Merge branch 'master' of ssh://master.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into next

218 files changed, 6730 insertions, 2263 deletions

diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h
index a1057c2d95e..3641ec1452f 100644
--- a/arch/alpha/include/asm/socket.h
+++ b/arch/alpha/include/asm/socket.h
@@ -62,6 +62,9 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
diff --git a/arch/alpha/include/asm/statfs.h b/arch/alpha/include/asm/statfs.h
index de35cd438a1..ccd2e186bfd 100644
--- a/arch/alpha/include/asm/statfs.h
+++ b/arch/alpha/include/asm/statfs.h
@@ -1,6 +1,8 @@
 #ifndef _ALPHA_STATFS_H
 #define _ALPHA_STATFS_H
 
+#include <linux/types.h>
+
 /* Alpha is the only 64-bit platform with 32-bit statfs. And doesn't
    even seem to implement statfs64 */
 #define __statfs_word __u32
diff --git a/arch/alpha/include/asm/swab.h b/arch/alpha/include/asm/swab.h
index 68e7089e02d..4d682b16c7c 100644
--- a/arch/alpha/include/asm/swab.h
+++ b/arch/alpha/include/asm/swab.h
@@ -1,7 +1,7 @@
 #ifndef _ALPHA_SWAB_H
 #define _ALPHA_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 #include <asm/compiler.h>
 
diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index e4a54b61589..b45d913a51c 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -903,8 +903,9 @@ sys_alpha_pipe:
 	stq	$26, 0($sp)
 	.prologue 0
 
+	mov	$31, $17
 	lda	$16, 8($sp)
-	jsr	$26, do_pipe
+	jsr	$26, do_pipe_flags
 
 	ldq	$26, 0($sp)
 	bne	$0, 1f
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 703731accda..d3812eb8401 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -90,7 +90,7 @@ show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(irq));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[irq]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[irq].chip->typename);
 		seq_printf(p, "  %c%s",
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index e16aeb6e79e..67c19f8a994 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -64,7 +64,7 @@ do_entInt(unsigned long type, unsigned long vector,
 		smp_percpu_timer_interrupt(regs);
 		cpu = smp_processor_id();
 		if (cpu != boot_cpuid) {
-		        kstat_cpu(cpu).irqs[RTC_IRQ]++;
+		        kstat_incr_irqs_this_cpu(RTC_IRQ, irq_to_desc(RTC_IRQ));
 		} else {
 			handle_irq(RTC_IRQ);
 		}
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index ae41f097864..42ee05981e7 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -46,8 +46,6 @@
 #include <asm/hwrpb.h>
 #include <asm/processor.h>
 
-extern int do_pipe(int *);
-
 /*
  * Brk needs to return an error.  Still support Linux's brk(0) query idiom,
  * which OSF programs just shouldn't be doing.  We're still not quite
diff --git a/arch/arm/include/asm/a.out.h b/arch/arm/include/asm/a.out.h
index 79489fdcc8b..083894b2e3b 100644
--- a/arch/arm/include/asm/a.out.h
+++ b/arch/arm/include/asm/a.out.h
@@ -2,7 +2,7 @@
 #define __ARM_A_OUT_H__
 
 #include <linux/personality.h>
-#include <asm/types.h>
+#include <linux/types.h>
 
 struct exec
 {
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index f2cd18a0932..ee1304f22f9 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -14,7 +14,7 @@
 #ifndef __ASMARM_SETUP_H
 #define __ASMARM_SETUP_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #define COMMAND_LINE_SIZE 1024
 
diff --git a/arch/arm/include/asm/socket.h b/arch/arm/include/asm/socket.h
index 6817be9573a..537de4e0ef5 100644
--- a/arch/arm/include/asm/socket.h
+++ b/arch/arm/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/arm/include/asm/swab.h b/arch/arm/include/asm/swab.h
index 27a689be085..ca2bf2f6d6e 100644
--- a/arch/arm/include/asm/swab.h
+++ b/arch/arm/include/asm/swab.h
@@ -16,7 +16,7 @@
 #define __ASM_ARM_SWAB_H
 
 #include <linux/compiler.h>
-#include <asm/types.h>
+#include <linux/types.h>
 
 #if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
 #  define __SWAB_64_THRU_32__
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 363db186cb9..7296f041628 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -76,7 +76,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_printf(p, "%3d: ", i);
 		for_each_present_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-");
 		seq_printf(p, "  %s", action->name);
 		for (action = action->next; action; action = action->next)
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index b3404b7775b..0d2074f51a5 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -231,14 +231,17 @@ static struct platform_device kirkwood_switch_device = {
 
 void __init kirkwood_ge00_switch_init(struct dsa_platform_data *d, int irq)
 {
+	int i;
+
 	if (irq != NO_IRQ) {
 		kirkwood_switch_resources[0].start = irq;
 		kirkwood_switch_resources[0].end = irq;
 		kirkwood_switch_device.num_resources = 1;
 	}
 
-	d->mii_bus = &kirkwood_ge00_shared.dev;
 	d->netdev = &kirkwood_ge00.dev;
+	for (i = 0; i < d->nr_chips; i++)
+		d->chip[i].mii_bus = &kirkwood_ge00_shared.dev;
 	kirkwood_switch_device.dev.platform_data = d;
 
 	platform_device_register(&kirkwood_switch_device);
diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c
index 9a0e905d10c..e1c0516c4df 100644
--- a/arch/arm/mach-kirkwood/rd88f6281-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c
@@ -75,7 +75,7 @@ static struct mv643xx_eth_platform_data rd88f6281_ge00_data = {
 	.duplex		= DUPLEX_FULL,
 };
 
-static struct dsa_platform_data rd88f6281_switch_data = {
+static struct dsa_chip_data rd88f6281_switch_chip_data = {
 	.port_names[0]	= "lan1",
 	.port_names[1]	= "lan2",
 	.port_names[2]	= "lan3",
@@ -83,6 +83,11 @@ static struct dsa_platform_data rd88f6281_switch_data = {
 	.port_names[5]	= "cpu",
 };
 
+static struct dsa_platform_data rd88f6281_switch_plat_data = {
+	.nr_chips	= 1,
+	.chip		= &rd88f6281_switch_chip_data,
+};
+
 static struct mv643xx_eth_platform_data rd88f6281_ge01_data = {
 	.phy_addr	= MV643XX_ETH_PHY_ADDR(11),
 };
@@ -105,12 +110,12 @@ static void __init rd88f6281_init(void)
 	kirkwood_ge00_init(&rd88f6281_ge00_data);
 	kirkwood_pcie_id(&dev, &rev);
 	if (rev == MV88F6281_REV_A0) {
-		rd88f6281_switch_data.sw_addr = 10;
+		rd88f6281_switch_chip_data.sw_addr = 10;
 		kirkwood_ge01_init(&rd88f6281_ge01_data);
 	} else {
-		rd88f6281_switch_data.port_names[4] = "wan";
+		rd88f6281_switch_chip_data.port_names[4] = "wan";
 	}
-	kirkwood_ge00_switch_init(&rd88f6281_switch_data, NO_IRQ);
+	kirkwood_ge00_switch_init(&rd88f6281_switch_plat_data, NO_IRQ);
 
 	kirkwood_rtc_init();
 	kirkwood_sata_init(&rd88f6281_sata_data);
diff --git a/arch/arm/mach-ns9xxx/irq.c b/arch/arm/mach-ns9xxx/irq.c
index 22e0eb6e9ec..feb0e54a91d 100644
--- a/arch/arm/mach-ns9xxx/irq.c
+++ b/arch/arm/mach-ns9xxx/irq.c
@@ -63,7 +63,6 @@ static struct irq_chip ns9xxx_chip = {
 #else
 static void handle_prio_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -72,7 +71,7 @@ static void handle_prio_irq(unsigned int irq, struct irq_desc *desc)
 	BUG_ON(desc->status & IRQ_INPROGRESS);
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index 8a0e49d8425..68cc3efae56 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -31,6 +31,7 @@
 #include <plat/ehci-orion.h>
 #include <plat/mv_xor.h>
 #include <plat/orion_nand.h>
+#include <plat/orion5x_wdt.h>
 #include <plat/time.h>
 #include "common.h"
 
@@ -219,14 +220,17 @@ static struct platform_device orion5x_switch_device = {
 
 void __init orion5x_eth_switch_init(struct dsa_platform_data *d, int irq)
 {
+	int i;
+
 	if (irq != NO_IRQ) {
 		orion5x_switch_resources[0].start = irq;
 		orion5x_switch_resources[0].end = irq;
 		orion5x_switch_device.num_resources = 1;
 	}
 
-	d->mii_bus = &orion5x_eth_shared.dev;
 	d->netdev = &orion5x_eth.dev;
+	for (i = 0; i < d->nr_chips; i++)
+		d->chip[i].mii_bus = &orion5x_eth_shared.dev;
 	orion5x_switch_device.dev.platform_data = d;
 
 	platform_device_register(&orion5x_switch_device);
@@ -533,6 +537,29 @@ void __init orion5x_xor_init(void)
 
 
 /*****************************************************************************
+ * Watchdog
+ ****************************************************************************/
+static struct orion5x_wdt_platform_data orion5x_wdt_data = {
+	.tclk			= 0,
+};
+
+static struct platform_device orion5x_wdt_device = {
+	.name		= "orion5x_wdt",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &orion5x_wdt_data,
+	},
+	.num_resources	= 0,
+};
+
+void __init orion5x_wdt_init(void)
+{
+	orion5x_wdt_data.tclk = orion5x_tclk;
+	platform_device_register(&orion5x_wdt_device);
+}
+
+
+/*****************************************************************************
  * Time handling
  ****************************************************************************/
 int orion5x_tclk;
@@ -631,6 +658,11 @@ void __init orion5x_init(void)
 		printk(KERN_INFO "Orion: Applying 5281 D0 WFI workaround.\n");
 		disable_hlt();
 	}
+
+	/*
+	 * Register watchdog driver
+	 */
+	orion5x_wdt_init();
 }
 
 /*
diff --git a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
index 15f53235ee3..9c1ca41730b 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
@@ -94,7 +94,7 @@ static struct mv643xx_eth_platform_data rd88f5181l_fxo_eth_data = {
 	.duplex		= DUPLEX_FULL,
 };
 
-static struct dsa_platform_data rd88f5181l_fxo_switch_data = {
+static struct dsa_chip_data rd88f5181l_fxo_switch_chip_data = {
 	.port_names[0]	= "lan2",
 	.port_names[1]	= "lan1",
 	.port_names[2]	= "wan",
@@ -103,6 +103,11 @@ static struct dsa_platform_data rd88f5181l_fxo_switch_data = {
 	.port_names[7]	= "lan3",
 };
 
+static struct dsa_platform_data rd88f5181l_fxo_switch_plat_data = {
+	.nr_chips	= 1,
+	.chip		= &rd88f5181l_fxo_switch_chip_data,
+};
+
 static void __init rd88f5181l_fxo_init(void)
 {
 	/*
@@ -117,7 +122,7 @@ static void __init rd88f5181l_fxo_init(void)
 	 */
 	orion5x_ehci0_init();
 	orion5x_eth_init(&rd88f5181l_fxo_eth_data);
-	orion5x_eth_switch_init(&rd88f5181l_fxo_switch_data, NO_IRQ);
+	orion5x_eth_switch_init(&rd88f5181l_fxo_switch_plat_data, NO_IRQ);
 	orion5x_uart0_init();
 
 	orion5x_setup_dev_boot_win(RD88F5181L_FXO_NOR_BOOT_BASE,
diff --git a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
index 8ad3934399d..ee1399ff0ce 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
@@ -95,7 +95,7 @@ static struct mv643xx_eth_platform_data rd88f5181l_ge_eth_data = {
 	.duplex		= DUPLEX_FULL,
 };
 
-static struct dsa_platform_data rd88f5181l_ge_switch_data = {
+static struct dsa_chip_data rd88f5181l_ge_switch_chip_data = {
 	.port_names[0]	= "lan2",
 	.port_names[1]	= "lan1",
 	.port_names[2]	= "wan",
@@ -104,6 +104,11 @@ static struct dsa_platform_data rd88f5181l_ge_switch_data = {
 	.port_names[7]	= "lan3",
 };
 
+static struct dsa_platform_data rd88f5181l_ge_switch_plat_data = {
+	.nr_chips	= 1,
+	.chip		= &rd88f5181l_ge_switch_chip_data,
+};
+
 static struct i2c_board_info __initdata rd88f5181l_ge_i2c_rtc = {
 	I2C_BOARD_INFO("ds1338", 0x68),
 };
@@ -122,7 +127,8 @@ static void __init rd88f5181l_ge_init(void)
 	 */
 	orion5x_ehci0_init();
 	orion5x_eth_init(&rd88f5181l_ge_eth_data);
-	orion5x_eth_switch_init(&rd88f5181l_ge_switch_data, gpio_to_irq(8));
+	orion5x_eth_switch_init(&rd88f5181l_ge_switch_plat_data,
+				gpio_to_irq(8));
 	orion5x_i2c_init();
 	orion5x_uart0_init();
 
diff --git a/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c b/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
index 262e25e4dac..7737cf9a8f5 100644
--- a/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
@@ -35,7 +35,7 @@ static struct mv643xx_eth_platform_data rd88f6183ap_ge_eth_data = {
 	.duplex		= DUPLEX_FULL,
 };
 
-static struct dsa_platform_data rd88f6183ap_ge_switch_data = {
+static struct dsa_chip_data rd88f6183ap_ge_switch_chip_data = {
 	.port_names[0]	= "lan1",
 	.port_names[1]	= "lan2",
 	.port_names[2]	= "lan3",
@@ -44,6 +44,11 @@ static struct dsa_platform_data rd88f6183ap_ge_switch_data = {
 	.port_names[5]	= "cpu",
 };
 
+static struct dsa_platform_data rd88f6183ap_ge_switch_plat_data = {
+	.nr_chips	= 1,
+	.chip		= &rd88f6183ap_ge_switch_chip_data,
+};
+
 static struct mtd_partition rd88f6183ap_ge_partitions[] = {
 	{
 		.name	= "kernel",
@@ -89,7 +94,8 @@ static void __init rd88f6183ap_ge_init(void)
 	 */
 	orion5x_ehci0_init();
 	orion5x_eth_init(&rd88f6183ap_ge_eth_data);
-	orion5x_eth_switch_init(&rd88f6183ap_ge_switch_data, gpio_to_irq(3));
+	orion5x_eth_switch_init(&rd88f6183ap_ge_switch_plat_data,
+				gpio_to_irq(3));
 	spi_register_board_info(rd88f6183ap_ge_spi_slave_info,
 				ARRAY_SIZE(rd88f6183ap_ge_spi_slave_info));
 	orion5x_spi_init();
diff --git a/arch/arm/mach-orion5x/wrt350n-v2-setup.c b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
index cc8f8920086..1b4ad9d5e2e 100644
--- a/arch/arm/mach-orion5x/wrt350n-v2-setup.c
+++ b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
@@ -106,7 +106,7 @@ static struct mv643xx_eth_platform_data wrt350n_v2_eth_data = {
 	.duplex		= DUPLEX_FULL,
 };
 
-static struct dsa_platform_data wrt350n_v2_switch_data = {
+static struct dsa_chip_data wrt350n_v2_switch_chip_data = {
 	.port_names[0]	= "lan2",
 	.port_names[1]	= "lan1",
 	.port_names[2]	= "wan",
@@ -115,6 +115,11 @@ static struct dsa_platform_data wrt350n_v2_switch_data = {
 	.port_names[7]	= "lan4",
 };
 
+static struct dsa_platform_data wrt350n_v2_switch_plat_data = {
+	.nr_chips	= 1,
+	.chip		= &wrt350n_v2_switch_chip_data,
+};
+
 static void __init wrt350n_v2_init(void)
 {
 	/*
@@ -129,7 +134,7 @@ static void __init wrt350n_v2_init(void)
 	 */
 	orion5x_ehci0_init();
 	orion5x_eth_init(&wrt350n_v2_eth_data);
-	orion5x_eth_switch_init(&wrt350n_v2_switch_data, NO_IRQ);
+	orion5x_eth_switch_init(&wrt350n_v2_switch_plat_data, NO_IRQ);
 	orion5x_uart0_init();
 
 	orion5x_setup_dev_boot_win(WRT350N_V2_NOR_BOOT_BASE,
diff --git a/arch/arm/plat-orion/include/plat/orion5x_wdt.h b/arch/arm/plat-orion/include/plat/orion5x_wdt.h
new file mode 100644
index 00000000000..3c9cf6a305e
--- /dev/null
+++ b/arch/arm/plat-orion/include/plat/orion5x_wdt.h
@@ -0,0 +1,18 @@
+/*
+ * arch/arm/plat-orion/include/plat/orion5x_wdt.h
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __PLAT_ORION5X_WDT_H
+#define __PLAT_ORION5X_WDT_H
+
+struct orion5x_wdt_platform_data {
+	u32	tclk;		/* no <linux/clk.h> support yet */
+};
+
+
+#endif
+
diff --git a/arch/avr32/include/asm/socket.h b/arch/avr32/include/asm/socket.h
index 35863f26092..04c86061970 100644
--- a/arch/avr32/include/asm/socket.h
+++ b/arch/avr32/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* __ASM_AVR32_SOCKET_H */
diff --git a/arch/avr32/include/asm/swab.h b/arch/avr32/include/asm/swab.h
index a14aa5b46d9..14cc737bbca 100644
--- a/arch/avr32/include/asm/swab.h
+++ b/arch/avr32/include/asm/swab.h
@@ -4,7 +4,7 @@
 #ifndef __ASM_AVR32_SWAB_H
 #define __ASM_AVR32_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #define __SWAB_64_THRU_32__
diff --git a/arch/avr32/kernel/irq.c b/arch/avr32/kernel/irq.c
index a8e767d836a..9f572229d31 100644
--- a/arch/avr32/kernel/irq.c
+++ b/arch/avr32/kernel/irq.c
@@ -58,7 +58,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_printf(p, "%3d: ", i);
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %8s", irq_desc[i].chip->name ? : "-");
 		seq_printf(p, "  %s", action->name);
 		for (action = action->next; action; action = action->next)
diff --git a/arch/blackfin/include/asm/socket.h b/arch/blackfin/include/asm/socket.h
index 2ca702e44d4..fac7fe9e1f8 100644
--- a/arch/blackfin/include/asm/socket.h
+++ b/arch/blackfin/include/asm/socket.h
@@ -53,4 +53,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif				/* _ASM_SOCKET_H */
diff --git a/arch/blackfin/include/asm/swab.h b/arch/blackfin/include/asm/swab.h
index 69a051b612b..6403ad2932e 100644
--- a/arch/blackfin/include/asm/swab.h
+++ b/arch/blackfin/include/asm/swab.h
@@ -1,7 +1,7 @@
 #ifndef _BLACKFIN_SWAB_H
 #define _BLACKFIN_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__)
diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c
index 7fd12656484..bd052a67032 100644
--- a/arch/blackfin/kernel/irqchip.c
+++ b/arch/blackfin/kernel/irqchip.c
@@ -83,7 +83,7 @@ int show_interrupts(struct seq_file *p, void *v)
 			goto skip;
 		seq_printf(p, "%3d: ", i);
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 		seq_printf(p, " %8s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 		for (action = action->next; action; action = action->next)
diff --git a/arch/cris/include/asm/socket.h b/arch/cris/include/asm/socket.h
index 9df0ca82f5d..d5cf7400540 100644
--- a/arch/cris/include/asm/socket.h
+++ b/arch/cris/include/asm/socket.h
@@ -56,6 +56,9 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/cris/kernel/irq.c b/arch/cris/kernel/irq.c
index 2dfac8c7909..7f642fcffbf 100644
--- a/arch/cris/kernel/irq.c
+++ b/arch/cris/kernel/irq.c
@@ -66,7 +66,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c
index 73abae767fd..af3e824b91b 100644
--- a/arch/frv/kernel/irq.c
+++ b/arch/frv/kernel/irq.c
@@ -74,7 +74,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (action) {
 			seq_printf(p, "%3d: ", i);
 			for_each_present_cpu(cpu)
-				seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+				seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 			seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-");
 			seq_printf(p, "  %s", action->name);
 			for (action = action->next;
diff --git a/arch/h8300/include/asm/socket.h b/arch/h8300/include/asm/socket.h
index da2520dbf25..602518a70a1 100644
--- a/arch/h8300/include/asm/socket.h
+++ b/arch/h8300/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/h8300/include/asm/swab.h b/arch/h8300/include/asm/swab.h
index c108f39b8bc..39abbf52807 100644
--- a/arch/h8300/include/asm/swab.h
+++ b/arch/h8300/include/asm/swab.h
@@ -1,7 +1,7 @@
 #ifndef _H8300_SWAB_H
 #define _H8300_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__)
 #  define __SWAB_64_THRU_32__
diff --git a/arch/h8300/kernel/irq.c b/arch/h8300/kernel/irq.c
index ef4f0047067..74f8dd7b34d 100644
--- a/arch/h8300/kernel/irq.c
+++ b/arch/h8300/kernel/irq.c
@@ -183,7 +183,7 @@ asmlinkage void do_IRQ(int irq)
 #if defined(CONFIG_PROC_FS)
 int show_interrupts(struct seq_file *p, void *v)
 {
-	int i = *(loff_t *) v, j;
+	int i = *(loff_t *) v;
 	struct irqaction * action;
 	unsigned long flags;
 
@@ -196,7 +196,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (!action)
 			goto unlock;
 		seq_printf(p, "%3d: ",i);
-		seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+		seq_printf(p, "%10u ", kstat_irqs(i));
 		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "-%-8s", irq_desc[i].name);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S
index a46f8395e9a..af9405cd70e 100644
--- a/arch/ia64/ia32/ia32_entry.S
+++ b/arch/ia64/ia32/ia32_entry.S
@@ -240,7 +240,7 @@ ia32_syscall_table:
 	data8 sys_ni_syscall
 	data8 sys_umask		  /* 60 */
 	data8 sys_chroot
-	data8 sys_ustat
+	data8 compat_sys_ustat
 	data8 sys_dup2
 	data8 sys_getppid
 	data8 sys_getpgrp	  /* 65 */
diff --git a/arch/ia64/include/asm/fpu.h b/arch/ia64/include/asm/fpu.h
index 3859558ff0a..0c26157cffa 100644
--- a/arch/ia64/include/asm/fpu.h
+++ b/arch/ia64/include/asm/fpu.h
@@ -6,8 +6,6 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-#include <asm/types.h>
-
 /* floating point status register: */
 #define FPSR_TRAP_VD	(1 << 0)	/* invalid op trap disabled */
 #define FPSR_TRAP_DD	(1 << 1)	/* denormal trap disabled */
diff --git a/arch/ia64/include/asm/gcc_intrin.h b/arch/ia64/include/asm/gcc_intrin.h
index 0f5b5592175..c2c5fd8fcac 100644
--- a/arch/ia64/include/asm/gcc_intrin.h
+++ b/arch/ia64/include/asm/gcc_intrin.h
@@ -6,6 +6,7 @@
  * Copyright (C) 2002,2003 Suresh Siddha <suresh.b.siddha@intel.com>
  */
 
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 /* define this macro to get some asm stmts included in 'c' files */
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index a3e44a5ed49..c47830e26cb 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -10,6 +10,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/types.h>
 /* include compiler specific intrinsics */
 #include <asm/ia64regs.h>
 #ifdef __INTEL_COMPILER
diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index bfa86b6af7c..18a7e49abbc 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -21,8 +21,7 @@
  *
  */
 
-#include <asm/types.h>
-
+#include <linux/types.h>
 #include <linux/ioctl.h>
 
 /* Select x86 specific features in <linux/kvm.h> */
@@ -166,7 +165,40 @@ struct saved_vpd {
 	unsigned long  vcpuid[5];
 	unsigned long  vpsr;
 	unsigned long  vpr;
-	unsigned long  vcr[128];
+	union {
+		unsigned long  vcr[128];
+		struct {
+			unsigned long dcr;
+			unsigned long itm;
+			unsigned long iva;
+			unsigned long rsv1[5];
+			unsigned long pta;
+			unsigned long rsv2[7];
+			unsigned long ipsr;
+			unsigned long isr;
+			unsigned long rsv3;
+			unsigned long iip;
+			unsigned long ifa;
+			unsigned long itir;
+			unsigned long iipa;
+			unsigned long ifs;
+			unsigned long iim;
+			unsigned long iha;
+			unsigned long rsv4[38];
+			unsigned long lid;
+			unsigned long ivr;
+			unsigned long tpr;
+			unsigned long eoi;
+			unsigned long irr[4];
+			unsigned long itv;
+			unsigned long pmv;
+			unsigned long cmcv;
+			unsigned long rsv5[5];
+			unsigned long lrr0;
+			unsigned long lrr1;
+			unsigned long rsv6[46];
+		};
+	};
 };
 
 struct kvm_regs {
@@ -214,4 +246,18 @@ struct kvm_sregs {
 struct kvm_fpu {
 };
 
+#define KVM_IA64_VCPU_STACK_SHIFT	16
+#define KVM_IA64_VCPU_STACK_SIZE	(1UL << KVM_IA64_VCPU_STACK_SHIFT)
+
+struct kvm_ia64_vcpu_stack {
+	unsigned char stack[KVM_IA64_VCPU_STACK_SIZE];
+};
+
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
 #endif
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 34866366165..4542651e6ac 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -112,7 +112,11 @@
 #define VCPU_STRUCT_SHIFT	16
 #define VCPU_STRUCT_SIZE	(__IA64_UL_CONST(1) << VCPU_STRUCT_SHIFT)
 
-#define KVM_STK_OFFSET		VCPU_STRUCT_SIZE
+/*
+ * This must match KVM_IA64_VCPU_STACK_{SHIFT,SIZE} arch/ia64/include/asm/kvm.h
+ */
+#define KVM_STK_SHIFT		16
+#define KVM_STK_OFFSET		(__IA64_UL_CONST(1)<< KVM_STK_SHIFT)
 
 #define KVM_VM_STRUCT_SHIFT	19
 #define KVM_VM_STRUCT_SIZE	(__IA64_UL_CONST(1) << KVM_VM_STRUCT_SHIFT)
@@ -153,10 +157,10 @@ struct kvm_vm_data {
 	struct kvm_vcpu_data vcpu_data[KVM_MAX_VCPUS];
 };
 
-#define VCPU_BASE(n)	KVM_VM_DATA_BASE + \
-				offsetof(struct kvm_vm_data, vcpu_data[n])
-#define VM_BASE		KVM_VM_DATA_BASE + \
-				offsetof(struct kvm_vm_data, kvm_vm_struct)
+#define VCPU_BASE(n)	(KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, vcpu_data[n]))
+#define KVM_VM_BASE	(KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, kvm_vm_struct))
 #define KVM_MEM_DIRTY_LOG_BASE	KVM_VM_DATA_BASE + \
 				offsetof(struct kvm_vm_data, kvm_mem_dirty_log)
 
@@ -235,8 +239,6 @@ struct kvm_vm_data {
 
 struct kvm;
 struct kvm_vcpu;
-struct kvm_guest_debug{
-};
 
 struct kvm_mmio_req {
 	uint64_t addr;          /*  physical address		*/
@@ -462,6 +464,8 @@ struct kvm_arch {
 	unsigned long	metaphysical_rr4;
 	unsigned long	vmm_init_rr;
 
+	int		online_vcpus;
+
 	struct kvm_ioapic *vioapic;
 	struct kvm_vm_stat stat;
 	struct kvm_sal_data rdv_sal_data;
diff --git a/arch/ia64/include/asm/msidef.h b/arch/ia64/include/asm/msidef.h
new file mode 100644
index 00000000000..592c1047a0c
--- /dev/null
+++ b/arch/ia64/include/asm/msidef.h
@@ -0,0 +1,42 @@
+#ifndef _IA64_MSI_DEF_H
+#define _IA64_MSI_DEF_H
+
+/*
+ * Shifts for APIC-based data
+ */
+
+#define     MSI_DATA_VECTOR_SHIFT	0
+#define	    MSI_DATA_VECTOR(v)		(((u8)v) << MSI_DATA_VECTOR_SHIFT)
+#define     MSI_DATA_VECTOR_MASK	0xffffff00
+
+#define     MSI_DATA_DELIVERY_MODE_SHIFT	8
+#define     MSI_DATA_DELIVERY_FIXED	(0 << MSI_DATA_DELIVERY_MODE_SHIFT)
+#define     MSI_DATA_DELIVERY_LOWPRI	(1 << MSI_DATA_DELIVERY_MODE_SHIFT)
+
+#define     MSI_DATA_LEVEL_SHIFT	14
+#define     MSI_DATA_LEVEL_DEASSERT	(0 << MSI_DATA_LEVEL_SHIFT)
+#define     MSI_DATA_LEVEL_ASSERT	(1 << MSI_DATA_LEVEL_SHIFT)
+
+#define     MSI_DATA_TRIGGER_SHIFT	15
+#define     MSI_DATA_TRIGGER_EDGE	(0 << MSI_DATA_TRIGGER_SHIFT)
+#define     MSI_DATA_TRIGGER_LEVEL	(1 << MSI_DATA_TRIGGER_SHIFT)
+
+/*
+ * Shift/mask fields for APIC-based bus address
+ */
+
+#define     MSI_ADDR_DEST_ID_SHIFT	4
+#define     MSI_ADDR_HEADER		0xfee00000
+
+#define     MSI_ADDR_DEST_ID_MASK	0xfff0000f
+#define     MSI_ADDR_DEST_ID_CPU(cpu)	((cpu) << MSI_ADDR_DEST_ID_SHIFT)
+
+#define     MSI_ADDR_DEST_MODE_SHIFT	2
+#define     MSI_ADDR_DEST_MODE_PHYS	(0 << MSI_ADDR_DEST_MODE_SHIFT)
+#define	    MSI_ADDR_DEST_MODE_LOGIC	(1 << MSI_ADDR_DEST_MODE_SHIFT)
+
+#define     MSI_ADDR_REDIRECTION_SHIFT	3
+#define     MSI_ADDR_REDIRECTION_CPU	(0 << MSI_ADDR_REDIRECTION_SHIFT)
+#define     MSI_ADDR_REDIRECTION_LOWPRI	(1 << MSI_ADDR_REDIRECTION_SHIFT)
+
+#endif/* _IA64_MSI_DEF_H */
diff --git a/arch/ia64/include/asm/socket.h b/arch/ia64/include/asm/socket.h
index d5ef0aa3e31..745421225ec 100644
--- a/arch/ia64/include/asm/socket.h
+++ b/arch/ia64/include/asm/socket.h
@@ -63,4 +63,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/ia64/include/asm/swab.h b/arch/ia64/include/asm/swab.h
index 6aa58b699ee..c89a8cb5d8a 100644
--- a/arch/ia64/include/asm/swab.h
+++ b/arch/ia64/include/asm/swab.h
@@ -6,7 +6,7 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co.
  */
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <asm/intrinsics.h>
 #include <linux/compiler.h>
 
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index a58f64ca9f0..4f596613bff 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -80,7 +80,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j) {
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 		}
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->name);
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 89033933903..368ee4e5266 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -7,44 +7,7 @@
 #include <linux/msi.h>
 #include <linux/dmar.h>
 #include <asm/smp.h>
-
-/*
- * Shifts for APIC-based data
- */
-
-#define MSI_DATA_VECTOR_SHIFT		0
-#define	    MSI_DATA_VECTOR(v)		(((u8)v) << MSI_DATA_VECTOR_SHIFT)
-#define MSI_DATA_VECTOR_MASK		0xffffff00
-
-#define MSI_DATA_DELIVERY_SHIFT		8
-#define     MSI_DATA_DELIVERY_FIXED	(0 << MSI_DATA_DELIVERY_SHIFT)
-#define     MSI_DATA_DELIVERY_LOWPRI	(1 << MSI_DATA_DELIVERY_SHIFT)
-
-#define MSI_DATA_LEVEL_SHIFT		14
-#define     MSI_DATA_LEVEL_DEASSERT	(0 << MSI_DATA_LEVEL_SHIFT)
-#define     MSI_DATA_LEVEL_ASSERT	(1 << MSI_DATA_LEVEL_SHIFT)
-
-#define MSI_DATA_TRIGGER_SHIFT		15
-#define     MSI_DATA_TRIGGER_EDGE	(0 << MSI_DATA_TRIGGER_SHIFT)
-#define     MSI_DATA_TRIGGER_LEVEL	(1 << MSI_DATA_TRIGGER_SHIFT)
-
-/*
- * Shift/mask fields for APIC-based bus address
- */
-
-#define MSI_TARGET_CPU_SHIFT		4
-#define MSI_ADDR_HEADER			0xfee00000
-
-#define MSI_ADDR_DESTID_MASK		0xfff0000f
-#define     MSI_ADDR_DESTID_CPU(cpu)	((cpu) << MSI_TARGET_CPU_SHIFT)
-
-#define MSI_ADDR_DESTMODE_SHIFT		2
-#define     MSI_ADDR_DESTMODE_PHYS	(0 << MSI_ADDR_DESTMODE_SHIFT)
-#define	    MSI_ADDR_DESTMODE_LOGIC	(1 << MSI_ADDR_DESTMODE_SHIFT)
-
-#define MSI_ADDR_REDIRECTION_SHIFT	3
-#define     MSI_ADDR_REDIRECTION_CPU	(0 << MSI_ADDR_REDIRECTION_SHIFT)
-#define     MSI_ADDR_REDIRECTION_LOWPRI	(1 << MSI_ADDR_REDIRECTION_SHIFT)
+#include <asm/msidef.h>
 
 static struct irq_chip	ia64_msi_chip;
 
@@ -65,8 +28,8 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 	read_msi_msg(irq, &msg);
 
 	addr = msg.address_lo;
-	addr &= MSI_ADDR_DESTID_MASK;
-	addr |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
+	addr &= MSI_ADDR_DEST_ID_MASK;
+	addr |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu));
 	msg.address_lo = addr;
 
 	data = msg.data;
@@ -98,9 +61,9 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
 	msg.address_hi = 0;
 	msg.address_lo =
 		MSI_ADDR_HEADER |
-		MSI_ADDR_DESTMODE_PHYS |
+		MSI_ADDR_DEST_MODE_PHYS |
 		MSI_ADDR_REDIRECTION_CPU |
-		MSI_ADDR_DESTID_CPU(dest_phys_id);
+		MSI_ADDR_DEST_ID_CPU(dest_phys_id);
 
 	msg.data =
 		MSI_DATA_TRIGGER_EDGE |
@@ -183,8 +146,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DESTID_MASK;
-	msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu));
 
 	dmar_msi_write(irq, &msg);
 	irq_desc[irq].affinity = *mask;
@@ -215,9 +178,9 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 	msg->address_hi = 0;
 	msg->address_lo =
 		MSI_ADDR_HEADER |
-		MSI_ADDR_DESTMODE_PHYS |
+		MSI_ADDR_DEST_MODE_PHYS |
 		MSI_ADDR_REDIRECTION_CPU |
-		MSI_ADDR_DESTID_CPU(dest);
+		MSI_ADDR_DEST_ID_CPU(dest);
 
 	msg->data =
 		MSI_DATA_TRIGGER_EDGE |
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 0e499757309..5c0f408cfd7 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2196,7 +2196,7 @@ pfmfs_delete_dentry(struct dentry *dentry)
 	return 1;
 }
 
-static struct dentry_operations pfmfs_dentry_operations = {
+static const struct dentry_operations pfmfs_dentry_operations = {
 	.d_delete = pfmfs_delete_dentry,
 };
 
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index f833a0b4188..0a2d6b86075 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -4,6 +4,10 @@
 config HAVE_KVM
 	bool
 
+config HAVE_KVM_IRQCHIP
+       bool
+       default y
+
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
 	depends on HAVE_KVM || IA64
diff --git a/arch/ia64/kvm/irq.h b/arch/ia64/kvm/irq.h
index c6786e8b1bf..c0785a72827 100644
--- a/arch/ia64/kvm/irq.h
+++ b/arch/ia64/kvm/irq.h
@@ -23,6 +23,8 @@
 #ifndef __IRQ_H
 #define __IRQ_H
 
+#include "lapic.h"
+
 static inline int irqchip_in_kernel(struct kvm *kvm)
 {
 	return 1;
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 28f982045f2..076b00d1dbf 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -182,7 +182,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
 	case KVM_CAP_MP_STATE:
-
+	case KVM_CAP_IRQ_INJECT_STATUS:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -314,7 +314,7 @@ static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
 	union ia64_lid lid;
 	int i;
 
-	for (i = 0; i < KVM_MAX_VCPUS; i++) {
+	for (i = 0; i < kvm->arch.online_vcpus; i++) {
 		if (kvm->vcpus[i]) {
 			lid.val = VCPU_LID(kvm->vcpus[i]);
 			if (lid.id == id && lid.eid == eid)
@@ -388,7 +388,7 @@ static int handle_global_purge(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	call_data.ptc_g_data = p->u.ptc_g_data;
 
-	for (i = 0; i < KVM_MAX_VCPUS; i++) {
+	for (i = 0; i < kvm->arch.online_vcpus; i++) {
 		if (!kvm->vcpus[i] || kvm->vcpus[i]->arch.mp_state ==
 						KVM_MP_STATE_UNINITIALIZED ||
 					vcpu == kvm->vcpus[i])
@@ -788,6 +788,8 @@ struct  kvm *kvm_arch_create_vm(void)
 		return ERR_PTR(-ENOMEM);
 	kvm_init_vm(kvm);
 
+	kvm->arch.online_vcpus = 0;
+
 	return kvm;
 
 }
@@ -919,7 +921,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_ioapic_init(kvm);
 		if (r)
 			goto out;
+		r = kvm_setup_default_irq_routing(kvm);
+		if (r) {
+			kfree(kvm->arch.vioapic);
+			goto out;
+		}
 		break;
+	case KVM_IRQ_LINE_STATUS:
 	case KVM_IRQ_LINE: {
 		struct kvm_irq_level irq_event;
 
@@ -927,10 +935,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
+			__s32 status;
 			mutex_lock(&kvm->lock);
-			kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 				    irq_event.irq, irq_event.level);
 			mutex_unlock(&kvm->lock);
+			if (ioctl == KVM_IRQ_LINE_STATUS) {
+				irq_event.status = status;
+				if (copy_to_user(argp, &irq_event,
+							sizeof irq_event))
+					goto out;
+			}
 			r = 0;
 		}
 		break;
@@ -1149,7 +1164,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 		/*Initialize itc offset for vcpus*/
 		itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
-		for (i = 0; i < KVM_MAX_VCPUS; i++) {
+		for (i = 0; i < kvm->arch.online_vcpus; i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
 			v->arch.itc_offset = itc_offset;
@@ -1283,6 +1298,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		goto fail;
 	}
 
+	kvm->arch.online_vcpus++;
+
 	return vcpu;
 fail:
 	return ERR_PTR(r);
@@ -1303,8 +1320,8 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return -EINVAL;
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-		struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	return -EINVAL;
 }
@@ -1421,6 +1438,23 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return 0;
 }
 
+int kvm_arch_vcpu_ioctl_get_stack(struct kvm_vcpu *vcpu,
+				  struct kvm_ia64_vcpu_stack *stack)
+{
+	memcpy(stack, vcpu, sizeof(struct kvm_ia64_vcpu_stack));
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_stack(struct kvm_vcpu *vcpu,
+				  struct kvm_ia64_vcpu_stack *stack)
+{
+	memcpy(vcpu + 1, &stack->stack[0] + sizeof(struct kvm_vcpu),
+	       sizeof(struct kvm_ia64_vcpu_stack) - sizeof(struct kvm_vcpu));
+
+	vcpu->arch.exit_data = ((struct kvm_vcpu *)stack)->arch.exit_data;
+	return 0;
+}
+
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 
@@ -1430,9 +1464,78 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 
 long kvm_arch_vcpu_ioctl(struct file *filp,
-		unsigned int ioctl, unsigned long arg)
+			 unsigned int ioctl, unsigned long arg)
 {
-	return -EINVAL;
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	struct kvm_ia64_vcpu_stack *stack = NULL;
+	long r;
+
+	switch (ioctl) {
+	case KVM_IA64_VCPU_GET_STACK: {
+		struct kvm_ia64_vcpu_stack __user *user_stack;
+	        void __user *first_p = argp;
+
+		r = -EFAULT;
+		if (copy_from_user(&user_stack, first_p, sizeof(void *)))
+			goto out;
+
+		if (!access_ok(VERIFY_WRITE, user_stack,
+			       sizeof(struct kvm_ia64_vcpu_stack))) {
+			printk(KERN_INFO "KVM_IA64_VCPU_GET_STACK: "
+			       "Illegal user destination address for stack\n");
+			goto out;
+		}
+		stack = kzalloc(sizeof(struct kvm_ia64_vcpu_stack), GFP_KERNEL);
+		if (!stack) {
+			r = -ENOMEM;
+			goto out;
+		}
+
+		r = kvm_arch_vcpu_ioctl_get_stack(vcpu, stack);
+		if (r)
+			goto out;
+
+		if (copy_to_user(user_stack, stack,
+				 sizeof(struct kvm_ia64_vcpu_stack)))
+			goto out;
+
+		break;
+	}
+	case KVM_IA64_VCPU_SET_STACK: {
+		struct kvm_ia64_vcpu_stack __user *user_stack;
+	        void __user *first_p = argp;
+
+		r = -EFAULT;
+		if (copy_from_user(&user_stack, first_p, sizeof(void *)))
+			goto out;
+
+		if (!access_ok(VERIFY_READ, user_stack,
+			    sizeof(struct kvm_ia64_vcpu_stack))) {
+			printk(KERN_INFO "KVM_IA64_VCPU_SET_STACK: "
+			       "Illegal user address for stack\n");
+			goto out;
+		}
+		stack = kmalloc(sizeof(struct kvm_ia64_vcpu_stack), GFP_KERNEL);
+		if (!stack) {
+			r = -ENOMEM;
+			goto out;
+		}
+		if (copy_from_user(stack, user_stack,
+				   sizeof(struct kvm_ia64_vcpu_stack)))
+			goto out;
+
+		r = kvm_arch_vcpu_ioctl_set_stack(vcpu, stack);
+		break;
+	}
+
+	default:
+		r = -EINVAL;
+	}
+
+out:
+	kfree(stack);
+	return r;
 }
 
 int kvm_arch_set_memory_region(struct kvm *kvm,
@@ -1472,7 +1575,7 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
 }
 
 long kvm_arch_dev_ioctl(struct file *filp,
-		unsigned int ioctl, unsigned long arg)
+			unsigned int ioctl, unsigned long arg)
 {
 	return -EINVAL;
 }
@@ -1737,7 +1840,7 @@ struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
 	struct kvm_vcpu *lvcpu = kvm->vcpus[0];
 	int i;
 
-	for (i = 1; i < KVM_MAX_VCPUS; i++) {
+	for (i = 1; i < kvm->arch.online_vcpus; i++) {
 		if (!kvm->vcpus[i])
 			continue;
 		if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
diff --git a/arch/ia64/kvm/kvm_fw.c b/arch/ia64/kvm/kvm_fw.c
index cb7600bdff9..a8ae52ed563 100644
--- a/arch/ia64/kvm/kvm_fw.c
+++ b/arch/ia64/kvm/kvm_fw.c
@@ -227,6 +227,18 @@ static struct ia64_pal_retval pal_proc_get_features(struct kvm_vcpu *vcpu)
 	return result;
 }
 
+static struct ia64_pal_retval pal_register_info(struct kvm_vcpu *vcpu)
+{
+
+	struct ia64_pal_retval result = {0, 0, 0, 0};
+	long in0, in1, in2, in3;
+
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+	result.status = ia64_pal_register_info(in1, &result.v1, &result.v2);
+
+	return result;
+}
+
 static struct ia64_pal_retval pal_cache_info(struct kvm_vcpu *vcpu)
 {
 
@@ -268,8 +280,12 @@ static struct ia64_pal_retval pal_vm_summary(struct kvm_vcpu *vcpu)
 static struct ia64_pal_retval pal_vm_info(struct kvm_vcpu *vcpu)
 {
 	struct ia64_pal_retval result;
+	unsigned long in0, in1, in2, in3;
 
