEM
-#define MPC826x_PCI_LOWER_MEM  0x80000000
-#define MPC826x_PCI_UPPER_MEM  0x9fffffff
-#define MPC826x_PCI_MEM_OFFSET 0x00000000
-#endif
-
-#ifndef MPC826x_PCI_LOWER_MMIO
-#define MPC826x_PCI_LOWER_MMIO  0xa0000000
-#define MPC826x_PCI_UPPER_MMIO  0xafffffff
-#define MPC826x_PCI_MMIO_OFFSET 0x00000000
-#endif
-
-#ifndef MPC826x_PCI_LOWER_IO
-#define MPC826x_PCI_LOWER_IO   0x00000000
-#define MPC826x_PCI_UPPER_IO   0x00ffffff
-#define MPC826x_PCI_IO_BASE    0xb0000000
-#define MPC826x_PCI_IO_SIZE    0x01000000
-#endif
-
-#ifndef _IO_BASE
-#define _IO_BASE isa_io_base
-#endif
-
-#ifdef CONFIG_8260_PCI9
-struct pci_controller;
-extern void setup_m8260_indirect_pci(struct pci_controller* hose,
-				     u32 cfg_addr, u32 cfg_data);
-#else
-#define setup_m8260_indirect_pci setup_indirect_pci
-#endif
-
-#endif /* _PPC_KERNEL_M8260_PCI_H */

arch/ppc/syslib/m8260_pci_erratum9.c

@@ -31,7 +31,7 @@
 #include <asm/immap_cpm2.h>
 #include <asm/cpm2.h>
 
-#include "m8260_pci.h"
+#include "m82xx_pci.h"
 
 #ifdef CONFIG_8260_PCI9
 /*#include <asm/mpc8260_pci9.h>*/ /* included in asm/io.h */
@@ -248,11 +248,11 @@ EXPORT_SYMBOL(idma_pci9_read_le);
 
 static inline int is_pci_mem(unsigned long addr)
 {
-	if (addr >= MPC826x_PCI_LOWER_MMIO &&
-	    addr <= MPC826x_PCI_UPPER_MMIO)
+	if (addr >= M82xx_PCI_LOWER_MMIO &&
+		addr <= M82xx_PCI_UPPER_MMIO)
 		return 1;
-	if (addr >= MPC826x_PCI_LOWER_MEM &&
-	    addr <= MPC826x_PCI_UPPER_MEM)
+	if (addr >= M82xx_PCI_LOWER_MEM &&
+		addr <= M82xx_PCI_UPPER_MEM)
 		return 1;
 	return 0;
 }

arch/ppc/syslib/m8260_setup.c

@@ -34,7 +34,8 @@
 unsigned char __res[sizeof(bd_t)];
 
 extern void cpm2_reset(void);
-extern void m8260_find_bridges(void);
+extern void pq2_find_bridges(void);
+extern void pq2pci_init_irq(void);
 extern void idma_pci9_init(void);
 
 /* Place-holder for board-specific init */
@@ -56,7 +57,7 @@ m8260_setup_arch(void)
 	idma_pci9_init();
 #endif
 #ifdef CONFIG_PCI_8260
-	m8260_find_bridges();
+	pq2_find_bridges();
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
@@ -173,6 +174,12 @@ m8260_init_IRQ(void)
 	 * in case the boot rom changed something on us.
 	 */
 	cpm2_immr->im_intctl.ic_siprr = 0x05309770;
+
+#if defined(CONFIG_PCI) && (defined(CONFIG_ADS8272) || defined(CONFIG_PQ2FADS))
+ 	/* Initialize stuff for the 82xx CPLD IC and install demux  */
+ 	pq2pci_init_irq();
+#endif
+
 }
 
 /*

arch/ppc/syslib/m82xx_pci.c

@@ -0,0 +1,383 @@
+/*
+ *
+ * (C) Copyright 2003
+ * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
+ *
+ * (C) Copyright 2004 Red Hat, Inc.
+ *
+ * 2005 (c) MontaVista Software, Inc.
+ * Vitaly Bordug <vbordug@ru.mvista.com>
+ *
+ * See file CREDITS for list of people who contributed to this
+ * project.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include <asm/byteorder.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/uaccess.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <asm/immap_cpm2.h>
+#include <asm/mpc8260.h>
+#include <asm/cpm2.h>
+
+#include "m82xx_pci.h"
+
+/*
+ * Interrupt routing
+ */
+
+static inline int
+pq2pci_map_irq(struct pci_dev *dev, unsigned char idsel, unsigned char pin)
+{
+	static char pci_irq_table[][4] =
+	/*
+	 *	PCI IDSEL/INTPIN->INTLINE
+	 * 	  A      B      C      D
+	 */
+	{
+		{ PIRQA, PIRQB, PIRQC, PIRQD },	/* IDSEL 22 - PCI slot 0 */
+		{ PIRQD, PIRQA, PIRQB, PIRQC },	/* IDSEL 23 - PCI slot 1 */
+		{ PIRQC, PIRQD, PIRQA, PIRQB },	/* IDSEL 24 - PCI slot 2 */
+	};
+
+	const long min_idsel = 22, max_idsel = 24, irqs_per_slot = 4;
+	return PCI_IRQ_TABLE_LOOKUP;
+}
+
+static void
+pq2pci_mask_irq(unsigned int irq)
+{
+	int bit = irq - NR_CPM_INTS;
+
+	*(volatile unsigned long *) PCI_INT_MASK_REG |= (1 << (31 - bit));
+	return;
+}
+
+static void
+pq2pci_unmask_irq(unsigned int irq)
+{
+	int bit = irq - NR_CPM_INTS;
+
+	*(volatile unsigned long *) PCI_INT_MASK_REG &= ~(1 << (31 - bit));
+	return;
+}
+
+static void
+pq2pci_mask_and_ack(unsigned int irq)
+{
+	int bit = irq - NR_CPM_INTS;
+
+	*(volatile unsigned long *) PCI_INT_MASK_REG |= (1 << (31 - bit));
+	return;
+}
+
+static void
+pq2pci_end_irq(unsigned int irq)
+{
+	int bit = irq - NR_CPM_INTS;
+
+	*(volatile unsigned long *) PCI_INT_MASK_REG &= ~(1 << (31 - bit));
+	return;
+}
+
+struct hw_interrupt_type pq2pci_ic = {
+	"PQ2 PCI",
+	NULL,
+	NULL,
+	pq2pci_unmask_irq,
+	pq2pci_mask_irq,
+	pq2pci_mask_and_ack,
+	pq2pci_end_irq,
+	0
+};
+
+static irqreturn_t
+pq2pci_irq_demux(int irq, void *dev_id, struct pt_regs *regs)
+{
+	unsigned long stat, mask, pend;
+	int bit;
+
+	for(;;) {
+		stat = *(volatile unsigned long *) PCI_INT_STAT_REG;
+		mask = *(volatile unsigned long *) PCI_INT_MASK_REG;
+		pend = stat & ~mask & 0xf0000000;
+		if (!pend)
+			break;
+		for (bit = 0; pend != 0; ++bit, pend <<= 1) {
+			if (pend & 0x80000000)
+				__do_IRQ(NR_CPM_INTS + bit, regs);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction pq2pci_irqaction = {
+	.handler = pq2pci_irq_demux,
+	.flags 	 = SA_INTERRUPT,
+	.mask	 = CPU_MASK_NONE,
+	.name	 = "PQ2 PCI cascade",
+};
+
+
+void
+pq2pci_init_irq(void)
+{
+	int irq;
+	volatile cpm2_map_t *immap = cpm2_immr;
+#if defined CONFIG_ADS8272
+	/* configure chip select for PCI interrupt controller */
+	immap->im_memctl.memc_br3 = PCI_INT_STAT_REG | 0x00001801;
+	immap->im_memctl.memc_or3 = 0xffff8010;
+#elif defined CONFIG_PQ2FADS
+	immap->im_memctl.memc_br8 = PCI_INT_STAT_REG | 0x00001801;
+	immap->im_memctl.memc_or8 = 0xffff8010;
+#endif
+	for (irq = NR_CPM_INTS; irq < NR_CPM_INTS + 4; irq++)
+		irq_desc[irq].handler = &pq2pci_ic;
+
+	/* make PCI IRQ level sensitive */
+	immap->im_intctl.ic_siexr &=
+		~(1 << (14 - (PCI_INT_TO_SIU - SIU_INT_IRQ1)));
+
+	/* mask all PCI interrupts */
+	*(volatile unsigned long *) PCI_INT_MASK_REG |= 0xfff00000;
+
+	/* install the demultiplexer for the PCI cascade interrupt */
+	setup_irq(PCI_INT_TO_SIU, &pq2pci_irqaction);
+	return;
+}
+
+static int
+pq2pci_exclude_device(u_char bus, u_char devfn)
+{
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/* PCI bus configuration registers.
+ */
+static void
+pq2ads_setup_pci(struct pci_controller *hose)
+{
+	__u32 val;
+	volatile cpm2_map_t *immap = cpm2_immr;
+	bd_t* binfo = (bd_t*) __res;
+	u32 sccr = immap->im_clkrst.car_sccr;
+	uint pci_div,freq,time;
+		/* PCI int lowest prio */
+	/* Each 4 bits is a device bus request	and the MS 4bits
+	 is highest priority */
+	/* Bus                4bit value
+	   ---                ----------
+	   CPM high      	0b0000
+	   CPM middle           0b0001
+	   CPM low       	0b0010
+	   PCI reguest          0b0011
+	   Reserved      	0b0100
+	   Reserved      	0b0101
+	   Internal Core     	0b0110
+	   External Master 1 	0b0111
+	   External Master 2 	0b1000
+	   External Master 3 	0b1001
+	   The rest are reserved
+	 */
+	immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x61207893;
+	/* park bus on core */
+	immap->im_siu_conf.siu_82xx.sc_ppc_acr = PPC_ACR_BUS_PARK_CORE;
+	/*
+	 * Set up master windows that allow the CPU to access PCI space. These
+	 * windows are set up using the two SIU PCIBR registers.
+	 */
+
+	immap->im_memctl.memc_pcimsk0 = M82xx_PCI_PRIM_WND_SIZE;
+	immap->im_memctl.memc_pcibr0  = M82xx_PCI_PRIM_WND_BASE | PCIBR_ENABLE;
+
+#ifdef M82xx_PCI_SEC_WND_SIZE
+	immap->im_memctl.memc_pcimsk1 = M82xx_PCI_SEC_WND_SIZE;
+	immap->im_memctl.memc_pcibr1  = M82xx_PCI_SEC_WND_BASE | PCIBR_ENABLE;
+#endif
+
+#if defined CONFIG_ADS8272
+	immap->im_siu_conf.siu_82xx.sc_siumcr =
+		(immap->im_siu_conf.siu_82xx.sc_siumcr &
+		~(SIUMCR_BBD | SIUMCR_ESE | SIUMCR_PBSE |
+		SIUMCR_CDIS | SIUMCR_DPPC11 | SIUMCR_L2CPC11 |
+		SIUMCR_LBPC11 | SIUMCR_APPC11 |
+		SIUMCR_CS10PC11 | SIUMCR_BCTLC11 | SIUMCR_MMR11)) |
+		SIUMCR_DPPC11 | SIUMCR_L2CPC01 | SIUMCR_LBPC00 |
+		SIUMCR_APPC10 | SIUMCR_CS10PC00 |
+		SIUMCR_BCTLC00 | SIUMCR_MMR11 ;
+
+#elif defined CONFIG_PQ2FADS
+	/*
+	 * Setting required to enable IRQ1-IRQ7 (SIUMCR [DPPC]),
+	 * and local bus for PCI (SIUMCR [LBPC]).
+	 */
+	immap->im_siu_conf.siu_82xx.sc_siumcr = (immap->im_siu_conf.sc_siumcr &
+				~(SIUMCR_L2PC11 | SIUMCR_LBPC11 | SIUMCR_CS10PC11 | SIUMCR_APPC11) |
+				SIUMCR_BBD | SIUMCR_LBPC01 | SIUMCR_DPPC11 | SIUMCR_APPC10;
+#endif
+	/* Enable PCI  */
+	immap->im_pci.pci_gcr = cpu_to_le32(PCIGCR_PCI_BUS_EN);
+
+	pci_div = ( (sccr & SCCR_PCI_MODCK) ? 2 : 1) *
+			( ( (sccr & SCCR_PCIDF_MSK) >> SCCR_PCIDF_SHIFT) + 1);
+	freq = (uint)((2*binfo->bi_cpmfreq)/(pci_div));
+	time = (int)666666/freq;
+	/* due to PCI Local Bus spec, some devices needs to wait such a long
+	time after RST 	deassertion. More specifically, 0.508s for 66MHz & twice more for 33 */
+	printk("%s: The PCI bus is %d Mhz.\nWaiting %s after deasserting RST...\n",__FILE__,freq,
+	(time==1) ? "0.5 seconds":"1 second" );
+
+	{
+		int i;
+		for(i=0;i<(500*time);i++)
+			udelay(1000);
+	}
+
+	/* setup ATU registers */
+	immap->im_pci.pci_pocmr0 = cpu_to_le32(POCMR_ENABLE | POCMR_PCI_IO |
+				((~(M82xx_PCI_IO_SIZE - 1U)) >> POTA_ADDR_SHIFT));
+	immap->im_pci.pci_potar0 = cpu_to_le32(M82xx_PCI_LOWER_IO >> POTA_ADDR_SHIFT);
+	immap->im_pci.pci_pobar0 = cpu_to_le32(M82xx_PCI_IO_BASE >> POTA_ADDR_SHIFT);
+
+	/* Set-up non-prefetchable window */
+	immap->im_pci.pci_pocmr1 = cpu_to_le32(POCMR_ENABLE | ((~(M82xx_PCI_MMIO_SIZE-1U)) >> POTA_ADDR_SHIFT));
+	immap->im_pci.pci_potar1 = cpu_to_le32(M82xx_PCI_LOWER_MMIO >> POTA_ADDR_SHIFT);
+	immap->im_pci.pci_pobar1 = cpu_to_le32((M82xx_PCI_LOWER_MMIO - M82xx_PCI_MMIO_OFFSET) >> POTA_ADDR_SHIFT);
+
+	/* Set-up prefetchable window */
+	immap->im_pci.pci_pocmr2 = cpu_to_le32(POCMR_ENABLE |POCMR_PREFETCH_EN |
+		(~(M82xx_PCI_MEM_SIZE-1U) >> POTA_ADDR_SHIFT));
+	immap->im_pci.pci_potar2 = cpu_to_le32(M82xx_PCI_LOWER_MEM >> POTA_ADDR_SHIFT);
+	immap->im_pci.pci_pobar2 = cpu_to_le32((M82xx_PCI_LOWER_MEM - M82xx_PCI_MEM_OFFSET) >> POTA_ADDR_SHIFT);
+
+ 	/* Inbound transactions from PCI memory space */
+	immap->im_pci.pci_picmr0 = cpu_to_le32(PICMR_ENABLE | PICMR_PREFETCH_EN |
+					((~(M82xx_PCI_SLAVE_MEM_SIZE-1U)) >> PITA_ADDR_SHIFT));
+	immap->im_pci.pci_pibar0 = cpu_to_le32(M82xx_PCI_SLAVE_MEM_BUS  >> PITA_ADDR_SHIFT);
+	immap->im_pci.pci_pitar0 = cpu_to_le32(M82xx_PCI_SLAVE_MEM_LOCAL>> PITA_ADDR_SHIFT);
+
+#if defined CONFIG_ADS8272
+	/* PCI int highest prio */
+	immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x01236745;
+#elif defined CONFIG_PQ2FADS
+	immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x03124567;
+#endif
+	/* park bus on PCI */
+	immap->im_siu_conf.siu_82xx.sc_ppc_acr = PPC_ACR_BUS_PARK_PCI;
+
+	/* Enable bus mastering and inbound memory transactions */
+	early_read_config_dword(hose, hose->first_busno, 0, PCI_COMMAND, &val);
+	val &= 0xffff0000;
+	val |= PCI_COMMAND_MEMORY|PCI_COMMAND_MASTER;
+	early_write_config_dword(hose, hose->first_busno, 0, PCI_COMMAND, val);
+
+}
+
+void __init pq2_find_bridges(void)
+{
+	extern int pci_assign_all_busses;
+	struct pci_controller * hose;
+	int host_bridge;
+
+	pci_assign_all_busses = 1;
+
+	hose = pcibios_alloc_controller();
+
+	if (!hose)
+		return;
+
+	ppc_md.pci_swizzle = common_swizzle;
+
+	hose->first_busno = 0;
+	hose->bus_offset = 0;
+	hose->last_busno = 0xff;
+
+#ifdef CONFIG_ADS8272
+	hose->set_cfg_type = 1;
+#endif
+
+	setup_m8260_indirect_pci(hose,
+				 (unsigned long)&cpm2_immr->im_pci.pci_cfg_addr,
+				 (unsigned long)&cpm2_immr->im_pci.pci_cfg_data);
+
+	/* Make sure it is a supported bridge */
+	early_read_config_dword(hose,
+				0,
+				PCI_DEVFN(0,0),
+				PCI_VENDOR_ID,
+				&host_bridge);
+	switch (host_bridge) {
+		case PCI_DEVICE_ID_MPC8265:
+			break;
+		case PCI_DEVICE_ID_MPC8272:
+			break;
+		default:
+			printk("Attempting to use unrecognized host bridge ID"
+				" 0x%08x.\n", host_bridge);
+			break;
+	}
+
+	pq2ads_setup_pci(hose);
+
+	hose->io_space.start =	M82xx_PCI_LOWER_IO;
+	hose->io_space.end = M82xx_PCI_UPPER_IO;
+	hose->mem_space.start = M82xx_PCI_LOWER_MEM;
+	hose->mem_space.end = M82xx_PCI_UPPER_MMIO;
+	hose->pci_mem_offset = M82xx_PCI_MEM_OFFSET;
+
+	isa_io_base =
+	(unsigned long) ioremap(M82xx_PCI_IO_BASE,
+					M82xx_PCI_IO_SIZE);
+	hose->io_base_virt = (void *) isa_io_base;
+
+	/* setup resources */
+	pci_init_resource(&hose->mem_resources[0],
+			M82xx_PCI_LOWER_MEM,
+			M82xx_PCI_UPPER_MEM,
+			IORESOURCE_MEM|IORESOURCE_PREFETCH, "PCI prefetchable memory");
+
+	pci_init_resource(&hose->mem_resources[1],
+			M82xx_PCI_LOWER_MMIO,
+			M82xx_PCI_UPPER_MMIO,
+			IORESOURCE_MEM, "PCI memory");
+
+	pci_init_resource(&hose->io_resource,
+			M82xx_PCI_LOWER_IO,
+			M82xx_PCI_UPPER_IO,
+			IORESOURCE_IO | 1, "PCI I/O");
+
+	ppc_md.pci_exclude_device = pq2pci_exclude_device;
+	hose->last_busno = pciauto_bus_scan(hose, hose->first_busno);
+
+	ppc_md.pci_map_irq = pq2pci_map_irq;
+	ppc_md.pcibios_fixup = NULL;
+	ppc_md.pcibios_fixup_bus = NULL;
+
+}

