Merge remote branch 'origin' into secretlab/next-devicetree

Merging in current state of Linus' tree to deal with merge conflicts and
build failures in vio.c after merge.

Conflicts:
	drivers/i2c/busses/i2c-cpm.c
	drivers/i2c/busses/i2c-mpc.c
	drivers/net/gianfar.c

Also fixed up one line in arch/powerpc/kernel/vio.c to use the
correct node pointer.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>

14 files changed, 272 insertions, 149 deletions

diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 0ff5174..3dbef30 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -7,7 +7,7 @@ EXTRA_CFLAGS		+= -DDEBUG
 endif
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
-			   setup.o iommu.o ras.o \
+			   setup.o iommu.o event_sources.o ras.o \
 			   firmware.o power.o dlpar.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_XICS)	+= xics.o
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index e1682bc..d71e585 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -79,13 +79,12 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa)
 	 * prepend this to the full_name.
 	 */
 	name = (char *)ccwa + ccwa->name_offset;
-	dn->full_name = kmalloc(strlen(name) + 2, GFP_KERNEL);
+	dn->full_name = kasprintf(GFP_KERNEL, "/%s", name);
 	if (!dn->full_name) {
 		kfree(dn);
 		return NULL;
 	}
 
-	sprintf(dn->full_name, "/%s", name);
 	return dn;
 }
 
@@ -410,15 +409,13 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	 * directory of the device tree.  CPUs actually live in the
 	 * cpus directory so we need to fixup the full_name.
 	 */
-	cpu_name = kzalloc(strlen(dn->full_name) + strlen("/cpus") + 1,
-			   GFP_KERNEL);
+	cpu_name = kasprintf(GFP_KERNEL, "/cpus%s", dn->full_name);
 	if (!cpu_name) {
 		dlpar_free_cc_nodes(dn);
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	sprintf(cpu_name, "/cpus%s", dn->full_name);
 	kfree(dn->full_name);
 	dn->full_name = cpu_name;
 
@@ -433,6 +430,7 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	if (rc) {
 		dlpar_release_drc(drc_index);
 		dlpar_free_cc_nodes(dn);
+		goto out;
 	}
 
 	rc = dlpar_online_cpu(dn);
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 7df7fbb..34b7dc1 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -749,7 +749,7 @@ static void __rtas_set_slot_reset(struct pci_dn *pdn)
 	/* Determine type of EEH reset required by device,
 	 * default hot reset or fundamental reset
 	 */
-	if (dev->needs_freset)
+	if (dev && dev->needs_freset)
 		rtas_pci_slot_reset(pdn, 3);
 	else
 		rtas_pci_slot_reset(pdn, 1);
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
new file mode 100644
index 0000000..e889c9d
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) 2001 Dave Engebretsen IBM Corporation
+ *
+ * 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 <asm/prom.h>
+
+#include "pseries.h"
+
+void request_event_sources_irqs(struct device_node *np,
+				irq_handler_t handler,
+				const char *name)
+{
+	int i, index, count = 0;
+	struct of_irq oirq;
+	const u32 *opicprop;
+	unsigned int opicplen;
+	unsigned int virqs[16];
+
+	/* Check for obsolete "open-pic-interrupt" property. If present, then
+	 * map those interrupts using the default interrupt host and default
+	 * trigger
+	 */
+	opicprop = of_get_property(np, "open-pic-interrupt", &opicplen);
+	if (opicprop) {
+		opicplen /= sizeof(u32);
+		for (i = 0; i < opicplen; i++) {
+			if (count > 15)
+				break;
+			virqs[count] = irq_create_mapping(NULL, *(opicprop++));
+			if (virqs[count] == NO_IRQ)
+				printk(KERN_ERR "Unable to allocate interrupt "
+				       "number for %s\n", np->full_name);
+			else
+				count++;
+
+		}
+	}
+	/* Else use normal interrupt tree parsing */
+	else {
+		/* First try to do a proper OF tree parsing */
+		for (index = 0; of_irq_map_one(np, index, &oirq) == 0;
+		     index++) {
+			if (count > 15)
+				break;
+			virqs[count] = irq_create_of_mapping(oirq.controller,
+							    oirq.specifier,
+							    oirq.size);
+			if (virqs[count] == NO_IRQ)
+				printk(KERN_ERR "Unable to allocate interrupt "
+				       "number for %s\n", np->full_name);
+			else
+				count++;
+		}
+	}
+
+	/* Now request them */
+	for (i = 0; i < count; i++) {
+		if (request_irq(virqs[i], handler, 0, name, NULL)) {
+			printk(KERN_ERR "Unable to request interrupt %d for "
+			       "%s\n", virqs[i], np->full_name);
+			return;
+		}
+	}
+}
+
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index a8e1d5d..8f85f39 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -154,30 +154,6 @@ static void pseries_mach_cpu_die(void)
 	for(;;);
 }
 