-	INIT_PAL_STATUS_UNIMPLEMENTED(result);
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+
+	result.status = ia64_pal_vm_info(in1, in2,
+			(pal_tc_info_u_t *)&result.v1, &result.v2);
 
 	return result;
 }
@@ -292,6 +308,108 @@ static void prepare_for_halt(struct kvm_vcpu *vcpu)
 	vcpu->arch.timer_fired = 0;
 }
 
+static struct ia64_pal_retval pal_perf_mon_info(struct kvm_vcpu *vcpu)
+{
+	long status;
+	unsigned long in0, in1, in2, in3, r9;
+	unsigned long pm_buffer[16];
+
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+	status = ia64_pal_perf_mon_info(pm_buffer,
+				(pal_perf_mon_info_u_t *) &r9);
+	if (status != 0) {
+		printk(KERN_DEBUG"PAL_PERF_MON_INFO fails ret=%ld\n", status);
+	} else {
+		if (in1)
+			memcpy((void *)in1, pm_buffer, sizeof(pm_buffer));
+		else {
+			status = PAL_STATUS_EINVAL;
+			printk(KERN_WARNING"Invalid parameters "
+						"for PAL call:0x%lx!\n", in0);
+		}
+	}
+	return (struct ia64_pal_retval){status, r9, 0, 0};
+}
+
+static struct ia64_pal_retval pal_halt_info(struct kvm_vcpu *vcpu)
+{
+	unsigned long in0, in1, in2, in3;
+	long status;
+	unsigned long res = 1000UL | (1000UL << 16) | (10UL << 32)
+					| (1UL << 61) | (1UL << 60);
+
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+	if (in1) {
+		memcpy((void *)in1, &res, sizeof(res));
+		status = 0;
+	} else{
+		status = PAL_STATUS_EINVAL;
+		printk(KERN_WARNING"Invalid parameters "
+					"for PAL call:0x%lx!\n", in0);
+	}
+
+	return (struct ia64_pal_retval){status, 0, 0, 0};
+}
+
+static struct ia64_pal_retval pal_mem_attrib(struct kvm_vcpu *vcpu)
+{
+	unsigned long r9;
+	long status;
+
+	status = ia64_pal_mem_attrib(&r9);
+
+	return (struct ia64_pal_retval){status, r9, 0, 0};
+}
+
+static void remote_pal_prefetch_visibility(void *v)
+{
+	s64 trans_type = (s64)v;
+	ia64_pal_prefetch_visibility(trans_type);
+}
+
+static struct ia64_pal_retval pal_prefetch_visibility(struct kvm_vcpu *vcpu)
+{
+	struct ia64_pal_retval result = {0, 0, 0, 0};
+	unsigned long in0, in1, in2, in3;
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+	result.status = ia64_pal_prefetch_visibility(in1);
+	if (result.status == 0) {
+		/* Must be performed on all remote processors
+		in the coherence domain. */
+		smp_call_function(remote_pal_prefetch_visibility,
+					(void *)in1, 1);
+		/* Unnecessary on remote processor for other vcpus!*/
+		result.status = 1;
+	}
+	return result;
+}
+
+static void remote_pal_mc_drain(void *v)
+{
+	ia64_pal_mc_drain();
+}
+
+static struct ia64_pal_retval pal_get_brand_info(struct kvm_vcpu *vcpu)
+{
+	struct ia64_pal_retval result = {0, 0, 0, 0};
+	unsigned long in0, in1, in2, in3;
+
+	kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+
+	if (in1 == 0 && in2) {
+		char brand_info[128];
+		result.status = ia64_pal_get_brand_info(brand_info);
+		if (result.status == PAL_STATUS_SUCCESS)
+			memcpy((void *)in2, brand_info, 128);
+	} else {
+		result.status = PAL_STATUS_REQUIRES_MEMORY;
+		printk(KERN_WARNING"Invalid parameters for "
+					"PAL call:0x%lx!\n", in0);
+	}
+
+	return result;
+}
+
 int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 
@@ -300,14 +418,22 @@ int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	int ret = 1;
 
 	gr28 = kvm_get_pal_call_index(vcpu);
-	/*printk("pal_call index:%lx\n",gr28);*/
 	switch (gr28) {
 	case PAL_CACHE_FLUSH:
 		result = pal_cache_flush(vcpu);
 		break;
+	case PAL_MEM_ATTRIB:
+		result = pal_mem_attrib(vcpu);
+		break;
 	case PAL_CACHE_SUMMARY:
 		result = pal_cache_summary(vcpu);
 		break;
+	case PAL_PERF_MON_INFO:
+		result = pal_perf_mon_info(vcpu);
+		break;
+	case PAL_HALT_INFO:
+		result = pal_halt_info(vcpu);
+		break;
 	case PAL_HALT_LIGHT:
 	{
 		INIT_PAL_STATUS_SUCCESS(result);
@@ -317,6 +443,16 @@ int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	}
 		break;
 
+	case PAL_PREFETCH_VISIBILITY:
+		result = pal_prefetch_visibility(vcpu);
+		break;
+	case PAL_MC_DRAIN:
+		result.status = ia64_pal_mc_drain();
+		/* FIXME: All vcpus likely call PAL_MC_DRAIN.
+		   That causes the congestion. */
+		smp_call_function(remote_pal_mc_drain, NULL, 1);
+		break;
+
 	case PAL_FREQ_RATIOS:
 		result = pal_freq_ratios(vcpu);
 		break;
@@ -346,6 +482,9 @@ int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		INIT_PAL_STATUS_SUCCESS(result);
 		result.v1 = (1L << 32) | 1L;
 		break;
+	case PAL_REGISTER_INFO:
+		result = pal_register_info(vcpu);
+		break;
 	case PAL_VM_PAGE_SIZE:
 		result.status = ia64_pal_vm_page_size(&result.v0,
 							&result.v1);
@@ -365,12 +504,18 @@ int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		result.status = ia64_pal_version(
 				(pal_version_u_t *)&result.v0,
 				(pal_version_u_t *)&result.v1);
-
 		break;
 	case PAL_FIXED_ADDR:
 		result.status = PAL_STATUS_SUCCESS;
 		result.v0 = vcpu->vcpu_id;
 		break;
+	case PAL_BRAND_INFO:
+		result = pal_get_brand_info(vcpu);
+		break;
+	case PAL_GET_PSTATE:
+	case PAL_CACHE_SHARED_INFO:
+		INIT_PAL_STATUS_UNIMPLEMENTED(result);
+		break;
 	default:
 		INIT_PAL_STATUS_UNIMPLEMENTED(result);
 		printk(KERN_WARNING"kvm: Unsupported pal call,"
diff --git a/arch/ia64/kvm/process.c b/arch/ia64/kvm/process.c
index 230eae482f3..b1dc80952d9 100644
--- a/arch/ia64/kvm/process.c
+++ b/arch/ia64/kvm/process.c
@@ -167,7 +167,6 @@ static u64 vcpu_get_itir_on_fault(struct kvm_vcpu *vcpu, u64 ifa)
 	return (rr1.val);
 }
 
-
 /*
  * Set vIFA & vITIR & vIHA, when vPSR.ic =1
  * Parameter:
@@ -222,8 +221,6 @@ void itlb_fault(struct kvm_vcpu *vcpu, u64 vadr)
 	inject_guest_interruption(vcpu, IA64_INST_TLB_VECTOR);
 }
 
-
-
 /*
  * Data Nested TLB Fault
  *  @ Data Nested TLB Vector
@@ -245,7 +242,6 @@ void alt_dtlb(struct kvm_vcpu *vcpu, u64 vadr)
 	inject_guest_interruption(vcpu, IA64_ALT_DATA_TLB_VECTOR);
 }
 
-
 /*
  * Data TLB Fault
  *  @ Data TLB vector
@@ -265,8 +261,6 @@ static void _vhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
 	/* If vPSR.ic, IFA, ITIR, IHA*/
 	set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
 	inject_guest_interruption(vcpu, IA64_VHPT_TRANS_VECTOR);
-
-
 }
 
 /*
@@ -279,7 +273,6 @@ void ivhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
 	_vhpt_fault(vcpu, vadr);
 }
 
-
 /*
  * VHPT Data Fault
  *  @ VHPT Translation vector
@@ -290,8 +283,6 @@ void dvhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
 	_vhpt_fault(vcpu, vadr);
 }
 
-
-
 /*
  * Deal with:
  *  General Exception vector
@@ -301,7 +292,6 @@ void _general_exception(struct kvm_vcpu *vcpu)
 	inject_guest_interruption(vcpu, IA64_GENEX_VECTOR);
 }
 
-
 /*
  * Illegal Operation Fault
  *  @ General Exception Vector
@@ -419,19 +409,16 @@ static void __page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
 	inject_guest_interruption(vcpu, IA64_PAGE_NOT_PRESENT_VECTOR);
 }
 
-
 void data_page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
 {
 	__page_not_present(vcpu, vadr);
 }
 
-
 void inst_page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
 {
 	__page_not_present(vcpu, vadr);
 }
 
-
 /* Deal with
  *  Data access rights vector
  */
@@ -563,22 +550,64 @@ void reflect_interruption(u64 ifa, u64 isr, u64 iim,
 	inject_guest_interruption(vcpu, vector);
 }
 
+static unsigned long kvm_trans_pal_call_args(struct kvm_vcpu *vcpu,
+						unsigned long arg)
+{
+	struct thash_data *data;
+	unsigned long gpa, poff;
+
+	if (!is_physical_mode(vcpu)) {
+		/* Depends on caller to provide the DTR or DTC mapping.*/
+		data = vtlb_lookup(vcpu, arg, D_TLB);
+		if (data)
+			gpa = data->page_flags & _PAGE_PPN_MASK;
+		else {
+			data = vhpt_lookup(arg);
+			if (!data)
+				return 0;
+			gpa = data->gpaddr & _PAGE_PPN_MASK;
+		}
+
+		poff = arg & (PSIZE(data->ps) - 1);
+		arg = PAGEALIGN(gpa, data->ps) | poff;
+	}
+	arg = kvm_gpa_to_mpa(arg << 1 >> 1);
+
+	return (unsigned long)__va(arg);
+}
+
 static void set_pal_call_data(struct kvm_vcpu *vcpu)
 {
 	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+	unsigned long gr28 = vcpu_get_gr(vcpu, 28);
+	unsigned long gr29 = vcpu_get_gr(vcpu, 29);
+	unsigned long gr30 = vcpu_get_gr(vcpu, 30);
 
 	/*FIXME:For static and stacked convention, firmware
 	 * has put the parameters in gr28-gr31 before
 	 * break to vmm  !!*/
 
-	p->u.pal_data.gr28 = vcpu_get_gr(vcpu, 28);
-	p->u.pal_data.gr29 = vcpu_get_gr(vcpu, 29);
-	p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30);
+	switch (gr28) {
+	case PAL_PERF_MON_INFO:
+	case PAL_HALT_INFO:
+		p->u.pal_data.gr29 =  kvm_trans_pal_call_args(vcpu, gr29);
+		p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30);
+		break;
+	case PAL_BRAND_INFO:
+		p->u.pal_data.gr29 = gr29;;
+		p->u.pal_data.gr30 = kvm_trans_pal_call_args(vcpu, gr30);
+		break;
+	default:
+		p->u.pal_data.gr29 = gr29;;
+		p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30);
+	}
+	p->u.pal_data.gr28 = gr28;
 	p->u.pal_data.gr31 = vcpu_get_gr(vcpu, 31);
+
 	p->exit_reason = EXIT_REASON_PAL_CALL;
 }
 
-static void set_pal_call_result(struct kvm_vcpu *vcpu)
+static void get_pal_call_result(struct kvm_vcpu *vcpu)
 {
 	struct exit_ctl_data *p = &vcpu->arch.exit_data;
 
@@ -606,7 +635,7 @@ static void set_sal_call_data(struct kvm_vcpu *vcpu)
 	p->exit_reason = EXIT_REASON_SAL_CALL;
 }
 
-static void set_sal_call_result(struct kvm_vcpu *vcpu)
+static void get_sal_call_result(struct kvm_vcpu *vcpu)
 {
 	struct exit_ctl_data *p = &vcpu->arch.exit_data;
 
@@ -629,13 +658,13 @@ void  kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
 		if (iim == DOMN_PAL_REQUEST) {
 			set_pal_call_data(v);
 			vmm_transition(v);
-			set_pal_call_result(v);
+			get_pal_call_result(v);
 			vcpu_increment_iip(v);
 			return;
 		} else if (iim == DOMN_SAL_REQUEST) {
 			set_sal_call_data(v);
 			vmm_transition(v);
-			set_sal_call_result(v);
+			get_sal_call_result(v);
 			vcpu_increment_iip(v);
 			return;
 		}
@@ -703,7 +732,6 @@ void vhpi_detection(struct kvm_vcpu *vcpu)
 	}
 }
 
-
 void leave_hypervisor_tail(void)
 {
 	struct kvm_vcpu *v = current_vcpu;
@@ -737,7 +765,6 @@ void leave_hypervisor_tail(void)
 	}
 }
 
-
 static inline void handle_lds(struct kvm_pt_regs *regs)
 {
 	regs->cr_ipsr |= IA64_PSR_ED;
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
index ecd526b5532..d4d28050587 100644
--- a/arch/ia64/kvm/vcpu.c
+++ b/arch/ia64/kvm/vcpu.c
@@ -112,7 +112,6 @@ void switch_to_physical_rid(struct kvm_vcpu *vcpu)
 	return;
 }
 
-
 void switch_to_virtual_rid(struct kvm_vcpu *vcpu)
 {
 	unsigned long psr;
@@ -166,8 +165,6 @@ void switch_mm_mode(struct kvm_vcpu *vcpu, struct ia64_psr old_psr,
 	return;
 }
 
-
-
 /*
  * In physical mode, insert tc/tr for region 0 and 4 uses
  * RID[0] and RID[4] which is for physical mode emulation.
@@ -269,7 +266,6 @@ static inline unsigned long fph_index(struct kvm_pt_regs *regs,
 	return rotate_reg(96, rrb_fr, (regnum - IA64_FIRST_ROTATING_FR));
 }
 
-
 /*
  * The inverse of the above: given bspstore and the number of
  * registers, calculate ar.bsp.
@@ -811,12 +807,15 @@ static inline void vcpu_set_itm(struct kvm_vcpu *vcpu, u64 val);
 static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
 {
 	struct kvm_vcpu *v;
+	struct kvm *kvm;
 	int i;
 	long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC);
 	unsigned long vitv = VCPU(vcpu, itv);
 
+	kvm = (struct kvm *)KVM_VM_BASE;
+
 	if (vcpu->vcpu_id == 0) {
-		for (i = 0; i < KVM_MAX_VCPUS; i++) {
+		for (i = 0; i < kvm->arch.online_vcpus; i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
 			VMX(v, itc_offset) = itc_offset;
@@ -1039,8 +1038,6 @@ u64 vcpu_tak(struct kvm_vcpu *vcpu, u64 vadr)
 	return key;
 }
 
-
-
 void kvm_thash(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long thash, vadr;
@@ -1050,7 +1047,6 @@ void kvm_thash(struct kvm_vcpu *vcpu, INST64 inst)
 	vcpu_set_gr(vcpu, inst.M46.r1, thash, 0);
 }
 
-
 void kvm_ttag(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long tag, vadr;
@@ -1131,7 +1127,6 @@ int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, u64 *padr)
 	return IA64_NO_FAULT;
 }
 
-
 int kvm_tpa(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long r1, r3;
@@ -1154,7 +1149,6 @@ void kvm_tak(struct kvm_vcpu *vcpu, INST64 inst)
 	vcpu_set_gr(vcpu, inst.M46.r1, r1, 0);
 }
 
-
 /************************************
  * Insert/Purge translation register/cache
  ************************************/
@@ -1385,7 +1379,6 @@ void kvm_mov_to_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
 	vcpu_set_itc(vcpu, r2);
 }
 
-
 void kvm_mov_from_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long r1;
@@ -1393,8 +1386,9 @@ void kvm_mov_from_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
 	r1 = vcpu_get_itc(vcpu);
 	vcpu_set_gr(vcpu, inst.M31.r1, r1, 0);
 }
+
 /**************************************************************************
-  struct kvm_vcpu*protection key register access routines
+  struct kvm_vcpu protection key register access routines
  **************************************************************************/
 
 unsigned long vcpu_get_pkr(struct kvm_vcpu *vcpu, unsigned long reg)
@@ -1407,20 +1401,6 @@ void vcpu_set_pkr(struct kvm_vcpu *vcpu, unsigned long reg, unsigned long val)
 	ia64_set_pkr(reg, val);
 }
 
-
-unsigned long vcpu_get_itir_on_fault(struct kvm_vcpu *vcpu, unsigned long ifa)
-{
-	union ia64_rr rr, rr1;
-
-	rr.val = vcpu_get_rr(vcpu, ifa);
-	rr1.val = 0;
-	rr1.ps = rr.ps;
-	rr1.rid = rr.rid;
-	return (rr1.val);
-}
-
-
-
 /********************************
  * Moves to privileged registers
  ********************************/
@@ -1464,8 +1444,6 @@ unsigned long vcpu_set_rr(struct kvm_vcpu *vcpu, unsigned long reg,
 	return (IA64_NO_FAULT);
 }
 
-
-
 void kvm_mov_to_rr(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long r3, r2;
@@ -1510,8 +1488,6 @@ void kvm_mov_to_pkr(struct kvm_vcpu *vcpu, INST64 inst)
 	vcpu_set_pkr(vcpu, r3, r2);
 }
 
-
-
 void kvm_mov_from_rr(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long r3, r1;
@@ -1557,7 +1533,6 @@ void kvm_mov_from_pmc(struct kvm_vcpu *vcpu, INST64 inst)
 	vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
 }
 
-
 unsigned long vcpu_get_cpuid(struct kvm_vcpu *vcpu, unsigned long reg)
 {
 	/* FIXME: This could get called as a result of a rsvd-reg fault */
@@ -1609,7 +1584,6 @@ unsigned long kvm_mov_to_cr(struct kvm_vcpu *vcpu, INST64 inst)
 	return 0;
 }
 
-
 unsigned long kvm_mov_from_cr(struct kvm_vcpu *vcpu, INST64 inst)
 {
 	unsigned long tgt = inst.M33.r1;
@@ -1633,8 +1607,6 @@ unsigned long kvm_mov_from_cr(struct kvm_vcpu *vcpu, INST64 inst)
 	return 0;
 }
 
-
-
 void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val)
 {
 
@@ -1776,9 +1748,6 @@ void vcpu_bsw1(struct kvm_vcpu *vcpu)
 	}
 }
 
-
-
-
 void vcpu_rfi(struct kvm_vcpu *vcpu)
 {
 	unsigned long ifs, psr;
@@ -1796,7 +1765,6 @@ void vcpu_rfi(struct kvm_vcpu *vcpu)
 	regs->cr_iip = VCPU(vcpu, iip);
 }
 
-
 /*
    VPSR can't keep track of below bits of guest PSR
    This function gets guest PSR
diff --git a/arch/ia64/kvm/vcpu.h b/arch/ia64/kvm/vcpu.h
index b2f12a562bd..042af92ced8 100644
--- a/arch/ia64/kvm/vcpu.h
+++ b/arch/ia64/kvm/vcpu.h
@@ -703,7 +703,7 @@ extern u64 guest_vhpt_lookup(u64 iha, u64 *pte);
 extern void thash_purge_entries(struct kvm_vcpu *v, u64 va, u64 ps);
 extern void thash_purge_entries_remote(struct kvm_vcpu *v, u64 va, u64 ps);
 extern u64 translate_phy_pte(u64 *pte, u64 itir, u64 va);
-extern int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte,
+extern void thash_purge_and_insert(struct kvm_vcpu *v, u64 pte,
 		u64 itir, u64 ifa, int type);
 extern void thash_purge_all(struct kvm_vcpu *v);
 extern struct thash_data *vtlb_lookup(struct kvm_vcpu *v,
@@ -738,7 +738,7 @@ void kvm_init_vhpt(struct kvm_vcpu *v);
 void thash_init(struct thash_cb *hcb, u64 sz);
 
 void panic_vm(struct kvm_vcpu *v, const char *fmt, ...);
-
+u64 kvm_gpa_to_mpa(u64 gpa);
 extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2, u64 arg3,
 		u64 arg4, u64 arg5, u64 arg6, u64 arg7);
 
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 6b6307a3bd5..38232b37668 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -164,11 +164,11 @@ static void vhpt_insert(u64 pte, u64 itir, u64 ifa, u64 gpte)
 	unsigned long ps, gpaddr;
 
 	ps = itir_ps(itir);
+	rr.val = ia64_get_rr(ifa);
 
-	gpaddr = ((gpte & _PAGE_PPN_MASK) >> ps << ps) |
-		(ifa & ((1UL << ps) - 1));
+	 gpaddr = ((gpte & _PAGE_PPN_MASK) >> ps << ps) |
+					(ifa & ((1UL << ps) - 1));
 
-	rr.val = ia64_get_rr(ifa);
 	head = (struct thash_data *)ia64_thash(ifa);
 	head->etag = INVALID_TI_TAG;
 	ia64_mf();
@@ -412,16 +412,14 @@ u64 translate_phy_pte(u64 *pte, u64 itir, u64 va)
 
 /*
  * Purge overlap TCs and then insert the new entry to emulate itc ops.
- *    Notes: Only TC entry can purge and insert.
- *    1 indicates this is MMIO
+ * Notes: Only TC entry can purge and insert.
  */
-int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
+void  thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
 						u64 ifa, int type)
 {
 	u64 ps;
 	u64 phy_pte, io_mask, index;
 	union ia64_rr vrr, mrr;
-	int ret = 0;
 
 	ps = itir_ps(itir);
 	vrr.val = vcpu_get_rr(v, ifa);
@@ -441,25 +439,19 @@ int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
 		phy_pte &= ~_PAGE_MA_MASK;
 	}
 
-	if (pte & VTLB_PTE_IO)
-		ret = 1;
-
 	vtlb_purge(v, ifa, ps);
 	vhpt_purge(v, ifa, ps);
 
-	if (ps == mrr.ps) {
-		if (!(pte&VTLB_PTE_IO)) {
-			vhpt_insert(phy_pte, itir, ifa, pte);
-		} else {
-			vtlb_insert(v, pte, itir, ifa);
-			vcpu_quick_region_set(VMX(v, tc_regions), ifa);
-		}
-	} else if (ps > mrr.ps) {
+	if ((ps != mrr.ps) || (pte & VTLB_PTE_IO)) {
 		vtlb_insert(v, pte, itir, ifa);
 		vcpu_quick_region_set(VMX(v, tc_regions), ifa);
-		if (!(pte&VTLB_PTE_IO))
-			vhpt_insert(phy_pte, itir, ifa, pte);
-	} else {
+	}
+	if (pte & VTLB_PTE_IO)
+		return;
+
+	if (ps >= mrr.ps)
+		vhpt_insert(phy_pte, itir, ifa, pte);
+	else {
 		u64 psr;
 		phy_pte  &= ~PAGE_FLAGS_RV_MASK;
 		psr = ia64_clear_ic();
@@ -469,7 +461,6 @@ int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
 	if (!(pte&VTLB_PTE_IO))
 		mark_pages_dirty(v, pte, ps);
 
-	return ret;
 }
 
 /*
@@ -509,7 +500,6 @@ void thash_purge_all(struct kvm_vcpu *v)
 	local_flush_tlb_all();
 }
 
-
 /*
  * Lookup the hash table and its collision chain to find an entry
  * covering this address rid:va or the entry.
@@ -517,7 +507,6 @@ void thash_purge_all(struct kvm_vcpu *v)
  * INPUT:
  *  in: TLB format for both VHPT & TLB.
  */
-
 struct thash_data *vtlb_lookup(struct kvm_vcpu *v, u64 va, int is_data)
 {
 	struct thash_data  *cch;
@@ -547,7 +536,6 @@ struct thash_data *vtlb_lookup(struct kvm_vcpu *v, u64 va, int is_data)
 	return NULL;
 }
 
-
 /*
  * Initialize internal control data before service.
  */
@@ -573,6 +561,10 @@ void thash_init(struct thash_cb *hcb, u64 sz)
 u64 kvm_get_mpt_entry(u64 gpfn)
 {
 	u64 *base = (u64 *) KVM_P2M_BASE;
+
+	if (gpfn >= (KVM_P2M_SIZE >> 3))
+		panic_vm(current_vcpu, "Invalid gpfn =%lx\n", gpfn);
+
 	return *(base + gpfn);
 }
 
@@ -589,7 +581,6 @@ u64 kvm_gpa_to_mpa(u64 gpa)
 	return (pte >> PAGE_SHIFT << PAGE_SHIFT) | (gpa & ~PAGE_MASK);
 }
 
-
 /*
  * Fetch guest bundle code.
  * INPUT:
@@ -631,7 +622,6 @@ int fetch_code(struct kvm_vcpu *vcpu, u64 gip, IA64_BUNDLE *pbundle)
 	return IA64_NO_FAULT;
 }
 
-
 void kvm_init_vhpt(struct kvm_vcpu *v)
 {
 	v->arch.vhpt.num = VHPT_NUM_ENTRIES;
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index 2aeae467009..8dfd31e87c4 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -49,7 +49,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 8133dbc4496..570d85c3f97 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -117,3 +117,6 @@ endif
 
 archclean:
 	rm -f vmlinux.gz vmlinux.bz2
+
+install:
+	sh $(srctree)/arch/m68k/install.sh $(KERNELRELEASE) vmlinux.gz System.map "$(INSTALL_PATH)"
diff --git a/arch/m68k/include/asm/irq_mm.h b/arch/m68k/include/asm/irq_mm.h
index 226bfc0f21b..0cab42cad79 100644
--- a/arch/m68k/include/asm/irq_mm.h
+++ b/arch/m68k/include/asm/irq_mm.h
@@ -3,6 +3,7 @@
 
 #include <linux/linkage.h>
 #include <linux/hardirq.h>
+#include <linux/irqreturn.h>
 #include <linux/spinlock_types.h>
 
 /*
@@ -80,7 +81,7 @@ struct pt_regs;
  * interrupt source (if it supports chaining).
  */
 typedef struct irq_node {
-	int		(*handler)(int, void *);
+	irqreturn_t	(*handler)(int, void *);
 	void		*dev_id;
 	struct irq_node *next;
 	unsigned long	flags;
diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index 05309f7e3d0..50db3591ca1 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -34,6 +34,7 @@ struct mac_model
 	char scc_type;
 	char ether_type;
 	char nubus_type;
+	char floppy_type;
 };
 
 #define MAC_ADB_NONE		0
@@ -71,6 +72,12 @@ struct mac_model
 #define MAC_NO_NUBUS		0
 #define MAC_NUBUS		1
 
+#define MAC_FLOPPY_IWM		0
+#define MAC_FLOPPY_SWIM_ADDR1	1
+#define MAC_FLOPPY_SWIM_ADDR2	2
+#define MAC_FLOPPY_SWIM_IOP	3
+#define MAC_FLOPPY_AV		4
+
 /*
  *	Gestalt numbers
  */
diff --git a/arch/m68k/include/asm/socket.h b/arch/m68k/include/asm/socket.h
index dbc64e92c41..ca87f938b03 100644
--- a/arch/m68k/include/asm/socket.h
+++ b/arch/m68k/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/m68k/install.sh b/arch/m68k/install.sh
new file mode 100644
index 00000000000..9c6bae6112e
--- /dev/null
+++ b/arch/m68k/install.sh
@@ -0,0 +1,52 @@
+#!/bin/sh
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1995 by Linus Torvalds
+#
+# Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin
+#
+# "make install" script for m68k architecture
+#
+# Arguments:
+#   $1 - kernel version
+#   $2 - kernel image file
+#   $3 - kernel map file
+#   $4 - default install path (blank if root directory)
+#
+
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
+# User may have a custom install script
+
+if [ -x ~/bin/${CROSS_COMPILE}installkernel ]; then exec ~/bin/${CROSS_COMPILE}installkernel "$@"; fi
+if [ -x /sbin/${CROSS_COMPILE}installkernel ]; then exec /sbin/${CROSS_COMPILE}installkernel "$@"; fi
+
+# Default install - same as make zlilo
+
+if [ -f $4/vmlinuz ]; then
+	mv $4/vmlinuz $4/vmlinuz.old
+fi
+
+if [ -f $4/System.map ]; then
+	mv $4/System.map $4/System.old
+fi
+
+cat $2 > $4/vmlinuz
+cp $3 $4/System.map
+
+sync
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 98b6bcfb37b..be017984a45 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -22,6 +22,7 @@
 /* keyb */
 #include <linux/init.h>
 #include <linux/vt_kern.h>
+#include <linux/platform_device.h>
 
 #define BOOTINFO_COMPAT_1_0
 #include <asm/setup.h>
@@ -43,6 +44,10 @@
 #include <asm/mac_oss.h>
 #include <asm/mac_psc.h>
 
+/* platform device info */
+
+#define SWIM_IO_SIZE 0x2000	/* SWIM IO resource size */
+
 /* Mac bootinfo struct */
 
 struct mac_booter_data mac_bi_data;
@@ -224,7 +229,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_IWM
 	},
 
 	/*
@@ -239,7 +245,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_IWM
 	}, {
 		.ident		= MAC_MODEL_IIX,
 		.name		= "IIx",
@@ -247,7 +254,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_IICX,
 		.name		= "IIcx",
@@ -255,7 +263,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_SE30,
 		.name		= "SE/30",
@@ -263,7 +272,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_II,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 
 	/*
@@ -280,7 +290,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_IIFX,
 		.name		= "IIfx",
@@ -288,7 +299,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_IOP,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_IOP
 	}, {
 		.ident		= MAC_MODEL_IISI,
 		.name		= "IIsi",
@@ -296,7 +308,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_IIVI,
 		.name		= "IIvi",
@@ -304,7 +317,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_IIVX,
 		.name		= "IIvx",
@@ -312,7 +326,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 
 	/*
@@ -326,7 +341,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_CCL,
 		.name		= "Color Classic",
@@ -334,7 +350,9 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS},
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
+	},
 
 	/*
 	 *	Some Mac LC machines. Basically the same as the IIci, ADB like IIsi
@@ -347,7 +365,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_LCII,
 		.name		= "LC II",
@@ -355,7 +374,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_LCIII,
 		.name		= "LC III",
@@ -363,7 +383,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 
 	/*
@@ -383,7 +404,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_Q605_ACC,
 		.name		= "Quadra 605",
@@ -391,7 +413,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_Q610,
 		.name		= "Quadra 610",
@@ -400,7 +423,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_Q630,
 		.name		= "Quadra 630",
@@ -410,7 +434,8 @@ static struct mac_model mac_data_table[] = {
 		.ide_type	= MAC_IDE_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_Q650,
 		.name		= "Quadra 650",
@@ -419,7 +444,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	},
 	/*	The Q700 does have a NS Sonic */
 	{
@@ -430,7 +456,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA2,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_Q800,
 		.name		= "Quadra 800",
@@ -439,7 +466,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_Q840,
 		.name		= "Quadra 840AV",
@@ -448,7 +476,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA3,
 		.scc_type	= MAC_SCC_PSC,
 		.ether_type	= MAC_ETHER_MACE,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_AV
 	}, {
 		.ident		= MAC_MODEL_Q900,
 		.name		= "Quadra 900",
@@ -457,7 +486,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA2,
 		.scc_type	= MAC_SCC_IOP,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_IOP
 	}, {
 		.ident		= MAC_MODEL_Q950,
 		.name		= "Quadra 950",
@@ -466,7 +496,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA2,
 		.scc_type	= MAC_SCC_IOP,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_IOP
 	},
 
 	/*
@@ -480,7 +511,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_P475,
 		.name		=  "Performa 475",
@@ -488,7 +520,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_P475F,
 		.name		=  "Performa 475",
@@ -496,7 +529,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_P520,
 		.name		=  "Performa 520",
@@ -504,7 +538,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_P550,
 		.name		=  "Performa 550",
@@ -512,7 +547,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 	/* These have the comm slot, and therefore the possibility of SONIC ethernet */
 	{
@@ -523,7 +559,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_II,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_P588,
 		.name		= "Performa 588",
@@ -533,7 +570,8 @@ static struct mac_model mac_data_table[] = {
 		.ide_type	= MAC_IDE_QUADRA,
 		.scc_type	= MAC_SCC_II,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type	= MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_TV,
 		.name		= "TV",
@@ -541,7 +579,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_P600,
 		.name		= "Performa 600",
@@ -549,7 +588,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_II,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 
 	/*
@@ -565,7 +605,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_C650,
 		.name		= "Centris 650",
@@ -574,7 +615,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR1
 	}, {
 		.ident		= MAC_MODEL_C660,
 		.name		= "Centris 660AV",
@@ -583,7 +625,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_QUADRA3,
 		.scc_type	= MAC_SCC_PSC,
 		.ether_type	= MAC_ETHER_MACE,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_AV
 	},
 
 	/*
@@ -599,7 +642,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB145,
 		.name		= "PowerBook 145",
@@ -607,7 +651,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB150,
 		.name		= "PowerBook 150",
@@ -616,7 +661,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_OLD,
 		.ide_type	= MAC_IDE_PB,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB160,
 		.name		= "PowerBook 160",
@@ -624,7 +670,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB165,
 		.name		= "PowerBook 165",
@@ -632,7 +679,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB165C,
 		.name		= "PowerBook 165c",
@@ -640,7 +688,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB170,
 		.name		= "PowerBook 170",
@@ -648,7 +697,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB180,
 		.name		= "PowerBook 180",
@@ -656,7 +706,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB180C,
 		.name		= "PowerBook 180c",
@@ -664,7 +715,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_QUADRA,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB190,
 		.name		= "PowerBook 190",
@@ -673,7 +725,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_OLD,
 		.ide_type	= MAC_IDE_BABOON,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB520,
 		.name		= "PowerBook 520",
@@ -682,7 +735,8 @@ static struct mac_model mac_data_table[] = {
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 
 	/*
@@ -702,7 +756,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB230,
 		.name		= "PowerBook Duo 230",
@@ -710,7 +765,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB250,
 		.name		= "PowerBook Duo 250",
@@ -718,7 +774,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB270C,
 		.name		= "PowerBook Duo 270c",
@@ -726,7 +783,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB280,
 		.name		= "PowerBook Duo 280",
@@ -734,7 +792,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	}, {
 		.ident		= MAC_MODEL_PB280C,
 		.name		= "PowerBook Duo 280c",
@@ -742,7 +801,8 @@ static struct mac_model mac_data_table[] = {
 		.via_type	= MAC_VIA_IIci,
 		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
-		.nubus_type	= MAC_NUBUS
+		.nubus_type	= MAC_NUBUS,
+		.floppy_type    = MAC_FLOPPY_SWIM_ADDR2
 	},
 
 	/*
@@ -815,3 +875,42 @@ static void mac_get_model(char *str)
 	strcpy(str, "Macintosh ");
 	strcat(str, macintosh_config->name);
 }
+
+static struct resource swim_resources[1];
+
+static struct platform_device swim_device = {
+	.name		= "swim",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(swim_resources),
+	.resource	= swim_resources,
+};
+
+static struct platform_device *mac_platform_devices[] __initdata = {
+	&swim_device
+};
+
+int __init mac_platform_init(void)
+{
+	u8 *swim_base;
+
+	switch (macintosh_config->floppy_type) {
+	case MAC_FLOPPY_SWIM_ADDR1:
+		swim_base = (u8 *)(VIA1_BASE + 0x1E000);
+		break;
+	case MAC_FLOPPY_SWIM_ADDR2:
+		swim_base = (u8 *)(VIA1_BASE + 0x16000);
+		break;
+	default:
+		return 0;
+	}
+
+	swim_resources[0].name = "swim-regs";
+	swim_resources[0].start = (resource_size_t)swim_base;
+	swim_resources[0].end = (resource_size_t)(swim_base + SWIM_IO_SIZE);
+	swim_resources[0].flags = IORESOURCE_MEM;
+
+	return platform_add_devices(mac_platform_devices,
+				    ARRAY_SIZE(mac_platform_devices));
+}
+
+arch_initcall(mac_platform_init);
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 7d97ba54536..11bce3cb648 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -645,3 +645,12 @@ int via_irq_pending(int irq)
 	}
 	return 0;
 }
+
+void via1_set_head(int head)
+{
+	if (head == 0)
+		via1[vBufA] &= ~VIA1A_vHeadSel;
+	else
+		via1[vBufA] |= VIA1A_vHeadSel;
+}
+EXPORT_SYMBOL(via1_set_head);
diff --git a/arch/m68knommu/platform/520x/config.c b/arch/m68knommu/platform/520x/config.c
index 06d887cdcbf..855fc6a79d7 100644
--- a/arch/m68knommu/platform/520x/config.c
+++ b/arch/m68knommu/platform/520x/config.c
@@ -49,8 +49,39 @@ static struct platform_device m520x_uart = {
 	.dev.platform_data	= m520x_uart_platform,
 };
 
+static struct resource m520x_fec_resources[] = {
+	{
+		.start		= MCF_MBAR + 0x30000,
+		.end		= MCF_MBAR + 0x30000 + 0x7ff,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 64 + 36,
+		.end		= 64 + 36,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 40,
+		.end		= 64 + 40,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 42,
+		.end		= 64 + 42,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device m520x_fec = {
+	.name			= "fec",
+	.id			= 0,
+	.num_resources		= ARRAY_SIZE(m520x_fec_resources),
+	.resource		= m520x_fec_resources,
+};
+
 static struct platform_device *m520x_devices[] __initdata = {
 	&m520x_uart,
+	&m520x_fec,
 };
 
 /***************************************************************************/
@@ -103,6 +134,30 @@ static void __init m520x_uarts_init(void)
 
 /***************************************************************************/
 
+static void __init m520x_fec_init(void)
+{
+	u32 imr;
+	u8 v;
+
+	/* Unmask FEC interrupts at ColdFire interrupt controller */
+	writeb(0x4, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 36);
+	writeb(0x4, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 40);
+	writeb(0x4, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 42);
+
+	imr = readl(MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
+	imr &= ~0x0001FFF0;
+	writel(imr, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
+
+	/* Set multi-function pins to ethernet mode */
+	v = readb(MCF_IPSBAR + MCF_GPIO_PAR_FEC);
+	writeb(v | 0xf0, MCF_IPSBAR + MCF_GPIO_PAR_FEC);
+
+	v = readb(MCF_IPSBAR + MCF_GPIO_PAR_FECI2C);
+	writeb(v | 0x0f, MCF_IPSBAR + MCF_GPIO_PAR_FECI2C);
+}
+
+/***************************************************************************/
+
 /*
  *  Program the vector to be an auto-vectored.
  */
@@ -118,6 +173,7 @@ void __init config_BSP(char *commandp, int size)
 {
 	mach_reset = coldfire_reset;
 	m520x_uarts_init();
+	m520x_fec_init();
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/523x/config.c b/arch/m68knommu/platform/523x/config.c
index 13f02611ea2..74133f27b30 100644
--- a/arch/m68knommu/platform/523x/config.c
+++ b/arch/m68knommu/platform/523x/config.c
@@ -50,8 +50,39 @@ static struct platform_device m523x_uart = {
 	.dev.platform_data	= m523x_uart_platform,
 };
 
+static struct resource m523x_fec_resources[] = {
+	{
+		.start		= MCF_MBAR + 0x1000,
+		.end		= MCF_MBAR + 0x1000 + 0x7ff,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 64 + 23,
+		.end		= 64 + 23,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 27,
+		.end		= 64 + 27,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 29,
+		.end		= 64 + 29,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device m523x_fec = {
+	.name			= "fec",
+	.id			= 0,
+	.num_resources		= ARRAY_SIZE(m523x_fec_resources),
+	.resource		= m523x_fec_resources,
+};
+
 static struct platform_device *m523x_devices[] __initdata = {
 	&m523x_uart,
+	&m523x_fec,
 };
 
 /***************************************************************************/
@@ -83,6 +114,25 @@ static void __init m523x_uarts_init(void)
 
 /***************************************************************************/
 
+static void __init m523x_fec_init(void)
+{
+	u32 imr;
+
+	/* Unmask FEC interrupts at ColdFire interrupt controller */
+	writeb(0x28, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 23);
+	writeb(0x27, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 27);
+	writeb(0x26, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 29);
+
+	imr = readl(MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
+	imr &= ~0xf;
+	writel(imr, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
+	imr = readl(MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRL);
+	imr &= ~0xff800001;
+	writel(imr, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRL);
+}
+
+/***************************************************************************/
+
 void mcf_disableall(void)
 {
 	*((volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH)) = 0xffffffff;
@@ -103,6 +153,7 @@ void __init config_BSP(char *commandp, int size)
 	mcf_disableall();
 	mach_reset = coldfire_reset;
 	m523x_uarts_init();
+	m523x_fec_init();
 }
 
 /***************************************************************************/
diff --git a/arch/m68knommu/platform/5272/config.c b/arch/m68knommu/platform/5272/config.c
index 230bae691a7..e049245f409 100644
--- a/arch/m68knommu/platform/5272/config.c
+++ b/arch/m68knommu/platform/5272/config.c
@@ -55,8 +55,39 @@ static struct platform_device m5272_uart = {
 	.dev.platform_data	= m5272_uart_platform,
 };
 
+static struct resource m5272_fec_resources[] = {
+	{
+		.start		= MCF_MBAR + 0x840,
+		.end		= MCF_MBAR + 0x840 + 0x1cf,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 86,
+		.end		= 86,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 87,
+		.end		= 87,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 88,
+		.end		= 88,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device m5272_fec = {
+	.name			= "fec",
+	.id			= 0,
+	.num_resources		= ARRAY_SIZE(m5272_fec_resources),
+	.resource		= m5272_fec_resources,
+};
+
 static struct platform_device *m5272_devices[] __initdata = {
 	&m5272_uart,
+	&m5272_fec,
 };
 
 /***************************************************************************/
@@ -91,6 +122,22 @@ static void __init m5272_uarts_init(void)
 
 /***************************************************************************/
 
+static void __init m5272_fec_init(void)
+{
+	u32 imr;
+
+	/* Unmask FEC interrupts at ColdFire interrupt controller */
+	imr = readl(MCF_MBAR + MCFSIM_ICR3);
+	imr = (imr & ~0x00000fff) | 0x00000ddd;
+	writel(imr, MCF_MBAR + MCFSIM_ICR3);
+
+	imr = readl(MCF_MBAR + MCFSIM_ICR1);
+	imr = (imr & ~0x0f000000) | 0x0d000000;
+	writel(imr, MCF_MBAR + MCFSIM_ICR1);
+}
+
+/***************************************************************************/
+
 void mcf_disableall(void)
 {
 	volatile unsigned long	*icrp;
@@ -155,6 +202,7 @@ void __init config_BSP(char *commandp, int size)
 static int __init init_BSP(void)
 {
 	m5272_uarts_init();
+	m5272_fec_init();
 	platform_add_devices(m5272_devices, ARRAY_SIZE(m5272_devices));
 	return 0;
 }
diff --git a/arch/m68knommu/platform/527x/config.c b/arch/m68knommu/platform/527x/config.c
index 73cd1aef4a9..49343fb157b 100644
--- a/arch/m68knommu/platform/527x/config.c
+++ b/arch/m68knommu/platform/527x/config.c
@@ -50,8 +50,73 @@ static struct platform_device m527x_uart = {
 	.dev.platform_data	= m527x_uart_platform,
 };
 
+static struct resource m527x_fec0_resources[] = {
+	{
+		.start		= MCF_MBAR + 0x1000,
+		.end		= MCF_MBAR + 0x1000 + 0x7ff,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 64 + 23,
+		.end		= 64 + 23,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 27,
+		.end		= 64 + 27,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 29,
+		.end		= 64 + 29,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct resource m527x_fec1_resources[] = {
+	{
+		.start		= MCF_MBAR + 0x1800,
+		.end		= MCF_MBAR + 0x1800 + 0x7ff,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 128 + 23,
+		.end		= 128 + 23,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 128 + 27,
+		.end		= 128 + 27,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 128 + 29,
+		.end		= 128 + 29,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device m527x_fec[] = {
+	{
+		.name		= "fec",
+		.id		= 0,
+		.num_resources	= ARRAY_SIZE(m527x_fec0_resources),
+		.resource	= m527x_fec0_resources,
+	},
+	{
+		.name		= "fec",
+		.id		= 1,
+		.num_resources	= ARRAY_SIZE(m527x_fec1_resources),
+		.resource	= m527x_fec1_resources,
+	},
+};
+
 static struct platform_device *m527x_devices[] __initdata = {
 	&m527x_uart,
+	&m527x_fec[0],
+#ifdef CONFIG_FEC2
+	&m527x_fec[1],
+#endif
 };
 