arch/ppc/syslib/m82xx_pci.h

@@ -0,0 +1,92 @@
+
+#ifndef _PPC_KERNEL_M82XX_PCI_H
+#define _PPC_KERNEL_M82XX_PCI_H
+
+#include <asm/m8260_pci.h>
+/*
+ *   Local->PCI map (from CPU)                             controlled by
+ *   MPC826x master window
+ *
+ *   0xF6000000 - 0xF7FFFFFF    IO space
+ *   0x80000000 - 0xBFFFFFFF    CPU2PCI memory space       PCIBR0
+ *
+ *   0x80000000 - 0x9FFFFFFF    PCI Mem with prefetch      (Outbound ATU #1)
+ *   0xA0000000 - 0xBFFFFFFF    PCI Mem w/o  prefetch      (Outbound ATU #2)
+ *   0xF6000000 - 0xF7FFFFFF    32-bit PCI IO              (Outbound ATU #3)
+ *
+ *   PCI->Local map (from PCI)
+ *   MPC826x slave window                                  controlled by
+ *
+ *   0x00000000 - 0x07FFFFFF    MPC826x local memory       (Inbound ATU #1)
+ */
+
+/*
+ * Slave window that allows PCI masters to access MPC826x local memory.
+ * This window is set up using the first set of Inbound ATU registers
+ */
+
+#ifndef M82xx_PCI_SLAVE_MEM_LOCAL
+#define M82xx_PCI_SLAVE_MEM_LOCAL	(((struct bd_info *)__res)->bi_memstart)
+#define M82xx_PCI_SLAVE_MEM_BUS		(((struct bd_info *)__res)->bi_memstart)
+#define M82xx_PCI_SLAVE_MEM_SIZE	(((struct bd_info *)__res)->bi_memsize)
+#endif
+
+/*
+ * This is the window that allows the CPU to access PCI address space.
+ * It will be setup with the SIU PCIBR0 register. All three PCI master
+ * windows, which allow the CPU to access PCI prefetch, non prefetch,
+ * and IO space (see below), must all fit within this window.
+ */
+
+#ifndef M82xx_PCI_LOWER_MEM
+#define M82xx_PCI_LOWER_MEM		0x80000000
+#define M82xx_PCI_UPPER_MEM		0x9fffffff
+#define M82xx_PCI_MEM_OFFSET		0x00000000
+#define M82xx_PCI_MEM_SIZE		0x20000000
+#endif
+
+#ifndef M82xx_PCI_LOWER_MMIO
+#define M82xx_PCI_LOWER_MMIO		0xa0000000
+#define M82xx_PCI_UPPER_MMIO		0xafffffff
+#define M82xx_PCI_MMIO_OFFSET		0x00000000
+#define M82xx_PCI_MMIO_SIZE		0x20000000
+#endif
+
+#ifndef M82xx_PCI_LOWER_IO
+#define M82xx_PCI_LOWER_IO		0x00000000
+#define M82xx_PCI_UPPER_IO		0x01ffffff
+#define M82xx_PCI_IO_BASE		0xf6000000
+#define M82xx_PCI_IO_SIZE		0x02000000
+#endif
+
+#ifndef M82xx_PCI_PRIM_WND_SIZE
+#define M82xx_PCI_PRIM_WND_SIZE 	~(M82xx_PCI_IO_SIZE - 1U)
+#define M82xx_PCI_PRIM_WND_BASE		(M82xx_PCI_IO_BASE)
+#endif
+
+#ifndef M82xx_PCI_SEC_WND_SIZE
+#define M82xx_PCI_SEC_WND_SIZE 		~(M82xx_PCI_MEM_SIZE + M82xx_PCI_MMIO_SIZE - 1U)
+#define M82xx_PCI_SEC_WND_BASE 		(M82xx_PCI_LOWER_MEM)
+#endif
+
+#ifndef POTA_ADDR_SHIFT
+#define POTA_ADDR_SHIFT		12
+#endif
+
+#ifndef PITA_ADDR_SHIFT
+#define PITA_ADDR_SHIFT		12
+#endif
+
+#ifndef _IO_BASE
+#define _IO_BASE isa_io_base
+#endif
+
+#ifdef CONFIG_8260_PCI9
+struct pci_controller;
+extern void setup_m8260_indirect_pci(struct pci_controller* hose,
+					u32 cfg_addr, u32 cfg_data);
+#else
+#define setup_m8260_indirect_pci setup_indirect_pci
+#endif
+
+#endif /* _PPC_KERNEL_M8260_PCI_H */

arch/ppc/syslib/open_pic.c

@@ -275,7 +275,7 @@ static void __init openpic_enable_sie(void)
 }
 #endif
 
-#if defined(CONFIG_EPIC_SERIAL_MODE) || defined(CONFIG_PM)
+#if defined(CONFIG_EPIC_SERIAL_MODE)
 static void openpic_reset(void)
 {
 	openpic_setfield(&OpenPIC->Global.Global_Configuration0,
@@ -993,8 +993,6 @@ int openpic_resume(struct sys_device *sysdev)
 		return 0;
 	}
 
-	openpic_reset();
-
 	/* OpenPIC sometimes seem to need some time to be fully back up... */
 	do {
 		openpic_set_spurious(OPENPIC_VEC_SPURIOUS);

arch/ppc/syslib/ppc83xx_setup.c

@@ -29,6 +29,7 @@
 #include <asm/mmu.h>
 #include <asm/ppc_sys.h>
 #include <asm/kgdb.h>
+#include <asm/delay.h>
 
 #include <syslib/ppc83xx_setup.h>
 
@@ -117,7 +118,34 @@ mpc83xx_early_serial_map(void)
 void
 mpc83xx_restart(char *cmd)
 {
+	volatile unsigned char __iomem *reg;
+	unsigned char tmp;
+
+	reg = ioremap(BCSR_PHYS_ADDR, BCSR_SIZE);
+
 	local_irq_disable();
+
+	/*
+	 * Unlock the BCSR bits so a PRST will update the contents.
+	 * Otherwise the reset asserts but doesn't clear.
+	 */
+	tmp = in_8(reg + BCSR_MISC_REG3_OFF);
+	tmp |= BCSR_MISC_REG3_CNFLOCK; /* low true, high false */
+	out_8(reg + BCSR_MISC_REG3_OFF, tmp);
+
+	/*
+	 * Trigger a reset via a low->high transition of the
+	 * PORESET bit.
+	 */
+	tmp = in_8(reg + BCSR_MISC_REG2_OFF);
+	tmp &= ~BCSR_MISC_REG2_PORESET;
+	out_8(reg + BCSR_MISC_REG2_OFF, tmp);
+
+	udelay(1);
+
+	tmp |= BCSR_MISC_REG2_PORESET;
+	out_8(reg + BCSR_MISC_REG2_OFF, tmp);
+
 	for(;;);
 }
 

arch/ppc/syslib/ppc85xx_setup.c

@@ -132,6 +132,12 @@ mpc85xx_halt(void)
 }
 
 #ifdef CONFIG_PCI
+
+#if defined(CONFIG_MPC8555_CDS)
+extern void mpc85xx_cds_enable_via(struct pci_controller *hose);
+extern void mpc85xx_cds_fixup_via(struct pci_controller *hose);
+#endif
+
 static void __init
 mpc85xx_setup_pci1(struct pci_controller *hose)
 {
@@ -302,8 +308,18 @@ mpc85xx_setup_hose(void)
 
 	ppc_md.pci_exclude_device = mpc85xx_exclude_device;
 
+#if defined(CONFIG_MPC8555_CDS)
+	/* Pre pciauto_bus_scan VIA init */
+	mpc85xx_cds_enable_via(hose_a);
+#endif
+
 	hose_a->last_busno = pciauto_bus_scan(hose_a, hose_a->first_busno);
 
+#if defined(CONFIG_MPC8555_CDS)
+	/* Post pciauto_bus_scan VIA fixup */
+	mpc85xx_cds_fixup_via(hose_a);
+#endif
+
 #ifdef CONFIG_85xx_PCI2
 	hose_b = pcibios_alloc_controller();
 

arch/ppc/syslib/prom_init.c

@@ -626,8 +626,18 @@ inspect_node(phandle node, struct device_node *dad,
 	l = call_prom("package-to-path", 3, 1, node,
 		      mem_start, mem_end - mem_start);
 	if (l >= 0) {
+		char *p, *ep;
+
 		np->full_name = PTRUNRELOC((char *) mem_start);
 		*(char *)(mem_start + l) = 0;
+		/* Fixup an Apple bug where they have bogus \0 chars in the
+		 * middle of the path in some properties
+		 */
+		for (p = (char *)mem_start, ep = p + l; p < ep; p++)
+			if ((*p) == '\0') {
+				memmove(p, p+1, ep - p);
+				ep--;
+			}
 		mem_start = ALIGNUL(mem_start + l + 1);
 	}
 

arch/ppc64/kernel/pSeries_reconfig.c

@@ -47,14 +47,6 @@ static void remove_node_proc_entries(struct device_node *np)
 		remove_proc_entry(pp->name, np->pde);
 		pp = pp->next;
 	}
-
-	/* Assuming that symlinks have the same parent directory as
-	 * np->pde.
-	 */
-	if (np->name_link)
-		remove_proc_entry(np->name_link->name, parent->pde);
-	if (np->addr_link)
-		remove_proc_entry(np->addr_link->name, parent->pde);
 	if (np->pde)
 		remove_proc_entry(np->pde->name, parent->pde);
 }

arch/ppc64/kernel/prom_init.c

@@ -211,13 +211,23 @@ struct {
  */
 #define ADDR(x)		(u32) ((unsigned long)(x) - offset)
 
+/*
+ * Error results ... some OF calls will return "-1" on error, some
+ * will return 0, some will return either. To simplify, here are
+ * macros to use with any ihandle or phandle return value to check if
+ * it is valid
+ */
+
+#define PROM_ERROR		(-1u)
+#define PHANDLE_VALID(p)	((p) != 0 && (p) != PROM_ERROR)
+#define IHANDLE_VALID(i)	((i) != 0 && (i) != PROM_ERROR)
+
+
 /* This is the one and *ONLY* place where we actually call open
  * firmware from, since we need to make sure we're running in 32b
  * mode when we do.  We switch back to 64b mode upon return.
  */
 
-#define PROM_ERROR	(-1)
-
 static int __init call_prom(const char *service, int nargs, int nret, ...)
 {
 	int i;
@@ -587,14 +597,13 @@ static void __init prom_send_capabilities(void)
 {
 	unsigned long offset = reloc_offset();
 	ihandle elfloader;
-	int ret;
 
 	elfloader = call_prom("open", 1, 1, ADDR("/packages/elf-loader"));
 	if (elfloader == 0) {
 		prom_printf("couldn't open /packages/elf-loader\n");
 		return;
 	}
-	ret = call_prom("call-method", 3, 1, ADDR("process-elf-header"),
+	call_prom("call-method", 3, 1, ADDR("process-elf-header"),
 			elfloader, ADDR(&fake_elf));
 	call_prom("close", 1, 0, elfloader);
 }
@@ -646,7 +655,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align)
 	    base = _ALIGN_UP(base + 0x100000, align)) {
 		prom_debug("    trying: 0x%x\n\r", base);
 		addr = (unsigned long)prom_claim(base, size, 0);
-		if ((int)addr != PROM_ERROR)
+		if (addr != PROM_ERROR)
 			break;
 		addr = 0;
 		if (align == 0)
@@ -708,7 +717,7 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align,
 	for(; base > RELOC(alloc_bottom); base = _ALIGN_DOWN(base - 0x100000, align))  {
 		prom_debug("    trying: 0x%x\n\r", base);
 		addr = (unsigned long)prom_claim(base, size, 0);
-		if ((int)addr != PROM_ERROR)
+		if (addr != PROM_ERROR)
 			break;
 		addr = 0;
 	}
@@ -902,18 +911,19 @@ static void __init prom_instantiate_rtas(void)
 {
 	unsigned long offset = reloc_offset();
 	struct prom_t *_prom = PTRRELOC(&prom);
-	phandle prom_rtas, rtas_node;
+	phandle rtas_node;
+	ihandle rtas_inst;
 	u32 base, entry = 0;
 	u32 size = 0;
 
 	prom_debug("prom_instantiate_rtas: start...\n");
 
-	prom_rtas = call_prom("finddevice", 1, 1, ADDR("/rtas"));
-	prom_debug("prom_rtas: %x\n", prom_rtas);
-	if (prom_rtas == (phandle) -1)
+	rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas"));
+	prom_debug("rtas_node: %x\n", rtas_node);
+	if (!PHANDLE_VALID(rtas_node))
 		return;
 
