Merge branch 'sched/locking' into sched/core

Merge reason: the rq locking changes are stable,
              propagate them into the .40 queue.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

39 files changed, 140 insertions, 113 deletions

diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 42aa078..5a621c6 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -585,8 +585,7 @@ handle_ipi(struct pt_regs *regs)
 
 		switch (which) {
 		case IPI_RESCHEDULE:
-			/* Reschedule callback.  Everything to be done
-			   is done by the interrupt return path.  */
+			scheduler_ipi();
 			break;
 
 		case IPI_CALL_FUNC:
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 8fe05ad..7a561eb 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -560,10 +560,7 @@ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_RESCHEDULE:
-		/*
-		 * nothing more to do - eveything is
-		 * done on the interrupt return path
-		 */
+		scheduler_ipi();
 		break;
 
 	case IPI_CALL_FUNC:
diff --git a/arch/avr32/include/asm/setup.h b/arch/avr32/include/asm/setup.h
index ff5b7cf..160543d 100644
--- a/arch/avr32/include/asm/setup.h
+++ b/arch/avr32/include/asm/setup.h
@@ -94,6 +94,13 @@ struct tag_ethernet {
 
 #define ETH_INVALID_PHY	0xff
 
+/* board information */
+#define ATAG_BOARDINFO	0x54410008
+
+struct tag_boardinfo {
+	u32	board_number;
+};
+
 struct tag {
 	struct tag_header hdr;
 	union {
@@ -102,6 +109,7 @@ struct tag {
 		struct tag_cmdline cmdline;
 		struct tag_clock clock;
 		struct tag_ethernet ethernet;
+		struct tag_boardinfo boardinfo;
 	} u;
 };
 
@@ -128,6 +136,7 @@ extern struct tag *bootloader_tags;
 
 extern resource_size_t fbmem_start;
 extern resource_size_t fbmem_size;
+extern u32 board_number;
 
 void setup_processor(void);
 
diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c
index 5c70839..bb0974c 100644
--- a/arch/avr32/kernel/setup.c
+++ b/arch/avr32/kernel/setup.c
@@ -391,6 +391,21 @@ static int __init parse_tag_clock(struct tag *tag)
 __tagtable(ATAG_CLOCK, parse_tag_clock);
 
 /*
+ * The board_number correspond to the bd->bi_board_number in U-Boot. This
+ * parameter is only available during initialisation and can be used in some
+ * kind of board identification.
+ */
+u32 __initdata board_number;
+
+static int __init parse_tag_boardinfo(struct tag *tag)
+{
+	board_number = tag->u.boardinfo.board_number;
+
+	return 0;
+}
+__tagtable(ATAG_BOARDINFO, parse_tag_boardinfo);
+
+/*
  * Scan the tag table for this tag, and call its parse function. The
  * tag table is built by the linker from all the __tagtable
  * declarations.
diff --git a/arch/avr32/kernel/traps.c b/arch/avr32/kernel/traps.c
index b91b204..7aa2575 100644
--- a/arch/avr32/kernel/traps.c
+++ b/arch/avr32/kernel/traps.c
@@ -95,28 +95,6 @@ void _exception(long signr, struct pt_regs *regs, int code,
 	info.si_code = code;
 	info.si_addr = (void __user *)addr;
 	force_sig_info(signr, &info, current);
-
-	/*
-	 * Init gets no signals that it doesn't have a handler for.
-	 * That's all very well, but if it has caused a synchronous
-	 * exception and we ignore the resulting signal, it will just
-	 * generate the same exception over and over again and we get
-	 * nowhere.  Better to kill it and let the kernel panic.
-	 */
-	if (is_global_init(current)) {
-		__sighandler_t handler;
-
-		spin_lock_irq(&current->sighand->siglock);
-		handler = current->sighand->action[signr-1].sa.sa_handler;
-		spin_unlock_irq(&current->sighand->siglock);
-		if (handler == SIG_DFL) {
-			/* init has generated a synchronous exception
-			   and it doesn't have a handler for the signal */
-			printk(KERN_CRIT "init has generated signal %ld "
-			       "but has no handler for it\n", signr);
-			do_exit(signr);
-		}
-	}
 }
 
 asmlinkage void do_nmi(unsigned long ecr, struct pt_regs *regs)
diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c
index 442f08c..86925fd 100644
--- a/arch/avr32/mach-at32ap/clock.c
+++ b/arch/avr32/mach-at32ap/clock.c
@@ -35,22 +35,30 @@ void at32_clk_register(struct clk *clk)
 	spin_unlock(&clk_list_lock);
 }
 