 /***************************************************************************/
@@ -97,6 +162,51 @@ static void __init m527x_uarts_init(void)
 
 /***************************************************************************/
 
+static void __init m527x_fec_irq_init(int nr)
+{
+	unsigned long base;
+	u32 imr;
+
+	base = MCF_IPSBAR + (nr ? MCFICM_INTC1 : MCFICM_INTC0);
+
+	writeb(0x28, base + MCFINTC_ICR0 + 23);
+	writeb(0x27, base + MCFINTC_ICR0 + 27);
+	writeb(0x26, base + MCFINTC_ICR0 + 29);
+
+	imr = readl(base + MCFINTC_IMRH);
+	imr &= ~0xf;
+	writel(imr, base + MCFINTC_IMRH);
+	imr = readl(base + MCFINTC_IMRL);
+	imr &= ~0xff800001;
+	writel(imr, base + MCFINTC_IMRL);
+}
+
+static void __init m527x_fec_init(void)
+{
+	u16 par;
+	u8 v;
+
+	m527x_fec_irq_init(0);
+
+	/* Set multi-function pins to ethernet mode for fec0 */
+	par = readw(MCF_IPSBAR + 0x100082);
+	writew(par | 0xf00, MCF_IPSBAR + 0x100082);
+	v = readb(MCF_IPSBAR + 0x100078);
+	writeb(v | 0xc0, MCF_IPSBAR + 0x100078);
+
+#ifdef CONFIG_FEC2
+	m527x_fec_irq_init(1);
+
+	/* Set multi-function pins to ethernet mode for fec1 */
+	par = readw(MCF_IPSBAR + 0x100082);
+	writew(par | 0xa0, MCF_IPSBAR + 0x100082);
+	v = readb(MCF_IPSBAR + 0x100079);
+	writeb(v | 0xc0, MCF_IPSBAR + 0x100079);
+#endif
+}
+
+/***************************************************************************/
+
 void mcf_disableall(void)
 {
 	*((volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH)) = 0xffffffff;
@@ -116,13 +226,14 @@ void __init config_BSP(char *commandp, int size)
 {
 	mcf_disableall();
 	mach_reset = coldfire_reset;
+	m527x_uarts_init();
+	m527x_fec_init();
 }
 
 /***************************************************************************/
 
 static int __init init_BSP(void)
 {
-	m527x_uarts_init();
 	platform_add_devices(m527x_devices, ARRAY_SIZE(m527x_devices));
 	return 0;
 }
diff --git a/arch/m68knommu/platform/528x/config.c b/arch/m68knommu/platform/528x/config.c
index 44baeb225dc..bee526f4d1a 100644
--- a/arch/m68knommu/platform/528x/config.c
+++ b/arch/m68knommu/platform/528x/config.c
@@ -57,8 +57,40 @@ static struct platform_device m528x_uart = {
 	.dev.platform_data	= m528x_uart_platform,
 };
 
+static struct resource m528x_fec_resources[] = {
+	{
+		.start		= MCF_MBAR + 0x1000,
+		.end		= MCF_MBAR + 0x1000 + 0x7ff,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 64 + 23,
+		.end		= 64 + 23,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 27,
+		.end		= 64 + 27,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 29,
+		.end		= 64 + 29,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device m528x_fec = {
+	.name			= "fec",
+	.id			= 0,
+	.num_resources		= ARRAY_SIZE(m528x_fec_resources),
+	.resource		= m528x_fec_resources,
+};
+
+
 static struct platform_device *m528x_devices[] __initdata = {
 	&m528x_uart,
+	&m528x_fec,
 };
 
 /***************************************************************************/
@@ -99,6 +131,31 @@ static void __init m528x_uarts_init(void)
 
 /***************************************************************************/
 
+static void __init m528x_fec_init(void)
+{
+	u32 imr;
+	u16 v16;
+
+	/* Unmask FEC interrupts at ColdFire interrupt controller */
+	writeb(0x28, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 23);
+	writeb(0x27, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 27);
+	writeb(0x26, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_ICR0 + 29);
+
+	imr = readl(MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
+	imr &= ~0xf;
+	writel(imr, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH);
+	imr = readl(MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRL);
+	imr &= ~0xff800001;
+	writel(imr, MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRL);
+
+	/* Set multi-function pins to ethernet mode for fec0 */
+	v16 = readw(MCF_IPSBAR + 0x100056);
+	writew(v16 | 0xf00, MCF_IPSBAR + 0x100056);
+	writeb(0xc0, MCF_IPSBAR + 0x100058);
+}
+
+/***************************************************************************/
+
 void mcf_disableall(void)
 {
 	*((volatile unsigned long *) (MCF_IPSBAR + MCFICM_INTC0 + MCFINTC_IMRH)) = 0xffffffff;
@@ -158,6 +215,7 @@ void __init config_BSP(char *commandp, int size)
 static int __init init_BSP(void)
 {
 	m528x_uarts_init();
+	m528x_fec_init();
 	platform_add_devices(m528x_devices, ARRAY_SIZE(m528x_devices));
 	return 0;
 }
diff --git a/arch/m68knommu/platform/532x/config.c b/arch/m68knommu/platform/532x/config.c
index a347623d6ee..591f2f80113 100644
--- a/arch/m68knommu/platform/532x/config.c
+++ b/arch/m68knommu/platform/532x/config.c
@@ -61,8 +61,38 @@ static struct platform_device m532x_uart = {
 	.dev.platform_data	= m532x_uart_platform,
 };
 
+static struct resource m532x_fec_resources[] = {
+	{
+		.start		= 0xfc030000,
+		.end		= 0xfc0307ff,
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= 64 + 36,
+		.end		= 64 + 36,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 40,
+		.end		= 64 + 40,
+		.flags		= IORESOURCE_IRQ,
+	},
+	{
+		.start		= 64 + 42,
+		.end		= 64 + 42,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device m532x_fec = {
+	.name			= "fec",
+	.id			= 0,
+	.num_resources		= ARRAY_SIZE(m532x_fec_resources),
+	.resource		= m532x_fec_resources,
+};
 static struct platform_device *m532x_devices[] __initdata = {
 	&m532x_uart,
+	&m532x_fec,
 };
 
 /***************************************************************************/
@@ -93,6 +123,24 @@ static void __init m532x_uarts_init(void)
 	for (line = 0; (line < nrlines); line++)
 		m532x_uart_init_line(line, m532x_uart_platform[line].irq);
 }
+/***************************************************************************/
+
+static void __init m532x_fec_init(void)
+{
+	/* Unmask FEC interrupts at ColdFire interrupt controller */
+	MCF_INTC0_ICR36 = 0x2;
+	MCF_INTC0_ICR40 = 0x2;
+	MCF_INTC0_ICR42 = 0x2;
+
+	MCF_INTC0_IMRH &= ~(MCF_INTC_IMRH_INT_MASK36 |
+		MCF_INTC_IMRH_INT_MASK40 | MCF_INTC_IMRH_INT_MASK42);
+
+	/* Set multi-function pins to ethernet mode for fec0 */
+	MCF_GPIO_PAR_FECI2C |= (MCF_GPIO_PAR_FECI2C_PAR_MDC_EMDC |
+		MCF_GPIO_PAR_FECI2C_PAR_MDIO_EMDIO);
+	MCF_GPIO_PAR_FEC = (MCF_GPIO_PAR_FEC_PAR_FEC_7W_FEC |
+		MCF_GPIO_PAR_FEC_PAR_FEC_MII_FEC);
+}
 
 /***************************************************************************/
 
@@ -150,6 +198,7 @@ void __init config_BSP(char *commandp, int size)
 static int __init init_BSP(void)
 {
 	m532x_uarts_init();
+	m532x_fec_init();
 	platform_add_devices(m532x_devices, ARRAY_SIZE(m532x_devices));
 	return 0;
 }
diff --git a/arch/mips/include/asm/sigcontext.h b/arch/mips/include/asm/sigcontext.h
index 9ce0607d7a4..9e89cf99d4e 100644
--- a/arch/mips/include/asm/sigcontext.h
+++ b/arch/mips/include/asm/sigcontext.h
@@ -9,6 +9,7 @@
 #ifndef _ASM_SIGCONTEXT_H
 #define _ASM_SIGCONTEXT_H
 
+#include <linux/types.h>
 #include <asm/sgidefs.h>
 
 #if _MIPS_SIM == _MIPS_SIM_ABI32
diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h
index facc2d7a87c..2abca178016 100644
--- a/arch/mips/include/asm/socket.h
+++ b/arch/mips/include/asm/socket.h
@@ -75,6 +75,9 @@ To add: #define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #ifdef __KERNEL__
 
 /** sock_type - Socket types
diff --git a/arch/mips/include/asm/swab.h b/arch/mips/include/asm/swab.h
index 88f1f7d555c..99993c0d6c1 100644
--- a/arch/mips/include/asm/swab.h
+++ b/arch/mips/include/asm/swab.h
@@ -9,7 +9,7 @@
 #define _ASM_SWAB_H
 
 #include <linux/compiler.h>
-#include <asm/types.h>
+#include <linux/types.h>
 
 #define __SWAB_64_THRU_32__
 
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 4b4007b3083..7b845ba9dff 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -108,7 +108,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 49aac6e17df..2a472713de8 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -355,40 +355,6 @@ SYSCALL_DEFINE1(32_personality, unsigned long, personality)
 	return ret;
 }
 
-/* ustat compatibility */
-struct ustat32 {
-	compat_daddr_t	f_tfree;
-	compat_ino_t	f_tinode;
-	char		f_fname[6];
-	char		f_fpack[6];
-};
-
-extern asmlinkage long sys_ustat(dev_t dev, struct ustat __user * ubuf);
-
-SYSCALL_DEFINE2(32_ustat, dev_t, dev, struct ustat32 __user *, ubuf32)
-{
-	int err;
-	struct ustat tmp;
-	struct ustat32 tmp32;
-	mm_segment_t old_fs = get_fs();
-
-	set_fs(KERNEL_DS);
-	err = sys_ustat(dev, (struct ustat __user *)&tmp);
-	set_fs(old_fs);
-
-	if (err)
-		goto out;
-
-	memset(&tmp32, 0, sizeof(struct ustat32));
-	tmp32.f_tfree = tmp.f_tfree;
-	tmp32.f_tinode = tmp.f_tinode;
-
-	err = copy_to_user(ubuf32, &tmp32, sizeof(struct ustat32)) ? -EFAULT : 0;
-
-out:
-	return err;
-}
-
 SYSCALL_DEFINE4(32_sendfile, long, out_fd, long, in_fd,
 	compat_off_t __user *, offset, s32, count)
 {
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 7438e92f8a0..f61d6b0e573 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -253,7 +253,7 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_utime		/* 6130 */
 	PTR	sys_mknod
 	PTR	sys_32_personality
-	PTR	sys_32_ustat
+	PTR	compat_sys_ustat
 	PTR	compat_sys_statfs
 	PTR	compat_sys_fstatfs		/* 6135 */
 	PTR	sys_sysfs
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index b0fef4ff982..60997f1f69d 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -265,7 +265,7 @@ sys_call_table:
 	PTR	sys_olduname
 	PTR	sys_umask			/* 4060 */
 	PTR	sys_chroot
-	PTR	sys_32_ustat
+	PTR	compat_sys_ustat
 	PTR	sys_dup2
 	PTR	sys_getppid
 	PTR	sys_getpgrp			/* 4065 */
diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c
index 56c64ccc9c2..50fdb5c16e0 100644
--- a/arch/mn10300/kernel/irq.c
+++ b/arch/mn10300/kernel/irq.c
@@ -221,7 +221,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (action) {
 			seq_printf(p, "%3d: ", i);
 			for_each_present_cpu(cpu)
-				seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+				seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 			seq_printf(p, " %14s.%u", irq_desc[i].chip->name,
 				   (GxICR(i) & GxICR_LEVEL) >>
 				   GxICR_LEVEL_SHIFT);
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
index c584b00c607..430f1aeea0b 100644
--- a/arch/parisc/include/asm/pdc.h
+++ b/arch/parisc/include/asm/pdc.h
@@ -336,10 +336,11 @@
 #define NUM_PDC_RESULT	32
 
 #if !defined(__ASSEMBLY__)
-#ifdef __KERNEL__
 
 #include <linux/types.h>
 
+#ifdef __KERNEL__
+
 extern int pdc_type;
 
 /* Values for pdc_type */
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
index fba402c95ac..885472bf7b7 100644
--- a/arch/parisc/include/asm/socket.h
+++ b/arch/parisc/include/asm/socket.h
@@ -54,6 +54,9 @@
 
 #define SO_MARK			0x401f
 
+#define SO_TIMESTAMPING		0x4020
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
diff --git a/arch/parisc/include/asm/swab.h b/arch/parisc/include/asm/swab.h
index 3ff16c5a335..e78403b129e 100644
--- a/arch/parisc/include/asm/swab.h
+++ b/arch/parisc/include/asm/swab.h
@@ -1,7 +1,7 @@
 #ifndef _PARISC_SWAB_H
 #define _PARISC_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #define __SWAB_64_THRU_32__
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 29e70e16ede..adfd617b4c1 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -185,7 +185,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%3d: ", i);
 #ifdef CONFIG_SMP
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #else
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #endif
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 303d2b647e4..03b9a01bc16 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -130,7 +130,7 @@
 	ENTRY_OURS(newuname)
 	ENTRY_SAME(umask)		/* 60 */
 	ENTRY_SAME(chroot)
-	ENTRY_SAME(ustat)
+	ENTRY_COMP(ustat)
 	ENTRY_SAME(dup2)
 	ENTRY_SAME(getppid)
 	ENTRY_SAME(getpgrp)		/* 65 */
diff --git a/arch/powerpc/include/asm/bootx.h b/arch/powerpc/include/asm/bootx.h
index 57b82e3f89c..60a3c9ef301 100644
--- a/arch/powerpc/include/asm/bootx.h
+++ b/arch/powerpc/include/asm/bootx.h
@@ -9,7 +9,7 @@
 #ifndef __ASM_BOOTX_H__
 #define __ASM_BOOTX_H__
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 #ifdef macintosh
 #include <Types.h>
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index cd46f023ec6..b5600ce6055 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -7,7 +7,7 @@
 #include <asm/string.h>
 #endif
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <asm/ptrace.h>
 #include <asm/cputable.h>
 #include <asm/auxvec.h>
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f993e4198d5..bb2de6aa5ce 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -20,7 +20,7 @@
 #ifndef __LINUX_KVM_POWERPC_H
 #define __LINUX_KVM_POWERPC_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 struct kvm_regs {
 	__u64 pc;
@@ -52,4 +52,11 @@ struct kvm_fpu {
 	__u64 fpr[32];
 };
 
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_44x.h b/arch/powerpc/include/asm/kvm_44x.h
index f49031b632c..d22d39942a9 100644
--- a/arch/powerpc/include/asm/kvm_44x.h
+++ b/arch/powerpc/include/asm/kvm_44x.h
@@ -28,6 +28,13 @@
  * need to find some way of advertising it. */
 #define KVM44x_GUEST_TLB_SIZE 64
 
+struct kvmppc_44x_tlbe {
+	u32 tid; /* Only the low 8 bits are used. */
+	u32 word0;
+	u32 word1;
+	u32 word2;
+};
+
 struct kvmppc_44x_shadow_ref {
 	struct page *page;
 	u16 gtlb_index;
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 2197764796d..56bfae59837 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -42,7 +42,12 @@
 #define BOOKE_INTERRUPT_DTLB_MISS 13
 #define BOOKE_INTERRUPT_ITLB_MISS 14
 #define BOOKE_INTERRUPT_DEBUG 15
-#define BOOKE_MAX_INTERRUPT 15
+
+/* E500 */
+#define BOOKE_INTERRUPT_SPE_UNAVAIL 32
+#define BOOKE_INTERRUPT_SPE_FP_DATA 33
+#define BOOKE_INTERRUPT_SPE_FP_ROUND 34
+#define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
new file mode 100644
index 00000000000..9d497ce4972
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/include/asm/kvm_44x.h,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * 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.
+ */
+
+#ifndef __ASM_KVM_E500_H__
+#define __ASM_KVM_E500_H__
+
+#include <linux/kvm_host.h>
+
+#define BOOKE_INTERRUPT_SIZE 36
+
+#define E500_PID_NUM   3
+#define E500_TLB_NUM   2
+
+struct tlbe{
+	u32 mas1;
+	u32 mas2;
+	u32 mas3;
+	u32 mas7;
+};
+
+struct kvmppc_vcpu_e500 {
+	/* Unmodified copy of the guest's TLB. */
+	struct tlbe *guest_tlb[E500_TLB_NUM];
+	/* TLB that's actually used when the guest is running. */
+	struct tlbe *shadow_tlb[E500_TLB_NUM];
+	/* Pages which are referenced in the shadow TLB. */
+	struct page **shadow_pages[E500_TLB_NUM];
+
+	unsigned int guest_tlb_size[E500_TLB_NUM];
+	unsigned int shadow_tlb_size[E500_TLB_NUM];
+	unsigned int guest_tlb_nv[E500_TLB_NUM];
+
+	u32 host_pid[E500_PID_NUM];
+	u32 pid[E500_PID_NUM];
+
+	u32 mas0;
+	u32 mas1;
+	u32 mas2;
+	u32 mas3;
+	u32 mas4;
+	u32 mas5;
+	u32 mas6;
+	u32 mas7;
+	u32 l1csr1;
+	u32 hid0;
+	u32 hid1;
+
+	struct kvm_vcpu vcpu;
+};
+
+static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
+{
+	return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
+}
+
+#endif /* __ASM_KVM_E500_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c1e436fe773..dfdf13c9fef 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -64,13 +64,6 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvmppc_44x_tlbe {
-	u32 tid; /* Only the low 8 bits are used. */
-	u32 word0;
-	u32 word1;
-	u32 word2;
-};
-
 enum kvm_exit_types {
 	MMIO_EXITS,
 	DCR_EXITS,
@@ -118,11 +111,6 @@ struct kvm_arch {
 struct kvm_vcpu_arch {
 	u32 host_stack;
 	u32 host_pid;
-	u32 host_dbcr0;
-	u32 host_dbcr1;
-	u32 host_dbcr2;
-	u32 host_iac[4];
-	u32 host_msr;
 
 	u64 fpr[32];
 	ulong gpr[32];
@@ -157,7 +145,7 @@ struct kvm_vcpu_arch {
 	u32 tbu;
 	u32 tcr;
 	u32 tsr;
-	u32 ivor[16];
+	u32 ivor[64];
 	ulong ivpr;
 	u32 pir;
 
@@ -170,6 +158,7 @@ struct kvm_vcpu_arch {
 	u32 ccr1;
 	u32 dbcr0;
 	u32 dbcr1;
+	u32 dbsr;
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	struct kvmppc_exit_timing timing_exit;
@@ -200,10 +189,4 @@ struct kvm_vcpu_arch {
 	unsigned long pending_exceptions;
 };
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
-
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 36d2a50a848..2c6ee349df5 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -52,13 +52,19 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run,
 extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 
+/* Core-specific hooks */
+
 extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
-                           u64 asid, u32 flags, u32 max_bytes,
                            unsigned int gtlb_idx);
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
-
-/* Core-specific hooks */
+extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu);
+extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
+extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
+extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
+                              gva_t eaddr);
+extern void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu);
 
 extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
                                                 unsigned int id);
@@ -71,9 +77,6 @@ extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 extern void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
-extern void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu);
-extern void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu);
-
 extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h
index 3f941c0f7e8..4285b64a65e 100644
--- a/arch/powerpc/include/asm/mmu-fsl-booke.h
+++ b/arch/powerpc/include/asm/mmu-fsl-booke.h
@@ -75,6 +75,8 @@
 
 #ifndef __ASSEMBLY__
 
+extern unsigned int tlbcam_index;
+
 typedef struct {
 	unsigned int	id;
 	unsigned int	active;
diff --git a/arch/powerpc/include/asm/ps3fb.h b/arch/powerpc/include/asm/ps3fb.h
index 3f121fe4010..e7233a84968 100644
--- a/arch/powerpc/include/asm/ps3fb.h
+++ b/arch/powerpc/include/asm/ps3fb.h
@@ -19,6 +19,7 @@
 #ifndef _ASM_POWERPC_PS3FB_H_
 #define _ASM_POWERPC_PS3FB_H_
 
+#include <linux/types.h>
 #include <linux/ioctl.h>
 
 /* ioctl */
diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h
index f5a4e168e49..1e5cfad0e3f 100644
--- a/arch/powerpc/include/asm/socket.h
+++ b/arch/powerpc/include/asm/socket.h
@@ -61,4 +61,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/include/asm/spu_info.h b/arch/powerpc/include/asm/spu_info.h
index 3545efbf989..1286c823f0d 100644
--- a/arch/powerpc/include/asm/spu_info.h
+++ b/arch/powerpc/include/asm/spu_info.h
@@ -23,9 +23,10 @@
 #ifndef _SPU_INFO_H
 #define _SPU_INFO_H
 
+#include <linux/types.h>
+
 #ifdef __KERNEL__
 #include <asm/spu.h>
-#include <linux/types.h>
 #else
 struct mfc_cq_sr {
 	__u64 mfc_cq_data0_RW;
diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h
index ef824ae4b79..c581e3ef73e 100644
--- a/arch/powerpc/include/asm/swab.h
+++ b/arch/powerpc/include/asm/swab.h
@@ -8,7 +8,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #ifdef __GNUC__
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 72353f6070a..fe166491e9d 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -65,7 +65,7 @@ SYSCALL(ni_syscall)
 SYSX(sys_ni_syscall,sys_olduname, sys_olduname)
 COMPAT_SYS_SPU(umask)
 SYSCALL_SPU(chroot)
-SYSCALL(ustat)
+COMPAT_SYS(ustat)
 SYSCALL_SPU(dup2)
 SYSCALL_SPU(getppid)
 SYSCALL_SPU(getpgrp)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 19ee491e9e2..42fe4da4e8a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -49,7 +49,7 @@
 #include <asm/iseries/alpaca.h>
 #endif
 #ifdef CONFIG_KVM
-#include <asm/kvm_44x.h>
+#include <linux/kvm_host.h>
 #endif
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
@@ -361,8 +361,6 @@ int main(void)
 	DEFINE(PTE_SIZE, sizeof(pte_t));
 
 #ifdef CONFIG_KVM
-	DEFINE(TLBE_BYTES, sizeof(struct kvmppc_44x_tlbe));
-
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 23b8b5e36f9..17efb7118db 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -190,7 +190,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%3d: ", i);
 #ifdef CONFIG_SMP
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #else
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #endif /* CONFIG_SMP */
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index a66bec57265..0cef809cec2 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -28,72 +28,6 @@
 
 #include "44x_tlb.h"
 
-/* Note: clearing MSR[DE] just means that the debug interrupt will not be
- * delivered *immediately*. Instead, it simply sets the appropriate DBSR bits.
- * If those DBSR bits are still set when MSR[DE] is re-enabled, the interrupt
- * will be delivered as an "imprecise debug event" (which is indicated by
- * DBSR[IDE].
- */
-static void kvm44x_disable_debug_interrupts(void)
-{
-	mtmsr(mfmsr() & ~MSR_DE);
-}
-
-void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
-{
-	kvm44x_disable_debug_interrupts();
-
-	mtspr(SPRN_IAC1, vcpu->arch.host_iac[0]);
-	mtspr(SPRN_IAC2, vcpu->arch.host_iac[1]);
-	mtspr(SPRN_IAC3, vcpu->arch.host_iac[2]);
-	mtspr(SPRN_IAC4, vcpu->arch.host_iac[3]);
-	mtspr(SPRN_DBCR1, vcpu->arch.host_dbcr1);
-	mtspr(SPRN_DBCR2, vcpu->arch.host_dbcr2);
-	mtspr(SPRN_DBCR0, vcpu->arch.host_dbcr0);
-	mtmsr(vcpu->arch.host_msr);
-}
-
-void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
-{
-	struct kvm_guest_debug *dbg = &vcpu->guest_debug;
-	u32 dbcr0 = 0;
-
-	vcpu->arch.host_msr = mfmsr();
-	kvm44x_disable_debug_interrupts();
-
-	/* Save host debug register state. */
-	vcpu->arch.host_iac[0] = mfspr(SPRN_IAC1);
-	vcpu->arch.host_iac[1] = mfspr(SPRN_IAC2);
-	vcpu->arch.host_iac[2] = mfspr(SPRN_IAC3);
-	vcpu->arch.host_iac[3] = mfspr(SPRN_IAC4);
-	vcpu->arch.host_dbcr0 = mfspr(SPRN_DBCR0);
-	vcpu->arch.host_dbcr1 = mfspr(SPRN_DBCR1);
-	vcpu->arch.host_dbcr2 = mfspr(SPRN_DBCR2);
-
-	/* set registers up for guest */
-
-	if (dbg->bp[0]) {
-		mtspr(SPRN_IAC1, dbg->bp[0]);
-		dbcr0 |= DBCR0_IAC1 | DBCR0_IDM;
-	}
-	if (dbg->bp[1]) {
-		mtspr(SPRN_IAC2, dbg->bp[1]);
-		dbcr0 |= DBCR0_IAC2 | DBCR0_IDM;
-	}
-	if (dbg->bp[2]) {
-		mtspr(SPRN_IAC3, dbg->bp[2]);
-		dbcr0 |= DBCR0_IAC3 | DBCR0_IDM;
-	}
-	if (dbg->bp[3]) {
-		mtspr(SPRN_IAC4, dbg->bp[3]);
-		dbcr0 |= DBCR0_IAC4 | DBCR0_IDM;
-	}
-
-	mtspr(SPRN_DBCR0, dbcr0);
-	mtspr(SPRN_DBCR1, 0);
-	mtspr(SPRN_DBCR2, 0);
-}
-
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvmppc_44x_tlb_load(vcpu);
@@ -149,8 +83,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
                                struct kvm_translation *tr)
 {
-	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
-	struct kvmppc_44x_tlbe *gtlbe;
 	int index;
 	gva_t eaddr;
 	u8 pid;
@@ -166,9 +98,7 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 		return 0;
 	}
 
-	gtlbe = &vcpu_44x->guest_tlb[index];
-
-	tr->physical_address = tlb_xlate(gtlbe, eaddr);
+	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
 	/* XXX what does "writeable" and "usermode" even mean? */
 	tr->valid = 1;
 
diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index 82489a743a6..61af58fcece 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -27,25 +27,12 @@
 #include "booke.h"
 #include "44x_tlb.h"
 
-#define OP_RFI      19
-
-#define XOP_RFI     50
-#define XOP_MFMSR   83
-#define XOP_WRTEE   131
-#define XOP_MTMSR   146
-#define XOP_WRTEEI  163
 #define XOP_MFDCR   323
 #define XOP_MTDCR   451
 #define XOP_TLBSX   914
 #define XOP_ICCCI   966
 #define XOP_TLBWE   978
 
-static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.pc = vcpu->arch.srr0;
-	kvmppc_set_msr(vcpu, vcpu->arch.srr1);
-}
-
 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
@@ -59,48 +46,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	int ws;
 
 	switch (get_op(inst)) {
-	case OP_RFI:
-		switch (get_xop(inst)) {
-		case XOP_RFI:
-			kvmppc_emul_rfi(vcpu);
-			kvmppc_set_exit_type(vcpu, EMULATED_RFI_EXITS);
-			*advance = 0;
-			break;
-
-		default:
-			emulated = EMULATE_FAIL;
-			break;
-		}
-		break;
-
 	case 31:
 		switch (get_xop(inst)) {
 
-		case XOP_MFMSR:
-			rt = get_rt(inst);
-			vcpu->arch.gpr[rt] = vcpu->arch.msr;
-			kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
-			break;
-
-		case XOP_MTMSR:
-			rs = get_rs(inst);
-			kvmppc_set_exit_type(vcpu, EMULATED_MTMSR_EXITS);
-			kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]);
-			break;
-
-		case XOP_WRTEE:
-			rs = get_rs(inst);
-			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
-							 | (vcpu->arch.gpr[rs] & MSR_EE);
-			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
-			break;
-
-		case XOP_WRTEEI:
-			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
-							 | (inst & MSR_EE);
-			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
-			break;
-
 		case XOP_MFDCR:
 			dcrn = get_dcrn(inst);
 			rt = get_rt(inst);
@@ -186,186 +134,51 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		emulated = EMULATE_FAIL;
 	}
 
+	if (emulated == EMULATE_FAIL)
+		emulated = kvmppc_booke_emulate_op(run, vcpu, inst, advance);
+
 	return emulated;
 }
 
 int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
+	int emulated = EMULATE_DONE;
+
 	switch (sprn) {
-	case SPRN_MMUCR:
-		vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break;
 	case SPRN_PID:
 		kvmppc_set_pid(vcpu, vcpu->arch.gpr[rs]); break;
+	case SPRN_MMUCR:
+		vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break;
 	case SPRN_CCR0:
 		vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break;
 	case SPRN_CCR1:
 		vcpu->arch.ccr1 = vcpu->arch.gpr[rs]; break;
-	case SPRN_DEAR:
-		vcpu->arch.dear = vcpu->arch.gpr[rs]; break;
-	case SPRN_ESR:
-		vcpu->arch.esr = vcpu->arch.gpr[rs]; break;
-	case SPRN_DBCR0:
-		vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
-	case SPRN_DBCR1:
-		vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
-	case SPRN_TSR:
-		vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
-	case SPRN_TCR:
-		vcpu->arch.tcr = vcpu->arch.gpr[rs];
-		kvmppc_emulate_dec(vcpu);
-		break;
-
-	/* Note: SPRG4-7 are user-readable. These values are
-	 * loaded into the real SPRGs when resuming the
-	 * guest. */
-	case SPRN_SPRG4:
-		vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break;
-	case SPRN_SPRG5:
-		vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break;
-	case SPRN_SPRG6:
-		vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break;
-	case SPRN_SPRG7:
-		vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break;
-
-	case SPRN_IVPR:
-		vcpu->arch.ivpr = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR0:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR1:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR2:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR3:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR4:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR5:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR6:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR7:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR8:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR9:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR10:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR11:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR12:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR13:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR14:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = vcpu->arch.gpr[rs];
-		break;
-	case SPRN_IVOR15:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = vcpu->arch.gpr[rs];
-		break;
-
 	default:
-		return EMULATE_FAIL;
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
 	}
 
 	kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);
-	return EMULATE_DONE;
+	return emulated;
 }
 
 int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 {
+	int emulated = EMULATE_DONE;
+
 	switch (sprn) {
-	/* 440 */
+	case SPRN_PID:
+		vcpu->arch.gpr[rt] = vcpu->arch.pid; break;
 	case SPRN_MMUCR:
 		vcpu->arch.gpr[rt] = vcpu->arch.mmucr; break;
 	case SPRN_CCR0:
 		vcpu->arch.gpr[rt] = vcpu->arch.ccr0; break;
 	case SPRN_CCR1:
 		vcpu->arch.gpr[rt] = vcpu->arch.ccr1; break;
-
-	/* Book E */
-	case SPRN_PID:
-		vcpu->arch.gpr[rt] = vcpu->arch.pid; break;
-	case SPRN_IVPR:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break;
-	case SPRN_DEAR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dear; break;
-	case SPRN_ESR:
-		vcpu->arch.gpr[rt] = vcpu->arch.esr; break;
-	case SPRN_DBCR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
-	case SPRN_DBCR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
-
-	case SPRN_IVOR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
-		break;
-	case SPRN_IVOR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
-		break;
-	case SPRN_IVOR2:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
-		break;
-	case SPRN_IVOR3:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
-		break;
-	case SPRN_IVOR4:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
-		break;
-	case SPRN_IVOR5:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
-		break;
-	case SPRN_IVOR6:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
-		break;
-	case SPRN_IVOR7:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
-		break;
-	case SPRN_IVOR8:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
-		break;
-	case SPRN_IVOR9:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
-		break;
-	case SPRN_IVOR10:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
-		break;
-	case SPRN_IVOR11:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
-		break;
-	case SPRN_IVOR12:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
-		break;
-	case SPRN_IVOR13:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
-		break;
-	case SPRN_IVOR14:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
-		break;
-	case SPRN_IVOR15:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
-		break;
-
 	default:
-		return EMULATE_FAIL;
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
 	}
 
 	kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
-	return EMULATE_DONE;
+	return emulated;
 }
 
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 9a34b8edb9e..4a16f472cc1 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -208,20 +208,38 @@ int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned int pid,
 	return -1;
 }
 
-int kvmppc_44x_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
+                       gva_t eaddr)
+{
+	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
+	struct kvmppc_44x_tlbe *gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
+	unsigned int pgmask = get_tlb_bytes(gtlbe) - 1;
+
+	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
+}
+
+int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
 
 	return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
 }
 
-int kvmppc_44x_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
 
 	return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
 }
 
+void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
+{
+}
+
 static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
                                       unsigned int stlb_index)
 {
@@ -248,7 +266,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 	KVMTRACE_1D(STLB_INVAL, &vcpu_44x->vcpu, stlb_index, handler);
 }
 
-void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu)
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	int i;
@@ -269,15 +287,19 @@ void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu)
  * Caller must ensure that the specified guest TLB entry is safe to insert into
  * the shadow TLB.
  */
-void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr, u64 asid,
-                    u32 flags, u32 max_bytes, unsigned int gtlb_index)
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
+                    unsigned int gtlb_index)
 {
 	struct kvmppc_44x_tlbe stlbe;
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
+	struct kvmppc_44x_tlbe *gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
 	struct kvmppc_44x_shadow_ref *ref;
 	struct page *new_page;
 	hpa_t hpaddr;
 	gfn_t gfn;
+	u32 asid = gtlbe->tid;
+	u32 flags = gtlbe->word2;
+	u32 max_bytes = get_tlb_bytes(gtlbe);
 	unsigned int victim;
 
 	/* Select TLB entry to clobber. Indirectly guard against races with the TLB
@@ -448,10 +470,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	}
 
 	if (tlbe_is_host_safe(vcpu, tlbe)) {
-		u64 asid;
 		gva_t eaddr;
 		gpa_t gpaddr;
-		u32 flags;
 		u32 bytes;
 
 		eaddr = get_tlb_eaddr(tlbe);
@@ -462,10 +482,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		eaddr &= ~(bytes - 1);
 		gpaddr &= ~(bytes - 1);
 
-		asid = (tlbe->word0 & PPC44x_TLB_TS) | tlbe->tid;
-		flags = tlbe->word2 & 0xffff;
-
-		kvmppc_mmu_map(vcpu, eaddr, gpaddr, asid, flags, bytes, gtlb_index);
+		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
 	KVMTRACE_5D(GTLB_WRITE, vcpu, gtlb_index, tlbe->tid, tlbe->word0,
diff --git a/arch/powerpc/kvm/44x_tlb.h b/arch/powerpc/kvm/44x_tlb.h
index 772191f29e6..a9ff80e5152 100644
--- a/arch/powerpc/kvm/44x_tlb.h
+++ b/arch/powerpc/kvm/44x_tlb.h
@@ -25,8 +25,6 @@
 
 extern int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr,
                                 unsigned int pid, unsigned int as);
-extern int kvmppc_44x_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
-extern int kvmppc_44x_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 
 extern int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb,
                                  u8 rc);
@@ -85,11 +83,4 @@ static inline unsigned int get_mmucr_sts(const struct kvm_vcpu *vcpu)
 	return (vcpu->arch.mmucr >> 16) & 0x1;
 }
 
-static inline gpa_t tlb_xlate(struct kvmppc_44x_tlbe *tlbe, gva_t eaddr)
-{
-	unsigned int pgmask = get_tlb_bytes(tlbe) - 1;
-
-	return get_tlb_raddr(tlbe) | (eaddr & pgmask);
-}
-
 #endif /* __KVM_POWERPC_TLB_H__ */
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 6dbdc4817d8..5a152a52796 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -2,6 +2,9 @@
 # KVM configuration
 #
 
+config HAVE_KVM_IRQCHIP
+       bool
+
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
 	---help---
@@ -43,6 +46,19 @@ config KVM_EXIT_TIMING
 
 	  If unsure, say N.
 
+config KVM_E500
+	bool "KVM support for PowerPC E500 processors"
+	depends on EXPERIMENTAL && E500
+	select KVM
+	---help---
+	  Support running unmodified E500 guest kernels in virtual machines on
+	  E500 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
 config KVM_TRACE
 	bool "KVM trace support"
 	depends on KVM && MARKERS && SYSFS
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index df7ba59e6d5..4b2df66c79d 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -16,8 +16,18 @@ AFLAGS_booke_interrupts.o := -I$(obj)
 
 kvm-440-objs := \
 	booke.o \
+	booke_emulate.o \
 	booke_interrupts.o \
 	44x.o \
 	44x_tlb.o \
 	44x_emulate.o
 obj-$(CONFIG_KVM_440) += kvm-440.o
+
+kvm-e500-objs := \
+	booke.o \
+	booke_emulate.o \
+	booke_interrupts.o \
+	e500.o \
+	e500_tlb.o \
+	e500_emulate.o
+obj-$(CONFIG_KVM_E500) += kvm-e500.o
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 35485dd6927..642e4204cf2 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -30,10 +30,8 @@
 #include <asm/kvm_ppc.h>
 #include "timing.h"
 #include <asm/cacheflush.h>
-#include <asm/kvm_44x.h>
 
 #include "booke.h"
-#include "44x_tlb.h"
 
 unsigned long kvmppc_booke_handlers;
 
@@ -120,6 +118,9 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_DATA_STORAGE:
 	case BOOKE_IRQPRIO_INST_STORAGE:
 	case BOOKE_IRQPRIO_FP_UNAVAIL:
+	case BOOKE_IRQPRIO_SPE_UNAVAIL:
+	case BOOKE_IRQPRIO_SPE_FP_DATA:
+	case BOOKE_IRQPRIO_SPE_FP_ROUND:
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
 	case BOOKE_IRQPRIO_ALIGNMENT:
 		allowed = 1;
@@ -165,7 +166,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 	unsigned int priority;
 
 	priority = __ffs(*pending);
-	while (priority <= BOOKE_MAX_INTERRUPT) {
+	while (priority <= BOOKE_IRQPRIO_MAX) {
 		if (kvmppc_booke_irqprio_deliver(vcpu, priority))
 			break;
 
@@ -263,6 +264,21 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_SPE_UNAVAIL:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_UNAVAIL);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_SPE_FP_DATA:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_DATA);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_SPE_FP_ROUND:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_ROUND);
+		r = RESUME_GUEST;
+		break;
+
 	case BOOKE_INTERRUPT_DATA_STORAGE:
 		vcpu->arch.dear = vcpu->arch.fault_dear;
 		vcpu->arch.esr = vcpu->arch.fault_esr;
@@ -284,29 +300,27 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
-	/* XXX move to a 440-specific file. */
 	case BOOKE_INTERRUPT_DTLB_MISS: {
-		struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
-		struct kvmppc_44x_tlbe *gtlbe;
 		unsigned long eaddr = vcpu->arch.fault_dear;
 		int gtlb_index;
+		gpa_t gpaddr;
 		gfn_t gfn;
 
 		/* Check the guest TLB. */
-		gtlb_index = kvmppc_44x_dtlb_index(vcpu, eaddr);
+		gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr);
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
 			vcpu->arch.dear = vcpu->arch.fault_dear;
 			vcpu->arch.esr = vcpu->arch.fault_esr;
+			kvmppc_mmu_dtlb_miss(vcpu);
 			kvmppc_account_exit(vcpu, DTLB_REAL_MISS_EXITS);
 			r = RESUME_GUEST;
 			break;
 		}
 
-		gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
-		vcpu->arch.paddr_accessed = tlb_xlate(gtlbe, eaddr);
-		gfn = vcpu->arch.paddr_accessed >> PAGE_SHIFT;
+		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
+		gfn = gpaddr >> PAGE_SHIFT;
 
 		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
 			/* The guest TLB had a mapping, but the shadow TLB
@@ -315,13 +329,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * b) the guest used a large mapping which we're faking
 			 * Either way, we need to satisfy the fault without
 			 * invoking the guest. */
-			kvmppc_mmu_map(vcpu, eaddr, vcpu->arch.paddr_accessed, gtlbe->tid,
-			               gtlbe->word2, get_tlb_bytes(gtlbe), gtlb_index);
+			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 			kvmppc_account_exit(vcpu, DTLB_VIRT_MISS_EXITS);
 			r = RESUME_GUEST;
 		} else {
 			/* Guest has mapped and accessed a page which is not
 			 * actually RAM. */
+			vcpu->arch.paddr_accessed = gpaddr;
 			r = kvmppc_emulate_mmio(run, vcpu);
 			kvmppc_account_exit(vcpu, MMIO_EXITS);
 		}
@@ -329,10 +343,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	/* XXX move to a 440-specific file. */
 	case BOOKE_INTERRUPT_ITLB_MISS: {
-		struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
-		struct kvmppc_44x_tlbe *gtlbe;
 		unsigned long eaddr = vcpu->arch.pc;
 		gpa_t gpaddr;
 		gfn_t gfn;
@@ -341,18 +352,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 
 		/* Check the guest TLB. */
-		gtlb_index = kvmppc_44x_itlb_index(vcpu, eaddr);
+		gtlb_index = kvmppc_mmu_itlb_index(vcpu, eaddr);
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ITLB_MISS);
+			kvmppc_mmu_itlb_miss(vcpu);
 			kvmppc_account_exit(vcpu, ITLB_REAL_MISS_EXITS);
 			break;
 		}
 
 		kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
 
-		gtlbe = &vcpu_44x->guest_tlb[gtlb_index];
-		gpaddr = tlb_xlate(gtlbe, eaddr);
+		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
 		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
@@ -362,8 +373,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * b) the guest used a large mapping which we're faking
 			 * Either way, we need to satisfy the fault without
 			 * invoking the guest. */
-			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlbe->tid,
-			               gtlbe->word2, get_tlb_bytes(gtlbe), gtlb_index);
+			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 		} else {
 			/* Guest mapped and leaped at non-RAM! */
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_MACHINE_CHECK);
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index cf7c94ca24b..d59bcca1f9d 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -22,6 +22,7 @@
 
 #include <linux/types.h>
 #include <linux/kvm_host.h>
+#include <asm/kvm_ppc.h>
 #include "timing.h"
 
 /* interrupt priortity ordering */
@@ -30,17 +31,24 @@
 #define BOOKE_IRQPRIO_ALIGNMENT 2
 #define BOOKE_IRQPRIO_PROGRAM 3
 #define BOOKE_IRQPRIO_FP_UNAVAIL 4
-#define BOOKE_IRQPRIO_SYSCALL 5
-#define BOOKE_IRQPRIO_AP_UNAVAIL 6
-#define BOOKE_IRQPRIO_DTLB_MISS 7
-#define BOOKE_IRQPRIO_ITLB_MISS 8
-#define BOOKE_IRQPRIO_MACHINE_CHECK 9
-#define BOOKE_IRQPRIO_DEBUG 10
-#define BOOKE_IRQPRIO_CRITICAL 11
-#define BOOKE_IRQPRIO_WATCHDOG 12
-#define BOOKE_IRQPRIO_EXTERNAL 13
-#define BOOKE_IRQPRIO_FIT 14
-#define BOOKE_IRQPRIO_DECREMENTER 15
+#define BOOKE_IRQPRIO_SPE_UNAVAIL 5
+#define BOOKE_IRQPRIO_SPE_FP_DATA 6
+#define BOOKE_IRQPRIO_SPE_FP_ROUND 7
+#define BOOKE_IRQPRIO_SYSCALL 8
+#define BOOKE_IRQPRIO_AP_UNAVAIL 9
+#define BOOKE_IRQPRIO_DTLB_MISS 10
+#define BOOKE_IRQPRIO_ITLB_MISS 11
+#define BOOKE_IRQPRIO_MACHINE_CHECK 12
+#define BOOKE_IRQPRIO_DEBUG 13
+#define BOOKE_IRQPRIO_CRITICAL 14
+#define BOOKE_IRQPRIO_WATCHDOG 15
+#define BOOKE_IRQPRIO_EXTERNAL 16
+#define BOOKE_IRQPRIO_FIT 17
+#define BOOKE_IRQPRIO_DECREMENTER 18
+#define BOOKE_IRQPRIO_PERFORMANCE_MONITOR 19
+#define BOOKE_IRQPRIO_MAX 19
+
+extern unsigned long kvmppc_booke_handlers;
 