-	prom_getprop(prom_rtas, "rtas-size", &size, sizeof(size));
+	prom_getprop(rtas_node, "rtas-size", &size, sizeof(size));
 	if (size == 0)
 		return;
 
@@ -922,14 +932,18 @@ static void __init prom_instantiate_rtas(void)
 		prom_printf("RTAS allocation failed !\n");
 		return;
 	}
-	prom_printf("instantiating rtas at 0x%x", base);
 
-	rtas_node = call_prom("open", 1, 1, ADDR("/rtas"));
-	prom_printf("...");
+	rtas_inst = call_prom("open", 1, 1, ADDR("/rtas"));
+	if (!IHANDLE_VALID(rtas_inst)) {
+		prom_printf("opening rtas package failed");
+		return;
+	}
+
+	prom_printf("instantiating rtas at 0x%x ...", base);
 
 	if (call_prom("call-method", 3, 2,
 		      ADDR("instantiate-rtas"),
-		      rtas_node, base) != PROM_ERROR) {
+		      rtas_inst, base) != PROM_ERROR) {
 		entry = (long)_prom->args.rets[1];
 	}
 	if (entry == 0) {
@@ -940,8 +954,8 @@ static void __init prom_instantiate_rtas(void)
 
 	reserve_mem(base, size);
 
-	prom_setprop(prom_rtas, "linux,rtas-base", &base, sizeof(base));
-	prom_setprop(prom_rtas, "linux,rtas-entry", &entry, sizeof(entry));
+	prom_setprop(rtas_node, "linux,rtas-base", &base, sizeof(base));
+	prom_setprop(rtas_node, "linux,rtas-entry", &entry, sizeof(entry));
 
 	prom_debug("rtas base     = 0x%x\n", base);
 	prom_debug("rtas entry    = 0x%x\n", entry);
@@ -1062,7 +1076,7 @@ static void __init prom_initialize_tce_table(void)
 
 		prom_printf("opening PHB %s", path);
 		phb_node = call_prom("open", 1, 1, path);
-		if ( (long)phb_node <= 0)
+		if (phb_node == 0)
 			prom_printf("... failed\n");
 		else
 			prom_printf("... done\n");
@@ -1279,12 +1293,12 @@ static void __init prom_init_client_services(unsigned long pp)
 
 	/* get a handle for the stdout device */
 	_prom->chosen = call_prom("finddevice", 1, 1, ADDR("/chosen"));
-	if ((long)_prom->chosen <= 0)
+	if (!PHANDLE_VALID(_prom->chosen))
 		prom_panic("cannot find chosen"); /* msg won't be printed :( */
 
 	/* get device tree root */
 	_prom->root = call_prom("finddevice", 1, 1, ADDR("/"));
-	if ((long)_prom->root <= 0)
+	if (!PHANDLE_VALID(_prom->root))
 		prom_panic("cannot find device tree root"); /* msg won't be printed :( */
 }
 
@@ -1356,9 +1370,8 @@ 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 (rtas != (phandle) -1) {
-		unsigned long x;
-		x = prom_getproplen(rtas, "ibm,hypertas-functions");
+	if (!PHANDLE_VALID(rtas)) {
+		int x = prom_getproplen(rtas, "ibm,hypertas-functions");
 		if (x != PROM_ERROR) {
 			prom_printf("Hypertas detected, assuming LPAR !\n");
 			return PLATFORM_PSERIES_LPAR;
@@ -1426,12 +1439,13 @@ static void __init prom_check_displays(void)
 		 * leave some room at the end of the path for appending extra
 		 * arguments
 		 */
-		if (call_prom("package-to-path", 3, 1, node, path, PROM_SCRATCH_SIZE-10) < 0)
+		if (call_prom("package-to-path", 3, 1, node, path,
+			      PROM_SCRATCH_SIZE-10) == PROM_ERROR)
 			continue;
 		prom_printf("found display   : %s, opening ... ", path);
 		
 		ih = call_prom("open", 1, 1, path);
-		if (ih == (ihandle)0 || ih == (ihandle)-1) {
+		if (ih == 0) {
 			prom_printf("failed\n");
 			continue;
 		}
@@ -1514,6 +1528,12 @@ static unsigned long __init dt_find_string(char *str)
 	return 0;
 }
 
+/*
+ * The Open Firmware 1275 specification states properties must be 31 bytes or
+ * less, however not all firmwares obey this. Make it 64 bytes to be safe.
+ */
+#define MAX_PROPERTY_NAME 64
+
 static void __init scan_dt_build_strings(phandle node, unsigned long *mem_start,
 					 unsigned long *mem_end)
 {
@@ -1527,10 +1547,12 @@ static void __init scan_dt_build_strings(phandle node, unsigned long *mem_start,
 	/* get and store all property names */
 	prev_name = RELOC("");
 	for (;;) {
-		
-		/* 32 is max len of name including nul. */
-		namep = make_room(mem_start, mem_end, 32, 1);
-		if (call_prom("nextprop", 3, 1, node, prev_name, namep) <= 0) {
+		int rc;
+
+		/* 64 is max len of name including nul. */
+		namep = make_room(mem_start, mem_end, MAX_PROPERTY_NAME, 1);
+		rc = call_prom("nextprop", 3, 1, node, prev_name, namep);
+		if (rc != 1) {
 			/* No more nodes: unwind alloc */
 			*mem_start = (unsigned long)namep;
 			break;
@@ -1555,18 +1577,12 @@ static void __init scan_dt_build_strings(phandle node, unsigned long *mem_start,
 	}
 }
 
-/*
- * The Open Firmware 1275 specification states properties must be 31 bytes or
- * less, however not all firmwares obey this. Make it 64 bytes to be safe.
- */
-#define MAX_PROPERTY_NAME 64
-
 static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
 					unsigned long *mem_end)
 {
 	int l, align;
 	phandle child;
-	char *namep, *prev_name, *sstart;
+	char *namep, *prev_name, *sstart, *p, *ep;
 	unsigned long soff;
 	unsigned char *valp;
 	unsigned long offset = reloc_offset();
@@ -1588,6 +1604,14 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
 			call_prom("package-to-path", 3, 1, node, namep, l);
 		}
 		namep[l] = '\0';
+		/* Fixup an Apple bug where they have bogus \0 chars in the
+		 * middle of the path in some properties
+		 */
+		for (p = namep, ep = namep + l; p < ep; p++)
+			if (*p == '\0') {
+				memmove(p, p+1, ep - p);
+				ep--; l--;
+			}
 		*mem_start = _ALIGN(((unsigned long) namep) + strlen(namep) + 1, 4);
 	}
 
@@ -1599,7 +1623,10 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
 	prev_name = RELOC("");
 	sstart = (char *)RELOC(dt_string_start);
 	for (;;) {
-		if (call_prom("nextprop", 3, 1, node, prev_name, pname) <= 0)
+		int rc;
+
+		rc = call_prom("nextprop", 3, 1, node, prev_name, pname);
+		if (rc != 1)
 			break;
 
 		/* find string offset */
@@ -1615,7 +1642,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
 		l = call_prom("getproplen", 2, 1, node, pname);
 
 		/* sanity checks */
-		if (l < 0)
+		if (l == PROM_ERROR)
 			continue;
 		if (l > MAX_PROPERTY_LENGTH) {
 			prom_printf("WARNING: ignoring large property ");
@@ -1763,17 +1790,18 @@ static void __init fixup_device_tree(void)
 
 	/* Some G5s have a missing interrupt definition, fix it up here */
 	u3 = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000"));
-	if ((long)u3 <= 0)
+	if (!PHANDLE_VALID(u3))
 		return;
 	i2c = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/i2c@f8001000"));
-	if ((long)i2c <= 0)
+	if (!PHANDLE_VALID(i2c))
 		return;
 	mpic = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/mpic@f8040000"));
-	if ((long)mpic <= 0)
+	if (!PHANDLE_VALID(mpic))
 		return;
 
 	/* check if proper rev of u3 */
-	if (prom_getprop(u3, "device-rev", &u3_rev, sizeof(u3_rev)) <= 0)
+	if (prom_getprop(u3, "device-rev", &u3_rev, sizeof(u3_rev))
+	    == PROM_ERROR)
 		return;
 	if (u3_rev != 0x35)
 		return;
@@ -1880,6 +1908,12 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, unsigned long
 	prom_setprop(_prom->chosen, "linux,platform",
 		     &getprop_rval, sizeof(getprop_rval));
 
+	/*
+	 * On pSeries, inform the firmware about our capabilities
+	 */
+	if (RELOC(of_platform) & PLATFORM_PSERIES)
+		prom_send_capabilities();
+
 	/*
 	 * On pSeries, copy the CPU hold code
 	 */

arch/ppc64/kernel/time.c

@@ -325,9 +325,7 @@ int timer_interrupt(struct pt_regs * regs)
 
 	irq_enter();
 
-#ifndef CONFIG_PPC_ISERIES
 	profile_tick(CPU_PROFILING, regs);
-#endif
 
 	lpaca->lppaca.int_dword.fields.decr_int = 0;
 

arch/sparc64/kernel/pci_iommu.c

@@ -196,6 +196,34 @@ static iopte_t *alloc_consistent_cluster(struct pci_iommu *iommu, unsigned long
 	return NULL;
 }
 
+static int iommu_alloc_ctx(struct pci_iommu *iommu)
+{
+	int lowest = iommu->ctx_lowest_free;
+	int sz = IOMMU_NUM_CTXS - lowest;
+	int n = find_next_zero_bit(iommu->ctx_bitmap, sz, lowest);
+
+	if (unlikely(n == sz)) {
+		n = find_next_zero_bit(iommu->ctx_bitmap, lowest, 1);
+		if (unlikely(n == lowest)) {
+			printk(KERN_WARNING "IOMMU: Ran out of contexts.\n");
+			n = 0;
+		}
+	}
+	if (n)
+		__set_bit(n, iommu->ctx_bitmap);
+
+	return n;
+}
+
+static inline void iommu_free_ctx(struct pci_iommu *iommu, int ctx)
+{
+	if (likely(ctx)) {
+		__clear_bit(ctx, iommu->ctx_bitmap);
+		if (ctx < iommu->ctx_lowest_free)
+			iommu->ctx_lowest_free = ctx;
+	}
+}
+
 /* Allocate and map kernel buffer of size SIZE using consistent mode
  * DMA for PCI device PDEV.  Return non-NULL cpu-side address if
  * successful and set *DMA_ADDRP to the PCI side dma address.
@@ -236,7 +264,7 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t size, dma_addr_t *dma_ad
 	npages = size >> IO_PAGE_SHIFT;
 	ctx = 0;
 	if (iommu->iommu_ctxflush)
-		ctx = iommu->iommu_cur_ctx++;
+		ctx = iommu_alloc_ctx(iommu);
 	first_page = __pa(first_page);
 	while (npages--) {
 		iopte_val(*iopte) = (IOPTE_CONSISTENT(ctx) |
@@ -317,6 +345,8 @@ void pci_free_consistent(struct pci_dev *pdev, size_t size, void *cpu, dma_addr_
 		}
 	}
 
+	iommu_free_ctx(iommu, ctx);
+
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	order = get_order(size);
@@ -360,7 +390,7 @@ dma_addr_t pci_map_single(struct pci_dev *pdev, void *ptr, size_t sz, int direct
 	base_paddr = __pa(oaddr & IO_PAGE_MASK);
 	ctx = 0;
 	if (iommu->iommu_ctxflush)
-		ctx = iommu->iommu_cur_ctx++;
+		ctx = iommu_alloc_ctx(iommu);
 	if (strbuf->strbuf_enabled)
 		iopte_protection = IOPTE_STREAMING(ctx);
 	else
@@ -380,39 +410,53 @@ bad:
 	return PCI_DMA_ERROR_CODE;
 }
 
-static void pci_strbuf_flush(struct pci_strbuf *strbuf, struct pci_iommu *iommu, u32 vaddr, unsigned long ctx, unsigned long npages)
+static void pci_strbuf_flush(struct pci_strbuf *strbuf, struct pci_iommu *iommu, u32 vaddr, unsigned long ctx, unsigned long npages, int direction)
 {
 	int limit;
 
-	PCI_STC_FLUSHFLAG_INIT(strbuf);
 	if (strbuf->strbuf_ctxflush &&
 	    iommu->iommu_ctxflush) {
 		unsigned long matchreg, flushreg;
+		u64 val;
 
 		flushreg = strbuf->strbuf_ctxflush;
 		matchreg = PCI_STC_CTXMATCH_ADDR(strbuf, ctx);
 
-		limit = 100000;
 		pci_iommu_write(flushreg, ctx);
-		for(;;) {
-			if (((long)pci_iommu_read(matchreg)) >= 0L)
-				break;
-			limit--;
-			if (!limit)
-				break;
-			udelay(1);
+		val = pci_iommu_read(matchreg);
+		val &= 0xffff;
+		if (!val)
+			goto do_flush_sync;
+
+		while (val) {
+			if (val & 0x1)
+				pci_iommu_write(flushreg, ctx);
+			val >>= 1;
 		}
-		if (!limit)
+		val = pci_iommu_read(matchreg);
+		if (unlikely(val)) {
 			printk(KERN_WARNING "pci_strbuf_flush: ctx flush "
-			       "timeout vaddr[%08x] ctx[%lx]\n",
-			       vaddr, ctx);
+			       "timeout matchreg[%lx] ctx[%lx]\n",
+			       val, ctx);
+			goto do_page_flush;
+		}
 	} else {
 		unsigned long i;
 
+	do_page_flush:
 		for (i = 0; i < npages; i++, vaddr += IO_PAGE_SIZE)
 			pci_iommu_write(strbuf->strbuf_pflush, vaddr);
 	}
 
+do_flush_sync:
+	/* If the device could not have possibly put dirty data into
+	 * the streaming cache, no flush-flag synchronization needs
+	 * to be performed.
+	 */
+	if (direction == PCI_DMA_TODEVICE)
+		return;
+
+	PCI_STC_FLUSHFLAG_INIT(strbuf);
 	pci_iommu_write(strbuf->strbuf_fsync, strbuf->strbuf_flushflag_pa);
 	(void) pci_iommu_read(iommu->write_complete_reg);
 
@@ -466,7 +510,7 @@ void pci_unmap_single(struct pci_dev *pdev, dma_addr_t bus_addr, size_t sz, int
 
 	/* Step 1: Kick data out of streaming buffers if necessary. */
 	if (strbuf->strbuf_enabled)
-		pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages);
+		pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction);
 
 	/* Step 2: Clear out first TSB entry. */
 	iopte_make_dummy(iommu, base);
@@ -474,6 +518,8 @@ void pci_unmap_single(struct pci_dev *pdev, dma_addr_t bus_addr, size_t sz, int
 	free_streaming_cluster(iommu, bus_addr - iommu->page_table_map_base,
 			       npages, ctx);
 
+	iommu_free_ctx(iommu, ctx);
+
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -613,7 +659,7 @@ int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, int
 	/* Step 4: Choose a context if necessary. */
 	ctx = 0;
 	if (iommu->iommu_ctxflush)
-		ctx = iommu->iommu_cur_ctx++;
+		ctx = iommu_alloc_ctx(iommu);
 
 	/* Step 5: Create the mappings. */
 	if (strbuf->strbuf_enabled)
@@ -678,7 +724,7 @@ void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems,
 
 	/* Step 1: Kick data out of streaming buffers if necessary. */
 	if (strbuf->strbuf_enabled)
-		pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages);
+		pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction);
 
 	/* Step 2: Clear out first TSB entry. */
 	iopte_make_dummy(iommu, base);
@@ -686,6 +732,8 @@ void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems,
 	free_streaming_cluster(iommu, bus_addr - iommu->page_table_map_base,
 			       npages, ctx);
 