-static int qcss_tok;	/* query-cpu-stopped-state token */
-
-/* Get state of physical CPU.
- * Return codes:
- *	0	- The processor is in the RTAS stopped state
- *	1	- stop-self is in progress
- *	2	- The processor is not in the RTAS stopped state
- *	-1	- Hardware Error
- *	-2	- Hardware Busy, Try again later.
- */
-static int query_cpu_stopped(unsigned int pcpu)
-{
-	int cpu_status, status;
-
-	status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu);
-	if (status != 0) {
-		printk(KERN_ERR
-		       "RTAS query-cpu-stopped-state failed: %i\n", status);
-		return status;
-	}
-
-	return cpu_status;
-}
-
 static int pseries_cpu_disable(void)
 {
 	int cpu = smp_processor_id();
@@ -187,7 +163,7 @@ static int pseries_cpu_disable(void)
 
 	/*fix boot_cpuid here*/
 	if (cpu == boot_cpuid)
-		boot_cpuid = any_online_cpu(cpu_online_map);
+		boot_cpuid = cpumask_any(cpu_online_mask);
 
 	/* FIXME: abstract this to not be platform specific later on */
 	xics_migrate_irqs_away();
@@ -224,8 +200,9 @@ static void pseries_cpu_die(unsigned int cpu)
 	} else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
 
 		for (tries = 0; tries < 25; tries++) {
-			cpu_status = query_cpu_stopped(pcpu);
-			if (cpu_status == 0 || cpu_status == -1)
+			cpu_status = smp_query_cpu_stopped(pcpu);
+			if (cpu_status == QCSS_STOPPED ||
+			    cpu_status == QCSS_HARDWARE_ERROR)
 				break;
 			cpu_relax();
 		}
@@ -245,7 +222,7 @@ static void pseries_cpu_die(unsigned int cpu)
 }
 
 /*
- * Update cpu_present_map and paca(s) for a new cpu node.  The wrinkle
+ * Update cpu_present_mask and paca(s) for a new cpu node.  The wrinkle
  * here is that a cpu device node may represent up to two logical cpus
  * in the SMT case.  We must honor the assumption in other code that
  * the logical ids for sibling SMT threads x and y are adjacent, such
@@ -254,7 +231,7 @@ static void pseries_cpu_die(unsigned int cpu)
 static int pseries_add_processor(struct device_node *np)
 {
 	unsigned int cpu;
-	cpumask_t candidate_map, tmp = CPU_MASK_NONE;
+	cpumask_var_t candidate_mask, tmp;
 	int err = -ENOSPC, len, nthreads, i;
 	const u32 *intserv;
 
@@ -262,48 +239,53 @@ static int pseries_add_processor(struct device_node *np)
 	if (!intserv)
 		return 0;
 