-struct clk *clk_get(struct device *dev, const char *id)
+static struct clk *__clk_get(struct device *dev, const char *id)
 {
 	struct clk *clk;
 
-	spin_lock(&clk_list_lock);
-
 	list_for_each_entry(clk, &at32_clock_list, list) {
 		if (clk->dev == dev && strcmp(id, clk->name) == 0) {
-			spin_unlock(&clk_list_lock);
 			return clk;
 		}
 	}
 
-	spin_unlock(&clk_list_lock);
 	return ERR_PTR(-ENOENT);
 }
+
+struct clk *clk_get(struct device *dev, const char *id)
+{
+	struct clk *clk;
+
+	spin_lock(&clk_list_lock);
+	clk = __clk_get(dev, id);
+	spin_unlock(&clk_list_lock);
+
+	return clk;
+}
+
 EXPORT_SYMBOL(clk_get);
 
 void clk_put(struct clk *clk)
@@ -257,15 +265,15 @@ static int clk_show(struct seq_file *s, void *unused)
 	spin_lock(&clk_list_lock);
 
 	/* show clock tree as derived from the three oscillators */
-	clk = clk_get(NULL, "osc32k");
+	clk = __clk_get(NULL, "osc32k");
 	dump_clock(clk, &r);
 	clk_put(clk);
 
-	clk = clk_get(NULL, "osc0");
+	clk = __clk_get(NULL, "osc0");
 	dump_clock(clk, &r);
 	clk_put(clk);
 
-	clk = clk_get(NULL, "osc1");
+	clk = __clk_get(NULL, "osc1");
 	dump_clock(clk, &r);
 	clk_put(clk);
 
diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c
index 47ba4b9..fbc2aea 100644
--- a/arch/avr32/mach-at32ap/extint.c
+++ b/arch/avr32/mach-at32ap/extint.c
@@ -61,34 +61,34 @@ struct eic {
 static struct eic *nmi_eic;
 static bool nmi_enabled;
 
-static void eic_ack_irq(struct irq_chip *d)
+static void eic_ack_irq(struct irq_data *d)
 {
-	struct eic *eic = irq_data_get_irq_chip_data(data);
+	struct eic *eic = irq_data_get_irq_chip_data(d);
 	eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq));
 }
 
-static void eic_mask_irq(struct irq_chip *d)
+static void eic_mask_irq(struct irq_data *d)
 {
-	struct eic *eic = irq_data_get_irq_chip_data(data);
+	struct eic *eic = irq_data_get_irq_chip_data(d);
 	eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq));
 }
 
-static void eic_mask_ack_irq(struct irq_chip *d)
+static void eic_mask_ack_irq(struct irq_data *d)
 {
-	struct eic *eic = irq_data_get_irq_chip_data(data);
+	struct eic *eic = irq_data_get_irq_chip_data(d);
 	eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq));
 	eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq));
 }
 
-static void eic_unmask_irq(struct irq_chip *d)
+static void eic_unmask_irq(struct irq_data *d)
 {
-	struct eic *eic = irq_data_get_irq_chip_data(data);
+	struct eic *eic = irq_data_get_irq_chip_data(d);
 	eic_writel(eic, IER, 1 << (d->irq - eic->first_irq));
 }
 