+	iommu_free_ctx(iommu, ctx);
+
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -724,7 +772,7 @@ void pci_dma_sync_single_for_cpu(struct pci_dev *pdev, dma_addr_t bus_addr, size
 	}
 
 	/* Step 2: Kick data out of streaming buffers. */
-	pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages);
+	pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction);
 
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
@@ -768,7 +816,7 @@ void pci_dma_sync_sg_for_cpu(struct pci_dev *pdev, struct scatterlist *sglist, i
 	i--;
 	npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length)
 		  - bus_addr) >> IO_PAGE_SHIFT;
-	pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages);
+	pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction);
 
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }

arch/sparc64/kernel/pci_psycho.c

@@ -1212,7 +1212,7 @@ static void __init psycho_iommu_init(struct pci_controller_info *p)
 
 	/* Setup initial software IOMMU state. */
 	spin_lock_init(&iommu->lock);
-	iommu->iommu_cur_ctx = 0;
+	iommu->ctx_lowest_free = 1;
 
 	/* Register addresses. */
 	iommu->iommu_control  = p->pbm_A.controller_regs + PSYCHO_IOMMU_CONTROL;

arch/sparc64/kernel/pci_sabre.c

@@ -1265,7 +1265,7 @@ static void __init sabre_iommu_init(struct pci_controller_info *p,
 
 	/* Setup initial software IOMMU state. */
 	spin_lock_init(&iommu->lock);
-	iommu->iommu_cur_ctx = 0;
+	iommu->ctx_lowest_free = 1;
 
 	/* Register addresses. */
 	iommu->iommu_control  = p->pbm_A.controller_regs + SABRE_IOMMU_CONTROL;

arch/sparc64/kernel/pci_schizo.c

@@ -1753,7 +1753,7 @@ static void schizo_pbm_iommu_init(struct pci_pbm_info *pbm)
 
 	/* Setup initial software IOMMU state. */
 	spin_lock_init(&iommu->lock);
-	iommu->iommu_cur_ctx = 0;
+	iommu->ctx_lowest_free = 1;
 
 	/* Register addresses, SCHIZO has iommu ctx flushing. */
 	iommu->iommu_control  = pbm->pbm_regs + SCHIZO_IOMMU_CONTROL;

arch/sparc64/kernel/sbus.c

@@ -117,17 +117,25 @@ static void iommu_flush(struct sbus_iommu *iommu, u32 base, unsigned long npages
 
 #define STRBUF_TAG_VALID	0x02UL
 
-static void sbus_strbuf_flush(struct sbus_iommu *iommu, u32 base, unsigned long npages)
+static void sbus_strbuf_flush(struct sbus_iommu *iommu, u32 base, unsigned long npages, int direction)
 {
 	unsigned long n;
 	int limit;
 
-	iommu->strbuf_flushflag = 0UL;
 	n = npages;
 	while (n--)
 		upa_writeq(base + (n << IO_PAGE_SHIFT),
 			   iommu->strbuf_regs + STRBUF_PFLUSH);
 
+	/* If the device could not have possibly put dirty data into
+	 * the streaming cache, no flush-flag synchronization needs
+	 * to be performed.
+	 */
+	if (direction == SBUS_DMA_TODEVICE)
+		return;
+
+	iommu->strbuf_flushflag = 0UL;
+
 	/* Whoopee cushion! */
 	upa_writeq(__pa(&iommu->strbuf_flushflag),
 		   iommu->strbuf_regs + STRBUF_FSYNC);
@@ -421,7 +429,7 @@ void sbus_unmap_single(struct sbus_dev *sdev, dma_addr_t dma_addr, size_t size,
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	free_streaming_cluster(iommu, dma_base, size >> IO_PAGE_SHIFT);
-	sbus_strbuf_flush(iommu, dma_base, size >> IO_PAGE_SHIFT);
+	sbus_strbuf_flush(iommu, dma_base, size >> IO_PAGE_SHIFT, direction);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -584,7 +592,7 @@ void sbus_unmap_sg(struct sbus_dev *sdev, struct scatterlist *sg, int nents, int
 	iommu = sdev->bus->iommu;
 	spin_lock_irqsave(&iommu->lock, flags);
 	free_streaming_cluster(iommu, dvma_base, size >> IO_PAGE_SHIFT);
-	sbus_strbuf_flush(iommu, dvma_base, size >> IO_PAGE_SHIFT);
+	sbus_strbuf_flush(iommu, dvma_base, size >> IO_PAGE_SHIFT, direction);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -596,7 +604,7 @@ void sbus_dma_sync_single_for_cpu(struct sbus_dev *sdev, dma_addr_t base, size_t
 	size = (IO_PAGE_ALIGN(base + size) - (base & IO_PAGE_MASK));
 
 	spin_lock_irqsave(&iommu->lock, flags);
-	sbus_strbuf_flush(iommu, base & IO_PAGE_MASK, size >> IO_PAGE_SHIFT);
+	sbus_strbuf_flush(iommu, base & IO_PAGE_MASK, size >> IO_PAGE_SHIFT, direction);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
@@ -620,7 +628,7 @@ void sbus_dma_sync_sg_for_cpu(struct sbus_dev *sdev, struct scatterlist *sg, int
 	size = IO_PAGE_ALIGN(sg[i].dma_address + sg[i].dma_length) - base;
 
 	spin_lock_irqsave(&iommu->lock, flags);
-	sbus_strbuf_flush(iommu, base, size >> IO_PAGE_SHIFT);
+	sbus_strbuf_flush(iommu, base, size >> IO_PAGE_SHIFT, direction);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 

arch/um/Kconfig.debug

@@ -2,10 +2,6 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
-config FRAME_POINTER
-	bool
-	default y if DEBUG_INFO
-
 config PT_PROXY
 	bool "Enable ptrace proxy"
 	depends on XTERM_CHAN && DEBUG_INFO && MODE_TT

arch/um/drivers/random.c

@@ -1,5 +1,10 @@
-/* Much of this ripped from hw_random.c */
-
+/* Copyright (C) 2005 Jeff Dike <jdike@addtoit.com> */
+/* Much of this ripped from drivers/char/hw_random.c, see there for other
+ * copyright.
+ *
+ * This software may be used and distributed according to the terms
+ * of the GNU General Public License, incorporated herein by reference.
+ */
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
@@ -12,8 +17,6 @@
  */
 #define RNG_VERSION "1.0.0"
 #define RNG_MODULE_NAME "random"
-#define RNG_DRIVER_NAME   RNG_MODULE_NAME " virtual driver " RNG_VERSION
-#define PFX RNG_MODULE_NAME ": "
 
 #define RNG_MISCDEV_MINOR		183 /* official */
 
@@ -98,7 +101,7 @@ static int __init rng_init (void)
 
 	err = misc_register (&rng_miscdev);
 	if (err) {
-		printk (KERN_ERR PFX "misc device register failed\n");
+		printk (KERN_ERR RNG_MODULE_NAME ": misc device register failed\n");
 		goto err_out_cleanup_hw;
 	}
 
@@ -120,3 +123,6 @@ static void __exit rng_cleanup (void)
 
 module_init (rng_init);
 module_exit (rng_cleanup);
+
+MODULE_DESCRIPTION("UML Host Random Number Generator (RNG) driver");
+MODULE_LICENSE("GPL");

arch/um/drivers/ssl.c

@@ -22,7 +22,6 @@
 #include "init.h"
 #include "irq_user.h"
 #include "mconsole_kern.h"
-#include "2_5compat.h"
 
 static int ssl_version = 1;
 

arch/um/drivers/stdio_console.c

@@ -28,7 +28,6 @@
 #include "irq_user.h"
 #include "mconsole_kern.h"
 #include "init.h"
-#include "2_5compat.h"
 
 #define MAX_TTYS (16)
 

arch/um/drivers/ubd_kern.c

@@ -49,7 +49,6 @@
 #include "irq_user.h"
 #include "irq_kern.h"
 #include "ubd_user.h"
-#include "2_5compat.h"
 #include "os.h"
 #include "mem.h"
 #include "mem_kern.h"
@@ -440,9 +439,9 @@ static int udb_setup(char *str)
 __setup("udb", udb_setup);
 __uml_help(udb_setup,
 "udb\n"
-"    This option is here solely to catch ubd -> udb typos, which can be\n\n"
-"    to impossible to catch visually unless you specifically look for\n\n"
-"    them.  The only result of any option starting with 'udb' is an error\n\n"
+"    This option is here solely to catch ubd -> udb typos, which can be\n"
+"    to impossible to catch visually unless you specifically look for\n"
+"    them.  The only result of any option starting with 'udb' is an error\n"
 "    in the boot output.\n\n"
 );
 

arch/um/include/2_5compat.h

@@ -1,24 +0,0 @@
-/* 
- * Copyright (C) 2001 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __2_5_COMPAT_H__
-#define __2_5_COMPAT_H__
-
-#define INIT_HARDSECT(arr, maj, sizes)
-
-#define SET_PRI(task) do ; while(0)
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/um/include/sysrq.h

@@ -1,6 +1,7 @@
 #ifndef __UM_SYSRQ_H
 #define __UM_SYSRQ_H
 
-extern void show_trace(unsigned long *stack);
+struct task_struct;
+extern void show_trace(struct task_struct* task, unsigned long *stack);
 
 #endif

arch/um/kernel/exec_kern.c

@@ -16,7 +16,6 @@
 #include "kern.h"
 #include "irq_user.h"
 #include "tlb.h"
-#include "2_5compat.h"
 #include "os.h"
 #include "time_user.h"
 #include "choose-mode.h"

arch/um/kernel/initrd_kern.c

@@ -1,59 +0,0 @@
-/*
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#include "linux/init.h"
-#include "linux/bootmem.h"
-#include "linux/initrd.h"
-#include "asm/types.h"
-#include "user_util.h"
-#include "kern_util.h"
-#include "initrd.h"
-#include "init.h"
-#include "os.h"
-
-/* Changed by uml_initrd_setup, which is a setup */
-static char *initrd __initdata = NULL;
-
-static int __init read_initrd(void)
-{
-	void *area;
-	long long size;
-	int err;
-
-	if(initrd == NULL) return 0;
-	err = os_file_size(initrd, &size);
-	if(err) return 0;
-	area = alloc_bootmem(size);
-	if(area == NULL) return 0;
-	if(load_initrd(initrd, area, size) == -1) return 0;
-	initrd_start = (unsigned long) area;
-	initrd_end = initrd_start + size;
-	return 0;
-}
-
-__uml_postsetup(read_initrd);
-
-static int __init uml_initrd_setup(char *line, int *add)
-{
-	initrd = line;
-	return 0;
-}
-
-__uml_setup("initrd=", uml_initrd_setup, 
-"initrd=<initrd image>\n"
-"    This is used to boot UML from an initrd image.  The argument is the\n"
-"    name of the file containing the image.\n\n"
-);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/um/kernel/initrd_user.c

@@ -1,46 +0,0 @@
-/*
- * Copyright (C) 2000, 2001 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#include <unistd.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <errno.h>
-
-#include "user_util.h"
-#include "kern_util.h"
-#include "user.h"
-#include "initrd.h"
-#include "os.h"
-
-int load_initrd(char *filename, void *buf, int size)
-{
-	int fd, n;
-
-	fd = os_open_file(filename, of_read(OPENFLAGS()), 0);
-	if(fd < 0){
-		printk("Opening '%s' failed - err = %d\n", filename, -fd);
-		return(-1);
-	}
-	n = os_read_file(fd, buf, size);
-	if(n != size){
-		printk("Read of %d bytes from '%s' failed, err = %d\n", size,
-		       filename, -n);
-		return(-1);
-	}
-
-	os_close_file(fd);
-	return(0);
-}
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/um/kernel/main.c

@@ -71,7 +71,7 @@ static __init void do_uml_initcalls(void)
 
 static void last_ditch_exit(int sig)
 {
-	CHOOSE_MODE(kmalloc_ok = 0, (void) 0);
+        kmalloc_ok = 0;
 	signal(SIGINT, SIG_DFL);
 	signal(SIGTERM, SIG_DFL);
 	signal(SIGHUP, SIG_DFL);
@@ -87,7 +87,7 @@ int main(int argc, char **argv, char **envp)
 {
 	char **new_argv;
 	sigset_t mask;
-	int ret, i;
+	int ret, i, err;
 
 	/* Enable all signals except SIGIO - in some environments, we can
 	 * enter with some signals blocked
@@ -160,27 +160,29 @@ int main(int argc, char **argv, char **envp)
 	 */
 	change_sig(SIGPROF, 0);
 
-	/* Reboot */
-	if(ret){
-		int err;
-
-		printf("\n");
+        /* This signal stuff used to be in the reboot case.  However,
+         * sometimes a SIGVTALRM can come in when we're halting (reproducably
+         * when writing out gcov information, presumably because that takes
+         * some time) and cause a segfault.
+         */
 
-		/* stop timers and set SIG*ALRM to be ignored */
-		disable_timer();
+        /* stop timers and set SIG*ALRM to be ignored */
+        disable_timer();
 
-		/* disable SIGIO for the fds and set SIGIO to be ignored */
-		err = deactivate_all_fds();
-		if(err)
-			printf("deactivate_all_fds failed, errno = %d\n",
-			       -err);
+        /* disable SIGIO for the fds and set SIGIO to be ignored */
+        err = deactivate_all_fds();
+        if(err)
+                printf("deactivate_all_fds failed, errno = %d\n", -err);
 
-		/* Let any pending signals fire now.  This ensures
-		 * that they won't be delivered after the exec, when
-		 * they are definitely not expected.
-		 */
-		unblock_signals();
+        /* Let any pending signals fire now.  This ensures
+         * that they won't be delivered after the exec, when
+         * they are definitely not expected.
+         */
+        unblock_signals();
 
+	/* Reboot */
+	if(ret){
+		printf("\n");
 		execvp(new_argv[0], new_argv);
 		perror("Failed to exec kernel");
 		ret = 1;

arch/um/kernel/process_kern.c

@@ -43,7 +43,6 @@
 #include "tlb.h"
 #include "frame_kern.h"
 #include "sigcontext.h"
-#include "2_5compat.h"
 #include "os.h"
 #include "mode.h"
 #include "mode_kern.h"
@@ -55,18 +54,6 @@
  */
 struct cpu_task cpu_tasks[NR_CPUS] = { [0 ... NR_CPUS - 1] = { -1, NULL } };
 
-struct task_struct *get_task(int pid, int require)
-{
-        struct task_struct *ret;
-
-        read_lock(&tasklist_lock);
-	ret = find_task_by_pid(pid);
-        read_unlock(&tasklist_lock);
-
-        if(require && (ret == NULL)) panic("get_task couldn't find a task\n");
-        return(ret);
-}
-
 int external_pid(void *t)
 {
 	struct task_struct *task = t ? t : current;
@@ -189,7 +176,6 @@ void default_idle(void)
 
 	while(1){
 		/* endless idle loop with no priority at all */
-		SET_PRI(current);
 
 		/*
 		 * although we are an idle CPU, we do not want to
@@ -212,11 +198,6 @@ int page_size(void)
 	return(PAGE_SIZE);
 }
 
-unsigned long page_mask(void)
-{
-	return(PAGE_MASK);
-}
-
 void *um_virt_to_phys(struct task_struct *task, unsigned long addr, 
 		      pte_t *pte_out)
 {
@@ -349,11 +330,6 @@ char *uml_strdup(char *string)
 	return(new);
 }
 
-void *get_init_task(void)
-{
-	return(&init_thread_union.thread_info.task);
-}
-
 int copy_to_user_proc(void __user *to, void *from, int size)
 {
 	return(copy_to_user(to, from, size));
@@ -480,15 +456,3 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ~0xf;
 }
 #endif
-
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/um/kernel/ptrace.c