+	zalloc_cpumask_var(&candidate_mask, GFP_KERNEL);
+	zalloc_cpumask_var(&tmp, GFP_KERNEL);
+
 	nthreads = len / sizeof(u32);
 	for (i = 0; i < nthreads; i++)
-		cpu_set(i, tmp);
+		cpumask_set_cpu(i, tmp);
 
 	cpu_maps_update_begin();
 
-	BUG_ON(!cpus_subset(cpu_present_map, cpu_possible_map));
+	BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask));
 
 	/* Get a bitmap of unoccupied slots. */
-	cpus_xor(candidate_map, cpu_possible_map, cpu_present_map);
-	if (cpus_empty(candidate_map)) {
+	cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask);
+	if (cpumask_empty(candidate_mask)) {
 		/* If we get here, it most likely means that NR_CPUS is
 		 * less than the partition's max processors setting.
 		 */
 		printk(KERN_ERR "Cannot add cpu %s; this system configuration"
 		       " supports %d logical cpus.\n", np->full_name,
-		       cpus_weight(cpu_possible_map));
+		       cpumask_weight(cpu_possible_mask));
 		goto out_unlock;
 	}
 
-	while (!cpus_empty(tmp))
-		if (cpus_subset(tmp, candidate_map))
+	while (!cpumask_empty(tmp))
+		if (cpumask_subset(tmp, candidate_mask))
 			/* Found a range where we can insert the new cpu(s) */
 			break;
 		else
-			cpus_shift_left(tmp, tmp, nthreads);
+			cpumask_shift_left(tmp, tmp, nthreads);
 
-	if (cpus_empty(tmp)) {
-		printk(KERN_ERR "Unable to find space in cpu_present_map for"
+	if (cpumask_empty(tmp)) {
+		printk(KERN_ERR "Unable to find space in cpu_present_mask for"
 		       " processor %s with %d thread(s)\n", np->name,
 		       nthreads);
 		goto out_unlock;
 	}
 
-	for_each_cpu_mask(cpu, tmp) {
-		BUG_ON(cpu_isset(cpu, cpu_present_map));
+	for_each_cpu(cpu, tmp) {
+		BUG_ON(cpumask_test_cpu(cpu, cpu_present_mask));
 		set_cpu_present(cpu, true);
 		set_hard_smp_processor_id(cpu, *intserv++);
 	}
 	err = 0;
 out_unlock:
 	cpu_maps_update_done();
+	free_cpumask_var(candidate_mask);
+	free_cpumask_var(tmp);
 	return err;
 }
 
@@ -334,7 +316,7 @@ static void pseries_remove_processor(struct device_node *np)
 			set_hard_smp_processor_id(cpu, -1);
 			break;
 		}
-		if (cpu == NR_CPUS)
+		if (cpu >= nr_cpu_ids)
 			printk(KERN_WARNING "Could not find cpu to remove "
 			       "with physical id 0x%x\n", intserv[i]);
 	}
@@ -388,6 +370,7 @@ static int __init pseries_cpu_hotplug_init(void)
 	struct device_node *np;
 	const char *typep;
 	int cpu;
+	int qcss_tok;
 
 	for_each_node_by_name(np, "interrupt-controller") {
 		typep = of_get_property(np, "compatible", NULL);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9b21ee6..01e7b5b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -11,6 +11,7 @@
 
 #include <linux/of.h>
 #include <linux/lmb.h>
+#include <linux/vmalloc.h>
 #include <asm/firmware.h>
 #include <asm/machdep.h>
 #include <asm/pSeries_reconfig.h>
@@ -54,6 +55,12 @@ static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size)
 	 */
 	start = (unsigned long)__va(base);
 	ret = remove_section_mapping(start, start + lmb_size);
+
+	/* Ensure all vmalloc mappings are flushed in case they also
+	 * hit that section of memory
+	 */
+	vm_unmap_aliases();
+
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 383a5d0..48d2057 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -228,3 +228,41 @@ _GLOBAL(plpar_hcall9)
 	mtcrf	0xff,r0
 