-static int eic_set_irq_type(struct irq_chip *d, unsigned int flow_type)
+static int eic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
-	struct eic *eic = irq_data_get_irq_chip_data(data);
+	struct eic *eic = irq_data_get_irq_chip_data(d);
 	unsigned int irq = d->irq;
 	unsigned int i = irq - eic->first_irq;
 	u32 mode, edge, level;
@@ -191,7 +191,7 @@ static int __init eic_probe(struct platform_device *pdev)
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	int_irq = platform_get_irq(pdev, 0);
-	if (!regs || !int_irq) {
+	if (!regs || (int)int_irq <= 0) {
 		dev_dbg(&pdev->dev, "missing regs and/or irq resource\n");
 		return -ENXIO;
 	}
diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c
index f308e1d..2e0aa85 100644
--- a/arch/avr32/mach-at32ap/pio.c
+++ b/arch/avr32/mach-at32ap/pio.c
@@ -257,7 +257,7 @@ static void gpio_irq_mask(struct irq_data *d)
 	pio_writel(pio, IDR, 1 << (gpio & 0x1f));
 }
 
-static void gpio_irq_unmask(struct irq_data *d))
+static void gpio_irq_unmask(struct irq_data *d)
 {
 	unsigned		gpio = irq_to_gpio(d->irq);
 	struct pio_device	*pio = &pio_dev[gpio >> 5];
diff --git a/arch/avr32/mach-at32ap/pm-at32ap700x.S b/arch/avr32/mach-at32ap/pm-at32ap700x.S
index 17503b0..f868f4c 100644
--- a/arch/avr32/mach-at32ap/pm-at32ap700x.S
+++ b/arch/avr32/mach-at32ap/pm-at32ap700x.S
@@ -53,7 +53,7 @@ cpu_enter_idle:
 	st.w	r8[TI_flags], r9
 	unmask_interrupts
 	sleep	CPU_SLEEP_IDLE
-	.size	cpu_idle_sleep, . - cpu_idle_sleep
+	.size	cpu_enter_idle, . - cpu_enter_idle
 
 	/*
 	 * Common return path for PM functions that don't run from
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 6e17a26..326bb86 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -164,6 +164,9 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 	while (msg_queue->count) {
 		msg = &msg_queue->ipi_message[msg_queue->head];
 		switch (msg->type) {
+		case BFIN_IPI_RESCHEDULE:
+			scheduler_ipi();
+			break;
 		case BFIN_IPI_CALL_FUNC:
 			spin_unlock_irqrestore(&msg_queue->lock, flags);
 			ipi_call_function(cpu, msg);
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index 4c9e3e1..66cc756 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -342,15 +342,18 @@ irqreturn_t crisv32_ipi_interrupt(int irq, void *dev_id)
 
 	ipi = REG_RD(intr_vect, irq_regs[smp_processor_id()], rw_ipi);
 
+	if (ipi.vector & IPI_SCHEDULE) {
+		scheduler_ipi();
+	}
 	if (ipi.vector & IPI_CALL) {
-	         func(info);
+		func(info);
 	}
 	if (ipi.vector & IPI_FLUSH_TLB) {
-		     if (flush_mm == FLUSH_ALL)
-			 __flush_tlb_all();
-		     else if (flush_vma == FLUSH_ALL)
+		if (flush_mm == FLUSH_ALL)
+			__flush_tlb_all();
+		else if (flush_vma == FLUSH_ALL)
 			__flush_tlb_mm(flush_mm);
-		     else
+		else
 			__flush_tlb_page(flush_vma, flush_addr);
 	}
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 5b70474..782c3a35 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -31,6 +31,7 @@
 #include <linux/irq.h>
 #include <linux/ratelimit.h>
 #include <linux/acpi.h>
+#include <linux/sched.h>
 
 #include <asm/delay.h>
 #include <asm/intrinsics.h>
@@ -496,6 +497,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 			smp_local_flush_tlb();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else if (unlikely(IS_RESCHEDULE(vector))) {
+			scheduler_ipi();
 			kstat_incr_irqs_this_cpu(irq, desc);
 		} else {
 			ia64_setreg(_IA64_REG_CR_TPR, vector);
diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c
index 108bb85..b279e14 100644
--- a/arch/ia64/xen/irq_xen.c
+++ b/arch/ia64/xen/irq_xen.c
@@ -92,6 +92,8 @@ static unsigned short saved_irq_cnt;
 static int xen_slab_ready;
 