 /* Helper function for "full" MSR writes. No need to call this if only EE is
  * changing. */
@@ -57,4 +65,9 @@ static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 	};
 }
 
+int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                            unsigned int inst, int *advance);
+int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
+int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs);
+
 #endif /* __KVM_BOOKE_H__ */
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
new file mode 100644
index 00000000000..aebc65e93f4
--- /dev/null
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -0,0 +1,266 @@
+/*
+ * 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.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/disassemble.h>
+
+#include "booke.h"
+
+#define OP_19_XOP_RFI     50
+
+#define OP_31_XOP_MFMSR   83
+#define OP_31_XOP_WRTEE   131
+#define OP_31_XOP_MTMSR   146
+#define OP_31_XOP_WRTEEI  163
+
+static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pc = vcpu->arch.srr0;
+	kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+}
+
+int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                            unsigned int inst, int *advance)
+{
+	int emulated = EMULATE_DONE;
+	int rs;
+	int rt;
+
+	switch (get_op(inst)) {
+	case 19:
+		switch (get_xop(inst)) {
+		case OP_19_XOP_RFI:
+			kvmppc_emul_rfi(vcpu);
+			kvmppc_set_exit_type(vcpu, EMULATED_RFI_EXITS);
+			*advance = 0;
+			break;
+
+		default:
+			emulated = EMULATE_FAIL;
+			break;
+		}
+		break;
+
+	case 31:
+		switch (get_xop(inst)) {
+
+		case OP_31_XOP_MFMSR:
+			rt = get_rt(inst);
+			vcpu->arch.gpr[rt] = vcpu->arch.msr;
+			kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
+			break;
+
+		case OP_31_XOP_MTMSR:
+			rs = get_rs(inst);
+			kvmppc_set_exit_type(vcpu, EMULATED_MTMSR_EXITS);
+			kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]);
+			break;
+
+		case OP_31_XOP_WRTEE:
+			rs = get_rs(inst);
+			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+							 | (vcpu->arch.gpr[rs] & MSR_EE);
+			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
+			break;
+
+		case OP_31_XOP_WRTEEI:
+			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+							 | (inst & MSR_EE);
+			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
+			break;
+
+		default:
+			emulated = EMULATE_FAIL;
+		}
+
+		break;
+
+	default:
+		emulated = EMULATE_FAIL;
+	}
+
+	return emulated;
+}
+
+int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_DEAR:
+		vcpu->arch.dear = vcpu->arch.gpr[rs]; break;
+	case SPRN_ESR:
+		vcpu->arch.esr = vcpu->arch.gpr[rs]; break;
+	case SPRN_DBCR0:
+		vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
+	case SPRN_DBCR1:
+		vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
+	case SPRN_DBSR:
+		vcpu->arch.dbsr &= ~vcpu->arch.gpr[rs]; break;
+	case SPRN_TSR:
+		vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
+	case SPRN_TCR:
+		vcpu->arch.tcr = vcpu->arch.gpr[rs];
+		kvmppc_emulate_dec(vcpu);
+		break;
+
+	/* Note: SPRG4-7 are user-readable. These values are
+	 * loaded into the real SPRGs when resuming the
+	 * guest. */
+	case SPRN_SPRG4:
+		vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break;
+	case SPRN_SPRG5:
+		vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break;
+	case SPRN_SPRG6:
+		vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break;
+	case SPRN_SPRG7:
+		vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break;
+
+	case SPRN_IVPR:
+		vcpu->arch.ivpr = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR0:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR1:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR2:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR3:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR4:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR5:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR6:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR7:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR8:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR9:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR10:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR11:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR12:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR13:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR14:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR15:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = vcpu->arch.gpr[rs];
+		break;
+
+	default:
+		emulated = EMULATE_FAIL;
+	}
+
+	return emulated;
+}
+
+int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_IVPR:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break;
+	case SPRN_DEAR:
+		vcpu->arch.gpr[rt] = vcpu->arch.dear; break;
+	case SPRN_ESR:
+		vcpu->arch.gpr[rt] = vcpu->arch.esr; break;
+	case SPRN_DBCR0:
+		vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
+	case SPRN_DBCR1:
+		vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
+	case SPRN_DBSR:
+		vcpu->arch.gpr[rt] = vcpu->arch.dbsr; break;
+
+	case SPRN_IVOR0:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
+		break;
+	case SPRN_IVOR1:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
+		break;
+	case SPRN_IVOR2:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
+		break;
+	case SPRN_IVOR3:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
+		break;
+	case SPRN_IVOR4:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
+		break;
+	case SPRN_IVOR5:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
+		break;
+	case SPRN_IVOR6:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
+		break;
+	case SPRN_IVOR7:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
+		break;
+	case SPRN_IVOR8:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
+		break;
+	case SPRN_IVOR9:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
+		break;
+	case SPRN_IVOR10:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
+		break;
+	case SPRN_IVOR11:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
+		break;
+	case SPRN_IVOR12:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
+		break;
+	case SPRN_IVOR13:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
+		break;
+	case SPRN_IVOR14:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
+		break;
+	case SPRN_IVOR15:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
+		break;
+
+	default:
+		emulated = EMULATE_FAIL;
+	}
+
+	return emulated;
+}
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 084ebcd7dd8..d0c6f841bbd 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -86,6 +86,9 @@ KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
 KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
 KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
 KVM_HANDLER BOOKE_INTERRUPT_DEBUG
+KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND
 
 _GLOBAL(kvmppc_handler_len)
 	.long kvmppc_handler_1 - kvmppc_handler_0
@@ -347,7 +350,9 @@ lightweight_exit:
 	lwz	r3, VCPU_SHADOW_PID(r4)
 	mtspr	SPRN_PID, r3
 
+#ifdef CONFIG_44x
 	iccci	0, 0 /* XXX hack */
+#endif
 
 	/* Load some guest volatiles. */
 	lwz	r0, VCPU_GPR(r0)(r4)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
new file mode 100644
index 00000000000..d8067fd81cd
--- /dev/null
+++ b/arch/powerpc/kvm/e500.c
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/44x.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * 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/kvm_host.h>
+#include <linux/err.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/tlbflush.h>
+#include <asm/kvm_e500.h>
+#include <asm/kvm_ppc.h>
+
+#include "booke.h"
+#include "e500_tlb.h"
+
+void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	kvmppc_e500_tlb_load(vcpu, cpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	kvmppc_e500_tlb_put(vcpu);
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	int r;
+
+	if (strcmp(cur_cpu_spec->cpu_name, "e500v2") == 0)
+		r = 0;
+	else
+		r = -ENOTSUPP;
+
+	return r;
+}
+
+int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	kvmppc_e500_tlb_setup(vcpu_e500);
+
+	/* Use the same core vertion as host's */
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
+
+	return 0;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
+                               struct kvm_translation *tr)
+{
+	int index;
+	gva_t eaddr;
+	u8 pid;
+	u8 as;
+
+	eaddr = tr->linear_address;
+	pid = (tr->linear_address >> 32) & 0xff;
+	as = (tr->linear_address >> 40) & 0x1;
+
+	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
+	if (index < 0) {
+		tr->valid = 0;
+		return 0;
+	}
+
+	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
+	/* XXX what does "writeable" and "usermode" even mean? */
+	tr->valid = 1;
+
+	return 0;
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500;
+	struct kvm_vcpu *vcpu;
+	int err;
+
+	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu_e500) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	vcpu = &vcpu_e500->vcpu;
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	err = kvmppc_e500_tlb_init(vcpu_e500);
+	if (err)
+		goto uninit_vcpu;
+
+	return vcpu;
+
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+out:
+	return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+}
+
+static int kvmppc_e500_init(void)
+{
+	int r, i;
+	unsigned long ivor[3];
+	unsigned long max_ivor = 0;
+
+	r = kvmppc_booke_init();
+	if (r)
+		return r;
+
+	/* copy extra E500 exception handlers */
+	ivor[0] = mfspr(SPRN_IVOR32);
+	ivor[1] = mfspr(SPRN_IVOR33);
+	ivor[2] = mfspr(SPRN_IVOR34);
+	for (i = 0; i < 3; i++) {
+		if (ivor[i] > max_ivor)
+			max_ivor = ivor[i];
+
+		memcpy((void *)kvmppc_booke_handlers + ivor[i],
+		       kvmppc_handlers_start + (i + 16) * kvmppc_handler_len,
+		       kvmppc_handler_len);
+	}
+	flush_icache_range(kvmppc_booke_handlers,
+			kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
+}
+
+static void kvmppc_e500_exit(void)
+{
+	kvmppc_booke_exit();
+}
+
+module_init(kvmppc_e500_init);
+module_exit(kvmppc_e500_exit);
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
new file mode 100644
index 00000000000..3f760414b9f
--- /dev/null
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, <yu.liu@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/44x_emulate.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * 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 <asm/kvm_ppc.h>
+#include <asm/disassemble.h>
+#include <asm/kvm_e500.h>
+
+#include "booke.h"
+#include "e500_tlb.h"
+
+#define XOP_TLBIVAX 786
+#define XOP_TLBSX   914
+#define XOP_TLBRE   946
+#define XOP_TLBWE   978
+
+int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                           unsigned int inst, int *advance)
+{
+	int emulated = EMULATE_DONE;
+	int ra;
+	int rb;
+
+	switch (get_op(inst)) {
+	case 31:
+		switch (get_xop(inst)) {
+
+		case XOP_TLBRE:
+			emulated = kvmppc_e500_emul_tlbre(vcpu);
+			break;
+
+		case XOP_TLBWE:
+			emulated = kvmppc_e500_emul_tlbwe(vcpu);
+			break;
+
+		case XOP_TLBSX:
+			rb = get_rb(inst);
+			emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
+			break;
+
+		case XOP_TLBIVAX:
+			ra = get_ra(inst);
+			rb = get_rb(inst);
+			emulated = kvmppc_e500_emul_tlbivax(vcpu, ra, rb);
+			break;
+
+		default:
+			emulated = EMULATE_FAIL;
+		}
+
+		break;
+
+	default:
+		emulated = EMULATE_FAIL;
+	}
+
+	if (emulated == EMULATE_FAIL)
+		emulated = kvmppc_booke_emulate_op(run, vcpu, inst, advance);
+
+	return emulated;
+}
+
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_PID:
+		vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
+			vcpu->arch.pid = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_PID1:
+		vcpu_e500->pid[1] = vcpu->arch.gpr[rs]; break;
+	case SPRN_PID2:
+		vcpu_e500->pid[2] = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS0:
+		vcpu_e500->mas0 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS1:
+		vcpu_e500->mas1 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS2:
+		vcpu_e500->mas2 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS3:
+		vcpu_e500->mas3 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS4:
+		vcpu_e500->mas4 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS6:
+		vcpu_e500->mas6 = vcpu->arch.gpr[rs]; break;
+	case SPRN_MAS7:
+		vcpu_e500->mas7 = vcpu->arch.gpr[rs]; break;
+	case SPRN_L1CSR1:
+		vcpu_e500->l1csr1 = vcpu->arch.gpr[rs]; break;
+	case SPRN_HID0:
+		vcpu_e500->hid0 = vcpu->arch.gpr[rs]; break;
+	case SPRN_HID1:
+		vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break;
+
+	case SPRN_MMUCSR0:
+		emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500,
+				vcpu->arch.gpr[rs]);
+		break;
+
+	/* extra exceptions */
+	case SPRN_IVOR32:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR33:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR34:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IVOR35:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = vcpu->arch.gpr[rs];
+		break;
+
+	default:
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
+	}
+
+	return emulated;
+}
+
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_PID:
+		vcpu->arch.gpr[rt] = vcpu_e500->pid[0]; break;
+	case SPRN_PID1:
+		vcpu->arch.gpr[rt] = vcpu_e500->pid[1]; break;
+	case SPRN_PID2:
+		vcpu->arch.gpr[rt] = vcpu_e500->pid[2]; break;
+	case SPRN_MAS0:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas0; break;
+	case SPRN_MAS1:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas1; break;
+	case SPRN_MAS2:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas2; break;
+	case SPRN_MAS3:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas3; break;
+	case SPRN_MAS4:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas4; break;
+	case SPRN_MAS6:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas6; break;
+	case SPRN_MAS7:
+		vcpu->arch.gpr[rt] = vcpu_e500->mas7; break;
+
+	case SPRN_TLB0CFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB0CFG);
+		vcpu->arch.gpr[rt] &= ~0xfffUL;
+		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[0];
+		break;
+
+	case SPRN_TLB1CFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB1CFG);
+		vcpu->arch.gpr[rt] &= ~0xfffUL;
+		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[1];
+		break;
+
+	case SPRN_L1CSR1:
+		vcpu->arch.gpr[rt] = vcpu_e500->l1csr1; break;
+	case SPRN_HID0:
+		vcpu->arch.gpr[rt] = vcpu_e500->hid0; break;
+	case SPRN_HID1:
+		vcpu->arch.gpr[rt] = vcpu_e500->hid1; break;
+
+	case SPRN_MMUCSR0:
+		vcpu->arch.gpr[rt] = 0; break;
+
+	/* extra exceptions */
+	case SPRN_IVOR32:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
+		break;
+	case SPRN_IVOR33:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
+		break;
+	case SPRN_IVOR34:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
+		break;
+	case SPRN_IVOR35:
+		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+		break;
+	default:
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
+	}
+
+	return emulated;
+}
+
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
new file mode 100644
index 00000000000..0e773fc2d5e
--- /dev/null
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -0,0 +1,757 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, yu.liu@freescale.com
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * 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/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_e500.h>
+
+#include "../mm/mmu_decl.h"
+#include "e500_tlb.h"
+
+#define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
+
+static unsigned int tlb1_entry_num;
+
+void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct tlbe *tlbe;
+	int i, tlbsel;
+
+	printk("| %8s | %8s | %8s | %8s | %8s |\n",
+			"nr", "mas1", "mas2", "mas3", "mas7");
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		printk("Guest TLB%d:\n", tlbsel);
+		for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) {
+			tlbe = &vcpu_e500->guest_tlb[tlbsel][i];
+			if (tlbe->mas1 & MAS1_VALID)
+				printk(" G[%d][%3d] |  %08X | %08X | %08X | %08X |\n",
+					tlbsel, i, tlbe->mas1, tlbe->mas2,
+					tlbe->mas3, tlbe->mas7);
+		}
+	}
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		printk("Shadow TLB%d:\n", tlbsel);
+		for (i = 0; i < vcpu_e500->shadow_tlb_size[tlbsel]; i++) {
+			tlbe = &vcpu_e500->shadow_tlb[tlbsel][i];
+			if (tlbe->mas1 & MAS1_VALID)
+				printk(" S[%d][%3d] |  %08X | %08X | %08X | %08X |\n",
+					tlbsel, i, tlbe->mas1, tlbe->mas2,
+					tlbe->mas3, tlbe->mas7);
+		}
+	}
+}
+
+static inline unsigned int tlb0_get_next_victim(
+		struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	unsigned int victim;
+
+	victim = vcpu_e500->guest_tlb_nv[0]++;
+	if (unlikely(vcpu_e500->guest_tlb_nv[0] >= KVM_E500_TLB0_WAY_NUM))
+		vcpu_e500->guest_tlb_nv[0] = 0;
+
+	return victim;
+}
+
+static inline unsigned int tlb1_max_shadow_size(void)
+{
+	return tlb1_entry_num - tlbcam_index;
+}
+
+static inline int tlbe_is_writable(struct tlbe *tlbe)
+{
+	return tlbe->mas3 & (MAS3_SW|MAS3_UW);
+}
+
+static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
+{
+	/* Mask off reserved bits. */
+	mas3 &= MAS3_ATTRIB_MASK;
+
+	if (!usermode) {
+		/* Guest is in supervisor mode,
+		 * so we need to translate guest
+		 * supervisor permissions into user permissions. */
+		mas3 &= ~E500_TLB_USER_PERM_MASK;
+		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
+	}
+
+	return mas3 | E500_TLB_SUPER_PERM_MASK;
+}
+
+static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
+{
+#ifdef CONFIG_SMP
+	return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M;
+#else
+	return mas2 & MAS2_ATTRIB_MASK;
+#endif
+}
+
+/*
+ * writing shadow tlb entry to host TLB
+ */
+static inline void __write_host_tlbe(struct tlbe *stlbe)
+{
+	mtspr(SPRN_MAS1, stlbe->mas1);
+	mtspr(SPRN_MAS2, stlbe->mas2);
+	mtspr(SPRN_MAS3, stlbe->mas3);
+	mtspr(SPRN_MAS7, stlbe->mas7);
+	__asm__ __volatile__ ("tlbwe\n" : : );
+}
+
+static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+
+	local_irq_disable();
+	if (tlbsel == 0) {
+		__write_host_tlbe(stlbe);
+	} else {
+		unsigned register mas0;
+
+		mas0 = mfspr(SPRN_MAS0);
+
+		mtspr(SPRN_MAS0, MAS0_TLBSEL(1) | MAS0_ESEL(to_htlb1_esel(esel)));
+		__write_host_tlbe(stlbe);
+
+		mtspr(SPRN_MAS0, mas0);
+	}
+	local_irq_enable();
+}
+
+void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int i;
+	unsigned register mas0;
+
+	/* Load all valid TLB1 entries to reduce guest tlb miss fault */
+	local_irq_disable();
+	mas0 = mfspr(SPRN_MAS0);
+	for (i = 0; i < tlb1_max_shadow_size(); i++) {
+		struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
+
+		if (get_tlb_v(stlbe)) {
+			mtspr(SPRN_MAS0, MAS0_TLBSEL(1)
+					| MAS0_ESEL(to_htlb1_esel(i)));
+			__write_host_tlbe(stlbe);
+		}
+	}
+	mtspr(SPRN_MAS0, mas0);
+	local_irq_enable();
+}
+
+void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
+{
+	_tlbil_all();
+}
+
+/* Search the guest TLB for a matching entry. */
+static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
+		gva_t eaddr, int tlbsel, unsigned int pid, int as)
+{
+	int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++) {
+		struct tlbe *tlbe = &vcpu_e500->guest_tlb[tlbsel][i];
+		unsigned int tid;
+
+		if (eaddr < get_tlb_eaddr(tlbe))
+			continue;
+
+		if (eaddr > get_tlb_end(tlbe))
+			continue;
+
+		tid = get_tlb_tid(tlbe);
+		if (tid && (tid != pid))
+			continue;
+
+		if (!get_tlb_v(tlbe))
+			continue;
+
+		if (get_tlb_ts(tlbe) != as && as != -1)
+			continue;
+
+		return i;
+	}
+
+	return -1;
+}
+
+static void kvmppc_e500_shadow_release(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+	struct page *page = vcpu_e500->shadow_pages[tlbsel][esel];
+
+	if (page) {
+		vcpu_e500->shadow_pages[tlbsel][esel] = NULL;
+
+		if (get_tlb_v(stlbe)) {
+			if (tlbe_is_writable(stlbe))
+				kvm_release_page_dirty(page);
+			else
+				kvm_release_page_clean(page);
+		}
+	}
+}
+
+static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+
+	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
+	stlbe->mas1 = 0;
+	KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
+			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
+			handler);
+}
+
+static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
+		gva_t eaddr, gva_t eend, u32 tid)
+{
+	unsigned int pid = tid & 0xff;
+	unsigned int i;
+
+	/* XXX Replace loop with fancy data structures. */
+	for (i = 0; i < vcpu_e500->guest_tlb_size[1]; i++) {
+		struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
+		unsigned int tid;
+
+		if (!get_tlb_v(stlbe))
+			continue;
+
+		if (eend < get_tlb_eaddr(stlbe))
+			continue;
+
+		if (eaddr > get_tlb_end(stlbe))
+			continue;
+
+		tid = get_tlb_tid(stlbe);
+		if (tid && (tid != pid))
+			continue;
+
+		kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
+		write_host_tlbe(vcpu_e500, 1, i);
+	}
+}
+
+static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
+		unsigned int eaddr, int as)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	unsigned int victim, pidsel, tsized;
+	int tlbsel;
+
+	/* since we only have two TLBs, only lower bit is used. */
+	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
+	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
+	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
+	tsized = (vcpu_e500->mas4 >> 8) & 0xf;
+
+	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+		| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+	vcpu_e500->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
+		| MAS1_TID(vcpu_e500->pid[pidsel])
+		| MAS1_TSIZE(tsized);
+	vcpu_e500->mas2 = (eaddr & MAS2_EPN)
+		| (vcpu_e500->mas4 & MAS2_ATTRIB_MASK);
+	vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
+	vcpu_e500->mas6 = (vcpu_e500->mas6 & MAS6_SPID1)
+		| (get_cur_pid(vcpu) << 16)
+		| (as ? MAS6_SAS : 0);
+	vcpu_e500->mas7 = 0;
+}
+
+static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+	u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel)
+{
+	struct page *new_page;
+	struct tlbe *stlbe;
+	hpa_t hpaddr;
+
+	stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+
+	/* Get reference to new page. */
+	new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn);
+	if (is_error_page(new_page)) {
+		printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn);
+		kvm_release_page_clean(new_page);
+		return;
+	}
+	hpaddr = page_to_phys(new_page);
+
+	/* Drop reference to old page. */
+	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
+
+	vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
+
+	/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
+	stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
+		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
+	stlbe->mas2 = (gvaddr & MAS2_EPN)
+		| e500_shadow_mas2_attrib(gtlbe->mas2,
+				vcpu_e500->vcpu.arch.msr & MSR_PR);
+	stlbe->mas3 = (hpaddr & MAS3_RPN)
+		| e500_shadow_mas3_attrib(gtlbe->mas3,
+				vcpu_e500->vcpu.arch.msr & MSR_PR);
+	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
+
+	KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
+			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
+			handler);
+}
+
+/* XXX only map the one-one case, for now use TLB0 */
+static int kvmppc_e500_stlbe_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *gtlbe;
+
+	gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
+	kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
+			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
+			gtlbe, tlbsel, esel);
+
+	return esel;
+}
+
+/* Caller must ensure that the specified guest TLB entry is safe to insert into
+ * the shadow TLB. */
+/* XXX for both one-one and one-to-many , for now use TLB1 */
+static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+		u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe)
+{
+	unsigned int victim;
+
+	victim = vcpu_e500->guest_tlb_nv[1]++;
+
+	if (unlikely(vcpu_e500->guest_tlb_nv[1] >= tlb1_max_shadow_size()))
+		vcpu_e500->guest_tlb_nv[1] = 0;
+
+	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim);
+
+	return victim;
+}
+
+/* Invalidate all guest kernel mappings when enter usermode,
+ * so that when they fault back in they will get the
+ * proper permission bits. */
+void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode)
+{
+	if (usermode) {
+		struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+		int i;
+
+		/* XXX Replace loop with fancy data structures. */
+		for (i = 0; i < tlb1_max_shadow_size(); i++)
+			kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
+
+		_tlbil_all();
+	}
+}
+
+static int kvmppc_e500_gtlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int esel)
+{
+	struct tlbe *gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
+	if (unlikely(get_tlb_iprot(gtlbe)))
+		return -1;
+
+	if (tlbsel == 1) {
+		kvmppc_e500_tlb1_invalidate(vcpu_e500, get_tlb_eaddr(gtlbe),
+				get_tlb_end(gtlbe),
+				get_tlb_tid(gtlbe));
+	} else {
+		kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel);
+	}
+
+	gtlbe->mas1 = 0;
+
+	return 0;
+}
+
+int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
+{
+	int esel;
+
+	if (value & MMUCSR0_TLB0FI)
+		for (esel = 0; esel < vcpu_e500->guest_tlb_size[0]; esel++)
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 0, esel);
+	if (value & MMUCSR0_TLB1FI)
+		for (esel = 0; esel < vcpu_e500->guest_tlb_size[1]; esel++)
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
+
+	_tlbil_all();
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	unsigned int ia;
+	int esel, tlbsel;
+	gva_t ea;
+
+	ea = ((ra) ? vcpu->arch.gpr[ra] : 0) + vcpu->arch.gpr[rb];
+
+	ia = (ea >> 2) & 0x1;
+
+	/* since we only have two TLBs, only lower bit is used. */
+	tlbsel = (ea >> 3) & 0x1;
+
+	if (ia) {
+		/* invalidate all entries */
+		for (esel = 0; esel < vcpu_e500->guest_tlb_size[tlbsel]; esel++)
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+	} else {
+		ea &= 0xfffff000;
+		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel,
+				get_cur_pid(vcpu), -1);
+		if (esel >= 0)
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+	}
+
+	_tlbil_all();
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int tlbsel, esel;
+	struct tlbe *gtlbe;
+
+	tlbsel = get_tlb_tlbsel(vcpu_e500);
+	esel = get_tlb_esel(vcpu_e500, tlbsel);
+
+	gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+	vcpu_e500->mas0 &= ~MAS0_NV(~0);
+	vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+	vcpu_e500->mas1 = gtlbe->mas1;
+	vcpu_e500->mas2 = gtlbe->mas2;
+	vcpu_e500->mas3 = gtlbe->mas3;
+	vcpu_e500->mas7 = gtlbe->mas7;
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int as = !!get_cur_sas(vcpu_e500);
+	unsigned int pid = get_cur_spid(vcpu_e500);
+	int esel, tlbsel;
+	struct tlbe *gtlbe = NULL;
+	gva_t ea;
+
+	ea = vcpu->arch.gpr[rb];
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
+		if (esel >= 0) {
+			gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+			break;
+		}
+	}
+
+	if (gtlbe) {
+		vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
+			| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+		vcpu_e500->mas1 = gtlbe->mas1;
+		vcpu_e500->mas2 = gtlbe->mas2;
+		vcpu_e500->mas3 = gtlbe->mas3;
+		vcpu_e500->mas7 = gtlbe->mas7;
+	} else {
+		int victim;
+
+		/* since we only have two TLBs, only lower bit is used. */
+		tlbsel = vcpu_e500->mas4 >> 28 & 0x1;
+		victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
+
+		vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+			| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
+		vcpu_e500->mas1 = (vcpu_e500->mas6 & MAS6_SPID0)
+			| (vcpu_e500->mas6 & (MAS6_SAS ? MAS1_TS : 0))
+			| (vcpu_e500->mas4 & MAS4_TSIZED(~0));
+		vcpu_e500->mas2 &= MAS2_EPN;
+		vcpu_e500->mas2 |= vcpu_e500->mas4 & MAS2_ATTRIB_MASK;
+		vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
+		vcpu_e500->mas7 = 0;
+	}
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	u64 eaddr;
+	u64 raddr;
+	u32 tid;
+	struct tlbe *gtlbe;
+	int tlbsel, esel, stlbsel, sesel;
+
+	tlbsel = get_tlb_tlbsel(vcpu_e500);
+	esel = get_tlb_esel(vcpu_e500, tlbsel);
+
+	gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
+	if (get_tlb_v(gtlbe) && tlbsel == 1) {
+		eaddr = get_tlb_eaddr(gtlbe);
+		tid = get_tlb_tid(gtlbe);
+		kvmppc_e500_tlb1_invalidate(vcpu_e500, eaddr,
+				get_tlb_end(gtlbe), tid);
+	}
+
+	gtlbe->mas1 = vcpu_e500->mas1;
+	gtlbe->mas2 = vcpu_e500->mas2;
+	gtlbe->mas3 = vcpu_e500->mas3;
+	gtlbe->mas7 = vcpu_e500->mas7;
+
+	KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
+			gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
+			handler);
+
+	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
+	if (tlbe_is_host_safe(vcpu, gtlbe)) {
+		switch (tlbsel) {
+		case 0:
+			/* TLB0 */
+			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
+			gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
+
+			stlbsel = 0;
+			sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
+
+			break;
+
+		case 1:
+			/* TLB1 */
+			eaddr = get_tlb_eaddr(gtlbe);
+			raddr = get_tlb_raddr(gtlbe);
+
+			/* Create a 4KB mapping on the host.
+			 * If the guest wanted a large page,
+			 * only the first 4KB is mapped here and the rest
+			 * are mapped on the fly. */
+			stlbsel = 1;
+			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
+					raddr >> PAGE_SHIFT, gtlbe);
+			break;
+
+		default:
+			BUG();
+		}
+		write_host_tlbe(vcpu_e500, stlbsel, sesel);
+	}
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+
+	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
+}
+
+int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+
+	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
+}
+
+void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+
+	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
+}
+
+void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
+{
+	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+
+	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.fault_dear, as);
+}
+
+gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
+			gva_t eaddr)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct tlbe *gtlbe =
+		&vcpu_e500->guest_tlb[tlbsel_of(index)][esel_of(index)];
+	u64 pgmask = get_tlb_bytes(gtlbe) - 1;
+
+	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int tlbsel, i;
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++)
+		for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++)
+			kvmppc_e500_shadow_release(vcpu_e500, tlbsel, i);
+
+	/* discard all guest mapping */
+	_tlbil_all();
+}
+
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
+			unsigned int index)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int tlbsel = tlbsel_of(index);
+	int esel = esel_of(index);
+	int stlbsel, sesel;
+
+	switch (tlbsel) {
+	case 0:
+		stlbsel = 0;
+		sesel = esel;
+		break;
+
+	case 1: {
+		gfn_t gfn = gpaddr >> PAGE_SHIFT;
+		struct tlbe *gtlbe
+			= &vcpu_e500->guest_tlb[tlbsel][esel];
+
+		stlbsel = 1;
+		sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe);
+		break;
+	}
+
+	default:
+		BUG();
+		break;
+	}
+	write_host_tlbe(vcpu_e500, stlbsel, sesel);
+}
+
+int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
+				gva_t eaddr, unsigned int pid, int as)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int esel, tlbsel;
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
+		if (esel >= 0)
+			return index_of(tlbsel, esel);
+	}
+
+	return -1;
+}
+
+void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	struct tlbe *tlbe;
+
+	/* Insert large initial mapping for guest. */
+	tlbe = &vcpu_e500->guest_tlb[1][0];
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
+	tlbe->mas2 = 0;
+	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
+	tlbe->mas7 = 0;
+
+	/* 4K map for serial output. Used by kernel wrapper. */
+	tlbe = &vcpu_e500->guest_tlb[1][1];
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
+	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+	tlbe->mas7 = 0;
+}
+
+int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	tlb1_entry_num = mfspr(SPRN_TLB1CFG) & 0xFFF;
+
+	vcpu_e500->guest_tlb_size[0] = KVM_E500_TLB0_SIZE;
+	vcpu_e500->guest_tlb[0] =
+		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+	if (vcpu_e500->guest_tlb[0] == NULL)
+		goto err_out;
+
+	vcpu_e500->shadow_tlb_size[0] = KVM_E500_TLB0_SIZE;
+	vcpu_e500->shadow_tlb[0] =
+		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+	if (vcpu_e500->shadow_tlb[0] == NULL)
+		goto err_out_guest0;
+
+	vcpu_e500->guest_tlb_size[1] = KVM_E500_TLB1_SIZE;
+	vcpu_e500->guest_tlb[1] =
+		kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
+	if (vcpu_e500->guest_tlb[1] == NULL)
+		goto err_out_shadow0;
+
+	vcpu_e500->shadow_tlb_size[1] = tlb1_entry_num;
+	vcpu_e500->shadow_tlb[1] =
+		kzalloc(sizeof(struct tlbe) * tlb1_entry_num, GFP_KERNEL);
+	if (vcpu_e500->shadow_tlb[1] == NULL)
+		goto err_out_guest1;
+
+	vcpu_e500->shadow_pages[0] = (struct page **)
+		kzalloc(sizeof(struct page *) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+	if (vcpu_e500->shadow_pages[0] == NULL)
+		goto err_out_shadow1;
+
+	vcpu_e500->shadow_pages[1] = (struct page **)
+		kzalloc(sizeof(struct page *) * tlb1_entry_num, GFP_KERNEL);
+	if (vcpu_e500->shadow_pages[1] == NULL)
+		goto err_out_page0;
+
+	return 0;
+
+err_out_page0:
+	kfree(vcpu_e500->shadow_pages[0]);
+err_out_shadow1:
+	kfree(vcpu_e500->shadow_tlb[1]);
+err_out_guest1:
+	kfree(vcpu_e500->guest_tlb[1]);
+err_out_shadow0:
+	kfree(vcpu_e500->shadow_tlb[0]);
+err_out_guest0:
+	kfree(vcpu_e500->guest_tlb[0]);
+err_out:
+	return -1;
+}
+
+void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->shadow_pages[1]);
+	kfree(vcpu_e500->shadow_pages[0]);
+	kfree(vcpu_e500->shadow_tlb[1]);
+	kfree(vcpu_e500->guest_tlb[1]);
+	kfree(vcpu_e500->shadow_tlb[0]);
+	kfree(vcpu_e500->guest_tlb[0]);
+}
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
new file mode 100644
index 00000000000..45b064b7690
--- /dev/null
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -0,0 +1,185 @@
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, yu.liu@freescale.com
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.h,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * 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.
+ */
+
+#ifndef __KVM_E500_TLB_H__
+#define __KVM_E500_TLB_H__
+
+#include <linux/kvm_host.h>
+#include <asm/mmu-fsl-booke.h>
+#include <asm/tlb.h>
+#include <asm/kvm_e500.h>
+
+#define KVM_E500_TLB0_WAY_SIZE_BIT	7	/* Fixed */
+#define KVM_E500_TLB0_WAY_SIZE		(1UL << KVM_E500_TLB0_WAY_SIZE_BIT)
+#define KVM_E500_TLB0_WAY_SIZE_MASK	(KVM_E500_TLB0_WAY_SIZE - 1)
+
+#define KVM_E500_TLB0_WAY_NUM_BIT	1	/* No greater than 7 */
+#define KVM_E500_TLB0_WAY_NUM		(1UL << KVM_E500_TLB0_WAY_NUM_BIT)
+#define KVM_E500_TLB0_WAY_NUM_MASK	(KVM_E500_TLB0_WAY_NUM - 1)
+
+#define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
+#define KVM_E500_TLB1_SIZE  16
+
+#define index_of(tlbsel, esel)	(((tlbsel) << 16) | ((esel) & 0xFFFF))
+#define tlbsel_of(index)	((index) >> 16)
+#define esel_of(index)		((index) & 0xFFFF)
+
+#define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
+#define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
+#define MAS2_ATTRIB_MASK \
+	  (MAS2_X0 | MAS2_X1)
+#define MAS3_ATTRIB_MASK \
+	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
+	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
+
+extern void kvmppc_dump_tlbs(struct kvm_vcpu *);
+extern int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *, ulong);
+extern int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *);
+extern int kvmppc_e500_emul_tlbre(struct kvm_vcpu *);
+extern int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *, int, int);
+extern int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *, int);
+extern int kvmppc_e500_tlb_search(struct kvm_vcpu *, gva_t, unsigned int, int);
+extern void kvmppc_e500_tlb_put(struct kvm_vcpu *);
+extern void kvmppc_e500_tlb_load(struct kvm_vcpu *, int);
+extern int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *);
+extern void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *);
+extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
+
+/* TLB helper functions */
+static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 8) & 0xf;
+}
+
+static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+{
+	return tlbe->mas2 & 0xfffff000;
+}
+
+static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
+{
+	unsigned int pgsize = get_tlb_size(tlbe);
+	return 1ULL << 10 << (pgsize << 1);
+}
+
+static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+{
+	u64 bytes = get_tlb_bytes(tlbe);
+	return get_tlb_eaddr(tlbe) + bytes - 1;
+}
+
+static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+{
+	u64 rpn = tlbe->mas7;
+	return (rpn << 32) | (tlbe->mas3 & 0xfffff000);
+}
+
+static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 16) & 0xff;
+}
+
+static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 12) & 0x1;
+}
+
+static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 31) & 0x1;
+}
+
+static inline unsigned int get_tlb_iprot(const struct tlbe *tlbe)
+{
+	return (tlbe->mas1 >> 30) & 0x1;
+}
+
+static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pid & 0xff;
+}
+
+static inline unsigned int get_cur_spid(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return (vcpu_e500->mas6 >> 16) & 0xff;
+}
+
+static inline unsigned int get_cur_sas(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return vcpu_e500->mas6 & 0x1;
+}
+
+static inline unsigned int get_tlb_tlbsel(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	/*
+	 * Manual says that tlbsel has 2 bits wide.
+	 * Since we only have two TLBs, only lower bit is used.
+	 */
+	return (vcpu_e500->mas0 >> 28) & 0x1;
+}
+
+static inline unsigned int get_tlb_nv_bit(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return vcpu_e500->mas0 & 0xfff;
+}
+
+static inline unsigned int get_tlb_esel_bit(
+		const struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	return (vcpu_e500->mas0 >> 16) & 0xfff;
+}
+
+static inline unsigned int get_tlb_esel(
+		const struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel)
+{
+	unsigned int esel = get_tlb_esel_bit(vcpu_e500);
+
+	if (tlbsel == 0) {
+		esel &= KVM_E500_TLB0_WAY_NUM_MASK;
+		esel |= ((vcpu_e500->mas2 >> 12) & KVM_E500_TLB0_WAY_SIZE_MASK)
+				<< KVM_E500_TLB0_WAY_NUM_BIT;
+	} else {
+		esel &= KVM_E500_TLB1_SIZE - 1;
+	}
+
+	return esel;
+}
+
+static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
+			const struct tlbe *tlbe)
+{
+	gpa_t gpa;
+
+	if (!get_tlb_v(tlbe))
+		return 0;
+
+	/* Does it match current guest AS? */
+	/* XXX what about IS != DS? */
+	if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+		return 0;
+
+	gpa = get_tlb_raddr(tlbe);
+	if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
+		/* Mapping is not for RAM. */
+		return 0;
+
+	return 1;
+}
+
+#endif /* __KVM_E500_TLB_H__ */
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index d1d38daa93f..a561d6e8da1 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -30,6 +30,39 @@
 #include <asm/disassemble.h>
 #include "timing.h"
 
+#define OP_TRAP 3
+
+#define OP_31_XOP_LWZX      23
+#define OP_31_XOP_LBZX      87
+#define OP_31_XOP_STWX      151
+#define OP_31_XOP_STBX      215
+#define OP_31_XOP_STBUX     247
+#define OP_31_XOP_LHZX      279
+#define OP_31_XOP_LHZUX     311
+#define OP_31_XOP_MFSPR     339
+#define OP_31_XOP_STHX      407
+#define OP_31_XOP_STHUX     439
+#define OP_31_XOP_MTSPR     467
+#define OP_31_XOP_DCBI      470
+#define OP_31_XOP_LWBRX     534
+#define OP_31_XOP_TLBSYNC   566
+#define OP_31_XOP_STWBRX    662
+#define OP_31_XOP_LHBRX     790
+#define OP_31_XOP_STHBRX    918
+
+#define OP_LWZ  32
+#define OP_LWZU 33
+#define OP_LBZ  34
+#define OP_LBZU 35
+#define OP_STW  36
+#define OP_STWU 37
+#define OP_STB  38
+#define OP_STBU 39
+#define OP_LHZ  40
+#define OP_LHZU 41
+#define OP_STH  44
+#define OP_STHU 45
+
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->arch.tcr & TCR_DIE) {
@@ -78,7 +111,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
 
 	switch (get_op(inst)) {
-	case 3:                                             /* trap */
+	case OP_TRAP:
 		vcpu->arch.esr |= ESR_PTR;
 		kvmppc_core_queue_program(vcpu);
 		advance = 0;
@@ -87,31 +120,31 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	case 31:
 		switch (get_xop(inst)) {
 
-		case 23:                                        /* lwzx */
+		case OP_31_XOP_LWZX:
 			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 			break;
 
-		case 87:                                        /* lbzx */
+		case OP_31_XOP_LBZX:
 			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 			break;
 
-		case 151:                                       /* stwx */
+		case OP_31_XOP_STWX:
 			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
 			                               vcpu->arch.gpr[rs],
 			                               4, 1);
 			break;
 
-		case 215:                                       /* stbx */
+		case OP_31_XOP_STBX:
 			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
 			                               vcpu->arch.gpr[rs],
 			                               1, 1);
 			break;
 
-		case 247:                                       /* stbux */
+		case OP_31_XOP_STBUX:
 			rs = get_rs(inst);
 			ra = get_ra(inst);
 			rb = get_rb(inst);
@@ -126,12 +159,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			vcpu->arch.gpr[rs] = ea;
 			break;
 
-		case 279:                                       /* lhzx */
+		case OP_31_XOP_LHZX:
 			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 			break;
 
-		case 311:                                       /* lhzux */
+		case OP_31_XOP_LHZUX:
 			rt = get_rt(inst);
 			ra = get_ra(inst);
 			rb = get_rb(inst);
@@ -144,7 +177,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			vcpu->arch.gpr[ra] = ea;
 			break;
 
-		case 339:                                       /* mfspr */
+		case OP_31_XOP_MFSPR:
 			sprn = get_sprn(inst);
 			rt = get_rt(inst);
 
@@ -185,7 +218,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			}
 			break;
 
-		case 407:                                       /* sthx */
+		case OP_31_XOP_STHX:
 			rs = get_rs(inst);
 			ra = get_ra(inst);
 			rb = get_rb(inst);
@@ -195,7 +228,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			                               2, 1);
 			break;
 
-		case 439:                                       /* sthux */
+		case OP_31_XOP_STHUX:
 			rs = get_rs(inst);
 			ra = get_ra(inst);
 			rb = get_rb(inst);
@@ -210,7 +243,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			vcpu->arch.gpr[ra] = ea;
 			break;
 
-		case 467:                                       /* mtspr */
+		case OP_31_XOP_MTSPR:
 			sprn = get_sprn(inst);
 			rs = get_rs(inst);
 			switch (sprn) {
@@ -246,7 +279,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			}
 			break;
 
-		case 470:                                       /* dcbi */
+		case OP_31_XOP_DCBI:
 			/* Do nothing. The guest is performing dcbi because
 			 * hardware DMA is not snooped by the dcache, but
 			 * emulated DMA either goes through the dcache as
@@ -254,15 +287,15 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			 * coherence. */
 			break;
 
-		case 534:                                       /* lwbrx */
+		case OP_31_XOP_LWBRX:
 			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
 			break;
 
-		case 566:                                       /* tlbsync */
+		case OP_31_XOP_TLBSYNC:
 			break;
 
-		case 662:                                       /* stwbrx */
+		case OP_31_XOP_STWBRX:
 			rs = get_rs(inst);
 			ra = get_ra(inst);
 			rb = get_rb(inst);
@@ -272,12 +305,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			                               4, 0);
 			break;
 
-		case 790:                                       /* lhbrx */
+		case OP_31_XOP_LHBRX:
 			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
 			break;
 
-		case 918:                                       /* sthbrx */
+		case OP_31_XOP_STHBRX:
 			rs = get_rs(inst);
 			ra = get_ra(inst);
 			rb = get_rb(inst);
@@ -293,37 +326,37 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 		break;
 
-	case 32:                                                /* lwz */
+	case OP_LWZ:
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		break;
 
-	case 33:                                                /* lwzu */
+	case OP_LWZU:
 		ra = get_ra(inst);
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
 		break;
 
-	case 34:                                                /* lbz */
+	case OP_LBZ:
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 		break;
 
-	case 35:                                                /* lbzu */
+	case OP_LBZU:
 		ra = get_ra(inst);
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
 		break;
 
-	case 36:                                                /* stw */
+	case OP_STW:
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
 		                               4, 1);
 		break;
 
-	case 37:                                                /* stwu */
+	case OP_STWU:
 		ra = get_ra(inst);
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
@@ -331,13 +364,13 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
 		break;
 
-	case 38:                                                /* stb */
+	case OP_STB:
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
 		                               1, 1);
 		break;
 
-	case 39:                                                /* stbu */
+	case OP_STBU:
 		ra = get_ra(inst);
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
@@ -345,25 +378,25 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
 		break;
 