 	blr				/* return r3 = status */
+
+/* See plpar_hcall_raw to see why this is needed */
+_GLOBAL(plpar_hcall9_raw)
+	HMT_MEDIUM
+
+	mfcr	r0
+	stw	r0,8(r1)
+
+	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
+
+	mr	r4,r5
+	mr	r5,r6
+	mr	r6,r7
+	mr	r7,r8
+	mr	r8,r9
+	mr	r9,r10
+	ld	r10,STK_PARM(r11)(r1)	 /* put arg7 in R10 */
+	ld	r11,STK_PARM(r12)(r1)	 /* put arg8 in R11 */
+	ld	r12,STK_PARM(r13)(r1)    /* put arg9 in R12 */
+
+	HVSC				/* invoke the hypervisor */
+
+	mr	r0,r12
+	ld	r12,STK_PARM(r4)(r1)
+	std	r4,  0(r12)
+	std	r5,  8(r12)
+	std	r6, 16(r12)
+	std	r7, 24(r12)
+	std	r8, 32(r12)
+	std	r9, 40(r12)
+	std	r10,48(r12)
+	std	r11,56(r12)
+	std	r0, 64(r12)
+
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+
+	blr				/* return r3 = status */
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 0707653..cf79b46 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -367,21 +367,28 @@ static void pSeries_lpar_hptab_clear(void)
 {
 	unsigned long size_bytes = 1UL << ppc64_pft_size;
 	unsigned long hpte_count = size_bytes >> 4;
-	unsigned long dummy1, dummy2, dword0;
+	struct {
+		unsigned long pteh;
+		unsigned long ptel;
+	} ptes[4];
 	long lpar_rc;
-	int i;
+	int i, j;
 
-	/* TODO: Use bulk call */
-	for (i = 0; i < hpte_count; i++) {
-		/* dont remove HPTEs with VRMA mappings */
-		lpar_rc = plpar_pte_remove_raw(H_ANDCOND, i, HPTE_V_1TB_SEG,
-						&dummy1, &dummy2);
-		if (lpar_rc == H_NOT_FOUND) {
-			lpar_rc = plpar_pte_read_raw(0, i, &dword0, &dummy1);
-			if (!lpar_rc && ((dword0 & HPTE_V_VRMA_MASK)
-				!= HPTE_V_VRMA_MASK))
-				/* Can be hpte for 1TB Seg. So remove it */
-				plpar_pte_remove_raw(0, i, 0, &dummy1, &dummy2);
+	/* Read in batches of 4,
+	 * invalidate only valid entries not in the VRMA
+	 * hpte_count will be a multiple of 4
+         */
+	for (i = 0; i < hpte_count; i += 4) {
+		lpar_rc = plpar_pte_read_4_raw(0, i, (void *)ptes);
+		if (lpar_rc != H_SUCCESS)
+			continue;
+		for (j = 0; j < 4; j++){
+			if ((ptes[j].pteh & HPTE_V_VRMA_MASK) ==
+				HPTE_V_VRMA_MASK)
+				continue;
+			if (ptes[j].pteh & HPTE_V_VALID)
+				plpar_pte_remove_raw(0, i + j, 0,
+					&(ptes[j].pteh), &(ptes[j].ptel));
 		}
 	}
 }
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index a05f8d4..d980111 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -4,6 +4,14 @@
 #include <asm/hvcall.h>
 #include <asm/page.h>
 
+/* Get state of physical CPU from query_cpu_stopped */
+int smp_query_cpu_stopped(unsigned int pcpu);
+#define QCSS_STOPPED 0
+#define QCSS_STOPPING 1
+#define QCSS_NOT_STOPPED 2
+#define QCSS_HARDWARE_ERROR -1
+#define QCSS_HARDWARE_BUSY -2
+
 static inline long poll_pending(void)
 {
 	return plpar_hcall_norets(H_POLL_PENDING);
@@ -183,6 +191,24 @@ static inline long plpar_pte_read_raw(unsigned long flags, unsigned long ptex,
 	return rc;
 }
 