 #ifdef CONFIG_SMP
+#include <linux/sched.h>
+
 /* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ,
  * it ends up to issue several memory accesses upon percpu data and
  * thus adds unnecessary traffic to other paths.
@@ -99,7 +101,13 @@ static int xen_slab_ready;
 static irqreturn_t
 xen_dummy_handler(int irq, void *dev_id)
 {
+	return IRQ_HANDLED;
+}
 
+static irqreturn_t
+xen_resched_handler(int irq, void *dev_id)
+{
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 
@@ -110,7 +118,7 @@ static struct irqaction xen_ipi_irqaction = {
 };
 
 static struct irqaction xen_resched_irqaction = {
-	.handler =	xen_dummy_handler,
+	.handler =	xen_resched_handler,
 	.flags =	IRQF_DISABLED,
 	.name =		"resched"
 };
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index 31cef20..fc10b39 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -122,8 +122,6 @@ void smp_send_reschedule(int cpu_id)
  *
  * Description:  This routine executes on CPU which received
  *               'RESCHEDULE_IPI'.
- *               Rescheduling is processed at the exit of interrupt
- *               operation.
  *
  * Born on Date: 2002.02.05
  *
@@ -138,7 +136,7 @@ void smp_send_reschedule(int cpu_id)
  *==========================================================================*/
 void smp_reschedule_interrupt(void)
 {
-	/* nothing to do */
+	scheduler_ipi();
 }
 
 /*==========================================================================*
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 26d851d..29e1790 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -343,10 +343,14 @@
 #define __NR_fanotify_init	337
 #define __NR_fanotify_mark	338
 #define __NR_prlimit64		339
+#define __NR_name_to_handle_at	340
+#define __NR_open_by_handle_at	341
+#define __NR_clock_adjtime	342
+#define __NR_syncfs		343
 
 #ifdef __KERNEL__
 
-#define NR_syscalls		340
+#define NR_syscalls		344
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/m68k/kernel/entry_mm.S b/arch/m68k/kernel/entry_mm.S
index 1559dea..1359ee6 100644
--- a/arch/m68k/kernel/entry_mm.S
+++ b/arch/m68k/kernel/entry_mm.S
@@ -750,4 +750,8 @@ sys_call_table:
 	.long sys_fanotify_init
 	.long sys_fanotify_mark
 	.long sys_prlimit64
+	.long sys_name_to_handle_at	/* 340 */
+	.long sys_open_by_handle_at
+	.long sys_clock_adjtime
+	.long sys_syncfs
 
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 79b1ed1..9b8393d 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -358,6 +358,10 @@ ENTRY(sys_call_table)
 	.long sys_fanotify_init
 	.long sys_fanotify_mark
 	.long sys_prlimit64
+	.long sys_name_to_handle_at	/* 340 */
+	.long sys_open_by_handle_at
+	.long sys_clock_adjtime
+	.long sys_syncfs
 
 	.rept NR_syscalls-(.-sys_call_table)/4
 		.long sys_ni_syscall
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index ba78b21..76923ee 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -44,6 +44,8 @@ static irqreturn_t mailbox_interrupt(int irq, void *dev_id)
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	/* Check if we've been told to flush the icache */
 	if (action & SMP_ICACHE_FLUSH)
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 5a88cc4..cedac46 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -929,7 +929,7 @@ static void post_direct_ipi(int cpu, struct smtc_ipi *pipi)
 
 static void ipi_resched_interrupt(void)
 {
-	/* Return from interrupt should be enough to cause scheduler check */
+	scheduler_ipi();
 }
 
 static void ipi_call_interrupt(void)
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index 9027061..7d93e6f 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -309,6 +309,8 @@ static void ipi_call_dispatch(void)
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
+	scheduler_ipi();
+
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index efc9e88..2608752 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -55,6 +55,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 
 	case 1:
@@ -63,6 +65,8 @@ void titan_mailbox_irq(void)
 
 		if (status & 0x2)
 			smp_call_function_interrupt();
+		if (status & 0x4)
+			scheduler_ipi();
 		break;
 	}
 }
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 0a04603..b18b04e 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -147,8 +147,10 @@ static void ip27_do_irq_mask0(void)
 #ifdef CONFIG_SMP
 	if (pend0 & (1UL << CPU_RESCHED_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_A_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_RESCHED_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_RESCHED_B_IRQ);
+		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
 		smp_call_function_interrupt();
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index 47b347c..d667875 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
@@ -189,10 +190,8 @@ void bcm1480_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	__raw_writeq(((u64)action)<<48, mailbox_0_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index c00a5cb..38e7f6b 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 
 #include <asm/mmu_context.h>
 #include <asm/io.h>
@@ -177,10 +178,8 @@ void sb1250_mailbox_interrupt(void)
 	/* Clear the mailbox to clear the interrupt */
 	____raw_writeq(((u64)action) << 48, mailbox_clear_regs[cpu]);
 