-	case 40:                                                /* lhz */
+	case OP_LHZ:
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 		break;
 
-	case 41:                                                /* lhzu */
+	case OP_LHZU:
 		ra = get_ra(inst);
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
 		break;
 
-	case 44:                                                /* sth */
+	case OP_STH:
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
 		                               2, 1);
 		break;
 
-	case 45:                                                /* sthu */
+	case OP_STHU:
 		ra = get_ra(inst);
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 5f81256287f..9057335fdc6 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -216,46 +216,23 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	kvmppc_core_destroy_mmu(vcpu);
+	kvmppc_mmu_destroy(vcpu);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	if (vcpu->guest_debug.enabled)
-		kvmppc_core_load_guest_debugstate(vcpu);
-
 	kvmppc_core_vcpu_load(vcpu, cpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_debug.enabled)
-		kvmppc_core_load_host_debugstate(vcpu);
-
-	/* Don't leave guest TLB entries resident when being de-scheduled. */
-	/* XXX It would be nice to differentiate between heavyweight exit and
-	 * sched_out here, since we could avoid the TLB flush for heavyweight
-	 * exits. */
-	_tlbil_all();
 	kvmppc_core_vcpu_put(vcpu);
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-                                    struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+                                        struct kvm_guest_debug *dbg)
 {
-	int i;
-
-	vcpu->guest_debug.enabled = dbg->enabled;
-	if (vcpu->guest_debug.enabled) {
-		for (i=0; i < ARRAY_SIZE(vcpu->guest_debug.bp); i++) {
-			if (dbg->breakpoints[i].enabled)
-				vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
-			else
-				vcpu->guest_debug.bp[i] = 0;
-		}
-	}
-
-	return 0;
+	return -EINVAL;
 }
 
 static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 28c04dab263..882e47080e7 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -237,8 +237,6 @@ extern int noirqdebug;
 
 static void handle_iic_irq(unsigned int irq, struct irq_desc *desc)
 {
-	const unsigned int cpu = smp_processor_id();
-
 	spin_lock(&desc->lock);
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -254,7 +252,7 @@ static void handle_iic_irq(unsigned int irq, struct irq_desc *desc)
 		goto out_eoi;
 	}
 
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 6a0ad196aeb..f085369301b 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -508,7 +508,7 @@ static void __spu_add_to_rq(struct spu_context *ctx)
 		list_add_tail(&ctx->rq, &spu_prio->runq[ctx->prio]);
 		set_bit(ctx->prio, spu_prio->bitmap);
 		if (!spu_prio->nr_waiting++)
-			__mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK);
+			mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK);
 	}
 }
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 6b0a3538dc6..2a8af5e1634 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -343,13 +343,6 @@ source "mm/Kconfig"
 
 comment "I/O subsystem configuration"
 
-config MACHCHK_WARNING
-	bool "Process warning machine checks"
-	help
-	  Select this option if you want the machine check handler on IBM S/390 or
-	  zSeries to process warning machine checks (e.g. on power failures).
-	  If unsure, say "Y".
-
 config QDIO
 	tristate "QDIO support"
 	---help---
@@ -521,7 +514,7 @@ config APPLDATA_OS
 
 config APPLDATA_NET_SUM
 	tristate "Monitor overall network statistics"
-	depends on APPLDATA_BASE
+	depends on APPLDATA_BASE && NET
 	help
 	  This provides network related data to the Linux - VM Monitor Stream,
 	  currently there is only a total sum of network I/O statistics, no
@@ -552,7 +545,7 @@ config KEXEC
 	  but is independent of hardware/microcode support.
 
 config ZFCPDUMP
-	tristate "zfcpdump support"
+	bool "zfcpdump support"
 	select SMP
 	default n
 	help
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index eca724d229e..b49c00ce65e 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -201,8 +201,7 @@ out_free:
 static void __exit prng_exit(void)
 {
 	/* wipe me */
-	memset(p->buf, 0, prng_chunk_size);
-	kfree(p->buf);
+	kzfree(p->buf);
 	kfree(p);
 
 	misc_deregister(&prng_dev);
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 8e9243ae0c1..b30606f6d52 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -57,7 +57,7 @@
  * with operation of the form "set_bit(bitnr, flags)".
  */
 
-/* bitmap tables from arch/S390/kernel/bitmap.S */
+/* bitmap tables from arch/s390/kernel/bitmap.c */
 extern const char _oi_bitmap[];
 extern const char _ni_bitmap[];
 extern const char _zb_findmap[];
@@ -525,16 +525,16 @@ static inline unsigned long __ffs_word_loop(const unsigned long *addr,
 static inline unsigned long __ffz_word(unsigned long nr, unsigned long word)
 {
 #ifdef __s390x__
-	if (likely((word & 0xffffffff) == 0xffffffff)) {
+	if ((word & 0xffffffff) == 0xffffffff) {
 		word >>= 32;
 		nr += 32;
 	}
 #endif
-	if (likely((word & 0xffff) == 0xffff)) {
+	if ((word & 0xffff) == 0xffff) {
 		word >>= 16;
 		nr += 16;
 	}
-	if (likely((word & 0xff) == 0xff)) {
+	if ((word & 0xff) == 0xff) {
 		word >>= 8;
 		nr += 8;
 	}
@@ -549,16 +549,16 @@ static inline unsigned long __ffz_word(unsigned long nr, unsigned long word)
 static inline unsigned long __ffs_word(unsigned long nr, unsigned long word)
 {
 #ifdef __s390x__
-	if (likely((word & 0xffffffff) == 0)) {
+	if ((word & 0xffffffff) == 0) {
 		word >>= 32;
 		nr += 32;
 	}
 #endif
-	if (likely((word & 0xffff) == 0)) {
+	if ((word & 0xffff) == 0) {
 		word >>= 16;
 		nr += 16;
 	}
-	if (likely((word & 0xff) == 0)) {
+	if ((word & 0xff) == 0) {
 		word >>= 8;
 		nr += 8;
 	}
diff --git a/arch/s390/include/asm/crw.h b/arch/s390/include/asm/crw.h
new file mode 100644
index 00000000000..2185a6d619d
--- /dev/null
+++ b/arch/s390/include/asm/crw.h
@@ -0,0 +1,68 @@
+/*
+ *   Data definitions for channel report processing
+ *    Copyright IBM Corp. 2000,2009
+ *    Author(s): Ingo Adlung <adlung@de.ibm.com>,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Cornelia Huck <cornelia.huck@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
+ */
+
+#ifndef _ASM_S390_CRW_H
+#define _ASM_S390_CRW_H
+
+#include <linux/types.h>
+
+/*
+ * Channel Report Word
+ */
+struct crw {
+	__u32 res1 :  1;   /* reserved zero */
+	__u32 slct :  1;   /* solicited */
+	__u32 oflw :  1;   /* overflow */
+	__u32 chn  :  1;   /* chained */
+	__u32 rsc  :  4;   /* reporting source code */
+	__u32 anc  :  1;   /* ancillary report */
+	__u32 res2 :  1;   /* reserved zero */
+	__u32 erc  :  6;   /* error-recovery code */
+	__u32 rsid : 16;   /* reporting-source ID */
+} __attribute__ ((packed));
+
+typedef void (*crw_handler_t)(struct crw *, struct crw *, int);
+
+extern int crw_register_handler(int rsc, crw_handler_t handler);
+extern void crw_unregister_handler(int rsc);
+extern void crw_handle_channel_report(void);
+
+#define NR_RSCS 16
+
+#define CRW_RSC_MONITOR  0x2  /* monitoring facility */
+#define CRW_RSC_SCH	 0x3  /* subchannel */
+#define CRW_RSC_CPATH	 0x4  /* channel path */
+#define CRW_RSC_CONFIG	 0x9  /* configuration-alert facility */
+#define CRW_RSC_CSS	 0xB  /* channel subsystem */
+
+#define CRW_ERC_EVENT	 0x00 /* event information pending */
+#define CRW_ERC_AVAIL	 0x01 /* available */
+#define CRW_ERC_INIT	 0x02 /* initialized */
+#define CRW_ERC_TERROR	 0x03 /* temporary error */
+#define CRW_ERC_IPARM	 0x04 /* installed parm initialized */
+#define CRW_ERC_TERM	 0x05 /* terminal */
+#define CRW_ERC_PERRN	 0x06 /* perm. error, fac. not init */
+#define CRW_ERC_PERRI	 0x07 /* perm. error, facility init */
+#define CRW_ERC_PMOD	 0x08 /* installed parameters modified */
+
+static inline int stcrw(struct crw *pcrw)
+{
+	int ccode;
+
+	asm volatile(
+		"	stcrw	0(%2)\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (ccode), "=m" (*pcrw)
+		: "a" (pcrw)
+		: "cc" );
+	return ccode;
+}
+
+#endif /* _ASM_S390_CRW_H */
diff --git a/arch/s390/include/asm/dasd.h b/arch/s390/include/asm/dasd.h
index e2db6f16d9c..218bce81ec7 100644
--- a/arch/s390/include/asm/dasd.h
+++ b/arch/s390/include/asm/dasd.h
@@ -162,15 +162,15 @@ typedef struct dasd_profile_info_t {
         unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */
 } dasd_profile_info_t;
 
-/* 
+/*
  * struct format_data_t
  * represents all data necessary to format a dasd
  */
 typedef struct format_data_t {
-	int start_unit; /* from track */
-	int stop_unit;  /* to track */
-	int blksize;    /* sectorsize */
-        int intensity;  
+	unsigned int start_unit; /* from track */
+	unsigned int stop_unit;  /* to track */
+	unsigned int blksize;	 /* sectorsize */
+	unsigned int intensity;
 } format_data_t;
 
 /*
diff --git a/arch/s390/include/asm/idals.h b/arch/s390/include/asm/idals.h
index e82c10efe65..aae276d0038 100644
--- a/arch/s390/include/asm/idals.h
+++ b/arch/s390/include/asm/idals.h
@@ -44,24 +44,18 @@ idal_is_needed(void *vaddr, unsigned int length)
 /*
  * Return the number of idal words needed for an address/length pair.
  */
-static inline unsigned int
-idal_nr_words(void *vaddr, unsigned int length)
+static inline unsigned int idal_nr_words(void *vaddr, unsigned int length)
 {
-#ifdef __s390x__
-	if (idal_is_needed(vaddr, length))
-		return ((__pa(vaddr) & (IDA_BLOCK_SIZE-1)) + length + 
-			(IDA_BLOCK_SIZE-1)) >> IDA_SIZE_LOG;
-#endif
-	return 0;
+	return ((__pa(vaddr) & (IDA_BLOCK_SIZE-1)) + length +
+		(IDA_BLOCK_SIZE-1)) >> IDA_SIZE_LOG;
 }
 
 /*
  * Create the list of idal words for an address/length pair.
  */
-static inline unsigned long *
-idal_create_words(unsigned long *idaws, void *vaddr, unsigned int length)
+static inline unsigned long *idal_create_words(unsigned long *idaws,
+					       void *vaddr, unsigned int length)
 {
-#ifdef __s390x__
 	unsigned long paddr;
 	unsigned int cidaw;
 
@@ -74,7 +68,6 @@ idal_create_words(unsigned long *idaws, void *vaddr, unsigned int length)
 		paddr += IDA_BLOCK_SIZE;
 		*idaws++ = paddr;
 	}
-#endif
 	return idaws;
 }
 
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index e1f54654e3a..0b2f829f6d5 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -42,4 +42,11 @@ struct kvm_fpu {
 	__u64 fprs[16];
 };
 
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3c55e4107dc..c6e674f5fca 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -21,9 +21,6 @@
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
 
-struct kvm_guest_debug {
-};
-
 struct sca_entry {
 	atomic_t scn;
 	__u64	reserved;
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index f3720defdd1..b349f1c7fdf 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -11,129 +11,118 @@
 #ifndef _ASM_S390_LOWCORE_H
 #define _ASM_S390_LOWCORE_H
 
-#ifndef __s390x__
-#define __LC_EXT_OLD_PSW                0x018
-#define __LC_SVC_OLD_PSW                0x020
-#define __LC_PGM_OLD_PSW                0x028
-#define __LC_MCK_OLD_PSW                0x030
-#define __LC_IO_OLD_PSW                 0x038
-#define __LC_EXT_NEW_PSW                0x058
-#define __LC_SVC_NEW_PSW                0x060
-#define __LC_PGM_NEW_PSW                0x068
-#define __LC_MCK_NEW_PSW                0x070
-#define __LC_IO_NEW_PSW                 0x078
-#else /* !__s390x__ */
-#define __LC_EXT_OLD_PSW                0x0130
-#define __LC_SVC_OLD_PSW                0x0140
-#define __LC_PGM_OLD_PSW                0x0150
-#define __LC_MCK_OLD_PSW                0x0160
-#define __LC_IO_OLD_PSW                 0x0170
-#define __LC_EXT_NEW_PSW                0x01b0
-#define __LC_SVC_NEW_PSW                0x01c0
-#define __LC_PGM_NEW_PSW                0x01d0
-#define __LC_MCK_NEW_PSW                0x01e0
-#define __LC_IO_NEW_PSW                 0x01f0
-#endif /* !__s390x__ */
-
-#define __LC_IPL_PARMBLOCK_PTR		0x014
-#define __LC_EXT_PARAMS                 0x080
-#define __LC_CPU_ADDRESS                0x084
-#define __LC_EXT_INT_CODE               0x086
-
-#define __LC_SVC_ILC                    0x088
-#define __LC_SVC_INT_CODE               0x08A
-#define __LC_PGM_ILC                    0x08C
-#define __LC_PGM_INT_CODE               0x08E
+#define __LC_IPL_PARMBLOCK_PTR		0x0014
+#define __LC_EXT_PARAMS			0x0080
+#define __LC_CPU_ADDRESS		0x0084
+#define __LC_EXT_INT_CODE		0x0086
 
-#define __LC_PER_ATMID			0x096
-#define __LC_PER_ADDRESS		0x098
-#define __LC_PER_ACCESS_ID		0x0A1
-#define __LC_AR_MODE_ID			0x0A3
+#define __LC_SVC_ILC			0x0088
+#define __LC_SVC_INT_CODE		0x008a
+#define __LC_PGM_ILC			0x008c
+#define __LC_PGM_INT_CODE		0x008e
 
-#define __LC_SUBCHANNEL_ID              0x0B8
-#define __LC_SUBCHANNEL_NR              0x0BA
-#define __LC_IO_INT_PARM                0x0BC
-#define __LC_IO_INT_WORD                0x0C0
-#define __LC_MCCK_CODE                  0x0E8
+#define __LC_PER_ATMID			0x0096
+#define __LC_PER_ADDRESS		0x0098
+#define __LC_PER_ACCESS_ID		0x00a1
+#define __LC_AR_MODE_ID			0x00a3
 
-#define __LC_LAST_BREAK 		0x110
-
-#define __LC_RETURN_PSW                 0x200
-
-#define __LC_SAVE_AREA                  0xC00
-
-#ifndef __s390x__
-#define __LC_IRB			0x208
-#define __LC_SYNC_ENTER_TIMER		0x248
-#define __LC_ASYNC_ENTER_TIMER		0x250
-#define __LC_EXIT_TIMER			0x258
-#define __LC_USER_TIMER			0x260
-#define __LC_SYSTEM_TIMER		0x268
-#define __LC_STEAL_TIMER		0x270
-#define __LC_LAST_UPDATE_TIMER		0x278
-#define __LC_LAST_UPDATE_CLOCK		0x280
-#define __LC_RETURN_MCCK_PSW            0x288
-#define __LC_KERNEL_STACK               0xC40
-#define __LC_THREAD_INFO		0xC44
-#define __LC_ASYNC_STACK                0xC48
-#define __LC_KERNEL_ASCE		0xC4C
-#define __LC_USER_ASCE			0xC50
-#define __LC_PANIC_STACK                0xC54
-#define __LC_CPUID                      0xC60
-#define __LC_CPUADDR                    0xC68
-#define __LC_IPLDEV                     0xC7C
-#define __LC_CURRENT			0xC90
-#define __LC_INT_CLOCK			0xC98
-#else /* __s390x__ */
-#define __LC_IRB			0x210
-#define __LC_SYNC_ENTER_TIMER		0x250
-#define __LC_ASYNC_ENTER_TIMER		0x258
-#define __LC_EXIT_TIMER			0x260
-#define __LC_USER_TIMER			0x268
-#define __LC_SYSTEM_TIMER		0x270
-#define __LC_STEAL_TIMER		0x278
-#define __LC_LAST_UPDATE_TIMER		0x280
-#define __LC_LAST_UPDATE_CLOCK		0x288
-#define __LC_RETURN_MCCK_PSW            0x290
-#define __LC_KERNEL_STACK               0xD40
-#define __LC_THREAD_INFO		0xD48
-#define __LC_ASYNC_STACK                0xD50
-#define __LC_KERNEL_ASCE		0xD58
-#define __LC_USER_ASCE			0xD60
-#define __LC_PANIC_STACK                0xD68
-#define __LC_CPUID			0xD80
-#define __LC_CPUADDR			0xD88
-#define __LC_IPLDEV                     0xDB8
-#define __LC_CURRENT			0xDD8
-#define __LC_INT_CLOCK			0xDE8
-#define __LC_VDSO_PER_CPU		0xE38
-#endif /* __s390x__ */
+#define __LC_SUBCHANNEL_ID		0x00b8
+#define __LC_SUBCHANNEL_NR		0x00ba
+#define __LC_IO_INT_PARM		0x00bc
+#define __LC_IO_INT_WORD		0x00c0
+#define __LC_MCCK_CODE			0x00e8
 
-#define __LC_PASTE			0xE40
+#define __LC_DUMP_REIPL			0x0e00
 
-#define __LC_PANIC_MAGIC		0xE00
 #ifndef __s390x__
-#define __LC_PFAULT_INTPARM             0x080
-#define __LC_CPU_TIMER_SAVE_AREA        0x0D8
-#define __LC_CLOCK_COMP_SAVE_AREA	0x0E0
-#define __LC_PSW_SAVE_AREA		0x100
-#define __LC_PREFIX_SAVE_AREA		0x108
-#define __LC_AREGS_SAVE_AREA            0x120
-#define __LC_FPREGS_SAVE_AREA		0x160
-#define __LC_GPREGS_SAVE_AREA           0x180
-#define __LC_CREGS_SAVE_AREA            0x1C0
+#define __LC_EXT_OLD_PSW		0x0018
+#define __LC_SVC_OLD_PSW		0x0020
+#define __LC_PGM_OLD_PSW		0x0028
+#define __LC_MCK_OLD_PSW		0x0030
+#define __LC_IO_OLD_PSW			0x0038
+#define __LC_EXT_NEW_PSW		0x0058
+#define __LC_SVC_NEW_PSW		0x0060
+#define __LC_PGM_NEW_PSW		0x0068
+#define __LC_MCK_NEW_PSW		0x0070
+#define __LC_IO_NEW_PSW			0x0078
+#define __LC_SAVE_AREA			0x0200
+#define __LC_RETURN_PSW			0x0240
+#define __LC_RETURN_MCCK_PSW		0x0248
+#define __LC_SYNC_ENTER_TIMER		0x0250
+#define __LC_ASYNC_ENTER_TIMER		0x0258
+#define __LC_EXIT_TIMER			0x0260
+#define __LC_USER_TIMER			0x0268
+#define __LC_SYSTEM_TIMER		0x0270
+#define __LC_STEAL_TIMER		0x0278
+#define __LC_LAST_UPDATE_TIMER		0x0280
+#define __LC_LAST_UPDATE_CLOCK		0x0288
+#define __LC_CURRENT			0x0290
+#define __LC_THREAD_INFO		0x0294
+#define __LC_KERNEL_STACK		0x0298
+#define __LC_ASYNC_STACK		0x029c
+#define __LC_PANIC_STACK		0x02a0
+#define __LC_KERNEL_ASCE		0x02a4
+#define __LC_USER_ASCE			0x02a8
+#define __LC_USER_EXEC_ASCE		0x02ac
+#define __LC_CPUID			0x02b0
+#define __LC_INT_CLOCK			0x02c8
+#define __LC_IRB			0x0300
+#define __LC_PFAULT_INTPARM		0x0080
+#define __LC_CPU_TIMER_SAVE_AREA	0x00d8
+#define __LC_CLOCK_COMP_SAVE_AREA	0x00e0
+#define __LC_PSW_SAVE_AREA		0x0100
+#define __LC_PREFIX_SAVE_AREA		0x0108
+#define __LC_AREGS_SAVE_AREA		0x0120
+#define __LC_FPREGS_SAVE_AREA		0x0160
+#define __LC_GPREGS_SAVE_AREA		0x0180
+#define __LC_CREGS_SAVE_AREA		0x01c0
 #else /* __s390x__ */
-#define __LC_PFAULT_INTPARM             0x11B8
+#define __LC_LAST_BREAK			0x0110
+#define __LC_EXT_OLD_PSW		0x0130
+#define __LC_SVC_OLD_PSW		0x0140
+#define __LC_PGM_OLD_PSW		0x0150
+#define __LC_MCK_OLD_PSW		0x0160
+#define __LC_IO_OLD_PSW			0x0170
+#define __LC_EXT_NEW_PSW		0x01b0
+#define __LC_SVC_NEW_PSW		0x01c0
+#define __LC_PGM_NEW_PSW		0x01d0
+#define __LC_MCK_NEW_PSW		0x01e0
+#define __LC_IO_NEW_PSW			0x01f0
+#define __LC_SAVE_AREA			0x0200
+#define __LC_RETURN_PSW			0x0280
+#define __LC_RETURN_MCCK_PSW		0x0290
+#define __LC_SYNC_ENTER_TIMER		0x02a0
+#define __LC_ASYNC_ENTER_TIMER		0x02a8
+#define __LC_EXIT_TIMER			0x02b0
+#define __LC_USER_TIMER			0x02b8
+#define __LC_SYSTEM_TIMER		0x02c0
+#define __LC_STEAL_TIMER		0x02c8
+#define __LC_LAST_UPDATE_TIMER		0x02d0
+#define __LC_LAST_UPDATE_CLOCK		0x02d8
+#define __LC_CURRENT			0x02e0
+#define __LC_THREAD_INFO		0x02e8
+#define __LC_KERNEL_STACK		0x02f0
+#define __LC_ASYNC_STACK		0x02f8
+#define __LC_PANIC_STACK		0x0300
+#define __LC_KERNEL_ASCE		0x0308
+#define __LC_USER_ASCE			0x0310
+#define __LC_USER_EXEC_ASCE		0x0318
+#define __LC_CPUID			0x0320
+#define __LC_INT_CLOCK			0x0340
+#define __LC_VDSO_PER_CPU		0x0350
+#define __LC_IRB			0x0380
+#define __LC_PASTE			0x03c0
+#define __LC_PFAULT_INTPARM		0x11b8
 #define __LC_FPREGS_SAVE_AREA		0x1200
-#define __LC_GPREGS_SAVE_AREA           0x1280
+#define __LC_GPREGS_SAVE_AREA		0x1280
 #define __LC_PSW_SAVE_AREA		0x1300
 #define __LC_PREFIX_SAVE_AREA		0x1318
-#define __LC_FP_CREG_SAVE_AREA		0x131C
+#define __LC_FP_CREG_SAVE_AREA		0x131c
 #define __LC_TODREG_SAVE_AREA		0x1324
-#define __LC_CPU_TIMER_SAVE_AREA        0x1328
+#define __LC_CPU_TIMER_SAVE_AREA	0x1328
 #define __LC_CLOCK_COMP_SAVE_AREA	0x1331
-#define __LC_AREGS_SAVE_AREA            0x1340
-#define __LC_CREGS_SAVE_AREA            0x1380
+#define __LC_AREGS_SAVE_AREA		0x1340
+#define __LC_CREGS_SAVE_AREA		0x1380
 #endif /* __s390x__ */
 
 #ifndef __ASSEMBLY__
@@ -198,222 +187,240 @@ union save_area {
 struct _lowcore
 {
 #ifndef __s390x__
-        /* prefix area: defined by architecture */
-	psw_t        restart_psw;              /* 0x000 */
-	__u32        ccw2[4];                  /* 0x008 */
-	psw_t        external_old_psw;         /* 0x018 */
-	psw_t        svc_old_psw;              /* 0x020 */
-	psw_t        program_old_psw;          /* 0x028 */
-	psw_t        mcck_old_psw;             /* 0x030 */
-	psw_t        io_old_psw;               /* 0x038 */
-	__u8         pad1[0x58-0x40];          /* 0x040 */
-	psw_t        external_new_psw;         /* 0x058 */
-	psw_t        svc_new_psw;              /* 0x060 */
-	psw_t        program_new_psw;          /* 0x068 */
-	psw_t        mcck_new_psw;             /* 0x070 */
-	psw_t        io_new_psw;               /* 0x078 */
-	__u32        ext_params;               /* 0x080 */
-	__u16        cpu_addr;                 /* 0x084 */
-	__u16        ext_int_code;             /* 0x086 */
-        __u16        svc_ilc;                  /* 0x088 */
-        __u16        svc_code;                 /* 0x08a */
-        __u16        pgm_ilc;                  /* 0x08c */
-        __u16        pgm_code;                 /* 0x08e */
-	__u32        trans_exc_code;           /* 0x090 */
-	__u16        mon_class_num;            /* 0x094 */
-	__u16        per_perc_atmid;           /* 0x096 */
-	__u32        per_address;              /* 0x098 */
-	__u32        monitor_code;             /* 0x09c */
-	__u8         exc_access_id;            /* 0x0a0 */
-	__u8         per_access_id;            /* 0x0a1 */
-	__u8         pad2[0xB8-0xA2];          /* 0x0a2 */
-	__u16        subchannel_id;            /* 0x0b8 */
-	__u16        subchannel_nr;            /* 0x0ba */
-	__u32        io_int_parm;              /* 0x0bc */
-	__u32        io_int_word;              /* 0x0c0 */
-	__u8	     pad3[0xc8-0xc4];	       /* 0x0c4 */
-	__u32	     stfl_fac_list;	       /* 0x0c8 */
-	__u8	     pad4[0xd4-0xcc];	       /* 0x0cc */
-	__u32        extended_save_area_addr;  /* 0x0d4 */
-	__u32        cpu_timer_save_area[2];   /* 0x0d8 */
-	__u32        clock_comp_save_area[2];  /* 0x0e0 */
-	__u32        mcck_interruption_code[2]; /* 0x0e8 */
-	__u8	     pad5[0xf4-0xf0];	       /* 0x0f0 */
-	__u32        external_damage_code;     /* 0x0f4 */
-	__u32        failing_storage_address;  /* 0x0f8 */
-	__u8	     pad6[0x100-0xfc];	       /* 0x0fc */
-	__u32        st_status_fixed_logout[4];/* 0x100 */
-	__u8	     pad7[0x120-0x110];        /* 0x110 */
-	__u32        access_regs_save_area[16];/* 0x120 */
-	__u32        floating_pt_save_area[8]; /* 0x160 */
-	__u32        gpregs_save_area[16];     /* 0x180 */
-	__u32        cregs_save_area[16];      /* 0x1c0 */	
-
-        psw_t        return_psw;               /* 0x200 */
-	__u8	     irb[64];		       /* 0x208 */
-	__u64        sync_enter_timer;         /* 0x248 */
-	__u64        async_enter_timer;        /* 0x250 */
-	__u64        exit_timer;               /* 0x258 */
-	__u64	     user_timer;	       /* 0x260 */
-	__u64	     system_timer;	       /* 0x268 */
-	__u64	     steal_timer;	       /* 0x270 */
-	__u64	     last_update_timer;        /* 0x278 */
-	__u64	     last_update_clock;        /* 0x280 */
-        psw_t        return_mcck_psw;          /* 0x288 */
-	__u8         pad8[0xc00-0x290];        /* 0x290 */
-
-        /* System info area */
-	__u32        save_area[16];            /* 0xc00 */
-	__u32        kernel_stack;             /* 0xc40 */
-	__u32        thread_info;              /* 0xc44 */
-	__u32        async_stack;              /* 0xc48 */
-	__u32        kernel_asce;              /* 0xc4c */
-	__u32        user_asce;                /* 0xc50 */
-	__u32        panic_stack;              /* 0xc54 */
-	__u32	     user_exec_asce;	       /* 0xc58 */
-	__u8	     pad10[0xc60-0xc5c];       /* 0xc5c */
-	/* entry.S sensitive area start */
-	struct       cpuinfo_S390 cpu_data;    /* 0xc60 */
-	__u32        ipl_device;               /* 0xc7c */
-	/* entry.S sensitive area end */
-
-        /* SMP info area: defined by DJB */
-	__u64	     clock_comparator;	       /* 0xc80 */
-	__u32        ext_call_fast;            /* 0xc88 */
-	__u32        percpu_offset;            /* 0xc8c */
-	__u32        current_task;	       /* 0xc90 */
-	__u32        softirq_pending;	       /* 0xc94 */
-	__u64        int_clock;                /* 0xc98 */
-        __u8         pad11[0xe00-0xca0];       /* 0xca0 */
-
-        /* 0xe00 is used as indicator for dump tools */
-        /* whether the kernel died with panic() or not */
-        __u32        panic_magic;              /* 0xe00 */
-
-        /* Align to the top 1k of prefix area */
-	__u8         pad12[0x1000-0xe04];      /* 0xe04 */
+	/* 0x0000 - 0x01ff: defined by architecture */
+	psw_t	restart_psw;			/* 0x0000 */
+	__u32	ccw2[4];			/* 0x0008 */
+	psw_t	external_old_psw;		/* 0x0018 */
+	psw_t	svc_old_psw;			/* 0x0020 */
+	psw_t	program_old_psw;		/* 0x0028 */
+	psw_t	mcck_old_psw;			/* 0x0030 */
+	psw_t	io_old_psw;			/* 0x0038 */
+	__u8	pad_0x0040[0x0058-0x0040];	/* 0x0040 */
+	psw_t	external_new_psw;		/* 0x0058 */
+	psw_t	svc_new_psw;			/* 0x0060 */
+	psw_t	program_new_psw;		/* 0x0068 */
+	psw_t	mcck_new_psw;			/* 0x0070 */
+	psw_t	io_new_psw;			/* 0x0078 */
+	__u32	ext_params;			/* 0x0080 */
+	__u16	cpu_addr;			/* 0x0084 */
+	__u16	ext_int_code;			/* 0x0086 */
+	__u16	svc_ilc;			/* 0x0088 */
+	__u16	svc_code;			/* 0x008a */
+	__u16	pgm_ilc;			/* 0x008c */
+	__u16	pgm_code;			/* 0x008e */
+	__u32	trans_exc_code;			/* 0x0090 */
+	__u16	mon_class_num;			/* 0x0094 */
+	__u16	per_perc_atmid;			/* 0x0096 */
+	__u32	per_address;			/* 0x0098 */
+	__u32	monitor_code;			/* 0x009c */
+	__u8	exc_access_id;			/* 0x00a0 */
+	__u8	per_access_id;			/* 0x00a1 */
+	__u8	pad_0x00a2[0x00b8-0x00a2];	/* 0x00a2 */
+	__u16	subchannel_id;			/* 0x00b8 */
+	__u16	subchannel_nr;			/* 0x00ba */
+	__u32	io_int_parm;			/* 0x00bc */
+	__u32	io_int_word;			/* 0x00c0 */
+	__u8	pad_0x00c4[0x00c8-0x00c4];	/* 0x00c4 */
+	__u32	stfl_fac_list;			/* 0x00c8 */
+	__u8	pad_0x00cc[0x00d4-0x00cc];	/* 0x00cc */
+	__u32	extended_save_area_addr;	/* 0x00d4 */
+	__u32	cpu_timer_save_area[2];		/* 0x00d8 */
+	__u32	clock_comp_save_area[2];	/* 0x00e0 */
+	__u32	mcck_interruption_code[2];	/* 0x00e8 */
+	__u8	pad_0x00f0[0x00f4-0x00f0];	/* 0x00f0 */
+	__u32	external_damage_code;		/* 0x00f4 */
+	__u32	failing_storage_address;	/* 0x00f8 */
+	__u8	pad_0x00fc[0x0100-0x00fc];	/* 0x00fc */
+	__u32	st_status_fixed_logout[4];	/* 0x0100 */
+	__u8	pad_0x0110[0x0120-0x0110];	/* 0x0110 */
+
+	/* CPU register save area: defined by architecture */
+	__u32	access_regs_save_area[16];	/* 0x0120 */
+	__u32	floating_pt_save_area[8];	/* 0x0160 */
+	__u32	gpregs_save_area[16];		/* 0x0180 */
+	__u32	cregs_save_area[16];		/* 0x01c0 */
+
+	/* Return psws. */
+	__u32	save_area[16];			/* 0x0200 */
+	psw_t	return_psw;			/* 0x0240 */
+	psw_t	return_mcck_psw;		/* 0x0248 */
+
+	/* CPU time accounting values */
+	__u64	sync_enter_timer;		/* 0x0250 */
+	__u64	async_enter_timer;		/* 0x0258 */
+	__u64	exit_timer;			/* 0x0260 */
+	__u64	user_timer;			/* 0x0268 */
+	__u64	system_timer;			/* 0x0270 */
+	__u64	steal_timer;			/* 0x0278 */
+	__u64	last_update_timer;		/* 0x0280 */
+	__u64	last_update_clock;		/* 0x0288 */
+
+	/* Current process. */
+	__u32	current_task;			/* 0x0290 */
+	__u32	thread_info;			/* 0x0294 */
+	__u32	kernel_stack;			/* 0x0298 */
+
+	/* Interrupt and panic stack. */
+	__u32	async_stack;			/* 0x029c */
+	__u32	panic_stack;			/* 0x02a0 */
+
+	/* Address space pointer. */
+	__u32	kernel_asce;			/* 0x02a4 */
+	__u32	user_asce;			/* 0x02a8 */
+	__u32	user_exec_asce;			/* 0x02ac */
+
+	/* SMP info area */
+	cpuid_t	cpu_id;				/* 0x02b0 */
+	__u32	cpu_nr;				/* 0x02b8 */
+	__u32	softirq_pending;		/* 0x02bc */
+	__u32	percpu_offset;			/* 0x02c0 */
+	__u32	ext_call_fast;			/* 0x02c4 */
+	__u64	int_clock;			/* 0x02c8 */
+	__u64	clock_comparator;		/* 0x02d0 */
+	__u8	pad_0x02d8[0x0300-0x02d8];	/* 0x02d8 */
+
+	/* Interrupt response block */
+	__u8	irb[64];			/* 0x0300 */
+
+	__u8	pad_0x0400[0x0e00-0x0400];	/* 0x0400 */
+
+	/*
+	 * 0xe00 contains the address of the IPL Parameter Information
+	 * block. Dump tools need IPIB for IPL after dump.
+	 * Note: do not change the position of any fields in 0x0e00-0x0f00
+	 */
+	__u32	ipib;				/* 0x0e00 */
+	__u32	ipib_checksum;			/* 0x0e04 */
+
+	/* Align to the top 1k of prefix area */
+	__u8	pad_0x0e08[0x1000-0x0e08];	/* 0x0e08 */
 #else /* !__s390x__ */
-        /* prefix area: defined by architecture */
-	__u32        ccw1[2];                  /* 0x000 */
-	__u32        ccw2[4];                  /* 0x008 */
-	__u8         pad1[0x80-0x18];          /* 0x018 */
-	__u32        ext_params;               /* 0x080 */
-	__u16        cpu_addr;                 /* 0x084 */
-	__u16        ext_int_code;             /* 0x086 */
-        __u16        svc_ilc;                  /* 0x088 */
-        __u16        svc_code;                 /* 0x08a */
-        __u16        pgm_ilc;                  /* 0x08c */
-        __u16        pgm_code;                 /* 0x08e */
-	__u32        data_exc_code;            /* 0x090 */
-	__u16        mon_class_num;            /* 0x094 */
-	__u16        per_perc_atmid;           /* 0x096 */
-	addr_t       per_address;              /* 0x098 */
-	__u8         exc_access_id;            /* 0x0a0 */
-	__u8         per_access_id;            /* 0x0a1 */
-	__u8         op_access_id;             /* 0x0a2 */
-	__u8         ar_access_id;             /* 0x0a3 */
-	__u8         pad2[0xA8-0xA4];          /* 0x0a4 */
-	addr_t       trans_exc_code;           /* 0x0A0 */
-	addr_t       monitor_code;             /* 0x09c */
-	__u16        subchannel_id;            /* 0x0b8 */
-	__u16        subchannel_nr;            /* 0x0ba */
-	__u32        io_int_parm;              /* 0x0bc */
-	__u32        io_int_word;              /* 0x0c0 */
-	__u8         pad3[0xc8-0xc4];          /* 0x0c4 */
-	__u32        stfl_fac_list;            /* 0x0c8 */
-	__u8         pad4[0xe8-0xcc];          /* 0x0cc */
-	__u32        mcck_interruption_code[2]; /* 0x0e8 */
-	__u8         pad5[0xf4-0xf0];          /* 0x0f0 */
-	__u32        external_damage_code;     /* 0x0f4 */
-	addr_t       failing_storage_address;  /* 0x0f8 */
-	__u8         pad6[0x120-0x100];        /* 0x100 */
-	psw_t        restart_old_psw;          /* 0x120 */
-	psw_t        external_old_psw;         /* 0x130 */
-	psw_t        svc_old_psw;              /* 0x140 */
-	psw_t        program_old_psw;          /* 0x150 */
-	psw_t        mcck_old_psw;             /* 0x160 */
-	psw_t        io_old_psw;               /* 0x170 */
-	__u8         pad7[0x1a0-0x180];        /* 0x180 */
-	psw_t        restart_psw;              /* 0x1a0 */
-	psw_t        external_new_psw;         /* 0x1b0 */
-	psw_t        svc_new_psw;              /* 0x1c0 */
-	psw_t        program_new_psw;          /* 0x1d0 */
-	psw_t        mcck_new_psw;             /* 0x1e0 */
-	psw_t        io_new_psw;               /* 0x1f0 */
-        psw_t        return_psw;               /* 0x200 */
-	__u8	     irb[64];		       /* 0x210 */
-	__u64        sync_enter_timer;         /* 0x250 */
-	__u64        async_enter_timer;        /* 0x258 */
-	__u64        exit_timer;               /* 0x260 */
-	__u64	     user_timer;	       /* 0x268 */
-	__u64	     system_timer;	       /* 0x270 */
-	__u64	     steal_timer;	       /* 0x278 */
-	__u64	     last_update_timer;        /* 0x280 */
-	__u64	     last_update_clock;        /* 0x288 */
-        psw_t        return_mcck_psw;          /* 0x290 */
-        __u8         pad8[0xc00-0x2a0];        /* 0x2a0 */
-        /* System info area */
-	__u64        save_area[16];            /* 0xc00 */
-        __u8         pad9[0xd40-0xc80];        /* 0xc80 */
- 	__u64        kernel_stack;             /* 0xd40 */
-	__u64        thread_info;              /* 0xd48 */
-	__u64        async_stack;              /* 0xd50 */
-	__u64        kernel_asce;              /* 0xd58 */
-	__u64        user_asce;                /* 0xd60 */
-	__u64        panic_stack;              /* 0xd68 */
-	__u64	     user_exec_asce;	       /* 0xd70 */
-	__u8	     pad10[0xd80-0xd78];       /* 0xd78 */
-	/* entry.S sensitive area start */
-	struct       cpuinfo_S390 cpu_data;    /* 0xd80 */
-	__u32        ipl_device;               /* 0xdb8 */
-	__u32        pad11;                    /* 0xdbc */
-	/* entry.S sensitive area end */
-
-        /* SMP info area: defined by DJB */
-	__u64	     clock_comparator;	       /* 0xdc0 */
-	__u64        ext_call_fast;            /* 0xdc8 */
-	__u64        percpu_offset;            /* 0xdd0 */
-	__u64        current_task;	       /* 0xdd8 */
-	__u32	     softirq_pending;	       /* 0xde0 */
-	__u32	     pad_0x0de4;	       /* 0xde4 */
-	__u64        int_clock;                /* 0xde8 */
-        __u8         pad12[0xe00-0xdf0];       /* 0xdf0 */
-
-        /* 0xe00 is used as indicator for dump tools */
-        /* whether the kernel died with panic() or not */
-        __u32        panic_magic;              /* 0xe00 */
+	/* 0x0000 - 0x01ff: defined by architecture */
+	__u32	ccw1[2];			/* 0x0000 */
+	__u32	ccw2[4];			/* 0x0008 */
+	__u8	pad_0x0018[0x0080-0x0018];	/* 0x0018 */
+	__u32	ext_params;			/* 0x0080 */
+	__u16	cpu_addr;			/* 0x0084 */
+	__u16	ext_int_code;			/* 0x0086 */
+	__u16	svc_ilc;			/* 0x0088 */
+	__u16	svc_code;			/* 0x008a */
+	__u16	pgm_ilc;			/* 0x008c */
+	__u16	pgm_code;			/* 0x008e */
+	__u32	data_exc_code;			/* 0x0090 */
+	__u16	mon_class_num;			/* 0x0094 */
+	__u16	per_perc_atmid;			/* 0x0096 */
+	addr_t	per_address;			/* 0x0098 */
+	__u8	exc_access_id;			/* 0x00a0 */
+	__u8	per_access_id;			/* 0x00a1 */
+	__u8	op_access_id;			/* 0x00a2 */
+	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	pad_0x00a4[0x00a8-0x00a4];	/* 0x00a4 */
+	addr_t	trans_exc_code;			/* 0x00a8 */
+	addr_t	monitor_code;			/* 0x00b0 */
+	__u16	subchannel_id;			/* 0x00b8 */
+	__u16	subchannel_nr;			/* 0x00ba */
+	__u32	io_int_parm;			/* 0x00bc */
+	__u32	io_int_word;			/* 0x00c0 */
+	__u8	pad_0x00c4[0x00c8-0x00c4];	/* 0x00c4 */
+	__u32	stfl_fac_list;			/* 0x00c8 */
+	__u8	pad_0x00cc[0x00e8-0x00cc];	/* 0x00cc */
+	__u32	mcck_interruption_code[2];	/* 0x00e8 */
+	__u8	pad_0x00f0[0x00f4-0x00f0];	/* 0x00f0 */
+	__u32	external_damage_code;		/* 0x00f4 */
+	addr_t	failing_storage_address;	/* 0x00f8 */
+	__u8	pad_0x0100[0x0120-0x0100];	/* 0x0100 */
+	psw_t	restart_old_psw;		/* 0x0120 */
+	psw_t	external_old_psw;		/* 0x0130 */
+	psw_t	svc_old_psw;			/* 0x0140 */
+	psw_t	program_old_psw;		/* 0x0150 */
+	psw_t	mcck_old_psw;			/* 0x0160 */
+	psw_t	io_old_psw;			/* 0x0170 */
+	__u8	pad_0x0180[0x01a0-0x0180];	/* 0x0180 */
+	psw_t	restart_psw;			/* 0x01a0 */
+	psw_t	external_new_psw;		/* 0x01b0 */
+	psw_t	svc_new_psw;			/* 0x01c0 */
+	psw_t	program_new_psw;		/* 0x01d0 */
+	psw_t	mcck_new_psw;			/* 0x01e0 */
+	psw_t	io_new_psw;			/* 0x01f0 */
+
+	/* Entry/exit save area & return psws. */
+	__u64	save_area[16];			/* 0x0200 */
+	psw_t	return_psw;			/* 0x0280 */
+	psw_t	return_mcck_psw;		/* 0x0290 */
+
+	/* CPU accounting and timing values. */
+	__u64	sync_enter_timer;		/* 0x02a0 */
+	__u64	async_enter_timer;		/* 0x02a8 */
+	__u64	exit_timer;			/* 0x02b0 */
+	__u64	user_timer;			/* 0x02b8 */
+	__u64	system_timer;			/* 0x02c0 */
+	__u64	steal_timer;			/* 0x02c8 */
+	__u64	last_update_timer;		/* 0x02d0 */
+	__u64	last_update_clock;		/* 0x02d8 */
+
+	/* Current process. */
+	__u64	current_task;			/* 0x02e0 */
+	__u64	thread_info;			/* 0x02e8 */
+	__u64	kernel_stack;			/* 0x02f0 */
+
+	/* Interrupt and panic stack. */
+	__u64	async_stack;			/* 0x02f8 */
+	__u64	panic_stack;			/* 0x0300 */
+
+	/* Address space pointer. */
+	__u64	kernel_asce;			/* 0x0308 */
+	__u64	user_asce;			/* 0x0310 */
+	__u64	user_exec_asce;			/* 0x0318 */
+
+	/* SMP info area */
+	cpuid_t	cpu_id;				/* 0x0320 */
+	__u32	cpu_nr;				/* 0x0328 */
+	__u32	softirq_pending;		/* 0x032c */
+	__u64	percpu_offset;			/* 0x0330 */
+	__u64	ext_call_fast;			/* 0x0338 */
+	__u64	int_clock;			/* 0x0340 */
+	__u64	clock_comparator;		/* 0x0348 */
+	__u64	vdso_per_cpu_data;		/* 0x0350 */
+	__u8	pad_0x0358[0x0380-0x0358];	/* 0x0358 */
+
+	/* Interrupt response block. */
+	__u8	irb[64];			/* 0x0380 */
 