+/*
+ * plpar_pte_read_4_raw can be called in real mode.
+ * ptes must be 8*sizeof(unsigned long)
+ */
+static inline long plpar_pte_read_4_raw(unsigned long flags, unsigned long ptex,
+					unsigned long *ptes)
+
+{
+	long rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	rc = plpar_hcall9_raw(H_READ, retbuf, flags | H_READ_4, ptex);
+
+	memcpy(ptes, retbuf, 8*sizeof(unsigned long));
+
+	return rc;
+}
+
 static inline long plpar_pte_protect(unsigned long flags, unsigned long ptex,
 		unsigned long avpn)
 {
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 9e17c0d..40c93ca 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -10,6 +10,13 @@
 #ifndef _PSERIES_PSERIES_H
 #define _PSERIES_PSERIES_H
 
+#include <linux/interrupt.h>
+
+struct device_node;
+
+extern void request_event_sources_irqs(struct device_node *np,
+				       irq_handler_t handler, const char *name);
+
 extern void __init fw_feature_init(const char *hypertas, unsigned long len);
 
 struct pt_regs;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index db940d2..41a3e9a 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -67,63 +67,6 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id);
 static irqreturn_t ras_error_interrupt(int irq, void *dev_id);
 
 
-static void request_ras_irqs(struct device_node *np,
-			irq_handler_t handler,
-			const char *name)
-{
-	int i, index, count = 0;
-	struct of_irq oirq;
-	const u32 *opicprop;
-	unsigned int opicplen;
-	unsigned int virqs[16];
-
-	/* Check for obsolete "open-pic-interrupt" property. If present, then
-	 * map those interrupts using the default interrupt host and default
-	 * trigger
-	 */
-	opicprop = of_get_property(np, "open-pic-interrupt", &opicplen);
-	if (opicprop) {
-		opicplen /= sizeof(u32);
-		for (i = 0; i < opicplen; i++) {
-			if (count > 15)
-				break;
-			virqs[count] = irq_create_mapping(NULL, *(opicprop++));
-			if (virqs[count] == NO_IRQ)
-				printk(KERN_ERR "Unable to allocate interrupt "
-				       "number for %s\n", np->full_name);
-			else
-				count++;
-
-		}
-	}
-	/* Else use normal interrupt tree parsing */
-	else {
-		/* First try to do a proper OF tree parsing */
-		for (index = 0; of_irq_map_one(np, index, &oirq) == 0;
-		     index++) {
-			if (count > 15)
-				break;
-			virqs[count] = irq_create_of_mapping(oirq.controller,
-							    oirq.specifier,
-							    oirq.size);
-			if (virqs[count] == NO_IRQ)
-				printk(KERN_ERR "Unable to allocate interrupt "
-				       "number for %s\n", np->full_name);
-			else
-				count++;
-		}
-	}
-
-	/* Now request them */
-	for (i = 0; i < count; i++) {
-		if (request_irq(virqs[i], handler, 0, name, NULL)) {
-			printk(KERN_ERR "Unable to request interrupt %d for "
-			       "%s\n", virqs[i], np->full_name);
-			return;
-		}
-	}
-}
-
 /*
  * Initialize handlers for the set of interrupts caused by hardware errors
  * and power system events.
@@ -138,14 +81,15 @@ static int __init init_ras_IRQ(void)
 	/* Internal Errors */
 	np = of_find_node_by_path("/event-sources/internal-errors");
 	if (np != NULL) {
-		request_ras_irqs(np, ras_error_interrupt, "RAS_ERROR");
+		request_event_sources_irqs(np, ras_error_interrupt,
+					   "RAS_ERROR");
 		of_node_put(np);
 	}
 