-	/*
-	 * Nothing to do for SMP_RESCHEDULE_YOURSELF; returning from the
-	 * interrupt will do the reschedule for us
-	 */
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
 
 	if (action & SMP_CALL_FUNCTION)
 		smp_call_function_interrupt();
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index 226c826..83fb279 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -494,14 +494,11 @@ void smp_send_stop(void)
  * @irq: The interrupt number.
  * @dev_id: The device ID.
  *
- * We need do nothing here, since the scheduling will be effected on our way
- * back through entry.S.
- *
  * Returns IRQ_HANDLED to indicate we handled the interrupt successfully.
  */
 static irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id)
 {
-	/* do nothing */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 69d63d3..828305f 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -155,10 +155,7 @@ ipi_interrupt(int irq, void *dev_id)
 				
 			case IPI_RESCHEDULE:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu);
-				/*
-				 * Reschedule callback.  Everything to be
-				 * done is done by the interrupt return path.
-				 */
+				scheduler_ipi();
 				break;
 
 			case IPI_CALL_FUNC:
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index c00d4ca..28581f1 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -527,7 +527,7 @@ static int ibmebus_bus_pm_resume_noirq(struct device *dev)
 
 #endif /* !CONFIG_SUSPEND */
 
-#ifdef CONFIG_HIBERNATION
+#ifdef CONFIG_HIBERNATE_CALLBACKS
 
 static int ibmebus_bus_pm_freeze(struct device *dev)
 {
@@ -665,7 +665,7 @@ static int ibmebus_bus_pm_restore_noirq(struct device *dev)
 	return ret;
 }
 
-#else /* !CONFIG_HIBERNATION */
+#else /* !CONFIG_HIBERNATE_CALLBACKS */
 
 #define ibmebus_bus_pm_freeze		NULL
 #define ibmebus_bus_pm_thaw		NULL
@@ -676,7 +676,7 @@ static int ibmebus_bus_pm_restore_noirq(struct device *dev)
 #define ibmebus_bus_pm_poweroff_noirq	NULL
 #define ibmebus_bus_pm_restore_noirq	NULL
 
-#endif /* !CONFIG_HIBERNATION */
+#endif /* !CONFIG_HIBERNATE_CALLBACKS */
 
 static struct dev_pm_ops ibmebus_bus_dev_pm_ops = {
 	.prepare = ibmebus_bus_pm_prepare,
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index cbdbb14..9f9c204 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -116,7 +116,7 @@ void smp_message_recv(int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
-		/* we notice need_resched on exit */
+		scheduler_ipi();
 		break;
 	case PPC_MSG_CALL_FUNC_SINGLE:
 		generic_smp_call_function_single_interrupt();
@@ -146,7 +146,7 @@ static irqreturn_t call_function_action(int irq, void *data)
 
 static irqreturn_t reschedule_action(int irq, void *data)
 {
-	/* we just need the return path side effect of checking need_resched */
+	scheduler_ipi();
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 63a97db..63c7d9f 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -165,12 +165,12 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++;
 	/*
 	 * handle bit signal external calls
-	 *
-	 * For the ec_schedule signal we have to do nothing. All the work
-	 * is done automatically when we return from the interrupt.
 	 */
 	bits = xchg(&S390_lowcore.ext_call_fast, 0);
 
+	if (test_bit(ec_schedule, &bits))
+		scheduler_ipi();
+
 	if (test_bit(ec_call_function, &bits))
 		generic_smp_call_function_interrupt();
 