 	/* Per cpu primary space access list */
-	__u8	     pad_0xe04[0xe38-0xe04];   /* 0xe04 */
-	__u64	     vdso_per_cpu_data;	       /* 0xe38 */
-	__u32	     paste[16];		       /* 0xe40 */
-
-	__u8	     pad13[0x11b8-0xe80];      /* 0xe80 */
-
-	/* 64 bit extparam used for pfault, diag 250 etc  */
-	__u64        ext_params2;               /* 0x11B8 */
-
-	__u8         pad14[0x1200-0x11C0];      /* 0x11C0 */
-
-        /* System info area */ 
-
-	__u64        floating_pt_save_area[16]; /* 0x1200 */
-	__u64        gpregs_save_area[16];      /* 0x1280 */
-	__u32        st_status_fixed_logout[4]; /* 0x1300 */
-	__u8         pad15[0x1318-0x1310];      /* 0x1310 */
-	__u32        prefixreg_save_area;       /* 0x1318 */
-	__u32        fpt_creg_save_area;        /* 0x131c */
-	__u8         pad16[0x1324-0x1320];      /* 0x1320 */
-	__u32        tod_progreg_save_area;     /* 0x1324 */
-	__u32        cpu_timer_save_area[2];    /* 0x1328 */
-	__u32        clock_comp_save_area[2];   /* 0x1330 */
-	__u8         pad17[0x1340-0x1338];      /* 0x1338 */
-	__u32        access_regs_save_area[16]; /* 0x1340 */ 
-	__u64        cregs_save_area[16];       /* 0x1380 */
+	__u32	paste[16];			/* 0x03c0 */
+
+	__u8	pad_0x0400[0x0e00-0x0400];	/* 0x0400 */
+
+	/*
+	 * 0xe00 contains the address of the IPL Parameter Information
+	 * block. Dump tools need IPIB for IPL after dump.
+	 * Note: do not change the position of any fields in 0x0e00-0x0f00
+	 */
+	__u64	ipib;				/* 0x0e00 */
+	__u32	ipib_checksum;			/* 0x0e08 */
+	__u8	pad_0x0e0c[0x11b8-0x0e0c];	/* 0x0e0c */
+
+	/* 64 bit extparam used for pfault/diag 250: defined by architecture */
+	__u64	ext_params2;			/* 0x11B8 */
+	__u8	pad_0x11c0[0x1200-0x11C0];	/* 0x11C0 */
+
+	/* CPU register save area: defined by architecture */
+	__u64	floating_pt_save_area[16];	/* 0x1200 */
+	__u64	gpregs_save_area[16];		/* 0x1280 */
+	__u32	st_status_fixed_logout[4];	/* 0x1300 */
+	__u8	pad_0x1310[0x1318-0x1310];	/* 0x1310 */
+	__u32	prefixreg_save_area;		/* 0x1318 */
+	__u32	fpt_creg_save_area;		/* 0x131c */
+	__u8	pad_0x1320[0x1324-0x1320];	/* 0x1320 */
+	__u32	tod_progreg_save_area;		/* 0x1324 */
+	__u32	cpu_timer_save_area[2];		/* 0x1328 */
+	__u32	clock_comp_save_area[2];	/* 0x1330 */
+	__u8	pad_0x1338[0x1340-0x1338];	/* 0x1338 */
+	__u32	access_regs_save_area[16];	/* 0x1340 */
+	__u64	cregs_save_area[16];		/* 0x1380 */
 
 	/* align to the top of the prefix area */
-
-	__u8         pad18[0x2000-0x1400];      /* 0x1400 */
+	__u8	pad_0x1400[0x2000-0x1400];	/* 0x1400 */
 #endif /* !__s390x__ */
 } __attribute__((packed)); /* End structure*/
 
@@ -433,8 +440,6 @@ static inline __u32 store_prefix(void)
 	return address;
 }
 
-#define __PANIC_MAGIC           0xDEADC0DE
-
 #endif
 
 #endif
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 28ec870655a..fc7edd6f41b 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -74,7 +74,7 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
-	cpu_set(smp_processor_id(), next->cpu_vm_mask);
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
 	update_mm(next, tsk);
 }
 
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
new file mode 100644
index 00000000000..f4b60441adc
--- /dev/null
+++ b/arch/s390/include/asm/nmi.h
@@ -0,0 +1,66 @@
+/*
+ *   Machine check handler definitions
+ *
+ *    Copyright IBM Corp. 2000,2009
+ *    Author(s): Ingo Adlung <adlung@de.ibm.com>,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Cornelia Huck <cornelia.huck@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
+ */
+
+#ifndef _ASM_S390_NMI_H
+#define _ASM_S390_NMI_H
+
+#include <linux/types.h>
+
+struct mci {
+	__u32 sd :  1; /* 00 system damage */
+	__u32 pd :  1; /* 01 instruction-processing damage */
+	__u32 sr :  1; /* 02 system recovery */
+	__u32	 :  1; /* 03 */
+	__u32 cd :  1; /* 04 timing-facility damage */
+	__u32 ed :  1; /* 05 external damage */
+	__u32	 :  1; /* 06 */
+	__u32 dg :  1; /* 07 degradation */
+	__u32 w  :  1; /* 08 warning pending */
+	__u32 cp :  1; /* 09 channel-report pending */
+	__u32 sp :  1; /* 10 service-processor damage */
+	__u32 ck :  1; /* 11 channel-subsystem damage */
+	__u32	 :  2; /* 12-13 */
+	__u32 b  :  1; /* 14 backed up */
+	__u32	 :  1; /* 15 */
+	__u32 se :  1; /* 16 storage error uncorrected */
+	__u32 sc :  1; /* 17 storage error corrected */
+	__u32 ke :  1; /* 18 storage-key error uncorrected */
+	__u32 ds :  1; /* 19 storage degradation */
+	__u32 wp :  1; /* 20 psw mwp validity */
+	__u32 ms :  1; /* 21 psw mask and key validity */
+	__u32 pm :  1; /* 22 psw program mask and cc validity */
+	__u32 ia :  1; /* 23 psw instruction address validity */
+	__u32 fa :  1; /* 24 failing storage address validity */
+	__u32	 :  1; /* 25 */
+	__u32 ec :  1; /* 26 external damage code validity */
+	__u32 fp :  1; /* 27 floating point register validity */
+	__u32 gr :  1; /* 28 general register validity */
+	__u32 cr :  1; /* 29 control register validity */
+	__u32	 :  1; /* 30 */
+	__u32 st :  1; /* 31 storage logical validity */
+	__u32 ie :  1; /* 32 indirect storage error */
+	__u32 ar :  1; /* 33 access register validity */
+	__u32 da :  1; /* 34 delayed access exception */
+	__u32	 :  7; /* 35-41 */
+	__u32 pr :  1; /* 42 tod programmable register validity */
+	__u32 fc :  1; /* 43 fp control register validity */
+	__u32 ap :  1; /* 44 ancillary report */
+	__u32	 :  1; /* 45 */
+	__u32 ct :  1; /* 46 cpu timer validity */
+	__u32 cc :  1; /* 47 clock comparator validity */
+	__u32	 : 16; /* 47-63 */
+};
+
+struct pt_regs;
+
+extern void s390_handle_mcck(void);
+extern void s390_do_machine_check(struct pt_regs *regs);
+
+#endif /* _ASM_S390_NMI_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index db4523fe38a..61862b3ac79 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -42,22 +42,8 @@ static inline void get_cpu_id(cpuid_t *ptr)
 	asm volatile("stidp 0(%1)" : "=m" (*ptr) : "a" (ptr));
 }
 
-struct cpuinfo_S390
-{
-        cpuid_t  cpu_id;
-        __u16    cpu_addr;
-        __u16    cpu_nr;
-        unsigned long loops_per_jiffy;
-        unsigned long *pgd_quick;
-#ifdef __s390x__
-        unsigned long *pmd_quick;
-#endif /* __s390x__ */
-        unsigned long *pte_quick;
-        unsigned long pgtable_cache_sz;
-};
-
 extern void s390_adjust_jiffies(void);
-extern void print_cpu_info(struct cpuinfo_S390 *);
+extern void print_cpu_info(void);
 extern int get_cpu_capability(unsigned int *);
 
 /*
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 8920025c3c0..f1b051630c5 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -172,6 +172,8 @@
 #define NUM_CRS		16
 #define NUM_ACRS	16
 
+#define NUM_CR_WORDS	3
+
 #define FPR_SIZE	8
 #define FPC_SIZE	4
 #define FPC_PAD_SIZE	4 /* gcc insists on aligning the fpregs */
@@ -334,7 +336,7 @@ struct pt_regs
  */
 typedef struct
 {
-	unsigned long cr[3];
+	unsigned long cr[NUM_CR_WORDS];
 } per_cr_words;
 
 #define PER_EM_MASK 0xE8000000UL
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 27fc1746de1..402d6dcf0d2 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -314,6 +314,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
 			    int, int, unsigned long);
 
 /* qdio errors reported to the upper-layer program */
+#define QDIO_ERROR_SIGA_TARGET			0x02
 #define QDIO_ERROR_SIGA_ACCESS_EXCEPTION	0x10
 #define QDIO_ERROR_SIGA_BUSY			0x20
 #define QDIO_ERROR_ACTIVATE_CHECK_CONDITION	0x40
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 024b91e0623..2009158a450 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -50,12 +50,7 @@ extern void machine_power_off_smp(void);
  
 #define PROC_CHANGE_PENALTY	20		/* Schedule penalty */
 
-#define raw_smp_processor_id()	(S390_lowcore.cpu_data.cpu_nr)
-
-static inline __u16 hard_smp_processor_id(void)
-{
-	return stap();
-}
+#define raw_smp_processor_id()	(S390_lowcore.cpu_nr)
 
 /*
  * returns 1 if cpu is in stopped/check stopped state or not operational
diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h
index c786ab623b2..02330c50241 100644
--- a/arch/s390/include/asm/socket.h
+++ b/arch/s390/include/asm/socket.h
@@ -62,4 +62,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h
index d074673a6d9..cd0241db5a4 100644
--- a/arch/s390/include/asm/string.h
+++ b/arch/s390/include/asm/string.h
@@ -100,6 +100,7 @@ static inline char *strcat(char *dst, const char *src)
 
 static inline char *strcpy(char *dst, const char *src)
 {
+#if __GNUC__ < 4
 	register int r0 asm("0") = 0;
 	char *ret = dst;
 
@@ -109,10 +110,14 @@ static inline char *strcpy(char *dst, const char *src)
 		: "+&a" (dst), "+&a" (src) : "d" (r0)
 		: "cc", "memory");
 	return ret;
+#else
+	return __builtin_strcpy(dst, src);
+#endif
 }
 
 static inline size_t strlen(const char *s)
 {
+#if __GNUC__ < 4
 	register unsigned long r0 asm("0") = 0;
 	const char *tmp = s;
 
@@ -121,6 +126,9 @@ static inline size_t strlen(const char *s)
 		"	jo	0b"
 		: "+d" (r0), "+a" (tmp) :  : "cc");
 	return r0 - (unsigned long) s;
+#else
+	return __builtin_strlen(s);
+#endif
 }
 
 static inline size_t strnlen(const char * s, size_t n)
@@ -135,7 +143,13 @@ static inline size_t strnlen(const char * s, size_t n)
 		: "+a" (end), "+a" (tmp) : "d" (r0)  : "cc");
 	return end - s;
 }
-
+#else /* IN_ARCH_STRING_C */
+void *memchr(const void * s, int c, size_t n);
+void *memscan(void *s, int c, size_t n);
+char *strcat(char *dst, const char *src);
+char *strcpy(char *dst, const char *src);
+size_t strlen(const char *s);
+size_t strnlen(const char * s, size_t n);
 #endif /* !IN_ARCH_STRING_C */
 
 #endif /* __KERNEL__ */
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index ad93212d9e1..9d70057d828 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -100,6 +100,7 @@ struct sysinfo_3_2_2 {
 		char reserved_1[24];
 
 	} vm[8];
+	char reserved_544[3552];
 };
 
 static inline int stsi(void *sysinfo, int fc, int sel1, int sel2)
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index d60394b9745..304cffa623e 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -51,7 +51,7 @@ static inline void __tlb_flush_full(struct mm_struct *mm)
 	 * If the process only ran on the local cpu, do a local flush.
 	 */
 	local_cpumask = cpumask_of_cpu(smp_processor_id());
-	if (cpus_equal(mm->cpu_vm_mask, local_cpumask))
+	if (cpumask_equal(mm_cpumask(mm), &local_cpumask))
 		__tlb_flush_local();
 	else
 		__tlb_flush_global();
@@ -73,7 +73,7 @@ static inline void __tlb_flush_idte(unsigned long asce)
 
 static inline void __tlb_flush_mm(struct mm_struct * mm)
 {
-	if (unlikely(cpus_empty(mm->cpu_vm_mask)))
+	if (unlikely(cpumask_empty(mm_cpumask(mm))))
 		return;
 	/*
 	 * If the machine has IDTE we prefer to do a per mm flush
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index c979c3b56ab..5e0ad618dc4 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -5,7 +5,6 @@
 
 #define mc_capable()	(1)
 
-cpumask_t cpu_coregroup_map(unsigned int cpu);
 const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
 
 extern cpumask_t cpu_core_map[NR_CPUS];
diff --git a/arch/s390/include/asm/vtoc.h b/arch/s390/include/asm/vtoc.h
index 3a5267d90d2..8406a2b3157 100644
--- a/arch/s390/include/asm/vtoc.h
+++ b/arch/s390/include/asm/vtoc.h
@@ -39,7 +39,7 @@ struct vtoc_labeldate
 	__u16 day;
 } __attribute__ ((packed));
 
-struct vtoc_volume_label
+struct vtoc_volume_label_cdl
 {
 	char volkey[4];		/* volume key = volume label */
 	char vollbl[4];		/* volume label */
@@ -56,6 +56,14 @@ struct vtoc_volume_label
 	char res3[29];		/* reserved */
 } __attribute__ ((packed));
 
+struct vtoc_volume_label_ldl {
+	char vollbl[4];		/* volume label */
+	char volid[6];		/* volume identifier */
+	char res3[69];		/* reserved */
+	char ldl_version;	/* version number, valid for ldl format */
+	__u64 formatted_blocks; /* valid when ldl_version >= f2  */
+} __attribute__ ((packed));
+
 struct vtoc_extent
 {
 	__u8 typeind;			/* extent type indicator */
@@ -140,7 +148,11 @@ struct vtoc_format4_label
 	char res2[10];		/* reserved */
 	__u8 DS4EFLVL;		/* extended free-space management level */
 	struct vtoc_cchhb DS4EFPTR; /* pointer to extended free-space info */
-	char res3[9];		/* reserved */
+	char res3;		/* reserved */
+	__u32 DS4DCYL;		/* number of logical cyls */
+	char res4[2];		/* reserved */
+	__u8 DS4DEVF2;		/* device flags */
+	char res5;		/* reserved */
 } __attribute__ ((packed));
 
 struct vtoc_ds5ext
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 3edc6c6f258..228e3105ded 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -17,10 +17,12 @@ CFLAGS_smp.o	:= -Wno-nonnull
 #
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
+CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
+
 obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o \
 	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
 	    s390_ext.o debug.o irq.o ipl.o dis.o diag.o mem_detect.o \
-	    vdso.o vtime.o
+	    vdso.o vtime.o sysinfo.o nmi.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
diff --git a/arch/s390/kernel/bitmap.S b/arch/s390/kernel/bitmap.S
deleted file mode 100644
index dfb41f946e2..00000000000
--- a/arch/s390/kernel/bitmap.S
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- *  arch/s390/kernel/bitmap.S
- *    Bitmaps for set_bit, clear_bit, test_and_set_bit, ...
- *    See include/asm-s390/{bitops.h|posix_types.h} for details
- *
- *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- */
-
-         .globl _oi_bitmap
-_oi_bitmap:
-         .byte  0x01,0x02,0x04,0x08,0x10,0x20,0x40,0x80
-
-         .globl _ni_bitmap
-_ni_bitmap:
-         .byte  0xFE,0xFD,0xFB,0xF7,0xEF,0xDF,0xBF,0x7F
-
-         .globl _zb_findmap
-_zb_findmap:
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4 
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,7
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4
-         .byte  0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,8
-
-         .globl _sb_findmap
-_sb_findmap:
-         .byte  8,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  7,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-         .byte  4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0
-
diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c
new file mode 100644
index 00000000000..3ae4757b006
--- /dev/null
+++ b/arch/s390/kernel/bitmap.c
@@ -0,0 +1,54 @@
+/*
+ *    Bitmaps for set_bit, clear_bit, test_and_set_bit, ...
+ *    See include/asm/{bitops.h|posix_types.h} for details
+ *
+ *    Copyright IBM Corp. 1999,2009
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ */
+
+#include <linux/bitops.h>
+#include <linux/module.h>
+
+const char _oi_bitmap[] = { 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80 };
+EXPORT_SYMBOL(_oi_bitmap);
+
+const char _ni_bitmap[] = { 0xfe, 0xfd, 0xfb, 0xf7, 0xef, 0xdf, 0xbf, 0x7f };
+EXPORT_SYMBOL(_ni_bitmap);
+
+const char _zb_findmap[] = {
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,7,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
+	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,8 };
+EXPORT_SYMBOL(_zb_findmap);
+
+const char _sb_findmap[] = {
+	8,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	7,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
+	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0 };
+EXPORT_SYMBOL(_sb_findmap);
diff --git a/arch/s390/kernel/compat_ptrace.h b/arch/s390/kernel/compat_ptrace.h
index a2be3a978d5..123dd660d7f 100644
--- a/arch/s390/kernel/compat_ptrace.h
+++ b/arch/s390/kernel/compat_ptrace.h
@@ -1,10 +1,11 @@
 #ifndef _PTRACE32_H
 #define _PTRACE32_H
 
+#include <asm/ptrace.h>    /* needed for NUM_CR_WORDS */
 #include "compat_linux.h"  /* needed for psw_compat_t */
 
 typedef struct {
-	__u32 cr[3];
+	__u32 cr[NUM_CR_WORDS];
 } per_cr_words32;
 
 typedef struct {
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 62c706eb0de..87cf5a79a35 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -252,7 +252,7 @@ sys32_chroot_wrapper:
 sys32_ustat_wrapper:
 	llgfr	%r2,%r2			# dev_t
 	llgtr	%r3,%r3			# struct ustat *
-	jg	sys_ustat
+	jg	compat_sys_ustat
 
 	.globl	sys32_dup2_wrapper
 sys32_dup2_wrapper:
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index ba03fc0a3a5..be8bceaf37d 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -603,7 +603,7 @@ debug_input(struct file *file, const char __user *user_buf, size_t length,
 static int
 debug_open(struct inode *inode, struct file *file)
 {
-	int i = 0, rc = 0;
+	int i, rc = 0;
 	file_private_info_t *p_info;
 	debug_info_t *debug_info, *debug_info_snapshot;
 
@@ -642,8 +642,7 @@ found:
 	p_info = kmalloc(sizeof(file_private_info_t),
 						GFP_KERNEL);
 	if(!p_info){
-		if(debug_info_snapshot)
-			debug_info_free(debug_info_snapshot);
+		debug_info_free(debug_info_snapshot);
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -698,8 +697,7 @@ debug_info_t *debug_register_mode(const char *name, int pages_per_area,
 	if ((uid != 0) || (gid != 0))
 		pr_warning("Root becomes the owner of all s390dbf files "
 			   "in sysfs\n");
-	if (!initialized)
-		BUG();
+	BUG_ON(!initialized);
 	mutex_lock(&debug_mutex);
 
         /* create new debug_info */
@@ -1156,7 +1154,6 @@ debug_unregister_view(debug_info_t * id, struct debug_view *view)
 	else {
 		debugfs_remove(id->debugfs_entries[i]);
 		id->views[i] = NULL;
-		rc = 0;
 	}
 	spin_unlock_irqrestore(&id->lock, flags);
 out:
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 2a2ca268b1d..4d221c81c84 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -6,6 +6,7 @@
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
+#include <linux/compiler.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/string.h>
@@ -20,6 +21,7 @@
 #include <asm/processor.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/sclp.h>
 #include "entry.h"
@@ -173,19 +175,21 @@ static noinline __init void init_kernel_storage_key(void)
 		page_set_storage_key(init_pfn << PAGE_SHIFT, PAGE_DEFAULT_KEY);
 }
 
+static __initdata struct sysinfo_3_2_2 vmms __aligned(PAGE_SIZE);
+
 static noinline __init void detect_machine_type(void)
 {
-	struct cpuinfo_S390 *cpuinfo = &S390_lowcore.cpu_data;
-
-	get_cpu_id(&S390_lowcore.cpu_data.cpu_id);
-
-	/* Running under z/VM ? */
-	if (cpuinfo->cpu_id.version == 0xff)
-		machine_flags |= MACHINE_FLAG_VM;
+	/* No VM information? Looks like LPAR */
+	if (stsi(&vmms, 3, 2, 2) == -ENOSYS)
+		return;
+	if (!vmms.count)
+		return;
 
-	/* Running under KVM ? */
-	if (cpuinfo->cpu_id.version == 0xfe)
+	/* Running under KVM? If not we assume z/VM */
+	if (!memcmp(vmms.vm[0].cpi, "\xd2\xe5\xd4", 3))
 		machine_flags |= MACHINE_FLAG_KVM;
+	else
+		machine_flags |= MACHINE_FLAG_VM;
 }
 
 static __init void early_pgm_check_handler(void)
@@ -348,7 +352,6 @@ static void __init setup_boot_command_line(void)
 
 	/* copy arch command line */
 	strlcpy(boot_command_line, COMMAND_LINE, ARCH_COMMAND_LINE_SIZE);
-	boot_command_line[ARCH_COMMAND_LINE_SIZE - 1] = 0;
 
 	/* append IPL PARM data to the boot command line */
 	if (MACHINE_IS_VM) {
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index ec7e35f6055..1046c2c9f8d 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -469,6 +469,8 @@ start:
 	.org	0x10000
 startup:basr	%r13,0			# get base
 .LPG0:
+	xc	0x200(256),0x200	# partially clear lowcore
+	xc	0x300(256),0x300
 
 #ifndef CONFIG_MARCH_G5
 	# check processor version against MARCH_{G5,Z900,Z990,Z9_109,Z10}
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index db476d114ca..2ced846065b 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -20,7 +20,6 @@ startup_continue:
 	lctl	%c0,%c15,.Lctl-.LPG1(%r13) # load control registers
 	l	%r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area
 					# move IPL device to lowcore
-	mvc	__LC_IPLDEV(4),IPL_DEVICE-PARMAREA(%r12)
 #
 # Setup stack
 #
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index f9f70aa1524..65667b2e65c 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -86,7 +86,6 @@ startup_continue:
 	lctlg	%c0,%c15,.Lctl-.LPG1(%r13)	# load control registers
 	lg	%r12,.Lparmaddr-.LPG1(%r13)	# pointer to parameter area
 					# move IPL device to lowcore
-	mvc	__LC_IPLDEV(4),IPL_DEVICE+4-PARMAREA(%r12)
 	lghi	%r0,__LC_PASTE
 	stg	%r0,__LC_VDSO_PER_CPU
 #
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 2dcf590faba..6f3711a0eaa 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -23,7 +23,7 @@
 #include <asm/ebcdic.h>
 #include <asm/reset.h>
 #include <asm/sclp.h>
-#include <asm/setup.h>
+#include <asm/checksum.h>
 
 #define IPL_PARM_BLOCK_VERSION 0
 
@@ -56,13 +56,14 @@ struct shutdown_trigger {
 };
 
 /*
- * Five shutdown action types are supported:
+ * The following shutdown action types are supported:
  */
 #define SHUTDOWN_ACTION_IPL_STR		"ipl"
 #define SHUTDOWN_ACTION_REIPL_STR	"reipl"
 #define SHUTDOWN_ACTION_DUMP_STR	"dump"
 #define SHUTDOWN_ACTION_VMCMD_STR	"vmcmd"
 #define SHUTDOWN_ACTION_STOP_STR	"stop"
+#define SHUTDOWN_ACTION_DUMP_REIPL_STR	"dump_reipl"
 
 struct shutdown_action {
 	char *name;
@@ -146,6 +147,7 @@ static enum ipl_method reipl_method = REIPL_METHOD_DEFAULT;
 static struct ipl_parameter_block *reipl_block_fcp;
 static struct ipl_parameter_block *reipl_block_ccw;
 static struct ipl_parameter_block *reipl_block_nss;
+static struct ipl_parameter_block *reipl_block_actual;
 
 static int dump_capabilities = DUMP_TYPE_NONE;
 static enum dump_type dump_type = DUMP_TYPE_NONE;
@@ -835,6 +837,7 @@ static int reipl_set_type(enum ipl_type type)
 			reipl_method = REIPL_METHOD_CCW_VM;
 		else
 			reipl_method = REIPL_METHOD_CCW_CIO;
+		reipl_block_actual = reipl_block_ccw;
 		break;
 	case IPL_TYPE_FCP:
 		if (diag308_set_works)
@@ -843,6 +846,7 @@ static int reipl_set_type(enum ipl_type type)
 			reipl_method = REIPL_METHOD_FCP_RO_VM;
 		else
 			reipl_method = REIPL_METHOD_FCP_RO_DIAG;
+		reipl_block_actual = reipl_block_fcp;
 		break;
 	case IPL_TYPE_FCP_DUMP:
 		reipl_method = REIPL_METHOD_FCP_DUMP;
@@ -852,6 +856,7 @@ static int reipl_set_type(enum ipl_type type)
 			reipl_method = REIPL_METHOD_NSS_DIAG;
 		else
 			reipl_method = REIPL_METHOD_NSS;
+		reipl_block_actual = reipl_block_nss;
 		break;
 	case IPL_TYPE_UNKNOWN:
 		reipl_method = REIPL_METHOD_DEFAULT;
@@ -960,7 +965,6 @@ static void reipl_run(struct shutdown_trigger *trigger)
 		diag308(DIAG308_IPL, NULL);
 		break;
 	case REIPL_METHOD_FCP_DUMP:
-	default:
 		break;
 	}
 	disabled_wait((unsigned long) __builtin_return_address(0));
@@ -1069,10 +1073,12 @@ static int __init reipl_fcp_init(void)
 {
 	int rc;
 
-	if ((!diag308_set_works) && (ipl_info.type != IPL_TYPE_FCP))
-		return 0;
-	if ((!diag308_set_works) && (ipl_info.type == IPL_TYPE_FCP))
-		make_attrs_ro(reipl_fcp_attrs);
+	if (!diag308_set_works) {
+		if (ipl_info.type == IPL_TYPE_FCP)
+			make_attrs_ro(reipl_fcp_attrs);
+		else
+			return 0;
+	}
 
 	reipl_block_fcp = (void *) get_zeroed_page(GFP_KERNEL);
 	if (!reipl_block_fcp)
@@ -1253,7 +1259,6 @@ static void dump_run(struct shutdown_trigger *trigger)
 		diag308(DIAG308_DUMP, NULL);
 		break;
 	case DUMP_METHOD_NONE:
-	default:
 		return;
 	}
 	printk(KERN_EMERG "Dump failed!\n");
@@ -1332,6 +1337,49 @@ static struct shutdown_action __refdata dump_action = {
 	.init	= dump_init,
 };
 
+static void dump_reipl_run(struct shutdown_trigger *trigger)
+{
+	preempt_disable();
+	/*
+	 * Bypass dynamic address translation (DAT) when storing IPL parameter
+	 * information block address and checksum into the prefix area
+	 * (corresponding to absolute addresses 0-8191).
+	 * When enhanced DAT applies and the STE format control in one,
+	 * the absolute address is formed without prefixing. In this case a
+	 * normal store (stg/st) into the prefix area would no more match to
+	 * absolute addresses 0-8191.
+	 */
+#ifdef CONFIG_64BIT
+	asm volatile("sturg %0,%1"
+		:: "a" ((unsigned long) reipl_block_actual),
+		"a" (&lowcore_ptr[smp_processor_id()]->ipib));
+#else
+	asm volatile("stura %0,%1"
+		:: "a" ((unsigned long) reipl_block_actual),
+		"a" (&lowcore_ptr[smp_processor_id()]->ipib));
+#endif
+	asm volatile("stura %0,%1"
+		:: "a" (csum_partial(reipl_block_actual,
+				     reipl_block_actual->hdr.len, 0)),
+		"a" (&lowcore_ptr[smp_processor_id()]->ipib_checksum));
+	preempt_enable();
+	dump_run(trigger);
+}
+
+static int __init dump_reipl_init(void)
+{
+	if (!diag308_set_works)
+		return -EOPNOTSUPP;
+	else
+		return 0;
+}
+
+static struct shutdown_action __refdata dump_reipl_action = {
+	.name	= SHUTDOWN_ACTION_DUMP_REIPL_STR,
+	.fn	= dump_reipl_run,
+	.init	= dump_reipl_init,
+};
+
 /*
  * vmcmd shutdown action: Trigger vm command on shutdown.
  */
@@ -1421,7 +1469,8 @@ static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR,
 /* action list */
 
 static struct shutdown_action *shutdown_actions_list[] = {
-	&ipl_action, &reipl_action, &dump_action, &vmcmd_action, &stop_action};
+	&ipl_action, &reipl_action, &dump_reipl_action, &dump_action,
+	&vmcmd_action, &stop_action};
 #define SHUTDOWN_ACTIONS_COUNT (sizeof(shutdown_actions_list) / sizeof(void *))
 
 /*
@@ -1434,11 +1483,11 @@ static int set_trigger(const char *buf, struct shutdown_trigger *trigger,
 		       size_t len)
 {
 	int i;
+
 	for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) {
 		if (!shutdown_actions_list[i])
 			continue;
-		if (strncmp(buf, shutdown_actions_list[i]->name,
-			    strlen(shutdown_actions_list[i]->name)) == 0) {
+		if (sysfs_streq(buf, shutdown_actions_list[i]->name)) {
 			trigger->action = shutdown_actions_list[i];
 			return len;
 		}
@@ -1672,7 +1721,7 @@ static int on_panic_notify(struct notifier_block *self,
 
 static struct notifier_block on_panic_nb = {
 	.notifier_call = on_panic_notify,
-	.priority = 0,
+	.priority = INT_MIN,
 };
 
 void __init setup_ipl(void)
@@ -1696,7 +1745,6 @@ void __init setup_ipl(void)
 			sizeof(ipl_info.data.nss.name));
 		break;
 	case IPL_TYPE_UNKNOWN:
-	default:
 		/* We have no info to copy */
 		break;
 	}
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 59b4e796680..eed4a00cb67 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -310,15 +310,20 @@ apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
 			info->plt_initialized = 1;
 		}
 		if (r_type == R_390_PLTOFF16 ||
-		    r_type == R_390_PLTOFF32
-		    || r_type == R_390_PLTOFF64
-			)
+		    r_type == R_390_PLTOFF32 ||
+		    r_type == R_390_PLTOFF64)
 			val = me->arch.plt_offset - me->arch.got_offset +
 				info->plt_offset + rela->r_addend;
-		else
-			val =  (Elf_Addr) me->module_core +
-				me->arch.plt_offset + info->plt_offset + 
-				rela->r_addend - loc;
+		else {
+			if (!((r_type == R_390_PLT16DBL &&
+			       val - loc + 0xffffUL < 0x1ffffeUL) ||
+			      (r_type == R_390_PLT32DBL &&
+			       val - loc + 0xffffffffULL < 0x1fffffffeULL)))
+				val = (Elf_Addr) me->module_core +
+					me->arch.plt_offset +
+					info->plt_offset;
+			val += rela->r_addend - loc;
+		}
 		if (r_type == R_390_PLT16DBL)
 			*(unsigned short *) loc = val >> 1;
 		else if (r_type == R_390_PLTOFF16)
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
new file mode 100644
index 00000000000..4bfdc421d7e
--- /dev/null
+++ b/arch/s390/kernel/nmi.c
@@ -0,0 +1,376 @@
+/*
+ *   Machine check handler
+ *
+ *    Copyright IBM Corp. 2000,2009
+ *    Author(s): Ingo Adlung <adlung@de.ibm.com>,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Cornelia Huck <cornelia.huck@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
+ */
+
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/module.h>
+#include <asm/lowcore.h>
+#include <asm/smp.h>
+#include <asm/etr.h>
+#include <asm/cpu.h>
+#include <asm/nmi.h>
+#include <asm/crw.h>
+
+struct mcck_struct {
+	int kill_task;
+	int channel_report;
+	int warning;
+	unsigned long long mcck_code;
+};
+
+static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
+
+static NORET_TYPE void s390_handle_damage(char *msg)
+{
+	smp_send_stop();
+	disabled_wait((unsigned long) __builtin_return_address(0));
+	while (1);
+}
+
+/*
+ * Main machine check handler function. Will be called with interrupts enabled
+ * or disabled and machine checks enabled or disabled.
+ */
+void s390_handle_mcck(void)
+{
+	unsigned long flags;
+	struct mcck_struct mcck;
+
+	/*
+	 * Disable machine checks and get the current state of accumulated
+	 * machine checks. Afterwards delete the old state and enable machine
+	 * checks again.
+	 */
+	local_irq_save(flags);
+	local_mcck_disable();
+	mcck = __get_cpu_var(cpu_mcck);
+	memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct));
+	clear_thread_flag(TIF_MCCK_PENDING);
+	local_mcck_enable();
+	local_irq_restore(flags);
+
+	if (mcck.channel_report)
+		crw_handle_channel_report();
+	/*
+	 * A warning may remain for a prolonged period on the bare iron.
+	 * (actually until the machine is powered off, or the problem is gone)
+	 * So we just stop listening for the WARNING MCH and avoid continuously
+	 * being interrupted.  One caveat is however, that we must do this per
+	 * processor and cannot use the smp version of ctl_clear_bit().
+	 * On VM we only get one interrupt per virtally presented machinecheck.
+	 * Though one suffices, we may get one interrupt per (virtual) cpu.
+	 */
+	if (mcck.warning) {	/* WARNING pending ? */
+		static int mchchk_wng_posted = 0;
+
+		/* Use single cpu clear, as we cannot handle smp here. */
+		__ctl_clear_bit(14, 24);	/* Disable WARNING MCH */
+		if (xchg(&mchchk_wng_posted, 1) == 0)
+			kill_cad_pid(SIGPWR, 1);
+	}
+	if (mcck.kill_task) {
+		local_irq_enable();
+		printk(KERN_EMERG "mcck: Terminating task because of machine "
+		       "malfunction (code 0x%016llx).\n", mcck.mcck_code);
+		printk(KERN_EMERG "mcck: task: %s, pid: %d.\n",
+		       current->comm, current->pid);
+		do_exit(SIGSEGV);
+	}
+}
+EXPORT_SYMBOL_GPL(s390_handle_mcck);
+
+/*
+ * returns 0 if all registers could be validated
+ * returns 1 otherwise
+ */
+static int notrace s390_revalidate_registers(struct mci *mci)
+{
+	int kill_task;
+	u64 tmpclock;
+	u64 zero;
+	void *fpt_save_area, *fpt_creg_save_area;
+
+	kill_task = 0;
+	zero = 0;
+
+	if (!mci->gr) {
+		/*
+		 * General purpose registers couldn't be restored and have
+		 * unknown contents. Process needs to be terminated.
+		 */
+		kill_task = 1;
+	}
+	if (!mci->fp) {
+		/*
+		 * Floating point registers can't be restored and
+		 * therefore the process needs to be terminated.
+		 */
+		kill_task = 1;
+	}
+#ifndef CONFIG_64BIT
+	asm volatile(
+		"	ld	0,0(%0)\n"
+		"	ld	2,8(%0)\n"
+		"	ld	4,16(%0)\n"
+		"	ld	6,24(%0)"
+		: : "a" (&S390_lowcore.floating_pt_save_area));
+#endif
+
+	if (MACHINE_HAS_IEEE) {
+#ifdef CONFIG_64BIT
+		fpt_save_area = &S390_lowcore.floating_pt_save_area;
+		fpt_creg_save_area = &S390_lowcore.fpt_creg_save_area;
+#else
+		fpt_save_area = (void *) S390_lowcore.extended_save_area_addr;
+		fpt_creg_save_area = fpt_save_area + 128;
+#endif
+		if (!mci->fc) {
+			/*
+			 * Floating point control register can't be restored.
+			 * Task will be terminated.
+			 */
+			asm volatile("lfpc 0(%0)" : : "a" (&zero), "m" (zero));
+			kill_task = 1;
+
+		} else
+			asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area));
+
+		asm volatile(
+			"	ld	0,0(%0)\n"
+			"	ld	1,8(%0)\n"
+			"	ld	2,16(%0)\n"
+			"	ld	3,24(%0)\n"
+			"	ld	4,32(%0)\n"
+			"	ld	5,40(%0)\n"
+			"	ld	6,48(%0)\n"
+			"	ld	7,56(%0)\n"
+			"	ld	8,64(%0)\n"
+			"	ld	9,72(%0)\n"
+			"	ld	10,80(%0)\n"
+			"	ld	11,88(%0)\n"
+			"	ld	12,96(%0)\n"
+			"	ld	13,104(%0)\n"
+			"	ld	14,112(%0)\n"
+			"	ld	15,120(%0)\n"
+			: : "a" (fpt_save_area));
+	}
+	/* Revalidate access registers */
+	asm volatile(
+		"	lam	0,15,0(%0)"
+		: : "a" (&S390_lowcore.access_regs_save_area));
+	if (!mci->ar) {
+		/*
+		 * Access registers have unknown contents.
+		 * Terminating task.
+		 */
+		kill_task = 1;
+	}
+	/* Revalidate control registers */
+	if (!mci->cr) {
+		/*
+		 * Control registers have unknown contents.
+		 * Can't recover and therefore stopping machine.
+		 */
+		s390_handle_damage("invalid control registers.");
+	} else {
+#ifdef CONFIG_64BIT
+		asm volatile(
+			"	lctlg	0,15,0(%0)"
+			: : "a" (&S390_lowcore.cregs_save_area));
+#else
+		asm volatile(
+			"	lctl	0,15,0(%0)"
+			: : "a" (&S390_lowcore.cregs_save_area));
+#endif
+	}
+	/*
+	 * We don't even try to revalidate the TOD register, since we simply
+	 * can't write something sensible into that register.
+	 */
+#ifdef CONFIG_64BIT
+	/*
+	 * See if we can revalidate the TOD programmable register with its
+	 * old contents (should be zero) otherwise set it to zero.
+	 */
+	if (!mci->pr)
+		asm volatile(
+			"	sr	0,0\n"
+			"	sckpf"
+			: : : "0", "cc");
+	else
+		asm volatile(
+			"	l	0,0(%0)\n"
+			"	sckpf"
+			: : "a" (&S390_lowcore.tod_progreg_save_area)
+			: "0", "cc");
+#endif
+	/* Revalidate clock comparator register */
+	asm volatile(
+		"	stck	0(%1)\n"
+		"	sckc	0(%1)"
+		: "=m" (tmpclock) : "a" (&(tmpclock)) : "cc", "memory");
+
+	/* Check if old PSW is valid */
+	if (!mci->wp)
+		/*
+		 * Can't tell if we come from user or kernel mode
+		 * -> stopping machine.
+		 */
+		s390_handle_damage("old psw invalid.");
+
+	if (!mci->ms || !mci->pm || !mci->ia)
+		kill_task = 1;
+
+	return kill_task;
+}
+
+#define MAX_IPD_COUNT	29
+#define MAX_IPD_TIME	(5 * 60 * USEC_PER_SEC) /* 5 minutes */
+
+#define ED_STP_ISLAND	6	/* External damage STP island check */
+#define ED_STP_SYNC	7	/* External damage STP sync check */
+#define ED_ETR_SYNC	12	/* External damage ETR sync check */
+#define ED_ETR_SWITCH	13	/* External damage ETR switch to local */
+
+/*
+ * machine check handler.
+ */
+void notrace s390_do_machine_check(struct pt_regs *regs)
+{
+	static int ipd_count;
+	static DEFINE_SPINLOCK(ipd_lock);
+	static unsigned long long last_ipd;
+	struct mcck_struct *mcck;
+	unsigned long long tmp;
+	struct mci *mci;
+	int umode;
+
+	lockdep_off();
+	s390_idle_check();
+
+	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
+	mcck = &__get_cpu_var(cpu_mcck);
+	umode = user_mode(regs);
+
+	if (mci->sd) {
+		/* System damage -> stopping machine */
+		s390_handle_damage("received system damage machine check.");
+	}
+	if (mci->pd) {
+		if (mci->b) {
+			/* Processing backup -> verify if we can survive this */
+			u64 z_mcic, o_mcic, t_mcic;
+#ifdef CONFIG_64BIT
+			z_mcic = (1ULL<<63 | 1ULL<<59 | 1ULL<<29);
+			o_mcic = (1ULL<<43 | 1ULL<<42 | 1ULL<<41 | 1ULL<<40 |
+				  1ULL<<36 | 1ULL<<35 | 1ULL<<34 | 1ULL<<32 |
+				  1ULL<<30 | 1ULL<<21 | 1ULL<<20 | 1ULL<<17 |
+				  1ULL<<16);
+#else
+			z_mcic = (1ULL<<63 | 1ULL<<59 | 1ULL<<57 | 1ULL<<50 |
+				  1ULL<<29);
+			o_mcic = (1ULL<<43 | 1ULL<<42 | 1ULL<<41 | 1ULL<<40 |
+				  1ULL<<36 | 1ULL<<35 | 1ULL<<34 | 1ULL<<32 |
+				  1ULL<<30 | 1ULL<<20 | 1ULL<<17 | 1ULL<<16);
+#endif
+			t_mcic = *(u64 *)mci;
+
+			if (((t_mcic & z_mcic) != 0) ||
+			    ((t_mcic & o_mcic) != o_mcic)) {
+				s390_handle_damage("processing backup machine "
+						   "check with damage.");
+			}
+
+			/*
+			 * Nullifying exigent condition, therefore we might
+			 * retry this instruction.
+			 */
+			spin_lock(&ipd_lock);
+			tmp = get_clock();
+			if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME)
+				ipd_count++;
+			else
+				ipd_count = 1;
+			last_ipd = tmp;
+			if (ipd_count == MAX_IPD_COUNT)
+				s390_handle_damage("too many ipd retries.");
+			spin_unlock(&ipd_lock);
+		} else {
+			/* Processing damage -> stopping machine */
+			s390_handle_damage("received instruction processing "
+					   "damage machine check.");
+		}
+	}
+	if (s390_revalidate_registers(mci)) {
+		if (umode) {
+			/*
+			 * Couldn't restore all register contents while in
+			 * user mode -> mark task for termination.
+			 */
+			mcck->kill_task = 1;
+			mcck->mcck_code = *(unsigned long long *) mci;
+			set_thread_flag(TIF_MCCK_PENDING);
+		} else {
+			/*
+			 * Couldn't restore all register contents while in
+			 * kernel mode -> stopping machine.
+			 */
+			s390_handle_damage("unable to revalidate registers.");
+		}
+	}
+	if (mci->cd) {
+		/* Timing facility damage */
+		s390_handle_damage("TOD clock damaged");
+	}
+	if (mci->ed && mci->ec) {
+		/* External damage */
+		if (S390_lowcore.external_damage_code & (1U << ED_ETR_SYNC))
+			etr_sync_check();
+		if (S390_lowcore.external_damage_code & (1U << ED_ETR_SWITCH))
+			etr_switch_to_local();
+		if (S390_lowcore.external_damage_code & (1U << ED_STP_SYNC))
+			stp_sync_check();
+		if (S390_lowcore.external_damage_code & (1U << ED_STP_ISLAND))
+			stp_island_check();
+	}
+	if (mci->se)
+		/* Storage error uncorrected */
+		s390_handle_damage("received storage error uncorrected "
+				   "machine check.");
+	if (mci->ke)
+		/* Storage key-error uncorrected */
+		s390_handle_damage("received storage key-error uncorrected "
+				   "machine check.");
+	if (mci->ds && mci->fa)
+		/* Storage degradation */
+		s390_handle_damage("received storage degradation machine "
+				   "check.");
+	if (mci->cp) {
+		/* Channel report word pending */
+		mcck->channel_report = 1;
+		set_thread_flag(TIF_MCCK_PENDING);
+	}
+	if (mci->w) {
+		/* Warning pending */
+		mcck->warning = 1;
+		set_thread_flag(TIF_MCCK_PENDING);
+	}
+	lockdep_on();
+}
+
+static int __init machine_check_init(void)
+{
+	ctl_set_bit(14, 25);	/* enable external damage MCH */
+	ctl_set_bit(14, 27);	/* enable system recovery MCH */
+	ctl_set_bit(14, 24);	/* enable warning MCH */
+	return 0;
+}
+arch_initcall(machine_check_init);
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 5cd38a90e64..b48e961a38f 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -1,18 +1,10 @@
 /*
- *  arch/s390/kernel/process.c
+ * This file handles the architecture dependent parts of process handling.
  *
- *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- *               Hartmut Penner (hp@de.ibm.com),
- *               Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
- *
- *  Derived from "arch/i386/kernel/process.c"
- *    Copyright (C) 1995, Linus Torvalds
- */
-
-/*
- * This file handles the architecture-dependent parts of process handling..
+ *    Copyright IBM Corp. 1999,2009
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Hartmut Penner <hp@de.ibm.com>,
+ *		 Denis Joseph Barrow,
  */
 