@@ -322,11 +322,9 @@ void syscall_trace(union uml_pt_regs *regs, int entryexit)
 					    UPT_SYSCALL_ARG2(regs),
 					    UPT_SYSCALL_ARG3(regs),
 					    UPT_SYSCALL_ARG4(regs));
-		else {
-                        int res = UPT_SYSCALL_RET(regs);
-			audit_syscall_exit(current, AUDITSC_RESULT(res),
-                                           res);
-                }
+		else audit_syscall_exit(current,
+                                        AUDITSC_RESULT(UPT_SYSCALL_RET(regs)),
+                                        UPT_SYSCALL_RET(regs));
 	}
 
 	/* Fake a debug trap */
@@ -356,14 +354,3 @@ void syscall_trace(union uml_pt_regs *regs, int entryexit)
 		current->exit_code = 0;
 	}
 }
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/um/kernel/sysrq.c

@@ -3,6 +3,7 @@
  * Licensed under the GPL
  */
 
+#include "linux/config.h"
 #include "linux/sched.h"
 #include "linux/kernel.h"
 #include "linux/module.h"
@@ -12,14 +13,14 @@
 #include "sysrq.h"
 #include "user_util.h"
 
-void show_trace(unsigned long * stack)
+/* Catch non-i386 SUBARCH's. */
+#if !defined(CONFIG_UML_X86) || defined(CONFIG_64BIT)
+void show_trace(struct task_struct *task, unsigned long * stack)
 {
-	/* XXX: Copy the CONFIG_FRAME_POINTER stack-walking backtrace from
-	 * arch/i386/kernel/traps.c, and then move this to sys-i386/sysrq.c.*/
         unsigned long addr;
 
         if (!stack) {
-                stack = (unsigned long*) &stack;
+		stack = (unsigned long*) &stack;
 		WARN_ON(1);
 	}
 
@@ -35,6 +36,7 @@ void show_trace(unsigned long * stack)
         }
         printk("\n");
 }
+#endif
 
 /*
  * stack dumps generator - this is used by arch-independent code.
@@ -44,7 +46,7 @@ void dump_stack(void)
 {
 	unsigned long stack;
 
-	show_trace(&stack);
+	show_trace(current, &stack);
 }
 EXPORT_SYMBOL(dump_stack);
 
@@ -59,7 +61,11 @@ void show_stack(struct task_struct *task, unsigned long *esp)
 	int i;
 
 	if (esp == NULL) {
-		if (task != current) {
+		if (task != current && task != NULL) {
+			/* XXX: Isn't this bogus? I.e. isn't this the
+			 * *userspace* stack of this task? If not so, use this
+			 * even when task == current (as in i386).
+			 */
 			esp = (unsigned long *) KSTK_ESP(task);
 			/* Which one? No actual difference - just coding style.*/
 			//esp = (unsigned long *) PT_REGS_IP(&task->thread.regs);
@@ -77,5 +83,6 @@ void show_stack(struct task_struct *task, unsigned long *esp)
 		printk("%08lx ", *stack++);
 	}
 
-	show_trace(esp);
+	printk("Call Trace: \n");
+	show_trace(current, esp);
 }

arch/um/kernel/trap_kern.c

@@ -23,7 +23,6 @@
 #include "kern.h"
 #include "chan_kern.h"
 #include "mconsole_kern.h"
-#include "2_5compat.h"
 #include "mem.h"
 #include "mem_kern.h"
 

arch/um/kernel/tt/process_kern.c

@@ -32,10 +32,6 @@ void *switch_to_tt(void *prev, void *next, void *last)
 	unsigned long flags;
 	int err, vtalrm, alrm, prof, cpu;
 	char c;
-	/* jailing and SMP are incompatible, so this doesn't need to be 
-	 * made per-cpu 
-	 */
-	static int reading;
 
 	from = prev;
 	to = next;
@@ -59,13 +55,11 @@ void *switch_to_tt(void *prev, void *next, void *last)
 	c = 0;
 	set_current(to);
 
-	reading = 0;
 	err = os_write_file(to->thread.mode.tt.switch_pipe[1], &c, sizeof(c));
 	if(err != sizeof(c))
 		panic("write of switch_pipe failed, err = %d", -err);
 
-	reading = 1;
-        if(from->thread.mode.tt.switch_pipe[0] == -1)
+	if(from->thread.mode.tt.switch_pipe[0] == -1)
 		os_kill_process(os_getpid(), 0);
 
 	err = os_read_file(from->thread.mode.tt.switch_pipe[0], &c, sizeof(c));

arch/um/kernel/um_arch.c

@@ -111,12 +111,6 @@ struct seq_operations cpuinfo_op = {
 	.show	= show_cpuinfo,
 };
 
-pte_t * __bad_pagetable(void)
-{
-	panic("Someone should implement __bad_pagetable");
-	return(NULL);
-}
-
 /* Set in linux_main */
 unsigned long host_task_size;
 unsigned long task_size;

arch/um/sys-i386/sysrq.c

@@ -3,12 +3,15 @@
  * Licensed under the GPL
  */
 
+#include "linux/config.h"
 #include "linux/kernel.h"
 #include "linux/smp.h"
 #include "linux/sched.h"
+#include "linux/kallsyms.h"
 #include "asm/ptrace.h"
 #include "sysrq.h"
 
+/* This is declared by <linux/sched.h> */
 void show_regs(struct pt_regs *regs)
 {
         printk("\n");
@@ -31,5 +34,80 @@ void show_regs(struct pt_regs *regs)
 	       0xffff & PT_REGS_DS(regs), 
 	       0xffff & PT_REGS_ES(regs));
 
-        show_trace((unsigned long *) &regs);
+        show_trace(NULL, (unsigned long *) &regs);
 }
+
+/* Copied from i386. */
+static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
+{
+	return	p > (void *)tinfo &&
+		p < (void *)tinfo + THREAD_SIZE - 3;
+}
+
+/* Adapted from i386 (we also print the address we read from). */
+static inline unsigned long print_context_stack(struct thread_info *tinfo,
+				unsigned long *stack, unsigned long ebp)
+{
+	unsigned long addr;
+
+#ifdef CONFIG_FRAME_POINTER
+	while (valid_stack_ptr(tinfo, (void *)ebp)) {
+		addr = *(unsigned long *)(ebp + 4);
+		printk("%08lx:  [<%08lx>]", ebp + 4, addr);
+		print_symbol(" %s", addr);
+		printk("\n");
+		ebp = *(unsigned long *)ebp;
+	}
+#else
+	while (valid_stack_ptr(tinfo, stack)) {
+		addr = *stack;
+		if (__kernel_text_address(addr)) {
+			printk("%08lx:  [<%08lx>]", (unsigned long) stack, addr);
+			print_symbol(" %s", addr);
+			printk("\n");
+		}
+		stack++;
+	}
+#endif
+	return ebp;
+}
+
+void show_trace(struct task_struct* task, unsigned long * stack)
+{
+	unsigned long ebp;
+	struct thread_info *context;
+
+	/* Turn this into BUG_ON if possible. */
+	if (!stack) {
+		stack = (unsigned long*) &stack;
+		printk("show_trace: got NULL stack, implicit assumption task == current");
+		WARN_ON(1);
+	}
+
+	if (!task)
+		task = current;
+
+	if (task != current) {
+		//ebp = (unsigned long) KSTK_EBP(task);
+		/* Which one? No actual difference - just coding style.*/
+		ebp = (unsigned long) PT_REGS_EBP(&task->thread.regs);
+	} else {
+		asm ("movl %%ebp, %0" : "=r" (ebp) : );
+	}
+
+	context = (struct thread_info *)
+		((unsigned long)stack & (~(THREAD_SIZE - 1)));
+	print_context_stack(context, stack, ebp);
+
+	/*while (((long) stack & (THREAD_SIZE-1)) != 0) {
+		addr = *stack;
+		if (__kernel_text_address(addr)) {
+			printk("%08lx:	[<%08lx>]", (unsigned long) stack, addr);
+			print_symbol(" %s", addr);
+			printk("\n");
+		}
+		stack++;
+	}*/
+	printk("\n");
+}
+

arch/um/sys-ppc/sysrq.c

@@ -27,17 +27,5 @@ void show_regs(struct pt_regs_subarch *regs)
                 0xffff & regs->xds, 0xffff & regs->xes);
 #endif
 
-        show_trace(&regs->gpr[1]);
+        show_trace(current, &regs->gpr[1]);
 }
-
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/um/sys-x86_64/syscalls.c

@@ -133,23 +133,27 @@ static long arch_prctl_tt(int code, unsigned long addr)
 
 #ifdef CONFIG_MODE_SKAS
 
+/* XXX: Must also call arch_prctl in the host, beside saving the segment bases! */
 static long arch_prctl_skas(int code, unsigned long addr)
 {
 	long ret = 0;
 
 	switch(code){
-	case ARCH_SET_GS:
-		current->thread.regs.regs.skas.regs[GS_BASE / sizeof(unsigned long)] = addr;
-		break;
 	case ARCH_SET_FS:
 		current->thread.regs.regs.skas.regs[FS_BASE / sizeof(unsigned long)] = addr;
 		break;
+	case ARCH_SET_GS:
+		current->thread.regs.regs.skas.regs[GS_BASE / sizeof(unsigned long)] = addr;
+		break;
 	case ARCH_GET_FS:
-		ret = put_user(current->thread.regs.regs.skas.regs[GS / sizeof(unsigned long)], &addr);
+		ret = put_user(current->thread.regs.regs.skas.
+				regs[FS_BASE / sizeof(unsigned long)],
+				(unsigned long __user *)addr);
 	        break;
 	case ARCH_GET_GS:
-		ret = put_user(current->thread.regs.regs.skas.regs[FS / sizeof(unsigned \
-long)], &addr);
+		ret = put_user(current->thread.regs.regs.skas.
+				regs[GS_BASE / sizeof(unsigned long)],
+				(unsigned long __user *)addr);
 	        break;
 	default:
 		ret = -EINVAL;

arch/um/sys-x86_64/sysrq.c

@@ -36,14 +36,5 @@ void __show_regs(struct pt_regs * regs)
 void show_regs(struct pt_regs *regs)
 {
 	__show_regs(regs);
-	show_trace((unsigned long *) &regs);
+	show_trace(current, (unsigned long *) &regs);
 }
-
-/* Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */

arch/x86_64/Kconfig

@@ -305,6 +305,7 @@ config HPET_TIMER
 
 config X86_PM_TIMER
 	bool "PM timer"
+	depends on ACPI
 	default y
 	help
 	  Support the ACPI PM timer for time keeping. This is slow,

arch/x86_64/kernel/io_apic.c

@@ -37,6 +37,7 @@
 #include <asm/desc.h>
 #include <asm/proto.h>
 #include <asm/mach_apic.h>
+#include <asm/acpi.h>
 
 #define __apicdebuginit  __init
 

arch/x86_64/kernel/mpparse.c

@@ -30,6 +30,7 @@
 #include <asm/pgalloc.h>
 #include <asm/io_apic.h>
 #include <asm/proto.h>
+#include <asm/acpi.h>
 
 /* Have we found an MP table */
 int smp_found_config;

arch/x86_64/kernel/signal.c

@@ -28,6 +28,7 @@
 #include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/proto.h>
+#include <asm/ia32_unistd.h>
 
 /* #define DEBUG_SIG 1 */
 

arch/x86_64/kernel/time.c

@@ -27,7 +27,9 @@
 #include <linux/bcd.h>
 #include <linux/kallsyms.h>
 #include <linux/acpi.h>
+#ifdef CONFIG_ACPI
 #include <acpi/achware.h>	/* for PM timer frequency */
+#endif
 #include <asm/8253pit.h>
 #include <asm/pgtable.h>
 #include <asm/vsyscall.h>

drivers/cdrom/viocd.c

@@ -488,6 +488,20 @@ static int viocd_packet(struct cdrom_device_info *cdi,
 					 & (CDC_DVD_RAM | CDC_RAM)) != 0;
 		}
 		break;
+	case GPCMD_GET_CONFIGURATION:
+		if (cgc->cmd[3] == CDF_RWRT) {
+			struct rwrt_feature_desc *rfd = (struct rwrt_feature_desc *)(cgc->buffer + sizeof(struct feature_header));
+
+			if ((buflen >=
+			     (sizeof(struct feature_header) + sizeof(*rfd))) &&
+			    (cdi->ops->capability & ~cdi->mask
+			     & (CDC_DVD_RAM | CDC_RAM))) {
+				rfd->feature_code = cpu_to_be16(CDF_RWRT);
+				rfd->curr = 1;
+				ret = 0;
+			}
+		}
+		break;
 	default:
 		if (cgc->sense) {
 			/* indicate Unknown code */

drivers/cpufreq/Kconfig

@@ -46,6 +46,10 @@ config CPU_FREQ_STAT_DETAILS
          This will show detail CPU frequency translation table in sysfs file
          system
 
+# Note that it is not currently possible to set the other governors (such as ondemand)
+# as the default, since if they fail to initialise, cpufreq will be
+# left in an undefined state.
+
 choice
 	prompt "Default CPUFreq governor"
 	default CPU_FREQ_DEFAULT_GOV_USERSPACE if CPU_FREQ_SA1100 || CPU_FREQ_SA1110
@@ -115,4 +119,24 @@ config CPU_FREQ_GOV_ONDEMAND
 
 	  If in doubt, say N.
 
+config CPU_FREQ_GOV_CONSERVATIVE
+	tristate "'conservative' cpufreq governor"
+	depends on CPU_FREQ
+	help
+	  'conservative' - this driver is rather similar to the 'ondemand'
+	  governor both in its source code and its purpose, the difference is
+	  its optimisation for better suitability in a battery powered
+	  environment.  The frequency is gracefully increased and decreased
+	  rather than jumping to 100% when speed is required.
+
+	  If you have a desktop machine then you should really be considering
+	  the 'ondemand' governor instead, however if you are using a laptop,
+	  PDA or even an AMD64 based computer (due to the unacceptable
+	  step-by-step latency issues between the minimum and maximum frequency
+	  transitions in the CPU) you will probably want to use this governor.
+
+	  For details, take a look at linux/Documentation/cpu-freq.
+
+	  If in doubt, say N.
+
 endif	# CPU_FREQ

drivers/cpufreq/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_PERFORMANCE)	+= cpufreq_performance.o
 obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE)	+= cpufreq_powersave.o
 obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
 obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
+obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 
 # CPUfreq cross-arch helpers
 obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o

drivers/cpufreq/cpufreq.c

@@ -258,7 +258,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
 			    (likely(cpufreq_cpu_data[freqs->cpu]->cur)) &&
 			    (unlikely(freqs->old != cpufreq_cpu_data[freqs->cpu]->cur)))
 			{
-				printk(KERN_WARNING "Warning: CPU frequency is %u, "
+				dprintk(KERN_WARNING "Warning: CPU frequency is %u, "
 				       "cpufreq assumed %u kHz.\n", freqs->old, cpufreq_cpu_data[freqs->cpu]->cur);
 				freqs->old = cpufreq_cpu_data[freqs->cpu]->cur;
 			}
@@ -814,7 +814,7 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigne
 {
 	struct cpufreq_freqs freqs;
 
-	printk(KERN_WARNING "Warning: CPU frequency out of sync: cpufreq and timing "
+	dprintk(KERN_WARNING "Warning: CPU frequency out of sync: cpufreq and timing "
 	       "core thinks of %u, is %u kHz.\n", old_freq, new_freq);
 
 	freqs.cpu = cpu;
@@ -923,7 +923,7 @@ static int cpufreq_suspend(struct sys_device * sysdev, u32 state)
 		struct cpufreq_freqs freqs;
 
 		if (!(cpufreq_driver->flags & CPUFREQ_PM_NO_WARN))
-			printk(KERN_DEBUG "Warning: CPU frequency is %u, "
+			dprintk(KERN_DEBUG "Warning: CPU frequency is %u, "
 			       "cpufreq assumed %u kHz.\n",
 			       cur_freq, cpu_policy->cur);
 