 	/* EPOW Events */
 	np = of_find_node_by_path("/event-sources/epow-events");
 	if (np != NULL) {
-		request_ras_irqs(np, ras_epow_interrupt, "RAS_EPOW");
+		request_event_sources_irqs(np, ras_epow_interrupt, "RAS_EPOW");
 		of_node_put(np);
 	}
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 6710761..a6d19e3 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -496,13 +496,14 @@ static int __init pSeries_probe(void)
 }
 
 
-DECLARE_PER_CPU(unsigned long, smt_snooze_delay);
+DECLARE_PER_CPU(long, smt_snooze_delay);
 
 static void pseries_dedicated_idle_sleep(void)
 { 
 	unsigned int cpu = smp_processor_id();
 	unsigned long start_snooze;
 	unsigned long in_purr, out_purr;
+	long snooze = __get_cpu_var(smt_snooze_delay);
 
 	/*
 	 * Indicate to the HV that we are idle. Now would be
@@ -517,13 +518,12 @@ static void pseries_dedicated_idle_sleep(void)
 	 * has been checked recently.  If we should poll for a little
 	 * while, do so.
 	 */
-	if (__get_cpu_var(smt_snooze_delay)) {
-		start_snooze = get_tb() +
-			__get_cpu_var(smt_snooze_delay) * tb_ticks_per_usec;
+	if (snooze) {
+		start_snooze = get_tb() + snooze * tb_ticks_per_usec;
 		local_irq_enable();
 		set_thread_flag(TIF_POLLING_NRFLAG);
 
-		while (get_tb() < start_snooze) {
+		while ((snooze < 0) || (get_tb() < start_snooze)) {
 			if (need_resched() || cpu_is_offline(cpu))
 				goto out;
 			ppc64_runlatch_off();
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 4e7f89a..3b1bf61 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -55,7 +55,29 @@
  * The Primary thread of each non-boot processor was started from the OF client
  * interface by prom_hold_cpus and is spinning on secondary_hold_spinloop.
  */
-static cpumask_t of_spin_map;
+static cpumask_var_t of_spin_mask;
+
+/* Query where a cpu is now.  Return codes #defined in plpar_wrappers.h */
+int smp_query_cpu_stopped(unsigned int pcpu)
+{
+	int cpu_status, status;
+	int qcss_tok = rtas_token("query-cpu-stopped-state");
+
+	if (qcss_tok == RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_INFO "Firmware doesn't support "
+				"query-cpu-stopped-state\n");
+		return QCSS_HARDWARE_ERROR;
+	}
+
+	status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu);
+	if (status != 0) {
+		printk(KERN_ERR
+		       "RTAS query-cpu-stopped-state failed: %i\n", status);
+		return status;
+	}
+
+	return cpu_status;
+}
 
 /**
  * smp_startup_cpu() - start the given cpu
@@ -76,12 +98,18 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 	unsigned int pcpu;
 	int start_cpu;
 
-	if (cpu_isset(lcpu, of_spin_map))
+	if (cpumask_test_cpu(lcpu, of_spin_mask))
 		/* Already started by OF and sitting in spin loop */
 		return 1;
 
 	pcpu = get_hard_smp_processor_id(lcpu);
 
+	/* Check to see if the CPU out of FW already for kexec */
+	if (smp_query_cpu_stopped(pcpu) == QCSS_NOT_STOPPED){
+		cpumask_set_cpu(lcpu, of_spin_mask);
+		return 1;
+	}
+
 	/* Fixup atomic count: it exited inside IRQ handler. */
 	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
 
@@ -115,7 +143,7 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
 		vpa_init(cpu);
 
-	cpu_clear(cpu, of_spin_map);
+	cpumask_clear_cpu(cpu, of_spin_mask);
 	set_cpu_current_state(cpu, CPU_STATE_ONLINE);
 	set_default_offline_state(cpu);
 