 #include <linux/compiler.h>
@@ -47,6 +39,7 @@
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <asm/timer.h>
+#include <asm/nmi.h>
 #include "entry.h"
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
@@ -76,7 +69,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return sf->gprs[8];
 }
 
-extern void s390_handle_mcck(void);
 /*
  * The idle loop on a S390...
  */
@@ -149,6 +141,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 	return do_fork(flags | CLONE_VM | CLONE_UNTRACED,
 		       0, &regs, 0, NULL, NULL);
 }
+EXPORT_SYMBOL(kernel_thread);
 
 /*
  * Free current thread data structures etc..
@@ -168,34 +161,35 @@ void release_thread(struct task_struct *dead_task)
 }
 
 int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
-	unsigned long unused,
-        struct task_struct * p, struct pt_regs * regs)
+		unsigned long unused,
+		struct task_struct *p, struct pt_regs *regs)
 {
-        struct fake_frame
-          {
-	    struct stack_frame sf;
-            struct pt_regs childregs;
-          } *frame;
-
-        frame = container_of(task_pt_regs(p), struct fake_frame, childregs);
-        p->thread.ksp = (unsigned long) frame;
+	struct thread_info *ti;
+	struct fake_frame
+	{
+		struct stack_frame sf;
+		struct pt_regs childregs;
+	} *frame;
+
+	frame = container_of(task_pt_regs(p), struct fake_frame, childregs);
+	p->thread.ksp = (unsigned long) frame;
 	/* Store access registers to kernel stack of new process. */
-        frame->childregs = *regs;
+	frame->childregs = *regs;
 	frame->childregs.gprs[2] = 0;	/* child returns 0 on fork. */
-        frame->childregs.gprs[15] = new_stackp;
-        frame->sf.back_chain = 0;
+	frame->childregs.gprs[15] = new_stackp;
+	frame->sf.back_chain = 0;
 
-        /* new return point is ret_from_fork */
-        frame->sf.gprs[8] = (unsigned long) ret_from_fork;
+	/* new return point is ret_from_fork */
+	frame->sf.gprs[8] = (unsigned long) ret_from_fork;
 
-        /* fake return stack for resume(), don't go back to schedule */
-        frame->sf.gprs[9] = (unsigned long) frame;
+	/* fake return stack for resume(), don't go back to schedule */
+	frame->sf.gprs[9] = (unsigned long) frame;
 
 	/* Save access registers to new thread structure. */
 	save_access_regs(&p->thread.acrs[0]);
 
 #ifndef CONFIG_64BIT
-        /*
+	/*
 	 * save fprs to current->thread.fp_regs to merge them with
 	 * the emulated registers and then copy the result to the child.
 	 */
@@ -220,10 +214,13 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
 #endif /* CONFIG_64BIT */
 	/* start new process with ar4 pointing to the correct address space */
 	p->thread.mm_segment = get_fs();
-        /* Don't copy debug registers */
-        memset(&p->thread.per_info,0,sizeof(p->thread.per_info));
-
-        return 0;
+	/* Don't copy debug registers */
+	memset(&p->thread.per_info, 0, sizeof(p->thread.per_info));
+	/* Initialize per thread user and system timer values */
+	ti = task_thread_info(p);
+	ti->user_timer = 0;
+	ti->system_timer = 0;
+	return 0;
 }
 
 SYSCALL_DEFINE0(fork)
@@ -311,7 +308,7 @@ out:
 int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
 {
 #ifndef CONFIG_64BIT
-        /*
+	/*
 	 * save fprs to current->thread.fp_regs to merge them with
 	 * the emulated registers and then copy the result to the dump.
 	 */
@@ -322,6 +319,7 @@ int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
 #endif /* CONFIG_64BIT */
 	return 1;
 }
+EXPORT_SYMBOL(dump_fpu);
 
 unsigned long get_wchan(struct task_struct *p)
 {
@@ -346,4 +344,3 @@ unsigned long get_wchan(struct task_struct *p)
 	}
 	return 0;
 }
-
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 82c1872cfe8..802c8ab247f 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -18,10 +18,11 @@
 #include <asm/lowcore.h>
 #include <asm/param.h>
 
-void __cpuinit print_cpu_info(struct cpuinfo_S390 *cpuinfo)
+void __cpuinit print_cpu_info(void)
 {
 	pr_info("Processor %d started, address %d, identification %06X\n",
-		cpuinfo->cpu_nr, cpuinfo->cpu_addr, cpuinfo->cpu_id.ident);
+		S390_lowcore.cpu_nr, S390_lowcore.cpu_addr,
+		S390_lowcore.cpu_id.ident);
 }
 
 /*
@@ -30,48 +31,46 @@ void __cpuinit print_cpu_info(struct cpuinfo_S390 *cpuinfo)
 
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
-	static const char *hwcap_str[8] = {
+	static const char *hwcap_str[9] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat"
+		"edat", "etf3eh"
 	};
-       struct cpuinfo_S390 *cpuinfo;
-       unsigned long n = (unsigned long) v - 1;
-       int i;
+	struct _lowcore *lc;
+	unsigned long n = (unsigned long) v - 1;
+	int i;
 
-       s390_adjust_jiffies();
-       preempt_disable();
-       if (!n) {
-	       seq_printf(m, "vendor_id       : IBM/S390\n"
-			  "# processors    : %i\n"
-			  "bogomips per cpu: %lu.%02lu\n",
-			  num_online_cpus(), loops_per_jiffy/(500000/HZ),
-			  (loops_per_jiffy/(5000/HZ))%100);
-	       seq_puts(m, "features\t: ");
-	       for (i = 0; i < 8; i++)
-		       if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
-			       seq_printf(m, "%s ", hwcap_str[i]);
-	       seq_puts(m, "\n");
-       }
+	s390_adjust_jiffies();
+	preempt_disable();
+	if (!n) {
+		seq_printf(m, "vendor_id       : IBM/S390\n"
+			   "# processors    : %i\n"
+			   "bogomips per cpu: %lu.%02lu\n",
+			   num_online_cpus(), loops_per_jiffy/(500000/HZ),
+			   (loops_per_jiffy/(5000/HZ))%100);
+		seq_puts(m, "features\t: ");
+		for (i = 0; i < 9; i++)
+			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
+				seq_printf(m, "%s ", hwcap_str[i]);
+		seq_puts(m, "\n");
+	}
 
-       if (cpu_online(n)) {
+	if (cpu_online(n)) {
 #ifdef CONFIG_SMP
-	       if (smp_processor_id() == n)
-		       cpuinfo = &S390_lowcore.cpu_data;
-	       else
-		       cpuinfo = &lowcore_ptr[n]->cpu_data;
+		lc = (smp_processor_id() == n) ?
+			&S390_lowcore : lowcore_ptr[n];
 #else
-	       cpuinfo = &S390_lowcore.cpu_data;
+		lc = &S390_lowcore;
 #endif
-	       seq_printf(m, "processor %li: "
-			  "version = %02X,  "
-			  "identification = %06X,  "
-			  "machine = %04X\n",
-			  n, cpuinfo->cpu_id.version,
-			  cpuinfo->cpu_id.ident,
-			  cpuinfo->cpu_id.machine);
-       }
-       preempt_enable();
-       return 0;
+		seq_printf(m, "processor %li: "
+			   "version = %02X,  "
+			   "identification = %06X,  "
+			   "machine = %04X\n",
+			   n, lc->cpu_id.version,
+			   lc->cpu_id.ident,
+			   lc->cpu_id.machine);
+	}
+	preempt_enable();
+	return 0;
 }
 
 static void *c_start(struct seq_file *m, loff_t *pos)
diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S
index c41930499a5..774147824c3 100644
--- a/arch/s390/kernel/reipl64.S
+++ b/arch/s390/kernel/reipl64.S
@@ -1,10 +1,7 @@
 /*
- *  arch/s390/kernel/reipl.S
- *
- *  S390 version
- *    Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com)
-		 Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ *    Copyright IBM Corp 2000,2009
+ *    Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>,
+ *		 Denis Joseph Barrow,
  */
 
 #include <asm/lowcore.h>
@@ -30,7 +27,7 @@ do_reipl_asm:	basr	%r13,0
 		mvc	__LC_PREFIX_SAVE_AREA-0x1000(4,%r1),0(%r10)
 		stfpc	__LC_FP_CREG_SAVE_AREA-0x1000(%r1)
 		stckc	.Lclkcmp-.Lpg0(%r13)
-		mvc	__LC_CLOCK_COMP_SAVE_AREA-0x1000(8,%r1),.Lclkcmp-.Lpg0(%r13)
+		mvc	__LC_CLOCK_COMP_SAVE_AREA-0x1000(7,%r1),.Lclkcmp-.Lpg0(%r13)
 		stpt	__LC_CPU_TIMER_SAVE_AREA-0x1000(%r1)
 		stg	%r13, __LC_PSW_SAVE_AREA-0x1000+8(%r1)
 
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 46b90cb0370..656fcbb9bd8 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -1,49 +1,5 @@
-/*
- *  arch/s390/kernel/s390_ksyms.c
- *
- *  S390 version
- */
-#include <linux/highuid.h>
 #include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/syscalls.h>
-#include <linux/interrupt.h>
-#include <asm/checksum.h>
-#include <asm/cpcmd.h>
-#include <asm/delay.h>
-#include <asm/pgalloc.h>
-#include <asm/setup.h>
 #include <asm/ftrace.h>
-#ifdef CONFIG_IP_MULTICAST
-#include <net/arp.h>
-#endif
-
-/*
- * memory management
- */
-EXPORT_SYMBOL(_oi_bitmap);
-EXPORT_SYMBOL(_ni_bitmap);
-EXPORT_SYMBOL(_zb_findmap);
-EXPORT_SYMBOL(_sb_findmap);
-
-/*
- * binfmt_elf loader 
- */
-extern int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs);
-EXPORT_SYMBOL(dump_fpu);
-EXPORT_SYMBOL(empty_zero_page);
-
-/*
- * misc.
- */
-EXPORT_SYMBOL(machine_flags);
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(csum_fold);
-EXPORT_SYMBOL(console_mode);
-EXPORT_SYMBOL(console_devno);
-EXPORT_SYMBOL(console_irq);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c5cfb6185ea..06201b93cbb 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -74,9 +74,17 @@ EXPORT_SYMBOL(uaccess);
  * Machine setup..
  */
 unsigned int console_mode = 0;
+EXPORT_SYMBOL(console_mode);
+
 unsigned int console_devno = -1;
+EXPORT_SYMBOL(console_devno);
+
 unsigned int console_irq = -1;
+EXPORT_SYMBOL(console_irq);
+
 unsigned long machine_flags;
+EXPORT_SYMBOL(machine_flags);
+
 unsigned long elf_hwcap = 0;
 char elf_platform[ELF_PLATFORM_SIZE];
 
@@ -86,6 +94,10 @@ volatile int __cpu_logical_map[NR_CPUS]; /* logical cpu to cpu address */
 int __initdata memory_end_set;
 unsigned long __initdata memory_end;
 
+/* An array with a pointer to the lowcore of every CPU. */
+struct _lowcore *lowcore_ptr[NR_CPUS];
+EXPORT_SYMBOL(lowcore_ptr);
+
 /*
  * This is set up by the setup-routine at boot-time
  * for S390 need to find out, what we have to setup
@@ -109,13 +121,10 @@ static struct resource data_resource = {
  */
 void __cpuinit cpu_init(void)
 {
-        int addr = hard_smp_processor_id();
-
         /*
          * Store processor id in lowcore (used e.g. in timer_interrupt)
          */
-	get_cpu_id(&S390_lowcore.cpu_data.cpu_id);
-        S390_lowcore.cpu_data.cpu_addr = addr;
+	get_cpu_id(&S390_lowcore.cpu_id);
 
         /*
          * Force FPU initialization:
@@ -125,8 +134,7 @@ void __cpuinit cpu_init(void)
 
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
-        if (current->mm)
-                BUG();
+	BUG_ON(current->mm);
         enter_lazy_tlb(&init_mm, current);
 }
 
@@ -217,7 +225,7 @@ static void __init conmode_default(void)
 	}
 }
 
-#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)
+#ifdef CONFIG_ZFCPDUMP
 static void __init setup_zfcpdump(unsigned int console_devno)
 {
 	static char str[41];
@@ -289,11 +297,7 @@ static int __init early_parse_mem(char *p)
 early_param("mem", early_parse_mem);
 
 #ifdef CONFIG_S390_SWITCH_AMODE
-#ifdef CONFIG_PGSTE
-unsigned int switch_amode = 1;
-#else
 unsigned int switch_amode = 0;
-#endif
 EXPORT_SYMBOL_GPL(switch_amode);
 
 static int set_amode_and_uaccess(unsigned long user_amode,
@@ -414,7 +418,6 @@ setup_lowcore(void)
 		PSW_ADDR_AMODE | (unsigned long) mcck_int_handler;
 	lc->io_new_psw.mask = psw_kernel_bits;
 	lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler;
-	lc->ipl_device = S390_lowcore.ipl_device;
 	lc->clock_comparator = -1ULL;
 	lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE;
 	lc->async_stack = (unsigned long)
@@ -434,6 +437,7 @@ setup_lowcore(void)
 	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
 #endif
 	set_prefix((u32)(unsigned long) lc);
+	lowcore_ptr[0] = lc;
 }
 
 static void __init
@@ -510,7 +514,7 @@ static void __init setup_memory_end(void)
 	unsigned long max_mem;
 	int i;
 
-#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)
+#ifdef CONFIG_ZFCPDUMP
 	if (ipl_info.type == IPL_TYPE_FCP_DUMP) {
 		memory_end = ZFCPDUMP_HSA_SIZE;
 		memory_end_set = 1;
@@ -677,7 +681,6 @@ setup_memory(void)
 static void __init setup_hwcaps(void)
 {
 	static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
-	struct cpuinfo_S390 *cpuinfo = &S390_lowcore.cpu_data;
 	unsigned long long facility_list_extended;
 	unsigned int facility_list;
 	int i;
@@ -693,15 +696,22 @@ static void __init setup_hwcaps(void)
 	 *   Bit 17: the message-security assist is installed
 	 *   Bit 19: the long-displacement facility is installed
 	 *   Bit 21: the extended-immediate facility is installed
+	 *   Bit 22: extended-translation facility 3 is installed
+	 *   Bit 30: extended-translation facility 3 enhancement facility
 	 * These get translated to:
 	 *   HWCAP_S390_ESAN3 bit 0, HWCAP_S390_ZARCH bit 1,
 	 *   HWCAP_S390_STFLE bit 2, HWCAP_S390_MSA bit 3,
-	 *   HWCAP_S390_LDISP bit 4, and HWCAP_S390_EIMM bit 5.
+	 *   HWCAP_S390_LDISP bit 4, HWCAP_S390_EIMM bit 5 and
+	 *   HWCAP_S390_ETF3EH bit 8 (22 && 30).
 	 */
 	for (i = 0; i < 6; i++)
 		if (facility_list & (1UL << (31 - stfl_bits[i])))
 			elf_hwcap |= 1UL << i;
 
+	if ((facility_list & (1UL << (31 - 22)))
+	    && (facility_list & (1UL << (31 - 30))))
+		elf_hwcap |= 1UL << 8;
+
 	/*
 	 * Check for additional facilities with store-facility-list-extended.
 	 * stfle stores doublewords (8 byte) with bit 1ULL<<63 as bit 0
@@ -710,20 +720,22 @@ static void __init setup_hwcaps(void)
 	 * How many facility words are stored depends on the number of
 	 * doublewords passed to the instruction. The additional facilites
 	 * are:
-	 *   Bit 43: decimal floating point facility is installed
+	 *   Bit 42: decimal floating point facility is installed
+	 *   Bit 44: perform floating point operation facility is installed
 	 * translated to:
-	 *   HWCAP_S390_DFP bit 6.
+	 *   HWCAP_S390_DFP bit 6 (42 && 44).
 	 */
 	if ((elf_hwcap & (1UL << 2)) &&
 	    __stfle(&facility_list_extended, 1) > 0) {
-		if (facility_list_extended & (1ULL << (64 - 43)))
+		if ((facility_list_extended & (1ULL << (63 - 42)))
+		    && (facility_list_extended & (1ULL << (63 - 44))))
 			elf_hwcap |= 1UL << 6;
 	}
 
 	if (MACHINE_HAS_HPAGE)
 		elf_hwcap |= 1UL << 7;
 
-	switch (cpuinfo->cpu_id.machine) {
+	switch (S390_lowcore.cpu_id.machine) {
 	case 0x9672:
 #if !defined(CONFIG_64BIT)
 	default:	/* Use "g5" as default for 31 bit kernels. */
@@ -816,7 +828,7 @@ setup_arch(char **cmdline_p)
 	setup_lowcore();
 
         cpu_init();
-        __cpu_logical_map[0] = S390_lowcore.cpu_data.cpu_addr;
+	__cpu_logical_map[0] = stap();
 	s390_init_cpu_topology();
 
 	/*
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 2d337cbb932..006ed5016eb 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -32,6 +32,7 @@
 #include <linux/delay.h>
 #include <linux/cache.h>
 #include <linux/interrupt.h>
+#include <linux/irqflags.h>
 #include <linux/cpu.h>
 #include <linux/timex.h>
 #include <linux/bootmem.h>
@@ -50,12 +51,6 @@
 #include <asm/vdso.h>
 #include "entry.h"
 
-/*
- * An array with a pointer the lowcore of every CPU.
- */
-struct _lowcore *lowcore_ptr[NR_CPUS];
-EXPORT_SYMBOL(lowcore_ptr);
-
 static struct task_struct *current_set[NR_CPUS];
 
 static u8 smp_cpu_type;
@@ -81,9 +76,7 @@ void smp_send_stop(void)
 
 	/* Disable all interrupts/machine checks */
 	__load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK);
-
-	/* write magic number to zero page (absolute 0) */
-	lowcore_ptr[smp_processor_id()]->panic_magic = __PANIC_MAGIC;
+	trace_hardirqs_off();
 
 	/* stop all processors */
 	for_each_online_cpu(cpu) {
@@ -233,7 +226,7 @@ EXPORT_SYMBOL(smp_ctl_clear_bit);
  */
 #define CPU_INIT_NO	1
 
-#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)
+#ifdef CONFIG_ZFCPDUMP
 
 /*
  * zfcpdump_prefix_array holds prefix registers for the following scenario:
@@ -274,7 +267,7 @@ EXPORT_SYMBOL_GPL(zfcpdump_save_areas);
 
 static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { }
 
-#endif /* CONFIG_ZFCPDUMP || CONFIG_ZFCPDUMP_MODULE */
+#endif /* CONFIG_ZFCPDUMP */
 
 static int cpu_stopped(int cpu)
 {
@@ -304,8 +297,8 @@ static int smp_rescan_cpus_sigp(cpumask_t avail)
 {
 	int cpu_id, logical_cpu;
 
-	logical_cpu = first_cpu(avail);
-	if (logical_cpu == NR_CPUS)
+	logical_cpu = cpumask_first(&avail);
+	if (logical_cpu >= nr_cpu_ids)
 		return 0;
 	for (cpu_id = 0; cpu_id <= 65535; cpu_id++) {
 		if (cpu_known(cpu_id))
@@ -316,8 +309,8 @@ static int smp_rescan_cpus_sigp(cpumask_t avail)
 			continue;
 		cpu_set(logical_cpu, cpu_present_map);
 		smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
-		logical_cpu = next_cpu(logical_cpu, avail);
-		if (logical_cpu == NR_CPUS)
+		logical_cpu = cpumask_next(logical_cpu, &avail);
+		if (logical_cpu >= nr_cpu_ids)
 			break;
 	}
 	return 0;
@@ -329,8 +322,8 @@ static int smp_rescan_cpus_sclp(cpumask_t avail)
 	int cpu_id, logical_cpu, cpu;
 	int rc;
 
-	logical_cpu = first_cpu(avail);
-	if (logical_cpu == NR_CPUS)
+	logical_cpu = cpumask_first(&avail);
+	if (logical_cpu >= nr_cpu_ids)
 		return 0;
 	info = kmalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
@@ -351,8 +344,8 @@ static int smp_rescan_cpus_sclp(cpumask_t avail)
 			smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY;
 		else
 			smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
-		logical_cpu = next_cpu(logical_cpu, avail);
-		if (logical_cpu == NR_CPUS)
+		logical_cpu = cpumask_next(logical_cpu, &avail);
+		if (logical_cpu >= nr_cpu_ids)
 			break;
 	}
 out:
@@ -379,7 +372,7 @@ static void __init smp_detect_cpus(void)
 
 	c_cpus = 1;
 	s_cpus = 0;
-	boot_cpu_addr = S390_lowcore.cpu_data.cpu_addr;
+	boot_cpu_addr = __cpu_logical_map[0];
 	info = kmalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		panic("smp_detect_cpus failed to allocate memory\n");
@@ -453,7 +446,7 @@ int __cpuinit start_secondary(void *cpuvoid)
 	/* Switch on interrupts */
 	local_irq_enable();
 	/* Print info about this processor */
-	print_cpu_info(&S390_lowcore.cpu_data);
+	print_cpu_info();
 	/* cpu_idle will call schedule for us */
 	cpu_idle();
 	return 0;
@@ -515,7 +508,6 @@ out:
 	return -ENOMEM;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 static void smp_free_lowcore(int cpu)
 {
 	struct _lowcore *lowcore;
@@ -534,7 +526,6 @@ static void smp_free_lowcore(int cpu)
 	free_pages((unsigned long) lowcore, lc_order);
 	lowcore_ptr[cpu] = NULL;
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 /* Upping and downing of CPUs */
 int __cpuinit __cpu_up(unsigned int cpu)
@@ -543,16 +534,23 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	struct _lowcore *cpu_lowcore;
 	struct stack_frame *sf;
 	sigp_ccode ccode;
+	u32 lowcore;
 
 	if (smp_cpu_state[cpu] != CPU_STATE_CONFIGURED)
 		return -EIO;
 	if (smp_alloc_lowcore(cpu))
 		return -ENOMEM;
-
-	ccode = signal_processor_p((__u32)(unsigned long)(lowcore_ptr[cpu]),
-				   cpu, sigp_set_prefix);
-	if (ccode)
-		return -EIO;
+	do {
+		ccode = signal_processor(cpu, sigp_initial_cpu_reset);
+		if (ccode == sigp_busy)
+			udelay(10);
+		if (ccode == sigp_not_operational)
+			goto err_out;
+	} while (ccode == sigp_busy);
+
+	lowcore = (u32)(unsigned long)lowcore_ptr[cpu];
+	while (signal_processor_p(lowcore, cpu, sigp_set_prefix) == sigp_busy)
+		udelay(10);
 
 	idle = current_set[cpu];
 	cpu_lowcore = lowcore_ptr[cpu];
@@ -571,9 +569,8 @@ int __cpuinit __cpu_up(unsigned int cpu)
 		: : "a" (&cpu_lowcore->access_regs_save_area) : "memory");
 	cpu_lowcore->percpu_offset = __per_cpu_offset[cpu];
 	cpu_lowcore->current_task = (unsigned long) idle;
-	cpu_lowcore->cpu_data.cpu_nr = cpu;
+	cpu_lowcore->cpu_nr = cpu;
 	cpu_lowcore->kernel_asce = S390_lowcore.kernel_asce;
-	cpu_lowcore->ipl_device = S390_lowcore.ipl_device;
 	eieio();
 
 	while (signal_processor(cpu, sigp_restart) == sigp_busy)
@@ -582,6 +579,10 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	while (!cpu_online(cpu))
 		cpu_relax();
 	return 0;
+
+err_out:
+	smp_free_lowcore(cpu);
+	return -EIO;
 }
 
 static int __init setup_possible_cpus(char *s)
@@ -589,9 +590,8 @@ static int __init setup_possible_cpus(char *s)
 	int pcpus, cpu;
 
 	pcpus = simple_strtoul(s, NULL, 0);
-	cpu_possible_map = cpumask_of_cpu(0);
-	for (cpu = 1; cpu < pcpus && cpu < NR_CPUS; cpu++)
-		cpu_set(cpu, cpu_possible_map);
+	for (cpu = 0; cpu < pcpus && cpu < nr_cpu_ids; cpu++)
+		set_cpu_possible(cpu, true);
 	return 0;
 }
 early_param("possible_cpus", setup_possible_cpus);
@@ -663,7 +663,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	/* request the 0x1201 emergency signal external interrupt */
 	if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0)
 		panic("Couldn't request external interrupt 0x1201");
-	print_cpu_info(&S390_lowcore.cpu_data);
+	print_cpu_info();
 
 	/* Reallocate current lowcore, but keep its contents. */
 	lc_order = sizeof(long) == 8 ? 1 : 0;
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
new file mode 100644
index 00000000000..b5e75e1061c
--- /dev/null
+++ b/arch/s390/kernel/sysinfo.c
@@ -0,0 +1,428 @@
+/*
+ *  Copyright IBM Corp. 2001, 2009
+ *  Author(s): Ulrich Weigand <Ulrich.Weigand@de.ibm.com>,
+ *	       Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
+#include <asm/cpcmd.h>
+
+/* Sigh, math-emu. Don't ask. */
+#include <asm/sfp-util.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+
+static inline int stsi_0(void)
+{
+	int rc = stsi(NULL, 0, 0, 0);
+	return rc == -ENOSYS ? rc : (((unsigned int) rc) >> 28);
+}
+
+static int stsi_1_1_1(struct sysinfo_1_1_1 *info, char *page, int len)
+{
+	if (stsi(info, 1, 1, 1) == -ENOSYS)
+		return len;
+
+	EBCASC(info->manufacturer, sizeof(info->manufacturer));
+	EBCASC(info->type, sizeof(info->type));
+	EBCASC(info->model, sizeof(info->model));
+	EBCASC(info->sequence, sizeof(info->sequence));
+	EBCASC(info->plant, sizeof(info->plant));
+	EBCASC(info->model_capacity, sizeof(info->model_capacity));
+	EBCASC(info->model_perm_cap, sizeof(info->model_perm_cap));
+	EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap));
+	len += sprintf(page + len, "Manufacturer:         %-16.16s\n",
+		       info->manufacturer);
+	len += sprintf(page + len, "Type:                 %-4.4s\n",
+		       info->type);
+	if (info->model[0] != '\0')
+		/*
+		 * Sigh: the model field has been renamed with System z9
+		 * to model_capacity and a new model field has been added
+		 * after the plant field. To avoid confusing older programs
+		 * the "Model:" prints "model_capacity model" or just
+		 * "model_capacity" if the model string is empty .
+		 */
+		len += sprintf(page + len,
+			       "Model:                %-16.16s %-16.16s\n",
+			       info->model_capacity, info->model);
+	else
+		len += sprintf(page + len, "Model:                %-16.16s\n",
+			       info->model_capacity);
+	len += sprintf(page + len, "Sequence Code:        %-16.16s\n",
+		       info->sequence);
+	len += sprintf(page + len, "Plant:                %-4.4s\n",
+		       info->plant);
+	len += sprintf(page + len, "Model Capacity:       %-16.16s %08u\n",
+		       info->model_capacity, *(u32 *) info->model_cap_rating);
+	if (info->model_perm_cap[0] != '\0')
+		len += sprintf(page + len,
+			       "Model Perm. Capacity: %-16.16s %08u\n",
+			       info->model_perm_cap,
+			       *(u32 *) info->model_perm_cap_rating);
+	if (info->model_temp_cap[0] != '\0')
+		len += sprintf(page + len,
+			       "Model Temp. Capacity: %-16.16s %08u\n",
+			       info->model_temp_cap,
+			       *(u32 *) info->model_temp_cap_rating);
+	return len;
+}
+
+static int stsi_1_2_2(struct sysinfo_1_2_2 *info, char *page, int len)
+{
+	struct sysinfo_1_2_2_extension *ext;
+	int i;
+
+	if (stsi(info, 1, 2, 2) == -ENOSYS)
+		return len;
+	ext = (struct sysinfo_1_2_2_extension *)
+		((unsigned long) info + info->acc_offset);
+
+	len += sprintf(page + len, "\n");
+	len += sprintf(page + len, "CPUs Total:           %d\n",
+		       info->cpus_total);
+	len += sprintf(page + len, "CPUs Configured:      %d\n",
+		       info->cpus_configured);
+	len += sprintf(page + len, "CPUs Standby:         %d\n",
+		       info->cpus_standby);
+	len += sprintf(page + len, "CPUs Reserved:        %d\n",
+		       info->cpus_reserved);
+
+	if (info->format == 1) {
+		/*
+		 * Sigh 2. According to the specification the alternate
+		 * capability field is a 32 bit floating point number
+		 * if the higher order 8 bits are not zero. Printing
+		 * a floating point number in the kernel is a no-no,
+		 * always print the number as 32 bit unsigned integer.
+		 * The user-space needs to know about the strange
+		 * encoding of the alternate cpu capability.
+		 */
+		len += sprintf(page + len, "Capability:           %u %u\n",
+			       info->capability, ext->alt_capability);
+		for (i = 2; i <= info->cpus_total; i++)
+			len += sprintf(page + len,
+				       "Adjustment %02d-way:    %u %u\n",
+				       i, info->adjustment[i-2],
+				       ext->alt_adjustment[i-2]);
+
+	} else {
+		len += sprintf(page + len, "Capability:           %u\n",
+			       info->capability);
+		for (i = 2; i <= info->cpus_total; i++)
+			len += sprintf(page + len,
+				       "Adjustment %02d-way:    %u\n",
+				       i, info->adjustment[i-2]);
+	}
+
+	if (info->secondary_capability != 0)
+		len += sprintf(page + len, "Secondary Capability: %d\n",
+			       info->secondary_capability);
+	return len;
+}
+
+static int stsi_2_2_2(struct sysinfo_2_2_2 *info, char *page, int len)
+{
+	if (stsi(info, 2, 2, 2) == -ENOSYS)
+		return len;
+
+	EBCASC(info->name, sizeof(info->name));
+
+	len += sprintf(page + len, "\n");
+	len += sprintf(page + len, "LPAR Number:          %d\n",
+		       info->lpar_number);
+
+	len += sprintf(page + len, "LPAR Characteristics: ");
+	if (info->characteristics & LPAR_CHAR_DEDICATED)
+		len += sprintf(page + len, "Dedicated ");
+	if (info->characteristics & LPAR_CHAR_SHARED)
+		len += sprintf(page + len, "Shared ");
+	if (info->characteristics & LPAR_CHAR_LIMITED)
+		len += sprintf(page + len, "Limited ");
+	len += sprintf(page + len, "\n");
+
+	len += sprintf(page + len, "LPAR Name:            %-8.8s\n",
+		       info->name);
+
+	len += sprintf(page + len, "LPAR Adjustment:      %d\n",
+		       info->caf);
+
+	len += sprintf(page + len, "LPAR CPUs Total:      %d\n",
+		       info->cpus_total);
+	len += sprintf(page + len, "LPAR CPUs Configured: %d\n",
+		       info->cpus_configured);
+	len += sprintf(page + len, "LPAR CPUs Standby:    %d\n",
+		       info->cpus_standby);
+	len += sprintf(page + len, "LPAR CPUs Reserved:   %d\n",
+		       info->cpus_reserved);
+	len += sprintf(page + len, "LPAR CPUs Dedicated:  %d\n",
+		       info->cpus_dedicated);
+	len += sprintf(page + len, "LPAR CPUs Shared:     %d\n",
+		       info->cpus_shared);
+	return len;
+}
+
+static int stsi_3_2_2(struct sysinfo_3_2_2 *info, char *page, int len)
+{
+	int i;
+
+	if (stsi(info, 3, 2, 2) == -ENOSYS)
+		return len;
+	for (i = 0; i < info->count; i++) {
+		EBCASC(info->vm[i].name, sizeof(info->vm[i].name));
+		EBCASC(info->vm[i].cpi, sizeof(info->vm[i].cpi));
+		len += sprintf(page + len, "\n");
+		len += sprintf(page + len, "VM%02d Name:            %-8.8s\n",
+			       i, info->vm[i].name);
+		len += sprintf(page + len, "VM%02d Control Program: %-16.16s\n",
+			       i, info->vm[i].cpi);
+
+		len += sprintf(page + len, "VM%02d Adjustment:      %d\n",
+			       i, info->vm[i].caf);
+
+		len += sprintf(page + len, "VM%02d CPUs Total:      %d\n",
+			       i, info->vm[i].cpus_total);
+		len += sprintf(page + len, "VM%02d CPUs Configured: %d\n",
+			       i, info->vm[i].cpus_configured);
+		len += sprintf(page + len, "VM%02d CPUs Standby:    %d\n",
+			       i, info->vm[i].cpus_standby);
+		len += sprintf(page + len, "VM%02d CPUs Reserved:   %d\n",
+			       i, info->vm[i].cpus_reserved);
+	}
+	return len;
+}
+
+static int proc_read_sysinfo(char *page, char **start,
+			     off_t off, int count,
+			     int *eof, void *data)
+{
+	unsigned long info = get_zeroed_page(GFP_KERNEL);
+	int level, len;
+
+	if (!info)
+		return 0;
+
+	len = 0;
+	level = stsi_0();
+	if (level >= 1)
+		len = stsi_1_1_1((struct sysinfo_1_1_1 *) info, page, len);
+
+	if (level >= 1)
+		len = stsi_1_2_2((struct sysinfo_1_2_2 *) info, page, len);
+
+	if (level >= 2)
+		len = stsi_2_2_2((struct sysinfo_2_2_2 *) info, page, len);
+
+	if (level >= 3)
+		len = stsi_3_2_2((struct sysinfo_3_2_2 *) info, page, len);
+
+	free_page(info);
+	return len;
+}
+
+static __init int create_proc_sysinfo(void)
+{
+	create_proc_read_entry("sysinfo", 0444, NULL,
+			       proc_read_sysinfo, NULL);
+	return 0;
+}
+device_initcall(create_proc_sysinfo);
+
+/*
+ * Service levels interface.
+ */
+
+static DECLARE_RWSEM(service_level_sem);
+static LIST_HEAD(service_level_list);
+
+int register_service_level(struct service_level *slr)
+{
+	struct service_level *ptr;
+
+	down_write(&service_level_sem);
+	list_for_each_entry(ptr, &service_level_list, list)
+		if (ptr == slr) {
+			up_write(&service_level_sem);
+			return -EEXIST;
+		}
+	list_add_tail(&slr->list, &service_level_list);
+	up_write(&service_level_sem);
+	return 0;
+}
+EXPORT_SYMBOL(register_service_level);
+
+int unregister_service_level(struct service_level *slr)
+{
+	struct service_level *ptr, *next;
+	int rc = -ENOENT;
+
+	down_write(&service_level_sem);
+	list_for_each_entry_safe(ptr, next, &service_level_list, list) {
+		if (ptr != slr)
+			continue;
+		list_del(&ptr->list);
+		rc = 0;
+		break;
+	}
+	up_write(&service_level_sem);
+	return rc;
+}
+EXPORT_SYMBOL(unregister_service_level);
+
+static void *service_level_start(struct seq_file *m, loff_t *pos)
+{
+	down_read(&service_level_sem);
+	return seq_list_start(&service_level_list, *pos);
+}
+
+static void *service_level_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &service_level_list, pos);
+}
+
+static void service_level_stop(struct seq_file *m, void *p)
+{
+	up_read(&service_level_sem);
+}
+
+static int service_level_show(struct seq_file *m, void *p)
+{
+	struct service_level *slr;
+
+	slr = list_entry(p, struct service_level, list);
+	slr->seq_print(m, slr);
+	return 0;
+}
+
+static const struct seq_operations service_level_seq_ops = {
+	.start		= service_level_start,
+	.next		= service_level_next,
+	.stop		= service_level_stop,
+	.show		= service_level_show
+};
+
+static int service_level_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &service_level_seq_ops);
+}
+
+static const struct file_operations service_level_ops = {
+	.open		= service_level_open,
+	.read		= seq_read,
+	.llseek 	= seq_lseek,
+	.release	= seq_release
+};
+
+static void service_level_vm_print(struct seq_file *m,
+				   struct service_level *slr)
+{
+	char *query_buffer, *str;
+
+	query_buffer = kmalloc(1024, GFP_KERNEL | GFP_DMA);
+	if (!query_buffer)
+		return;
+	cpcmd("QUERY CPLEVEL", query_buffer, 1024, NULL);
+	str = strchr(query_buffer, '\n');
+	if (str)
+		*str = 0;
+	seq_printf(m, "VM: %s\n", query_buffer);
+	kfree(query_buffer);
+}
+
+static struct service_level service_level_vm = {
+	.seq_print = service_level_vm_print
+};
+
+static __init int create_proc_service_level(void)
+{
+	proc_create("service_levels", 0, NULL, &service_level_ops);
+	if (MACHINE_IS_VM)
+		register_service_level(&service_level_vm);
+	return 0;
+}
+subsys_initcall(create_proc_service_level);
+
+/*
+ * Bogomips calculation based on cpu capability.
+ */
+int get_cpu_capability(unsigned int *capability)
+{
+	struct sysinfo_1_2_2 *info;
+	int rc;
+
+	info = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+	rc = stsi(info, 1, 2, 2);
+	if (rc == -ENOSYS)
+		goto out;
+	rc = 0;
+	*capability = info->capability;
+out:
+	free_page((unsigned long) info);
+	return rc;
+}
+
+/*
+ * CPU capability might have changed. Therefore recalculate loops_per_jiffy.
+ */
+void s390_adjust_jiffies(void)
+{
+	struct sysinfo_1_2_2 *info;
+	const unsigned int fmil = 0x4b189680;	/* 1e7 as 32-bit float. */
+	FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR);
+	FP_DECL_EX;
+	unsigned int capability;
+
+	info = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!info)
+		return;
+
+	if (stsi(info, 1, 2, 2) != -ENOSYS) {
+		/*
+		 * Major sigh. The cpu capability encoding is "special".
+		 * If the first 9 bits of info->capability are 0 then it
+		 * is a 32 bit unsigned integer in the range 0 .. 2^23.
+		 * If the first 9 bits are != 0 then it is a 32 bit float.
+		 * In addition a lower value indicates a proportionally
+		 * higher cpu capacity. Bogomips are the other way round.
+		 * To get to a halfway suitable number we divide 1e7
+		 * by the cpu capability number. Yes, that means a floating
+		 * point division .. math-emu here we come :-)
+		 */
+		FP_UNPACK_SP(SA, &fmil);
+		if ((info->capability >> 23) == 0)
+			FP_FROM_INT_S(SB, info->capability, 32, int);
+		else
+			FP_UNPACK_SP(SB, &info->capability);
+		FP_DIV_S(SR, SA, SB);
+		FP_TO_INT_S(capability, SR, 32, 0);
+	} else
+		/*
+		 * Really old machine without stsi block for basic
+		 * cpu information. Report 42.0 bogomips.
+		 */
+		capability = 42;
+	loops_per_jiffy = capability * (500000/HZ);
+	free_page((unsigned long) info);
+}
+
+/*
+ * calibrate the delay loop
+ */
+void __cpuinit calibrate_delay(void)
+{
+	s390_adjust_jiffies();
+	/* Print the good old Bogomips line .. */
+	printk(KERN_DEBUG "Calibrating delay loop (skipped)... "
+	       "%lu.%02lu BogoMIPS preset\n", loops_per_jiffy/(500000/HZ),
+	       (loops_per_jiffy/(5000/HZ)) % 100);
+}
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index fc468cae446..f72d41068dc 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -331,6 +331,7 @@ static unsigned long long adjust_time(unsigned long long old,
 }
 
 static DEFINE_PER_CPU(atomic_t, clock_sync_word);
+static DEFINE_MUTEX(clock_sync_mutex);
 static unsigned long clock_sync_flags;
 
 #define CLOCK_SYNC_HAS_ETR	0
@@ -394,6 +395,20 @@ static void enable_sync_clock(void)
 	atomic_set_mask(0x80000000, sw_ptr);
 }
 
+/*
+ * Function to check if the clock is in sync.
+ */
+static inline int check_sync_clock(void)
+{
+	atomic_t *sw_ptr;
+	int rc;
+
+	sw_ptr = &get_cpu_var(clock_sync_word);
+	rc = (atomic_read(sw_ptr) & 0x80000000U) != 0;
+	put_cpu_var(clock_sync_sync);
+	return rc;
+}
+
 /* Single threaded workqueue used for etr and stp sync events */
 static struct workqueue_struct *time_sync_wq;
 
@@ -485,6 +500,8 @@ static void etr_reset(void)
 	if (etr_setr(&etr_eacr) == 0) {
 		etr_tolec = get_clock();
 		set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags);
+		if (etr_port0_online && etr_port1_online)
+			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 	} else if (etr_port0_online || etr_port1_online) {
 		pr_warning("The real or virtual hardware system does "
 			   "not provide an ETR interface\n");
@@ -533,8 +550,7 @@ void etr_switch_to_local(void)
 {
 	if (!etr_eacr.sl)
 		return;
-	if (test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
-		disable_sync_clock(NULL);
+	disable_sync_clock(NULL);
 	set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events);
 	queue_work(time_sync_wq, &etr_work);
 }
@@ -549,8 +565,7 @@ void etr_sync_check(void)
 {
 	if (!etr_eacr.es)
 		return;
-	if (test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
-		disable_sync_clock(NULL);
+	disable_sync_clock(NULL);
 	set_bit(ETR_EVENT_SYNC_CHECK, &etr_events);
 	queue_work(time_sync_wq, &etr_work);
 }
@@ -914,7 +929,7 @@ static struct etr_eacr etr_handle_update(struct etr_aib *aib,
 	 * Do not try to get the alternate port aib if the clock
 	 * is not in sync yet.
 	 */
-	if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags) && !eacr.es)
+	if (!check_sync_clock())
 		return eacr;
 
 	/*
@@ -997,7 +1012,6 @@ static void etr_work_fn(struct work_struct *work)
 		on_each_cpu(disable_sync_clock, NULL, 1);
 		del_timer_sync(&etr_timer);
 		etr_update_eacr(eacr);
-		clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 		goto out_unlock;
 	}
 