@@ -1004,7 +1004,7 @@ static int cpufreq_resume(struct sys_device * sysdev)
 			struct cpufreq_freqs freqs;
 
 			if (!(cpufreq_driver->flags & CPUFREQ_PM_NO_WARN))
-				printk(KERN_WARNING "Warning: CPU frequency"
+				dprintk(KERN_WARNING "Warning: CPU frequency"
 				       "is %u, cpufreq assumed %u kHz.\n",
 				       cur_freq, cpu_policy->cur);
 

drivers/cpufreq/cpufreq_conservative.c

@@ -0,0 +1,586 @@
+/*
+ *  drivers/cpufreq/cpufreq_conservative.c
+ *
+ *  Copyright (C)  2001 Russell King
+ *            (C)  2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *                      Jun Nakajima <jun.nakajima@intel.com>
+ *            (C)  2004 Alexander Clouter <alex-kernel@digriz.org.uk>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ctype.h>
+#include <linux/cpufreq.h>
+#include <linux/sysctl.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/sched.h>
+#include <linux/kmod.h>
+#include <linux/workqueue.h>
+#include <linux/jiffies.h>
+#include <linux/kernel_stat.h>
+#include <linux/percpu.h>
+
+/*
+ * dbs is used in this file as a shortform for demandbased switching
+ * It helps to keep variable names smaller, simpler
+ */
+
+#define DEF_FREQUENCY_UP_THRESHOLD		(80)
+#define MIN_FREQUENCY_UP_THRESHOLD		(0)
+#define MAX_FREQUENCY_UP_THRESHOLD		(100)
+
+#define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
+#define MIN_FREQUENCY_DOWN_THRESHOLD		(0)
+#define MAX_FREQUENCY_DOWN_THRESHOLD		(100)
+
+/* 
+ * The polling frequency of this governor depends on the capability of 
+ * the processor. Default polling frequency is 1000 times the transition
+ * latency of the processor. The governor will work on any processor with 
+ * transition latency <= 10mS, using appropriate sampling 
+ * rate.
+ * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
+ * this governor will not work.
+ * All times here are in uS.
+ */
+static unsigned int 				def_sampling_rate;
+#define MIN_SAMPLING_RATE			(def_sampling_rate / 2)
+#define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
+#define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(100000)
+#define DEF_SAMPLING_DOWN_FACTOR		(5)
+#define TRANSITION_LATENCY_LIMIT		(10 * 1000)
+
+static void do_dbs_timer(void *data);
+
+struct cpu_dbs_info_s {
+	struct cpufreq_policy 	*cur_policy;
+	unsigned int 		prev_cpu_idle_up;
+	unsigned int 		prev_cpu_idle_down;
+	unsigned int 		enable;
+};
+static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
+
+static unsigned int dbs_enable;	/* number of CPUs using this policy */
+
+static DECLARE_MUTEX 	(dbs_sem);
+static DECLARE_WORK	(dbs_work, do_dbs_timer, NULL);
+
+struct dbs_tuners {
+	unsigned int 		sampling_rate;
+	unsigned int		sampling_down_factor;
+	unsigned int		up_threshold;
+	unsigned int		down_threshold;
+	unsigned int		ignore_nice;
+	unsigned int		freq_step;
+};
+
+static struct dbs_tuners dbs_tuners_ins = {
+	.up_threshold 		= DEF_FREQUENCY_UP_THRESHOLD,
+	.down_threshold 	= DEF_FREQUENCY_DOWN_THRESHOLD,
+	.sampling_down_factor 	= DEF_SAMPLING_DOWN_FACTOR,
+};
+
+static inline unsigned int get_cpu_idle_time(unsigned int cpu)
+{
+	return	kstat_cpu(cpu).cpustat.idle +
+		kstat_cpu(cpu).cpustat.iowait +
+		( !dbs_tuners_ins.ignore_nice ? 
+		  kstat_cpu(cpu).cpustat.nice :
+		  0);
+}
+
+/************************** sysfs interface ************************/
+static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", MAX_SAMPLING_RATE);
+}
+
+static ssize_t show_sampling_rate_min(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf (buf, "%u\n", MIN_SAMPLING_RATE);
+}
+
+#define define_one_ro(_name) 					\
+static struct freq_attr _name =  				\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+define_one_ro(sampling_rate_max);
+define_one_ro(sampling_rate_min);
+
+/* cpufreq_conservative Governor Tunables */
+#define show_one(file_name, object)					\
+static ssize_t show_##file_name						\
+(struct cpufreq_policy *unused, char *buf)				\
+{									\
+	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
+}
+show_one(sampling_rate, sampling_rate);
+show_one(sampling_down_factor, sampling_down_factor);
+show_one(up_threshold, up_threshold);
+show_one(down_threshold, down_threshold);
+show_one(ignore_nice, ignore_nice);
+show_one(freq_step, freq_step);
+
+static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+	if (ret != 1 )
+		return -EINVAL;
+
+	down(&dbs_sem);
+	dbs_tuners_ins.sampling_down_factor = input;
+	up(&dbs_sem);
+
+	return count;
+}
+
+static ssize_t store_sampling_rate(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+
+	down(&dbs_sem);
+	if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) {
+		up(&dbs_sem);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.sampling_rate = input;
+	up(&dbs_sem);
+
+	return count;
+}
+
+static ssize_t store_up_threshold(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+
+	down(&dbs_sem);
+	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD || 
+			input < MIN_FREQUENCY_UP_THRESHOLD ||
+			input <= dbs_tuners_ins.down_threshold) {
+		up(&dbs_sem);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.up_threshold = input;
+	up(&dbs_sem);
+
+	return count;
+}
+
+static ssize_t store_down_threshold(struct cpufreq_policy *unused, 
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf (buf, "%u", &input);
+
+	down(&dbs_sem);
+	if (ret != 1 || input > MAX_FREQUENCY_DOWN_THRESHOLD || 
+			input < MIN_FREQUENCY_DOWN_THRESHOLD ||
+			input >= dbs_tuners_ins.up_threshold) {
+		up(&dbs_sem);
+		return -EINVAL;
+	}
+
+	dbs_tuners_ins.down_threshold = input;
+	up(&dbs_sem);
+
+	return count;
+}
+
+static ssize_t store_ignore_nice(struct cpufreq_policy *policy,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	unsigned int j;
+	
+	ret = sscanf (buf, "%u", &input);
+	if ( ret != 1 )
+		return -EINVAL;
+
+	if ( input > 1 )
+		input = 1;
+	
+	down(&dbs_sem);
+	if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */
+		up(&dbs_sem);
+		return count;
+	}
+	dbs_tuners_ins.ignore_nice = input;
+
+	/* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */
+	for_each_online_cpu(j) {
+		struct cpu_dbs_info_s *j_dbs_info;
+		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
+		j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up;
+	}
+	up(&dbs_sem);
+
+	return count;
+}
+
+static ssize_t store_freq_step(struct cpufreq_policy *policy,
+		const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	ret = sscanf (buf, "%u", &input);
+
+	if ( ret != 1 )
+		return -EINVAL;
+
+	if ( input > 100 )
+		input = 100;
+	
+	/* no need to test here if freq_step is zero as the user might actually
+	 * want this, they would be crazy though :) */
+	down(&dbs_sem);
+	dbs_tuners_ins.freq_step = input;
+	up(&dbs_sem);
+
+	return count;
+}
+
+#define define_one_rw(_name) \
+static struct freq_attr _name = \
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+define_one_rw(sampling_rate);
+define_one_rw(sampling_down_factor);
+define_one_rw(up_threshold);
+define_one_rw(down_threshold);
+define_one_rw(ignore_nice);
+define_one_rw(freq_step);
+
+static struct attribute * dbs_attributes[] = {
+	&sampling_rate_max.attr,
+	&sampling_rate_min.attr,
+	&sampling_rate.attr,
+	&sampling_down_factor.attr,
+	&up_threshold.attr,
+	&down_threshold.attr,
+	&ignore_nice.attr,
+	&freq_step.attr,
+	NULL
+};
+
+static struct attribute_group dbs_attr_group = {
+	.attrs = dbs_attributes,
+	.name = "conservative",
+};
+
+/************************** sysfs end ************************/
+
+static void dbs_check_cpu(int cpu)
+{
+	unsigned int idle_ticks, up_idle_ticks, down_idle_ticks;
+	unsigned int freq_step;
+	unsigned int freq_down_sampling_rate;
+	static int down_skip[NR_CPUS];
+	static int requested_freq[NR_CPUS];
+	static unsigned short init_flag = 0;
+	struct cpu_dbs_info_s *this_dbs_info;
+	struct cpu_dbs_info_s *dbs_info;
+
+	struct cpufreq_policy *policy;
+	unsigned int j;
+
+	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+	if (!this_dbs_info->enable)
+		return;
+
+	policy = this_dbs_info->cur_policy;
+
+	if ( init_flag == 0 ) {
+		for ( /* NULL */; init_flag < NR_CPUS; init_flag++ ) {
+			dbs_info = &per_cpu(cpu_dbs_info, init_flag);
+			requested_freq[cpu] = dbs_info->cur_policy->cur;
+		}
+		init_flag = 1;
+	}
+	
+	/* 
+	 * The default safe range is 20% to 80% 
+	 * Every sampling_rate, we check
+	 * 	- If current idle time is less than 20%, then we try to 
+	 * 	  increase frequency
+	 * Every sampling_rate*sampling_down_factor, we check
+	 * 	- If current idle time is more than 80%, then we try to
+	 * 	  decrease frequency
+	 *
+	 * Any frequency increase takes it to the maximum frequency. 
+	 * Frequency reduction happens at minimum steps of 
+	 * 5% (default) of max_frequency 
+	 */
+
+	/* Check for frequency increase */
+
+	idle_ticks = UINT_MAX;
+	for_each_cpu_mask(j, policy->cpus) {
+		unsigned int tmp_idle_ticks, total_idle_ticks;
+		struct cpu_dbs_info_s *j_dbs_info;
+
+		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		/* Check for frequency increase */
+		total_idle_ticks = get_cpu_idle_time(j);
+		tmp_idle_ticks = total_idle_ticks -
+			j_dbs_info->prev_cpu_idle_up;
+		j_dbs_info->prev_cpu_idle_up = total_idle_ticks;
+
+		if (tmp_idle_ticks < idle_ticks)
+			idle_ticks = tmp_idle_ticks;
+	}
+
+	/* Scale idle ticks by 100 and compare with up and down ticks */
+	idle_ticks *= 100;
+	up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) *
+		usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+
+	if (idle_ticks < up_idle_ticks) {
+		down_skip[cpu] = 0;
+		for_each_cpu_mask(j, policy->cpus) {
+			struct cpu_dbs_info_s *j_dbs_info;
+
+			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info->prev_cpu_idle_down = 
+					j_dbs_info->prev_cpu_idle_up;
+		}
+		/* if we are already at full speed then break out early */
+		if (requested_freq[cpu] == policy->max)
+			return;
+		
+		freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;
+
+		/* max freq cannot be less than 100. But who knows.... */
+		if (unlikely(freq_step == 0))
+			freq_step = 5;
+		
+		requested_freq[cpu] += freq_step;
+		if (requested_freq[cpu] > policy->max)
+			requested_freq[cpu] = policy->max;
+
+		__cpufreq_driver_target(policy, requested_freq[cpu], 
+			CPUFREQ_RELATION_H);
+		return;
+	}
+
+	/* Check for frequency decrease */
+	down_skip[cpu]++;
+	if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor)
+		return;
+
+	idle_ticks = UINT_MAX;
+	for_each_cpu_mask(j, policy->cpus) {
+		unsigned int tmp_idle_ticks, total_idle_ticks;
+		struct cpu_dbs_info_s *j_dbs_info;
+
+		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		total_idle_ticks = j_dbs_info->prev_cpu_idle_up;
+		tmp_idle_ticks = total_idle_ticks -
+			j_dbs_info->prev_cpu_idle_down;
+		j_dbs_info->prev_cpu_idle_down = total_idle_ticks;
+
+		if (tmp_idle_ticks < idle_ticks)
+			idle_ticks = tmp_idle_ticks;
+	}
+
+	/* Scale idle ticks by 100 and compare with up and down ticks */
+	idle_ticks *= 100;
+	down_skip[cpu] = 0;
+
+	freq_down_sampling_rate = dbs_tuners_ins.sampling_rate *
+		dbs_tuners_ins.sampling_down_factor;
+	down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) *
+			usecs_to_jiffies(freq_down_sampling_rate);
+
+	if (idle_ticks > down_idle_ticks) {
+		/* if we are already at the lowest speed then break out early
+		 * or if we 'cannot' reduce the speed as the user might want
+		 * freq_step to be zero */
+		if (requested_freq[cpu] == policy->min
+				|| dbs_tuners_ins.freq_step == 0)
+			return;
+
+		freq_step = (dbs_tuners_ins.freq_step * policy->max) / 100;
+
+		/* max freq cannot be less than 100. But who knows.... */
+		if (unlikely(freq_step == 0))
+			freq_step = 5;
+
+		requested_freq[cpu] -= freq_step;
+		if (requested_freq[cpu] < policy->min)
+			requested_freq[cpu] = policy->min;
+
+		__cpufreq_driver_target(policy,
+			requested_freq[cpu],
+			CPUFREQ_RELATION_H);
+		return;
+	}
+}
+
+static void do_dbs_timer(void *data)
+{ 
+	int i;
+	down(&dbs_sem);
+	for_each_online_cpu(i)
+		dbs_check_cpu(i);
+	schedule_delayed_work(&dbs_work, 
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
+	up(&dbs_sem);
+} 
+
+static inline void dbs_timer_init(void)
+{
+	INIT_WORK(&dbs_work, do_dbs_timer, NULL);
+	schedule_delayed_work(&dbs_work,
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
+	return;
+}
+
+static inline void dbs_timer_exit(void)
+{
+	cancel_delayed_work(&dbs_work);
+	return;
+}
+
+static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+				   unsigned int event)
+{
+	unsigned int cpu = policy->cpu;
+	struct cpu_dbs_info_s *this_dbs_info;
+	unsigned int j;
+
+	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if ((!cpu_online(cpu)) || 
+		    (!policy->cur))
+			return -EINVAL;
+
+		if (policy->cpuinfo.transition_latency >
+				(TRANSITION_LATENCY_LIMIT * 1000))
+			return -EINVAL;
+		if (this_dbs_info->enable) /* Already enabled */
+			break;
+		 
+		down(&dbs_sem);
+		for_each_cpu_mask(j, policy->cpus) {
+			struct cpu_dbs_info_s *j_dbs_info;
+			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info->cur_policy = policy;
+		
+			j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
+			j_dbs_info->prev_cpu_idle_down
+				= j_dbs_info->prev_cpu_idle_up;
+		}
+		this_dbs_info->enable = 1;
+		sysfs_create_group(&policy->kobj, &dbs_attr_group);
+		dbs_enable++;
+		/*
+		 * Start the timerschedule work, when this governor
+		 * is used for first time
+		 */
+		if (dbs_enable == 1) {
+			unsigned int latency;
+			/* policy latency is in nS. Convert it to uS first */
+
+			latency = policy->cpuinfo.transition_latency;
+			if (latency < 1000)
+				latency = 1000;
+
+			def_sampling_rate = (latency / 1000) *
+					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
+			dbs_tuners_ins.sampling_rate = def_sampling_rate;
+			dbs_tuners_ins.ignore_nice = 0;
+			dbs_tuners_ins.freq_step = 5;
+
+			dbs_timer_init();
+		}
+		
+		up(&dbs_sem);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		down(&dbs_sem);
+		this_dbs_info->enable = 0;
+		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
+		dbs_enable--;
+		/*
+		 * Stop the timerschedule work, when this governor
+		 * is used for first time
+		 */
+		if (dbs_enable == 0) 
+			dbs_timer_exit();
+		
+		up(&dbs_sem);
+
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		down(&dbs_sem);
+		if (policy->max < this_dbs_info->cur_policy->cur)
+			__cpufreq_driver_target(
+					this_dbs_info->cur_policy,
+				       	policy->max, CPUFREQ_RELATION_H);
+		else if (policy->min > this_dbs_info->cur_policy->cur)
+			__cpufreq_driver_target(
+					this_dbs_info->cur_policy,
+				       	policy->min, CPUFREQ_RELATION_L);
+		up(&dbs_sem);
+		break;
+	}
+	return 0;
+}
+
+static struct cpufreq_governor cpufreq_gov_dbs = {
+	.name		= "conservative",
+	.governor	= cpufreq_governor_dbs,
+	.owner		= THIS_MODULE,
+};
+
+static int __init cpufreq_gov_dbs_init(void)
+{
+	return cpufreq_register_governor(&cpufreq_gov_dbs);
+}
+
+static void __exit cpufreq_gov_dbs_exit(void)
+{
+	/* Make sure that the scheduled work is indeed not running */
+	flush_scheduled_work();
+
+	cpufreq_unregister_governor(&cpufreq_gov_dbs);
+}
+
+
+MODULE_AUTHOR ("Alexander Clouter <alex-kernel@digriz.org.uk>");
+MODULE_DESCRIPTION ("'cpufreq_conservative' - A dynamic cpufreq governor for "
+		"Low Latency Frequency Transition capable processors "
+		"optimised for use in a battery environment");
+MODULE_LICENSE ("GPL");
+
+module_init(cpufreq_gov_dbs_init);
+module_exit(cpufreq_gov_dbs_exit);