@@ -186,17 +214,19 @@ static void __init smp_init_pseries(void)
 
 	pr_debug(" -> smp_init_pSeries()\n");
 
+	alloc_bootmem_cpumask_var(&of_spin_mask);
+
 	/* Mark threads which are still spinning in hold loops. */
 	if (cpu_has_feature(CPU_FTR_SMT)) {
 		for_each_present_cpu(i) { 
 			if (cpu_thread_in_core(i) == 0)
-				cpu_set(i, of_spin_map);
+				cpumask_set_cpu(i, of_spin_mask);
 		}
 	} else {
-		of_spin_map = cpu_present_map;
+		cpumask_copy(of_spin_mask, cpu_present_mask);
 	}
 
-	cpu_clear(boot_cpuid, of_spin_map);
+	cpumask_clear_cpu(boot_cpuid, of_spin_mask);
 
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 1bcedd8..f19d194 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -163,29 +163,37 @@ static inline void lpar_qirr_info(int n_cpu , u8 value)
 /* Interface to generic irq subsystem */
 
 #ifdef CONFIG_SMP
-static int get_irq_server(unsigned int virq, cpumask_t cpumask,
+/*
+ * For the moment we only implement delivery to all cpus or one cpu.
+ *
+ * If the requested affinity is cpu_all_mask, we set global affinity.
+ * If not we set it to the first cpu in the mask, even if multiple cpus
+ * are set. This is so things like irqbalance (which set core and package
+ * wide affinities) do the right thing.
+ */
+static int get_irq_server(unsigned int virq, const struct cpumask *cpumask,
 			  unsigned int strict_check)
 {
-	int server;
-	/* For the moment only implement delivery to all cpus or one cpu */
-	cpumask_t tmp = CPU_MASK_NONE;
 
 	if (!distribute_irqs)
 		return default_server;
 
-	if (!cpus_equal(cpumask, CPU_MASK_ALL)) {
-		cpus_and(tmp, cpu_online_map, cpumask);
-
-		server = first_cpu(tmp);
+	if (!cpumask_equal(cpumask, cpu_all_mask)) {
+		int server = cpumask_first_and(cpu_online_mask, cpumask);
 
-		if (server < NR_CPUS)
+		if (server < nr_cpu_ids)
 			return get_hard_smp_processor_id(server);
 
 		if (strict_check)
 			return -1;
 	}
 
-	if (cpus_equal(cpu_online_map, cpu_present_map))
+	/*
+	 * Workaround issue with some versions of JS20 firmware that
+	 * deliver interrupts to cpus which haven't been started. This
+	 * happens when using the maxcpus= boot option.
+	 */
+	if (cpumask_equal(cpu_online_mask, cpu_present_mask))
 		return default_distrib_server;
 
 	return default_server;
@@ -207,7 +215,7 @@ static void xics_unmask_irq(unsigned int virq)
 	if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
 		return;
 
-	server = get_irq_server(virq, *(irq_to_desc(virq)->affinity), 0);
+	server = get_irq_server(virq, irq_to_desc(virq)->affinity, 0);
 
 	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, irq, server,
 				DEFAULT_PRIORITY);
@@ -398,11 +406,7 @@ static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 		return -1;
 	}
 
-	/*
-	 * For the moment only implement delivery to all cpus or one cpu.
-	 * Get current irq_server for the given irq
-	 */
-	irq_server = get_irq_server(virq, *cpumask, 1);
+	irq_server = get_irq_server(virq, cpumask, 1);
 	if (irq_server == -1) {
 		char cpulist[128];
 		cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
@@ -611,7 +615,7 @@ int __init smp_xics_probe(void)
 {
 	xics_request_ipi();
 
-	return cpus_weight(cpu_possible_map);
+	return cpumask_weight(cpu_possible_mask);
 }
 
 #endif /* CONFIG_SMP */