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 509b36b..6207561 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/atomic.h>
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -323,6 +324,7 @@ void smp_message_recv(unsigned int msg)
 		generic_smp_call_function_interrupt();
 		break;
 	case SMP_MSG_RESCHEDULE:
+		scheduler_ipi();
 		break;
 	case SMP_MSG_FUNCTION_SINGLE:
 		generic_smp_call_function_single_interrupt();
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index 91c10fb..f95690c 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -125,7 +125,9 @@ struct linux_prom_registers smp_penguin_ctable __cpuinitdata = { 0 };
 
 void smp_send_reschedule(int cpu)
 {
-	/* See sparc64 */
+	/*
+	 * XXX missing reschedule IPI, see scheduler_ipi()
+	 */
 }
 
 void smp_send_stop(void)
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 3e94a8c..9478da7 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1368,6 +1368,7 @@ void smp_send_reschedule(int cpu)
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	scheduler_ipi();
 }
 
 /* This is a nop because we capture all other cpus
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index a429310..c52224d 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -189,12 +189,8 @@ void flush_icache_range(unsigned long start, unsigned long end)
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	/*
-	 * Nothing to do here; when we return from interrupt, the
-	 * rescheduling will occur there. But do bump the interrupt
-	 * profiler count in the meantime.
-	 */
 	__get_cpu_var(irq_stat).irq_resched_count++;
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index 106bf27..eefb107 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -173,7 +173,7 @@ void IPI_handler(int cpu)
 			break;
 
 		case 'R':
-			set_tsk_need_resched(current);
+			scheduler_ipi();
 			break;
 
 		case 'S':
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 513deac..013e7eb 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -194,14 +194,13 @@ static void native_stop_other_cpus(int wait)
 }
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 void smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 1c7121b..5cc821c 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -39,6 +39,7 @@ config XEN_MAX_DOMAIN_MEMORY
 config XEN_SAVE_RESTORE
        bool
        depends on XEN
+       select HIBERNATE_CALLBACKS
        default y
 
 config XEN_DEBUG_FS
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 49dbd78..e3c6a06 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -238,6 +238,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 static __init void xen_init_cpuid_mask(void)
 {
 	unsigned int ax, bx, cx, dx;
+	unsigned int xsave_mask;
 
 	cpuid_leaf1_edx_mask =
 		~((1 << X86_FEATURE_MCE)  |  /* disable MCE */
@@ -249,24 +250,16 @@ static __init void xen_init_cpuid_mask(void)
 		cpuid_leaf1_edx_mask &=
 			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
 			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
-
 	ax = 1;
-	cx = 0;
 	xen_cpuid(&ax, &bx, &cx, &dx);
 
-	/* cpuid claims we support xsave; try enabling it to see what happens */
-	if (cx & (1 << (X86_FEATURE_XSAVE % 32))) {
-		unsigned long cr4;
-
-		set_in_cr4(X86_CR4_OSXSAVE);
-		
-		cr4 = read_cr4();
+	xsave_mask =
+		(1 << (X86_FEATURE_XSAVE % 32)) |
+		(1 << (X86_FEATURE_OSXSAVE % 32));
 
-		if ((cr4 & X86_CR4_OSXSAVE) == 0)
-			cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32));
-
-		clear_in_cr4(X86_CR4_OSXSAVE);
-	}
+	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
+	if ((cx & xsave_mask) != xsave_mask)
+		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
 }
 
 static void xen_set_debugreg(int reg, unsigned long val)
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index c82df6c..a991b57 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -565,13 +565,13 @@ pte_t xen_make_pte_debug(pteval_t pte)
 	if (io_page &&
 	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
 		other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
-		WARN(addr != other_addr,
+		WARN_ONCE(addr != other_addr,
 			"0x%lx is using VM_IO, but it is 0x%lx!\n",
 			(unsigned long)addr, (unsigned long)other_addr);
 	} else {
 		pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
 		other_addr = (_pte.pte & PTE_PFN_MASK);
-		WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+		WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
 			"0x%lx is missing VM_IO (and wasn't fixed)!\n",
 			(unsigned long)addr);
 	}
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 3061244..762b46a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -46,13 +46,12 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
 static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 {
 	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 
 	return IRQ_HANDLED;
 }