drivers/cpufreq/cpufreq_ondemand.c

@@ -34,13 +34,9 @@
  */
 
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
-#define MIN_FREQUENCY_UP_THRESHOLD		(0)
+#define MIN_FREQUENCY_UP_THRESHOLD		(11)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
-#define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
-#define MIN_FREQUENCY_DOWN_THRESHOLD		(0)
-#define MAX_FREQUENCY_DOWN_THRESHOLD		(100)
-
 /* 
  * The polling frequency of this governor depends on the capability of 
  * the processor. Default polling frequency is 1000 times the transition
@@ -55,9 +51,9 @@ static unsigned int 				def_sampling_rate;
 #define MIN_SAMPLING_RATE			(def_sampling_rate / 2)
 #define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
 #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(1000)
-#define DEF_SAMPLING_DOWN_FACTOR		(10)
+#define DEF_SAMPLING_DOWN_FACTOR		(1)
+#define MAX_SAMPLING_DOWN_FACTOR		(10)
 #define TRANSITION_LATENCY_LIMIT		(10 * 1000)
-#define sampling_rate_in_HZ(x)			(((x * HZ) < (1000 * 1000))?1:((x * HZ) / (1000 * 1000)))
 
 static void do_dbs_timer(void *data);
 
@@ -78,15 +74,23 @@ struct dbs_tuners {
 	unsigned int 		sampling_rate;
 	unsigned int		sampling_down_factor;
 	unsigned int		up_threshold;
-	unsigned int		down_threshold;
+	unsigned int		ignore_nice;
 };
 
 static struct dbs_tuners dbs_tuners_ins = {
 	.up_threshold 		= DEF_FREQUENCY_UP_THRESHOLD,
-	.down_threshold 	= DEF_FREQUENCY_DOWN_THRESHOLD,
 	.sampling_down_factor 	= DEF_SAMPLING_DOWN_FACTOR,
 };
 
+static inline unsigned int get_cpu_idle_time(unsigned int cpu)
+{
+	return	kstat_cpu(cpu).cpustat.idle +
+		kstat_cpu(cpu).cpustat.iowait +
+		( !dbs_tuners_ins.ignore_nice ? 
+		  kstat_cpu(cpu).cpustat.nice :
+		  0);
+}
+
 /************************** sysfs interface ************************/
 static ssize_t show_sampling_rate_max(struct cpufreq_policy *policy, char *buf)
 {
@@ -115,7 +119,7 @@ static ssize_t show_##file_name						\
 show_one(sampling_rate, sampling_rate);
 show_one(sampling_down_factor, sampling_down_factor);
 show_one(up_threshold, up_threshold);
-show_one(down_threshold, down_threshold);
+show_one(ignore_nice, ignore_nice);
 
 static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused, 
 		const char *buf, size_t count)
@@ -126,6 +130,9 @@ static ssize_t store_sampling_down_factor(struct cpufreq_policy *unused,
 	if (ret != 1 )
 		return -EINVAL;
 
+	if (input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
+		return -EINVAL;
+
 	down(&dbs_sem);
 	dbs_tuners_ins.sampling_down_factor = input;
 	up(&dbs_sem);
@@ -161,8 +168,7 @@ static ssize_t store_up_threshold(struct cpufreq_policy *unused,
 
 	down(&dbs_sem);
 	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD || 
-			input < MIN_FREQUENCY_UP_THRESHOLD ||
-			input <= dbs_tuners_ins.down_threshold) {
+			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		up(&dbs_sem);
 		return -EINVAL;
 	}
@@ -173,22 +179,35 @@ static ssize_t store_up_threshold(struct cpufreq_policy *unused,
 	return count;
 }
 
-static ssize_t store_down_threshold(struct cpufreq_policy *unused, 
+static ssize_t store_ignore_nice(struct cpufreq_policy *policy,
 		const char *buf, size_t count)
 {
 	unsigned int input;
 	int ret;
+
+	unsigned int j;
+	
 	ret = sscanf (buf, "%u", &input);
+	if ( ret != 1 )
+		return -EINVAL;
 
+	if ( input > 1 )
+		input = 1;
+	
 	down(&dbs_sem);
-	if (ret != 1 || input > MAX_FREQUENCY_DOWN_THRESHOLD || 
-			input < MIN_FREQUENCY_DOWN_THRESHOLD ||
-			input >= dbs_tuners_ins.up_threshold) {
+	if ( input == dbs_tuners_ins.ignore_nice ) { /* nothing to do */
 		up(&dbs_sem);
-		return -EINVAL;
+		return count;
 	}
+	dbs_tuners_ins.ignore_nice = input;
 
-	dbs_tuners_ins.down_threshold = input;
+	/* we need to re-evaluate prev_cpu_idle_up and prev_cpu_idle_down */
+	for_each_online_cpu(j) {
+		struct cpu_dbs_info_s *j_dbs_info;
+		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
+		j_dbs_info->prev_cpu_idle_down = j_dbs_info->prev_cpu_idle_up;
+	}
 	up(&dbs_sem);
 
 	return count;
@@ -201,7 +220,7 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
 define_one_rw(sampling_rate);
 define_one_rw(sampling_down_factor);
 define_one_rw(up_threshold);
-define_one_rw(down_threshold);
+define_one_rw(ignore_nice);
 
 static struct attribute * dbs_attributes[] = {
 	&sampling_rate_max.attr,
@@ -209,7 +228,7 @@ static struct attribute * dbs_attributes[] = {
 	&sampling_rate.attr,
 	&sampling_down_factor.attr,
 	&up_threshold.attr,
-	&down_threshold.attr,
+	&ignore_nice.attr,
 	NULL
 };
 
@@ -222,9 +241,8 @@ static struct attribute_group dbs_attr_group = {
 
 static void dbs_check_cpu(int cpu)
 {
-	unsigned int idle_ticks, up_idle_ticks, down_idle_ticks;
-	unsigned int total_idle_ticks;
-	unsigned int freq_down_step;
+	unsigned int idle_ticks, up_idle_ticks, total_ticks;
+	unsigned int freq_next;
 	unsigned int freq_down_sampling_rate;
 	static int down_skip[NR_CPUS];
 	struct cpu_dbs_info_s *this_dbs_info;
@@ -238,38 +256,25 @@ static void dbs_check_cpu(int cpu)
 
 	policy = this_dbs_info->cur_policy;
 	/* 
-	 * The default safe range is 20% to 80% 
-	 * Every sampling_rate, we check
-	 * 	- If current idle time is less than 20%, then we try to 
-	 * 	  increase frequency
-	 * Every sampling_rate*sampling_down_factor, we check
-	 * 	- If current idle time is more than 80%, then we try to
-	 * 	  decrease frequency
+	 * Every sampling_rate, we check, if current idle time is less
+	 * than 20% (default), then we try to increase frequency
+	 * Every sampling_rate*sampling_down_factor, we look for a the lowest
+	 * frequency which can sustain the load while keeping idle time over
+	 * 30%. If such a frequency exist, we try to decrease to this frequency.
 	 *
 	 * Any frequency increase takes it to the maximum frequency. 
 	 * Frequency reduction happens at minimum steps of 
-	 * 5% of max_frequency 
+	 * 5% (default) of current frequency 
 	 */
 
 	/* Check for frequency increase */
-	total_idle_ticks = kstat_cpu(cpu).cpustat.idle +
-		kstat_cpu(cpu).cpustat.iowait;
-	idle_ticks = total_idle_ticks -
-		this_dbs_info->prev_cpu_idle_up;
-	this_dbs_info->prev_cpu_idle_up = total_idle_ticks;
-	
-
+	idle_ticks = UINT_MAX;
 	for_each_cpu_mask(j, policy->cpus) {
-		unsigned int tmp_idle_ticks;
+		unsigned int tmp_idle_ticks, total_idle_ticks;
 		struct cpu_dbs_info_s *j_dbs_info;
 
-		if (j == cpu)
-			continue;
-
 		j_dbs_info = &per_cpu(cpu_dbs_info, j);
-		/* Check for frequency increase */
-		total_idle_ticks = kstat_cpu(j).cpustat.idle +
-			kstat_cpu(j).cpustat.iowait;
+		total_idle_ticks = get_cpu_idle_time(j);
 		tmp_idle_ticks = total_idle_ticks -
 			j_dbs_info->prev_cpu_idle_up;
 		j_dbs_info->prev_cpu_idle_up = total_idle_ticks;
@@ -281,13 +286,23 @@ static void dbs_check_cpu(int cpu)
 	/* Scale idle ticks by 100 and compare with up and down ticks */
 	idle_ticks *= 100;
 	up_idle_ticks = (100 - dbs_tuners_ins.up_threshold) *
-			sampling_rate_in_HZ(dbs_tuners_ins.sampling_rate);
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
 
 	if (idle_ticks < up_idle_ticks) {
+		down_skip[cpu] = 0;
+		for_each_cpu_mask(j, policy->cpus) {
+			struct cpu_dbs_info_s *j_dbs_info;
+
+			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info->prev_cpu_idle_down = 
+					j_dbs_info->prev_cpu_idle_up;
+		}
+		/* if we are already at full speed then break out early */
+		if (policy->cur == policy->max)
+			return;
+		
 		__cpufreq_driver_target(policy, policy->max, 
 			CPUFREQ_RELATION_H);
-		down_skip[cpu] = 0;
-		this_dbs_info->prev_cpu_idle_down = total_idle_ticks;
 		return;
 	}
 
@@ -296,23 +311,14 @@ static void dbs_check_cpu(int cpu)
 	if (down_skip[cpu] < dbs_tuners_ins.sampling_down_factor)
 		return;
 
-	total_idle_ticks = kstat_cpu(cpu).cpustat.idle +
-		kstat_cpu(cpu).cpustat.iowait;
-	idle_ticks = total_idle_ticks -
-		this_dbs_info->prev_cpu_idle_down;
-	this_dbs_info->prev_cpu_idle_down = total_idle_ticks;
-
+	idle_ticks = UINT_MAX;
 	for_each_cpu_mask(j, policy->cpus) {
-		unsigned int tmp_idle_ticks;
+		unsigned int tmp_idle_ticks, total_idle_ticks;
 		struct cpu_dbs_info_s *j_dbs_info;
 
-		if (j == cpu)
-			continue;
-
 		j_dbs_info = &per_cpu(cpu_dbs_info, j);
-		/* Check for frequency increase */
-		total_idle_ticks = kstat_cpu(j).cpustat.idle +
-			kstat_cpu(j).cpustat.iowait;
+		/* Check for frequency decrease */
+		total_idle_ticks = j_dbs_info->prev_cpu_idle_up;
 		tmp_idle_ticks = total_idle_ticks -
 			j_dbs_info->prev_cpu_idle_down;
 		j_dbs_info->prev_cpu_idle_down = total_idle_ticks;
@@ -321,38 +327,37 @@ static void dbs_check_cpu(int cpu)
 			idle_ticks = tmp_idle_ticks;
 	}
 
-	/* Scale idle ticks by 100 and compare with up and down ticks */
-	idle_ticks *= 100;
 	down_skip[cpu] = 0;
+	/* if we cannot reduce the frequency anymore, break out early */
+	if (policy->cur == policy->min)
+		return;
 
+	/* Compute how many ticks there are between two measurements */
 	freq_down_sampling_rate = dbs_tuners_ins.sampling_rate *
 		dbs_tuners_ins.sampling_down_factor;
-	down_idle_ticks = (100 - dbs_tuners_ins.down_threshold) *
-			sampling_rate_in_HZ(freq_down_sampling_rate);
+	total_ticks = usecs_to_jiffies(freq_down_sampling_rate);
 
-	if (idle_ticks > down_idle_ticks ) {
-		freq_down_step = (5 * policy->max) / 100;
-
-		/* max freq cannot be less than 100. But who knows.... */
-		if (unlikely(freq_down_step == 0))
-			freq_down_step = 5;
+	/*
+	 * The optimal frequency is the frequency that is the lowest that
+	 * can support the current CPU usage without triggering the up
+	 * policy. To be safe, we focus 10 points under the threshold.
+	 */
+	freq_next = ((total_ticks - idle_ticks) * 100) / total_ticks;
+	freq_next = (freq_next * policy->cur) / 
+			(dbs_tuners_ins.up_threshold - 10);
 
-		__cpufreq_driver_target(policy,
-			policy->cur - freq_down_step, 
-			CPUFREQ_RELATION_H);
-		return;
-	}
+	if (freq_next <= ((policy->cur * 95) / 100))
+		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L);
 }
 
 static void do_dbs_timer(void *data)
 { 
 	int i;
 	down(&dbs_sem);
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_online(i))
-			dbs_check_cpu(i);
+	for_each_online_cpu(i)
+		dbs_check_cpu(i);
 	schedule_delayed_work(&dbs_work, 
-			sampling_rate_in_HZ(dbs_tuners_ins.sampling_rate));
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
 	up(&dbs_sem);
 } 
 
@@ -360,7 +365,7 @@ static inline void dbs_timer_init(void)
 {
 	INIT_WORK(&dbs_work, do_dbs_timer, NULL);
 	schedule_delayed_work(&dbs_work,
-			sampling_rate_in_HZ(dbs_tuners_ins.sampling_rate));
+			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
 	return;
 }
 
@@ -397,12 +402,9 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			j_dbs_info = &per_cpu(cpu_dbs_info, j);
 			j_dbs_info->cur_policy = policy;
 		
-			j_dbs_info->prev_cpu_idle_up = 
-				kstat_cpu(j).cpustat.idle +
-				kstat_cpu(j).cpustat.iowait;
-			j_dbs_info->prev_cpu_idle_down = 
-				kstat_cpu(j).cpustat.idle +
-				kstat_cpu(j).cpustat.iowait;
+			j_dbs_info->prev_cpu_idle_up = get_cpu_idle_time(j);
+			j_dbs_info->prev_cpu_idle_down
+				= j_dbs_info->prev_cpu_idle_up;
 		}
 		this_dbs_info->enable = 1;
 		sysfs_create_group(&policy->kobj, &dbs_attr_group);
@@ -422,6 +424,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			def_sampling_rate = (latency / 1000) *
 					DEF_SAMPLING_RATE_LATENCY_MULTIPLIER;
 			dbs_tuners_ins.sampling_rate = def_sampling_rate;
+			dbs_tuners_ins.ignore_nice = 0;
 
 			dbs_timer_init();
 		}
@@ -461,12 +464,11 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	return 0;
 }
 
-struct cpufreq_governor cpufreq_gov_dbs = {
+static struct cpufreq_governor cpufreq_gov_dbs = {
 	.name		= "ondemand",
 	.governor	= cpufreq_governor_dbs,
 	.owner		= THIS_MODULE,
 };
-EXPORT_SYMBOL(cpufreq_gov_dbs);
 
 static int __init cpufreq_gov_dbs_init(void)
 {

drivers/cpufreq/cpufreq_stats.c

@@ -19,6 +19,7 @@
 #include <linux/percpu.h>
 #include <linux/kobject.h>
 #include <linux/spinlock.h>
+#include <asm/cputime.h>
 
 static spinlock_t cpufreq_stats_lock;
 
@@ -29,20 +30,14 @@ static struct freq_attr _attr_##_name = {\
 	.show = _show,\
 };
 
-static unsigned long
-delta_time(unsigned long old, unsigned long new)
-{
-	return (old > new) ? (old - new): (new + ~old + 1);
-}
-
 struct cpufreq_stats {
 	unsigned int cpu;
 	unsigned int total_trans;
-	unsigned long long last_time;
+	unsigned long long  last_time;
 	unsigned int max_state;
 	unsigned int state_num;
 	unsigned int last_index;
-	unsigned long long *time_in_state;
+	cputime64_t *time_in_state;
 	unsigned int *freq_table;
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	unsigned int *trans_table;
@@ -60,12 +55,16 @@ static int
 cpufreq_stats_update (unsigned int cpu)
 {
 	struct cpufreq_stats *stat;
+	unsigned long long cur_time;
+
+	cur_time = get_jiffies_64();
 	spin_lock(&cpufreq_stats_lock);
 	stat = cpufreq_stats_table[cpu];
 	if (stat->time_in_state)
-		stat->time_in_state[stat->last_index] +=
-			delta_time(stat->last_time, jiffies);
-	stat->last_time = jiffies;
+		stat->time_in_state[stat->last_index] =
+			cputime64_add(stat->time_in_state[stat->last_index],
+				      cputime_sub(cur_time, stat->last_time));
+	stat->last_time = cur_time;
 	spin_unlock(&cpufreq_stats_lock);
 	return 0;
 }
@@ -90,8 +89,8 @@ show_time_in_state(struct cpufreq_policy *policy, char *buf)
 		return 0;
 	cpufreq_stats_update(stat->cpu);
 	for (i = 0; i < stat->state_num; i++) {
-		len += sprintf(buf + len, "%u %llu\n",
-			stat->freq_table[i], stat->time_in_state[i]);
+		len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i], 
+			(unsigned long long)cputime64_to_clock_t(stat->time_in_state[i]));
 	}
 	return len;
 }
@@ -107,16 +106,30 @@ show_trans_table(struct cpufreq_policy *policy, char *buf)
 	if(!stat)
 		return 0;
 	cpufreq_stats_update(stat->cpu);
+	len += snprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
+	len += snprintf(buf + len, PAGE_SIZE - len, "         : ");
+	for (i = 0; i < stat->state_num; i++) {
+		if (len >= PAGE_SIZE)
+			break;
+		len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
+				stat->freq_table[i]);
+	}
+	if (len >= PAGE_SIZE)
+		return len;
+
+	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+
 	for (i = 0; i < stat->state_num; i++) {
 		if (len >= PAGE_SIZE)
 			break;
-		len += snprintf(buf + len, PAGE_SIZE - len, "%9u:\t",
+
+		len += snprintf(buf + len, PAGE_SIZE - len, "%9u: ",
 				stat->freq_table[i]);
 
 		for (j = 0; j < stat->state_num; j++)   {
 			if (len >= PAGE_SIZE)
 				break;
-			len += snprintf(buf + len, PAGE_SIZE - len, "%u\t",
+			len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
 					stat->trans_table[i*stat->max_state+j]);
 		}
 		len += snprintf(buf + len, PAGE_SIZE - len, "\n");
@@ -197,7 +210,7 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy,
 		count++;
 	}
 
-	alloc_size = count * sizeof(int) + count * sizeof(long long);
+	alloc_size = count * sizeof(int) + count * sizeof(cputime64_t);
 
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	alloc_size += count * count * sizeof(int);
@@ -224,7 +237,7 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy,
 	}
 	stat->state_num = j;
 	spin_lock(&cpufreq_stats_lock);
-	stat->last_time = jiffies;
+	stat->last_time = get_jiffies_64();
 	stat->last_index = freq_table_get_index(stat, policy->cur);
 	spin_unlock(&cpufreq_stats_lock);
 	cpufreq_cpu_put(data);

drivers/firmware/pcdp.c

@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/config.h>
 #include <linux/acpi.h>
 #include <linux/console.h>
 #include <linux/efi.h>

drivers/i2c/busses/i2c-ali1563.c

@@ -2,6 +2,7 @@
  *	i2c-ali1563.c - i2c driver for the ALi 1563 Southbridge
  *
  *	Copyright (C) 2004 Patrick Mochel
+ *		      2005 Rudolf Marek <r.marek@sh.cvut.cz>
  *
  *	The 1563 southbridge is deceptively similar to the 1533, with a
  *	few notable exceptions. One of those happens to be the fact they
@@ -57,10 +58,11 @@
 #define HST_CNTL2_BLOCK		0x05
 
 
+#define HST_CNTL2_SIZEMASK	0x38
 
 static unsigned short ali1563_smba;
 
-static int ali1563_transaction(struct i2c_adapter * a)
+static int ali1563_transaction(struct i2c_adapter * a, int size)
 {
 	u32 data;
 	int timeout;
@@ -73,7 +75,7 @@ static int ali1563_transaction(struct i2c_adapter * a)
 
 	data = inb_p(SMB_HST_STS);
 	if (data & HST_STS_BAD) {
-		dev_warn(&a->dev,"ali1563: Trying to reset busy device\n");
+		dev_err(&a->dev, "ali1563: Trying to reset busy device\n");
 		outb_p(data | HST_STS_BAD,SMB_HST_STS);
 		data = inb_p(SMB_HST_STS);
 		if (data & HST_STS_BAD)
@@ -94,19 +96,31 @@ static int ali1563_transaction(struct i2c_adapter * a)
 
 	if (timeout && !(data & HST_STS_BAD))
 		return 0;
-	dev_warn(&a->dev, "SMBus Error: %s%s%s%s%s\n",
-		timeout ? "Timeout " : "",
-		data & HST_STS_FAIL ? "Transaction Failed " : "",
-		data & HST_STS_BUSERR ? "No response or Bus Collision " : "",
-		data & HST_STS_DEVERR ? "Device Error " : "",
-		!(data & HST_STS_DONE) ? "Transaction Never Finished " : "");
 
-	if (!(data & HST_STS_DONE))
+	if (!timeout) {
+		dev_err(&a->dev, "Timeout - Trying to KILL transaction!\n");
 		/* Issue 'kill' to host controller */
 		outb_p(HST_CNTL2_KILL,SMB_HST_CNTL2);
-	else
-		/* Issue timeout to reset all devices on bus */
+		data = inb_p(SMB_HST_STS);
+ 	}
+
+	/* device error - no response, ignore the autodetection case */
+	if ((data & HST_STS_DEVERR) && (size != HST_CNTL2_QUICK)) {
+		dev_err(&a->dev, "Device error!\n");
+	}
+
+	/* bus collision */
+	if (data & HST_STS_BUSERR) {
+		dev_err(&a->dev, "Bus collision!\n");
+		/* Issue timeout, hoping it helps */
 		outb_p(HST_CNTL1_TIMEOUT,SMB_HST_CNTL1);
+	}
+
+	if (data & HST_STS_FAIL) {
+		dev_err(&a->dev, "Cleaning fail after KILL!\n");
+		outb_p(0x0,SMB_HST_CNTL2);
+	}
+
 	return -1;
 }
 
@@ -149,7 +163,7 @@ static int ali1563_block_start(struct i2c_adapter * a)
 
 	if (timeout && !(data & HST_STS_BAD))
 		return 0;
-	dev_warn(&a->dev, "SMBus Error: %s%s%s%s%s\n",
+	dev_err(&a->dev, "SMBus Error: %s%s%s%s%s\n",
 		timeout ? "Timeout " : "",
 		data & HST_STS_FAIL ? "Transaction Failed " : "",
 		data & HST_STS_BUSERR ? "No response or Bus Collision " : "",
@@ -242,13 +256,15 @@ static s32 ali1563_access(struct i2c_adapter * a, u16 addr,
 	}
 
 	outb_p(((addr & 0x7f) << 1) | (rw & 0x01), SMB_HST_ADD);
-	outb_p(inb_p(SMB_HST_CNTL2) | (size << 3), SMB_HST_CNTL2);
+	outb_p((inb_p(SMB_HST_CNTL2) & ~HST_CNTL2_SIZEMASK) | (size << 3), SMB_HST_CNTL2);
 
 	/* Write the command register */
+
 	switch(size) {
 	case HST_CNTL2_BYTE:
 		if (rw== I2C_SMBUS_WRITE)
-			outb_p(cmd, SMB_HST_CMD);
+			/* Beware it uses DAT0 register and not CMD! */
+			outb_p(cmd, SMB_HST_DAT0);
 		break;
 	case HST_CNTL2_BYTE_DATA:
 		outb_p(cmd, SMB_HST_CMD);
@@ -268,7 +284,7 @@ static s32 ali1563_access(struct i2c_adapter * a, u16 addr,
 		goto Done;
 	}
 
-	if ((error = ali1563_transaction(a)))
+	if ((error = ali1563_transaction(a, size)))
 		goto Done;
 
 	if ((rw == I2C_SMBUS_WRITE) || (size == HST_CNTL2_QUICK))

drivers/ide/ide-cd.c

@@ -1936,7 +1936,7 @@ static ide_startstop_t cdrom_do_block_pc(ide_drive_t *drive, struct request *rq)
 		 * NOTE! The "len" and "addr" checks should possibly have
 		 * separate masks.
 		 */
-		if ((rq->data_len & mask) || (addr & mask))
+		if ((rq->data_len & 15) || (addr & mask))
 			info->dma = 0;
 	}
 

drivers/ide/pci/amd74xx.c

@@ -72,6 +72,7 @@ static struct amd_ide_chip {
 	{ PCI_DEVICE_ID_NVIDIA_NFORCE3S_SATA2,	0x50, AMD_UDMA_133 },
 	{ PCI_DEVICE_ID_NVIDIA_NFORCE_CK804_IDE,	0x50, AMD_UDMA_133 },
 	{ PCI_DEVICE_ID_NVIDIA_NFORCE_MCP04_IDE,	0x50, AMD_UDMA_133 },
+	{ PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_IDE,	0x50, AMD_UDMA_133 },
 	{ 0 }
 };
 
@@ -487,6 +488,7 @@ static ide_pci_device_t amd74xx_chipsets[] __devinitdata = {
 	/* 12 */ DECLARE_NV_DEV("NFORCE3-250-SATA2"),
 	/* 13 */ DECLARE_NV_DEV("NFORCE-CK804"),
 	/* 14 */ DECLARE_NV_DEV("NFORCE-MCP04"),
+	/* 15 */ DECLARE_NV_DEV("NFORCE-MCP51"),
 };
 
 static int __devinit amd74xx_probe(struct pci_dev *dev, const struct pci_device_id *id)
@@ -521,6 +523,7 @@ static struct pci_device_id amd74xx_pci_tbl[] = {
 #endif
 	{ PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_CK804_IDE,	PCI_ANY_ID, PCI_ANY_ID, 0, 0, 13 },
 	{ PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP04_IDE,	PCI_ANY_ID, PCI_ANY_ID, 0, 0, 14 },
+	{ PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_IDE,	PCI_ANY_ID, PCI_ANY_ID, 0, 0, 15 },
 	{ 0, },
 };
 MODULE_DEVICE_TABLE(pci, amd74xx_pci_tbl);

drivers/input/gameport/Kconfig

@@ -68,23 +68,3 @@ config GAMEPORT_CS461X
 	depends on PCI
 
 endif
-
-# Yes, SOUND_GAMEPORT looks a bit odd. Yes, it ends up being turned on
-# in every .config. Please don't touch it. It is here to handle an
-# unusual dependency between GAMEPORT and sound drivers.
-#
-# Some sound drivers call gameport functions. If GAMEPORT is
-# not selected, empty stubs are provided for the functions and all is
-# well.
-# If GAMEPORT is built in, everything is fine.
-# If GAMEPORT is a module, however, it would need to be loaded for the
-# sound driver to be able to link properly. Therefore, the sound
-# driver must be a module as well in that case. Since there's no way
-# to express that directly in Kconfig, we use SOUND_GAMEPORT to
-# express it. SOUND_GAMEPORT boils down to "if GAMEPORT is 'm',
-# anything that depends on SOUND_GAMEPORT must be 'm' as well. if
-# GAMEPORT is 'y' or 'n', it can be anything".
-config SOUND_GAMEPORT
-	tristate
-	default m if GAMEPORT=m
-	default y

drivers/input/joydev.c

@@ -422,7 +422,7 @@ static struct input_handle *joydev_connect(struct input_handler *handler, struct
 			joydev->nkey++;
 		}
 
-	for (i = 0; i < BTN_JOYSTICK - BTN_MISC + 1; i++)
+	for (i = 0; i < BTN_JOYSTICK - BTN_MISC; i++)
 		if (test_bit(i + BTN_MISC, dev->keybit)) {
 			joydev->keymap[i] = joydev->nkey;
 			joydev->keypam[joydev->nkey] = i + BTN_MISC;

drivers/input/keyboard/atkbd.c

@@ -171,9 +171,9 @@ static struct {
 	unsigned char set2;
 } atkbd_scroll_keys[] = {
 	{ ATKBD_SCR_1,     0xc5 },
-	{ ATKBD_SCR_2,     0xa9 },
-	{ ATKBD_SCR_4,     0xb6 },
-	{ ATKBD_SCR_8,     0xa7 },
+	{ ATKBD_SCR_2,     0x9d },
+	{ ATKBD_SCR_4,     0xa4 },
+	{ ATKBD_SCR_8,     0x9b },
 	{ ATKBD_SCR_CLICK, 0xe0 },
 	{ ATKBD_SCR_LEFT,  0xcb },
 	{ ATKBD_SCR_RIGHT, 0xd2 },

drivers/input/mouse/psmouse-base.c

@@ -518,13 +518,16 @@ static int psmouse_probe(struct psmouse *psmouse)
 /*
  * First, we check if it's a mouse. It should send 0x00 or 0x03
  * in case of an IntelliMouse in 4-byte mode or 0x04 for IM Explorer.
+ * Sunrex K8561 IR Keyboard/Mouse reports 0xff on second and subsequent
+ * ID queries, probably due to a firmware bug.
  */
 
 	param[0] = 0xa5;
 	if (ps2_command(ps2dev, param, PSMOUSE_CMD_GETID))
 		return -1;
 
-	if (param[0] != 0x00 && param[0] != 0x03 && param[0] != 0x04)
+	if (param[0] != 0x00 && param[0] != 0x03 &&
+	    param[0] != 0x04 && param[0] != 0xff)
 		return -1;
 
 /*
@@ -972,7 +975,7 @@ static int psmouse_set_maxproto(const char *val, struct kernel_param *kp)
 		return -EINVAL;
 
 	if (!strncmp(val, "any", 3)) {
-		*((unsigned int *)kp->arg) = -1UL;
+		*((unsigned int *)kp->arg) = -1U;
 		return 0;
 	}