@@ -1071,18 +1085,13 @@ static void etr_work_fn(struct work_struct *work)
 		/* Both ports not usable. */
 		eacr.es = eacr.sl = 0;
 		sync_port = -1;
-		clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 	}
 
-	if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
-		eacr.es = 0;
-
 	/*
 	 * If the clock is in sync just update the eacr and return.
 	 * If there is no valid sync port wait for a port update.
 	 */
-	if (test_bit(CLOCK_SYNC_STP, &clock_sync_flags) ||
-	    eacr.es || sync_port < 0) {
+	if (check_sync_clock() || sync_port < 0) {
 		etr_update_eacr(eacr);
 		etr_set_tolec_timeout(now);
 		goto out_unlock;
@@ -1103,13 +1112,11 @@ static void etr_work_fn(struct work_struct *work)
 	 * and set up a timer to try again after 0.5 seconds
 	 */
 	etr_update_eacr(eacr);
-	set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 	if (now < etr_tolec + (1600000 << 12) ||
 	    etr_sync_clock_stop(&aib, sync_port) != 0) {
 		/* Sync failed. Try again in 1/2 second. */
 		eacr.es = 0;
 		etr_update_eacr(eacr);
-		clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 		etr_set_sync_timeout();
 	} else
 		etr_set_tolec_timeout(now);
@@ -1191,19 +1198,30 @@ static ssize_t etr_online_store(struct sys_device *dev,
 		return -EINVAL;
 	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
 		return -EOPNOTSUPP;
+	mutex_lock(&clock_sync_mutex);
 	if (dev == &etr_port0_dev) {
 		if (etr_port0_online == value)
-			return count;	/* Nothing to do. */
+			goto out;	/* Nothing to do. */
 		etr_port0_online = value;
+		if (etr_port0_online && etr_port1_online)
+			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+		else
+			clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
 		queue_work(time_sync_wq, &etr_work);
 	} else {
 		if (etr_port1_online == value)
-			return count;	/* Nothing to do. */
+			goto out;	/* Nothing to do. */
 		etr_port1_online = value;
+		if (etr_port0_online && etr_port1_online)
+			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+		else
+			clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
 		queue_work(time_sync_wq, &etr_work);
 	}
+out:
+	mutex_unlock(&clock_sync_mutex);
 	return count;
 }
 
@@ -1471,8 +1489,6 @@ static void stp_timing_alert(struct stp_irq_parm *intparm)
  */
 void stp_sync_check(void)
 {
-	if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
-		return;
 	disable_sync_clock(NULL);
 	queue_work(time_sync_wq, &stp_work);
 }
@@ -1485,8 +1501,6 @@ void stp_sync_check(void)
  */
 void stp_island_check(void)
 {
-	if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
-		return;
 	disable_sync_clock(NULL);
 	queue_work(time_sync_wq, &stp_work);
 }
@@ -1513,10 +1527,6 @@ static int stp_sync_clock(void *data)
 
 	enable_sync_clock();
 
-	set_bit(CLOCK_SYNC_STP, &clock_sync_flags);
-	if (test_and_clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
-		queue_work(time_sync_wq, &etr_work);
-
 	rc = 0;
 	if (stp_info.todoff[0] || stp_info.todoff[1] ||
 	    stp_info.todoff[2] || stp_info.todoff[3] ||
@@ -1535,9 +1545,6 @@ static int stp_sync_clock(void *data)
 	if (rc) {
 		disable_sync_clock(NULL);
 		stp_sync->in_sync = -EAGAIN;
-		clear_bit(CLOCK_SYNC_STP, &clock_sync_flags);
-		if (etr_port0_online || etr_port1_online)
-			queue_work(time_sync_wq, &etr_work);
 	} else
 		stp_sync->in_sync = 1;
 	xchg(&first, 0);
@@ -1569,6 +1576,10 @@ static void stp_work_fn(struct work_struct *work)
 	if (rc || stp_info.c == 0)
 		goto out_unlock;
 
+	/* Skip synchronization if the clock is already in sync. */
+	if (check_sync_clock())
+		goto out_unlock;
+
 	memset(&stp_sync, 0, sizeof(stp_sync));
 	get_online_cpus();
 	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
@@ -1684,8 +1695,14 @@ static ssize_t stp_online_store(struct sysdev_class *class,
 		return -EINVAL;
 	if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
 		return -EOPNOTSUPP;
+	mutex_lock(&clock_sync_mutex);
 	stp_online = value;
+	if (stp_online)
+		set_bit(CLOCK_SYNC_STP, &clock_sync_flags);
+	else
+		clear_bit(CLOCK_SYNC_STP, &clock_sync_flags);
 	queue_work(time_sync_wq, &stp_work);
+	mutex_unlock(&clock_sync_mutex);
 	return count;
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index cc362c9ea8f..3c72c9cf22b 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -74,7 +74,7 @@ static DEFINE_SPINLOCK(topology_lock);
 
 cpumask_t cpu_core_map[NR_CPUS];
 
-cpumask_t cpu_coregroup_map(unsigned int cpu)
+static cpumask_t cpu_coregroup_map(unsigned int cpu)
 {
 	struct core_info *core = &core_info;
 	unsigned long flags;
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 4584d81984c..c2e42cc65ce 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -61,9 +61,11 @@ extern pgm_check_handler_t do_asce_exception;
 #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
 
 #ifndef CONFIG_64BIT
+#define LONG "%08lx "
 #define FOURLONG "%08lx %08lx %08lx %08lx\n"
 static int kstack_depth_to_print = 12;
 #else /* CONFIG_64BIT */
+#define LONG "%016lx "
 #define FOURLONG "%016lx %016lx %016lx %016lx\n"
 static int kstack_depth_to_print = 20;
 #endif /* CONFIG_64BIT */
@@ -155,7 +157,7 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 			break;
 		if (i && ((i * sizeof (long) % 32) == 0))
 			printk("\n       ");
-		printk("%p ", (void *)*stack++);
+		printk(LONG, *stack++);
 	}
 	printk("\n");
 	show_trace(task, sp);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 690e1781968..89b2e7f1b7a 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -144,7 +144,6 @@ out:
 	return -ENOMEM;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
@@ -163,7 +162,6 @@ void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore)
 	free_page(page_table);
 	free_pages(segment_table, SEGMENT_ORDER);
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 static void __vdso_init_cr5(void *dummy)
 {
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index d796d05c9c0..7a2063eb88f 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -108,6 +108,8 @@ SECTIONS
 		EXIT_TEXT
 	}
 
+	/* early.c uses stsi, which requires page aligned data. */
+	. = ALIGN(PAGE_SIZE);
 	.init.data : {
 		INIT_DATA
 	}
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index e051cad1f1e..3e260b7e37b 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -4,6 +4,9 @@
 config HAVE_KVM
        bool
 
+config HAVE_KVM_IRQCHIP
+       bool
+
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
 	default y
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 61236102203..9d19803111b 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -103,7 +103,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 static intercept_handler_t instruction_handlers[256] = {
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
-	[0xb2] = kvm_s390_handle_priv,
+	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
 	[0xeb] = handle_lctlg,
 };
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index f4fe28a2521..0189356fe20 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -555,9 +555,14 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
 			   s390int->parm);
 		break;
+	case KVM_S390_SIGP_SET_PREFIX:
+		inti->prefix.address = s390int->parm;
+		inti->type = s390int->type;
+		VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
+			   s390int->parm);
+		break;
 	case KVM_S390_SIGP_STOP:
 	case KVM_S390_RESTART:
-	case KVM_S390_SIGP_SET_PREFIX:
 	case KVM_S390_INT_EMERGENCY:
 		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
 		inti->type = s390int->type;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0d33893e1e8..f4d56e9939c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -23,7 +23,7 @@
 #include <linux/timer.h>
 #include <asm/lowcore.h>
 #include <asm/pgtable.h>
-
+#include <asm/nmi.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -286,7 +286,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup,
 		 (unsigned long) vcpu);
 	get_cpu_id(&vcpu->arch.cpu_id);
-	vcpu->arch.cpu_id.version = 0xfe;
+	vcpu->arch.cpu_id.version = 0xff;
 	return 0;
 }
 
@@ -422,8 +422,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-				    struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	return -EINVAL; /* not implemented yet */
 }
@@ -440,8 +440,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
-extern void s390_handle_mcck(void);
-
 static void __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 3893cf12eac..00bbe69b78d 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -50,7 +50,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 
 /* implemented in priv.c */
-int kvm_s390_handle_priv(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 3605df45dd4..4b88834b8dd 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -304,12 +304,24 @@ static intercept_handler_t priv_handlers[256] = {
 	[0xb1] = handle_stfl,
 };
 
-int kvm_s390_handle_priv(struct kvm_vcpu *vcpu)
+int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 {
 	intercept_handler_t handler;
 
+	/*
+	 * a lot of B2 instructions are priviledged. We first check for
+	 * the priviledges ones, that we can handle in the kernel. If the
+	 * kernel can handle this instruction, we check for the problem
+	 * state bit and (a) handle the instruction or (b) send a code 2
+	 * program check.
+	 * Anything else goes to userspace.*/
 	handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
+	if (handler) {
+		if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+			return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+		else
+			return handler(vcpu);
+	}
 	return -ENOTSUPP;
 }
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 2a01b9e0280..f27dbedf086 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -153,8 +153,6 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 
 	switch (parameter & 0xff) {
 	case 0:
-		printk(KERN_WARNING "kvm: request to switch to ESA/390 mode"
-							" not supported");
 		rc = 3; /* not operational */
 		break;
 	case 1:
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 6ccb9fab055..3f5f680726e 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/timex.h>
+#include <linux/module.h>
 #include <linux/irqflags.h>
 #include <linux/interrupt.h>
 
@@ -92,6 +93,7 @@ out:
 	local_irq_restore(flags);
 	preempt_enable();
 }
+EXPORT_SYMBOL(__udelay);
 
 /*
  * Simple udelay variant. To be used on startup and reboot
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index ae5cf5d03d4..4143b7c1909 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -44,7 +44,11 @@ static inline char *__strnend(const char *s, size_t n)
  */
 size_t strlen(const char *s)
 {
+#if __GNUC__ < 4
 	return __strend(s) - s;
+#else
+	return __builtin_strlen(s);
+#endif
 }
 EXPORT_SYMBOL(strlen);
 
@@ -70,6 +74,7 @@ EXPORT_SYMBOL(strnlen);
  */
 char *strcpy(char *dest, const char *src)
 {
+#if __GNUC__ < 4
 	register int r0 asm("0") = 0;
 	char *ret = dest;
 
@@ -78,6 +83,9 @@ char *strcpy(char *dest, const char *src)
 		      : "+&a" (dest), "+&a" (src) : "d" (r0)
 		      : "cc", "memory" );
 	return ret;
+#else
+	return __builtin_strcpy(dest, src);
+#endif
 }
 EXPORT_SYMBOL(strcpy);
 
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 4d537205e83..833e8366c35 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -200,29 +200,6 @@ static void do_low_address(struct pt_regs *regs, unsigned long error_code)
 	do_no_context(regs, error_code, 0);
 }
 
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
-static int do_out_of_memory(struct pt_regs *regs, unsigned long error_code,
-			    unsigned long address)
-{
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
-
-	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		return 1;
-	}
-	printk("VM: killing process %s\n", tsk->comm);
-	if (regs->psw.mask & PSW_MASK_PSTATE)
-		do_group_exit(SIGKILL);
-	do_no_context(regs, error_code, address);
-	return 0;
-}
-
 static void do_sigbus(struct pt_regs *regs, unsigned long error_code,
 		      unsigned long address)
 {
@@ -367,7 +344,6 @@ good_area:
 			goto bad_area;
 	}
 
-survive:
 	if (is_vm_hugetlb_page(vma))
 		address &= HPAGE_MASK;
 	/*
@@ -378,8 +354,8 @@ survive:
 	fault = handle_mm_fault(mm, vma, address, write);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM) {
-			if (do_out_of_memory(regs, error_code, address))
-				goto survive;
+			up_read(&mm->mmap_sem);
+			pagefault_out_of_memory();
 			return;
 		} else if (fault & VM_FAULT_SIGBUS) {
 			do_sigbus(regs, error_code, address);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f0258ca3b17..c634dfbe92e 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -40,7 +40,9 @@
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
+
 char  empty_zero_page[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+EXPORT_SYMBOL(empty_zero_page);
 
 /*
  * paging_init() sets up the page tables
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 6b6ddc4ea02..be6c1cf4ad5 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -258,6 +258,10 @@ int s390_enable_sie(void)
 	struct task_struct *tsk = current;
 	struct mm_struct *mm, *old_mm;
 
+	/* Do we have switched amode? If no, we cannot do sie */
+	if (!switch_amode)
+		return -EINVAL;
+
 	/* Do we have pgstes? if yes, we are done */
 	if (tsk->mm->context.has_pgste)
 		return 0;
@@ -292,7 +296,7 @@ int s390_enable_sie(void)
 	tsk->mm = tsk->active_mm = mm;
 	preempt_disable();
 	update_mm(mm, tsk);
-	cpu_set(smp_processor_id(), mm->cpu_vm_mask);
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
 	preempt_enable();
 	task_unlock(tsk);
 	mmput(old_mm);
diff --git a/arch/sh/include/asm/socket.h b/arch/sh/include/asm/socket.h
index 6d4bf651295..345653b9682 100644
--- a/arch/sh/include/asm/socket.h
+++ b/arch/sh/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* __ASM_SH_SOCKET_H */
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 90d63aefd27..3f1372eb009 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -51,7 +51,7 @@ int show_interrupts(struct seq_file *p, void *v)
 			goto unlock;
 		seq_printf(p, "%3d: ",i);
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "-%-8s", irq_desc[i].name);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/sparc/include/asm/socket.h b/arch/sparc/include/asm/socket.h
index bf50d0c2d58..982a12f959f 100644
--- a/arch/sparc/include/asm/socket.h
+++ b/arch/sparc/include/asm/socket.h
@@ -50,6 +50,9 @@
 
 #define SO_MARK			0x0022
 
+#define SO_TIMESTAMPING		0x0023
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index ec81cdedef2..ee38e731bfa 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -57,6 +57,8 @@ static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned i
 
 static inline void tlb_flush_mmu(struct mmu_gather *mp)
 {
+	if (!mp->fullmm)
+		flush_tlb_pending();
 	if (mp->need_flush) {
 		free_pages_and_swap_cache(mp->pages, mp->pages_nr);
 		mp->pages_nr = 0;
@@ -78,8 +80,6 @@ static inline void tlb_finish_mmu(struct mmu_gather *mp, unsigned long start, un
 
 	if (mp->fullmm)
 		mp->fullmm = 0;
-	else
-		flush_tlb_pending();
 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 1c378d8e90c..8ba064f08a6 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -185,7 +185,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %9s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 6cd1a5b6506..79457f682b5 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1031,7 +1031,7 @@ void smp_fetch_global_regs(void)
  *    If the address space is non-shared (ie. mm->count == 1) we avoid
  *    cross calls when we want to flush the currently running process's
  *    tlb state.  This is done by clearing all cpu bits except the current
- *    processor's in current->active_mm->cpu_vm_mask and performing the
+ *    processor's in current->mm->cpu_vm_mask and performing the
  *    flush locally only.  This will force any subsequent cpus which run
  *    this task to flush the context from the local tlb if the process
  *    migrates to another cpu (again).
@@ -1074,7 +1074,7 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long
 	u32 ctx = CTX_HWBITS(mm->context);
 	int cpu = get_cpu();
 
-	if (mm == current->active_mm && atomic_read(&mm->mm_users) == 1)
+	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
 		mm->cpu_vm_mask = cpumask_of_cpu(cpu);
 	else
 		smp_cross_call_masked(&xcall_flush_tlb_pending,
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index f93c42a2b52..a8000b1cda7 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -51,7 +51,7 @@ sys_call_table32:
 /*150*/	.word sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64
 	.word compat_sys_fcntl64, sys_inotify_rm_watch, compat_sys_statfs, compat_sys_fstatfs, sys_oldumount
 /*160*/	.word compat_sys_sched_setaffinity, compat_sys_sched_getaffinity, sys32_getdomainname, sys32_setdomainname, sys_nis_syscall
-	.word sys_quotactl, sys_set_tid_address, compat_sys_mount, sys_ustat, sys32_setxattr
+	.word sys_quotactl, sys_set_tid_address, compat_sys_mount, compat_sys_ustat, sys32_setxattr
 /*170*/	.word sys32_lsetxattr, sys32_fsetxattr, sys_getxattr, sys_lgetxattr, compat_sys_getdents
 	.word sys_setsid, sys_fchdir, sys32_fgetxattr, sys_listxattr, sys_llistxattr
 /*180*/	.word sys32_flistxattr, sys_removexattr, sys_lremovexattr, compat_sys_sigpending, sys_ni_syscall
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 2db3c2229b9..4ee2e48c4b3 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -36,10 +36,10 @@
 #include <linux/clocksource.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/irq.h>
 
 #include <asm/oplib.h>
 #include <asm/timer.h>
-#include <asm/irq.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/starfire.h>
@@ -724,12 +724,14 @@ void timer_interrupt(int irq, struct pt_regs *regs)
 	unsigned long tick_mask = tick_ops->softint_mask;
 	int cpu = smp_processor_id();
 	struct clock_event_device *evt = &per_cpu(sparc64_events, cpu);
+	struct irq_desc *desc;
 
 	clear_softint(tick_mask);
 
 	irq_enter();
 
-	kstat_this_cpu.irqs[0]++;
+	desc = irq_to_desc(0);
+	kstat_incr_irqs_this_cpu(0, desc);
 
 	if (unlikely(!evt->event_handler)) {
 		printk(KERN_WARNING
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index fde510b664d..434224e2229 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -86,7 +86,7 @@ static int uml_net_rx(struct net_device *dev)
 		drop_skb->dev = dev;
 		/* Read a packet into drop_skb and don't do anything with it. */
 		(*lp->read)(lp->fd, drop_skb, lp);
-		lp->stats.rx_dropped++;
+		dev->stats.rx_dropped++;
 		return 0;
 	}
 
@@ -99,8 +99,8 @@ static int uml_net_rx(struct net_device *dev)
 		skb_trim(skb, pkt_len);
 		skb->protocol = (*lp->protocol)(skb);
 
-		lp->stats.rx_bytes += skb->len;
-		lp->stats.rx_packets++;
+		dev->stats.rx_bytes += skb->len;
+		dev->stats.rx_packets++;
 		netif_rx(skb);
 		return pkt_len;
 	}
@@ -224,8 +224,8 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	len = (*lp->write)(lp->fd, skb, lp);
 
 	if (len == skb->len) {
-		lp->stats.tx_packets++;
-		lp->stats.tx_bytes += skb->len;
+		dev->stats.tx_packets++;
+		dev->stats.tx_bytes += skb->len;
 		dev->trans_start = jiffies;
 		netif_start_queue(dev);
 
@@ -234,7 +234,7 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 	else if (len == 0) {
 		netif_start_queue(dev);
-		lp->stats.tx_dropped++;
+		dev->stats.tx_dropped++;
 	}
 	else {
 		netif_start_queue(dev);
@@ -248,12 +248,6 @@ static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static struct net_device_stats *uml_net_get_stats(struct net_device *dev)
-{
-	struct uml_net_private *lp = netdev_priv(dev);
-	return &lp->stats;
-}
-
 static void uml_net_set_multicast_list(struct net_device *dev)
 {
 	return;
@@ -377,6 +371,18 @@ static void net_device_release(struct device *dev)
 	free_netdev(netdev);
 }
 
+static const struct net_device_ops uml_netdev_ops = {
+	.ndo_open 		= uml_net_open,
+	.ndo_stop 		= uml_net_close,
+	.ndo_start_xmit 	= uml_net_start_xmit,
+	.ndo_set_multicast_list = uml_net_set_multicast_list,
+	.ndo_tx_timeout 	= uml_net_tx_timeout,
+	.ndo_set_mac_address	= uml_net_set_mac,
+	.ndo_change_mtu 	= uml_net_change_mtu,
+	.ndo_set_mac_address 	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
 /*
  * Ensures that platform_driver_register is called only once by
  * eth_configure.  Will be set in an initcall.
@@ -473,14 +479,7 @@ static void eth_configure(int n, void *init, char *mac,
 
 	set_ether_mac(dev, device->mac);
 	dev->mtu = transport->user->mtu;
-	dev->open = uml_net_open;
-	dev->hard_start_xmit = uml_net_start_xmit;
-	dev->stop = uml_net_close;
-	dev->get_stats = uml_net_get_stats;
-	dev->set_multicast_list = uml_net_set_multicast_list;
-	dev->tx_timeout = uml_net_tx_timeout;
-	dev->set_mac_address = uml_net_set_mac;
-	dev->change_mtu = uml_net_change_mtu;
+	dev->netdev_ops = &uml_netdev_ops;
 	dev->ethtool_ops = &uml_net_ethtool_ops;
 	dev->watchdog_timeo = (HZ >> 1);
 	dev->irq = UM_ETH_IRQ;
diff --git a/arch/um/include/shared/net_kern.h b/arch/um/include/shared/net_kern.h
index d843c7924a7..5c367f22595 100644
--- a/arch/um/include/shared/net_kern.h
+++ b/arch/um/include/shared/net_kern.h
@@ -26,7 +26,7 @@ struct uml_net_private {
 	spinlock_t lock;
 	struct net_device *dev;
 	struct timer_list tl;
-	struct net_device_stats stats;
+
 	struct work_struct work;
 	int fd;
 	unsigned char mac[ETH_ALEN];
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 3d7aad09b17..336b6156907 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -42,7 +42,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bc2fbadff9f..3a330a437c6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -165,6 +165,9 @@ config GENERIC_HARDIRQS
 	bool
 	default y
 
+config GENERIC_HARDIRQS_NO__DO_IRQ
+       def_bool y
+
 config GENERIC_IRQ_PROBE
 	bool
 	default y
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 5a0d76dc56a..8ef8876666b 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -557,7 +557,7 @@ ia32_sys_call_table:
 	.quad sys32_olduname
 	.quad sys_umask		/* 60 */
 	.quad sys_chroot
-	.quad sys32_ustat
+	.quad compat_sys_ustat
 	.quad sys_dup2
 	.quad sys_getppid
 	.quad sys_getpgrp		/* 65 */
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 6c0d7f6231a..efac92fd1ef 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -638,28 +638,6 @@ long sys32_uname(struct old_utsname __user *name)
 	return err ? -EFAULT : 0;
 }
 
-long sys32_ustat(unsigned dev, struct ustat32 __user *u32p)
-{
-	struct ustat u;
-	mm_segment_t seg;
-	int ret;
-
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-	ret = sys_ustat(dev, (struct ustat __user *)&u);
-	set_fs(seg);
-	if (ret < 0)
-		return ret;
-
-	if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) ||
-	    __put_user((__u32) u.f_tfree, &u32p->f_tfree) ||
-	    __put_user((__u32) u.f_tinode, &u32p->f_tfree) ||
-	    __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) ||
-	    __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack)))
-		ret = -EFAULT;
-	return ret;
-}
-
 asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv,
 			     compat_uptr_t __user *envp, struct pt_regs *regs)
 {
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 50ca486fd88..1f7e6251728 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -129,13 +129,6 @@ typedef struct compat_siginfo {
 	} _sifields;
 } compat_siginfo_t;
 
-struct ustat32 {
-	__u32			f_tfree;
-	compat_ino_t		f_tinode;
-	char			f_fname[6];
-	char			f_fpack[6];
-};
-
 #define IA32_STACK_TOP IA32_PAGE_OFFSET
 
 #ifdef __KERNEL__
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 886c9402ec4..dc3f6cf1170 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -15,6 +15,7 @@
 #define __KVM_HAVE_DEVICE_ASSIGNMENT
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
+#define __KVM_HAVE_GUEST_DEBUG
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -212,7 +213,30 @@ struct kvm_pit_channel_state {
 	__s64 count_load_time;
 };
 
+struct kvm_debug_exit_arch {
+	__u32 exception;
+	__u32 pad;
+	__u64 pc;
+	__u64 dr6;
+	__u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+#define KVM_GUESTDBG_USE_HW_BP		0x00020000
+#define KVM_GUESTDBG_INJECT_DB		0x00040000
+#define KVM_GUESTDBG_INJECT_BP		0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+	__u64 debugreg[8];
+};
+
 struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
+
+struct kvm_reinject_control {
+	__u8 pit_reinject;
+	__u8 reserved[31];
+};
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 730843d1d2f..f0faf58044f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -22,6 +22,7 @@
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
+#include <asm/msr-index.h>
 
 #define KVM_MAX_VCPUS 16
 #define KVM_MEMORY_SLOTS 32
@@ -134,11 +135,18 @@ enum {
 
 #define KVM_NR_MEM_OBJS 40
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
+#define KVM_NR_DB_REGS	4
+
+#define DR6_BD		(1 << 13)
+#define DR6_BS		(1 << 14)
+#define DR6_FIXED_1	0xffff0ff0
+#define DR6_VOLATILE	0x0000e00f
+
+#define DR7_BP_EN_MASK	0x000000ff
+#define DR7_GE		(1 << 9)
+#define DR7_GD		(1 << 13)
+#define DR7_FIXED_1	0x00000400
+#define DR7_VOLATILE	0xffff23ff
 
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
@@ -162,7 +170,8 @@ struct kvm_pte_chain {
  *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
  *   bits 4:7 - page table level for this shadow (1-4)
  *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
+ *   bit   16 - direct mapping of virtual to physical mapping at gfn
+ *              used for real mode and two-dimensional paging
  *   bits 17:19 - common access permissions for all ptes in this shadow page
  */
 union kvm_mmu_page_role {
@@ -172,9 +181,10 @@ union kvm_mmu_page_role {
 		unsigned level:4;
 		unsigned quadrant:2;
 		unsigned pad_for_nice_hex_output:6;
-		unsigned metaphysical:1;
+		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
+		unsigned cr4_pge:1;
 	};
 };
 
@@ -218,6 +228,18 @@ struct kvm_pv_mmu_op_buffer {
 	char buf[512] __aligned(sizeof(long));
 };
 
+struct kvm_pio_request {
+	unsigned long count;
+	int cur_count;
+	gva_t guest_gva;
+	int in;
+	int port;
+	int size;
+	int string;
+	int down;
+	int rep;
+};
+
 /*
  * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
  * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
@@ -236,6 +258,7 @@ struct kvm_mmu {
 	hpa_t root_hpa;
 	int root_level;
 	int shadow_root_level;
+	union kvm_mmu_page_role base_role;
 
 	u64 *pae_root;
 };
@@ -258,6 +281,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr3;
 	unsigned long cr4;
 	unsigned long cr8;
+	u32 hflags;
 	u64 pdptrs[4]; /* pae */
 	u64 shadow_efer;
 	u64 apic_base;
@@ -338,6 +362,15 @@ struct kvm_vcpu_arch {
 
 	struct mtrr_state_type mtrr_state;
 	u32 pat;
+
+	int switch_db_regs;
+	unsigned long host_db[KVM_NR_DB_REGS];
+	unsigned long host_dr6;
+	unsigned long host_dr7;
+	unsigned long db[KVM_NR_DB_REGS];
+	unsigned long dr6;
+	unsigned long dr7;
+	unsigned long eff_db[KVM_NR_DB_REGS];
 };
 
 struct kvm_mem_alias {
@@ -378,6 +411,7 @@ struct kvm_arch{
 
 	unsigned long irq_sources_bitmap;
 	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
+	u64 vm_init_tsc;
 };
 
 struct kvm_vm_stat {
@@ -446,8 +480,7 @@ struct kvm_x86_ops {
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
 	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
-			       struct kvm_debug_guest *dbg);
-	void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
+			       struct kvm_guest_debug *dbg);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -583,16 +616,12 @@ void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
 			   u32 error_code);
 
-void kvm_pic_set_irq(void *opaque, int irq, int level);
+int kvm_pic_set_irq(void *opaque, int irq, int level);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
 void fx_init(struct kvm_vcpu *vcpu);
 
-int emulator_read_std(unsigned long addr,
-		      void *val,
-		      unsigned int bytes,
-		      struct kvm_vcpu *vcpu);
 int emulator_write_emulated(unsigned long addr,
 			    const void *val,
 			    unsigned int bytes,
@@ -737,6 +766,10 @@ enum {
 	TASK_SWITCH_GATE = 3,
 };
 
+#define HF_GIF_MASK		(1 << 0)
+#define HF_HIF_MASK		(1 << 1)
+#define HF_VINTR_MASK		(1 << 2)
+
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 358acc59ae0..f4e505f286b 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -18,11 +18,15 @@
 #define _EFER_LME		8  /* Long mode enable */
 #define _EFER_LMA		10 /* Long mode active (read-only) */
 #define _EFER_NX		11 /* No execute enable */
+#define _EFER_SVME		12 /* Enable virtualization */
+#define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
 
 #define EFER_SCE		(1<<_EFER_SCE)
 #define EFER_LME		(1<<_EFER_LME)
 #define EFER_LMA		(1<<_EFER_LMA)
 #define EFER_NX			(1<<_EFER_NX)
+#define EFER_SVME		(1<<_EFER_SVME)
+#define EFER_FFXSR		(1<<_EFER_FFXSR)
 
 /* Intel MSRs. Some also available on other CPUs */
 #define MSR_IA32_PERFCTR0		0x000000c1
@@ -360,4 +364,9 @@
 #define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
 #define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
 
+/* AMD-V MSRs */
+
+#define MSR_VM_CR                       0xc0010114
+#define MSR_VM_HSAVE_PA                 0xc0010117
+
 #endif /* _ASM_X86_MSR_INDEX_H */
diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h
index a8894647dd9..3ac5032fae0 100644
--- a/arch/x86/include/asm/prctl.h
+++ b/arch/x86/include/asm/prctl.h
@@ -6,8 +6,4 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
-#ifdef CONFIG_X86_64
-extern long sys_arch_prctl(int, unsigned long);
-#endif /* CONFIG_X86_64 */
-
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ebe858cdc8a..c2308f5250f 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -1,27 +1,12 @@
 #ifndef _ASM_X86_SETUP_H
 #define _ASM_X86_SETUP_H
 
+#ifdef __KERNEL__
+
 #define COMMAND_LINE_SIZE 2048
 
 #ifndef __ASSEMBLY__
 
-/* Interrupt control for vSMPowered x86_64 systems */
-void vsmp_init(void);
-
-
-void setup_bios_corruption_check(void);
-
-
-#ifdef CONFIG_X86_VISWS
-extern void visws_early_detect(void);
-extern int is_visws_box(void);
-#else
-static inline void visws_early_detect(void) { }
-static inline int is_visws_box(void) { return 0; }
-#endif
-
-extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
-extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip);
 /*
  * Any setup quirks to be performed?
  */
@@ -48,16 +33,8 @@ struct x86_quirks {
 	int (*update_genapic)(void);
 };
 
-extern struct x86_quirks *x86_quirks;
-extern unsigned long saved_video_mode;
-
-#ifndef CONFIG_PARAVIRT
-#define paravirt_post_allocator_init()	do {} while (0)
-#endif
 #endif /* __ASSEMBLY__ */
 
-#ifdef __KERNEL__
-
 #ifdef __i386__
 
 #include <linux/pfn.h>
@@ -78,6 +55,28 @@ extern unsigned long saved_video_mode;
 #ifndef __ASSEMBLY__
 #include <asm/bootparam.h>
 
+/* Interrupt control for vSMPowered x86_64 systems */
+void vsmp_init(void);
+
+void setup_bios_corruption_check(void);
+
+#ifdef CONFIG_X86_VISWS
+extern void visws_early_detect(void);
+extern int is_visws_box(void);
+#else
+static inline void visws_early_detect(void) { }
+static inline int is_visws_box(void) { return 0; }
+#endif
+
+extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip);
+extern struct x86_quirks *x86_quirks;
+extern unsigned long saved_video_mode;
+
+#ifndef CONFIG_PARAVIRT
+#define paravirt_post_allocator_init()	do {} while (0)
+#endif
+
 #ifndef _SETUP
 
 /*
diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h
index 8ab9cc8b2ec..ca8bf2cd0ba 100644
--- a/arch/x86/include/asm/socket.h
+++ b/arch/x86/include/asm/socket.h
@@ -54,4 +54,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif /* _ASM_X86_SOCKET_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 1b8afa78e86..82ada75f3eb 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -174,10 +174,6 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_CPUID_FEATURE_SHIFT 2
 #define SVM_CPUID_FUNC 0x8000000a
 
-#define MSR_EFER_SVME_MASK (1ULL << 12)
-#define MSR_VM_CR       0xc0010114
-#define MSR_VM_HSAVE_PA 0xc0010117ULL
-
 #define SVM_VM_CR_SVM_DISABLE 4
 
 #define SVM_SELECTOR_S_SHIFT 4
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index ffb08be2a53..72a6dcd1299 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -70,8 +70,6 @@ struct old_utsname;
 asmlinkage long sys32_olduname(struct oldold_utsname __user *);
 long sys32_uname(struct old_utsname __user *);
 
-long sys32_ustat(unsigned, struct ustat32 __user *);
-
 asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *,
 			     compat_uptr_t __user *, struct pt_regs *);
 asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *);
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index c0b0bda754e..e26d34b0bc7 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -74,6 +74,7 @@ asmlinkage long sys_vfork(struct pt_regs *);
 asmlinkage long sys_execve(char __user *, char __user * __user *,
 			   char __user * __user *,
 			   struct pt_regs *);
+long sys_arch_prctl(int, unsigned long);
 
 /* kernel/ioport.c */
 asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 59363627523..e0f9aa16358 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -118,7 +118,7 @@ static inline void cpu_svm_disable(void)
 
 	wrmsrl(MSR_VM_HSAVE_PA, 0);
 	rdmsrl(MSR_EFER, efer);
-	wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
+	wrmsrl(MSR_EFER, efer & ~EFER_SVME);
 }
 
 /** Makes sure SVM is disabled, if it is supported on the CPU
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index d0238e6151d..498f944010b 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -270,8 +270,9 @@ enum vmcs_field {
 
 #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
 #define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
-#define INTR_TYPE_EXCEPTION             (3 << 8) /* processor exception */
+#define INTR_TYPE_HARD_EXCEPTION	(3 << 8) /* processor exception */
 #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
+#define INTR_TYPE_SOFT_EXCEPTION	(6 << 8) /* software exception */
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */
 #define GUEST_INTR_STATE_STI		0x00000001
@@ -311,7 +312,7 @@ enum vmcs_field {
 #define DEBUG_REG_ACCESS_TYPE           0x10    /* 4, direction of access */
 #define TYPE_MOV_TO_DR                  (0 << 4)
 #define TYPE_MOV_FROM_DR                (1 << 4)
-#define DEBUG_REG_ACCESS_REG            0xf00   /* 11:8, general purpose reg. */
+#define DEBUG_REG_ACCESS_REG(eq)        (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */
 
 
 /* segment AR */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 24ff26a38ad..5fff00c70de 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -4,6 +4,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/smp.h>
+#include <linux/sched.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
 
@@ -56,11 +57,16 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 
 	/*
 	 * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
-	 * with P/T states and does not stop in deep C-states
+	 * with P/T states and does not stop in deep C-states.
+	 *
+	 * It is also reliable across cores and sockets. (but not across
+	 * cabinets - we turn it off in that case explicitly.)
 	 */
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+		set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
+		sched_clock_stable = 1;
 	}
 
 }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index a00545fe5cd..648b3a2a3a4 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -80,6 +80,7 @@ static inline void hpet_clear_mapping(void)
  */
 static int boot_hpet_disable;
 int hpet_force_user;
+static int hpet_verbose;
 
 static int __init hpet_setup(char *str)
 {
@@ -88,6 +89,8 @@ static int __init hpet_setup(char *str)
 			boot_hpet_disable = 1;
 		if (!strncmp("force", str, 5))
 			hpet_force_user = 1;
+		if (!strncmp("verbose", str, 7))
+			hpet_verbose = 1;
 	}
 	return 1;
 }
@@ -119,6 +122,43 @@ int is_hpet_enabled(void)
 }
 EXPORT_SYMBOL_GPL(is_hpet_enabled);
 
+static void _hpet_print_config(const char *function, int line)
+{
+	u32 i, timers, l, h;
+	printk(KERN_INFO "hpet: %s(%d):\n", function, line);
+	l = hpet_readl(HPET_ID);
+	h = hpet_readl(HPET_PERIOD);
+	timers = ((l & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
+	printk(KERN_INFO "hpet: ID: 0x%x, PERIOD: 0x%x\n", l, h);
+	l = hpet_readl(HPET_CFG);
+	h = hpet_readl(HPET_STATUS);
+	printk(KERN_INFO "hpet: CFG: 0x%x, STATUS: 0x%x\n", l, h);
+	l = hpet_readl(HPET_COUNTER);
+	h = hpet_readl(HPET_COUNTER+4);
+	printk(KERN_INFO "hpet: COUNTER_l: 0x%x, COUNTER_h: 0x%x\n", l, h);
+
+	for (i = 0; i < timers; i++) {
+		l = hpet_readl(HPET_Tn_CFG(i));
+		h = hpet_readl(HPET_Tn_CFG(i)+4);
+		printk(KERN_INFO "hpet: T%d: CFG_l: 0x%x, CFG_h: 0x%x\n",
+		       i, l, h);
+		l = hpet_readl(HPET_Tn_CMP(i));
+		h = hpet_readl(HPET_Tn_CMP(i)+4);
+		printk(KERN_INFO "hpet: T%d: CMP_l: 0x%x, CMP_h: 0x%x\n",
+		       i, l, h);
+		l = hpet_readl(HPET_Tn_ROUTE(i));
+		h = hpet_readl(HPET_Tn_ROUTE(i)+4);
+		printk(KERN_INFO "hpet: T%d ROUTE_l: 0x%x, ROUTE_h: 0x%x\n",
+		       i, l, h);
+	}
+}
+
+#define hpet_print_config()					\
+do {								\
+	if (hpet_verbose)					\
+		_hpet_print_config(__FUNCTION__, __LINE__);	\
+} while (0)
+
 /*
  * When the hpet driver (/dev/hpet) is enabled, we need to reserve
  * timer 0 and timer 1 in case of RTC emulation.
@@ -191,27 +231,37 @@ static struct clock_event_device hpet_clockevent = {
 	.rating		= 50,
 };
 
-static void hpet_start_counter(void)
+static void hpet_stop_counter(void)
 {
 	unsigned long cfg = hpet_readl(HPET_CFG);
-
 	cfg &= ~HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 	hpet_writel(0, HPET_COUNTER);
 	hpet_writel(0, HPET_COUNTER + 4);
+}
+
+static void hpet_start_counter(void)
+{
+	unsigned long cfg = hpet_readl(HPET_CFG);
 	cfg |= HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 }
 
+static void hpet_restart_counter(void)
+{
+	hpet_stop_counter();
+	hpet_start_counter();
+}
+
 static void hpet_resume_device(void)
 {
 	force_hpet_resume();
 }
 
-static void hpet_restart_counter(void)
+static void hpet_resume_counter(void)
 {
 	hpet_resume_device();
-	hpet_start_counter();
+	hpet_restart_counter();
 }
 
 static void hpet_enable_legacy_int(void)
@@ -259,29 +309,23 @@ static int hpet_setup_msi_irq(unsigned int irq);
 static void hpet_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt, int timer)
 {
-	unsigned long cfg, cmp, now;
+	unsigned long cfg;
 	uint64_t delta;
 
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
+		hpet_stop_counter();
 		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
 		delta >>= evt->shift;
-		now = hpet_readl(HPET_COUNTER);
-		cmp = now + (unsigned long) delta;
 		cfg = hpet_readl(HPET_Tn_CFG(timer));
 		/* Make sure we use edge triggered interrupts */
 		cfg &= ~HPET_TN_LEVEL;
 		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
 		       HPET_TN_SETVAL | HPET_TN_32BIT;
 		hpet_writel(cfg, HPET_Tn_CFG(timer));
-		/*
-		 * The first write after writing TN_SETVAL to the
-		 * config register sets the counter value, the second
-		 * write sets the period.
-		 */
-		hpet_writel(cmp, HPET_Tn_CMP(timer));
-		udelay(1);
 		hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
+		hpet_start_counter();
+		hpet_print_config();
 		break;
 
 	case CLOCK_EVT_MODE_ONESHOT:
@@ -308,6 +352,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 			irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 			enable_irq(hdev->irq);
 		}
+		hpet_print_config();
 		break;
 	}
 }
@@ -526,6 +571,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 
 	num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT);
 	num_timers++; /* Value read out starts from 0 */
+	hpet_print_config();
 
 	hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
 	if (!hpet_devs)
@@ -695,7 +741,7 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.shift		= HPET_SHIFT,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-	.resume		= hpet_restart_counter,
+	.resume		= hpet_resume_counter,
 #ifdef CONFIG_X86_64
 	.vread		= vread_hpet,
 #endif
@@ -707,7 +753,7 @@ static int hpet_clocksource_register(void)
 	cycle_t t1;
 
 	/* Start the counter */
-	hpet_start_counter();
+	hpet_restart_counter();
 
 	/* Verify whether hpet counter works */
 	t1 = read_hpet();
@@ -793,6 +839,7 @@ int __init hpet_enable(void)
 	 * information and the number of channels
 	 */
 	id = hpet_readl(HPET_ID);
+	hpet_print_config();
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 	/*
@@ -845,6 +892,7 @@ static __init int hpet_late_init(void)
 		return -ENODEV;
 
 	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
+	hpet_print_config();
 
 	for_each_online_cpu(cpu) {
 		hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 309949e9e1c..697d1b78cfb 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -172,7 +172,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_4,
 			 ich_force_enable_hpet);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7,
 			 ich_force_enable_hpet);
-
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3a16,	/* ICH10 */
+			 ich_force_enable_hpet);
 
 static struct pci_dev *cached_dev;
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b8e7aaf7ef7..08afa1579e6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -17,20 +17,21 @@
 #include <asm/delay.h>
 #include <asm/hypervisor.h>
 
-unsigned int cpu_khz;           /* TSC clocks / usec, not used here */
+unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
-unsigned int tsc_khz;
+
+unsigned int __read_mostly tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
-static int tsc_unstable;
+static int __read_mostly tsc_unstable;
 
 /* native_sched_clock() is called before tsc_init(), so
    we must start with the TSC soft disabled to prevent
    erroneous rdtsc usage on !cpu_has_tsc processors */
-static int tsc_disabled = -1;
+static int __read_mostly tsc_disabled = -1;
 
 static int tsc_clocksource_reliable;
 /*
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b81125f0bde..0a303c3ed11 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -4,6 +4,10 @@
 config HAVE_KVM
        bool
 
+config HAVE_KVM_IRQCHIP
+       bool
+       default y
+
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
 	depends on HAVE_KVM || X86
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 72bd275a9b5..c13bb92d315 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -201,6 +201,9 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps)
 	if (!atomic_inc_and_test(&pt->pending))
 		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
 
+	if (!pt->reinject)
+		atomic_set(&pt->pending, 1);
+
 	if (vcpu0 && waitqueue_active(&vcpu0->wq))
 		wake_up_interruptible(&vcpu0->wq);
 
@@ -536,6 +539,16 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	pit->pit_state.irq_ack = 1;
 }
 
+static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
+{
+	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
+
+	if (!mask) {
+		atomic_set(&pit->pit_state.pit_timer.pending, 0);
+		pit->pit_state.irq_ack = 1;
+	}
+}
+
 struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 {
 	struct kvm_pit *pit;
@@ -545,9 +558,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	if (!pit)
 		return NULL;
 
-	mutex_lock(&kvm->lock);
 	pit->irq_source_id = kvm_request_irq_source_id(kvm);
-	mutex_unlock(&kvm->lock);
 	if (pit->irq_source_id < 0) {
 		kfree(pit);
 		return NULL;
@@ -580,10 +591,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
 	kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
+	pit_state->pit_timer.reinject = true;
 	mutex_unlock(&pit->pit_state.lock);
 
 	kvm_pit_reset(pit);
 
+	pit->mask_notifier.func = pit_mask_notifer;
+	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+
 	return pit;
 }
 
@@ -592,6 +607,8 @@ void kvm_free_pit(struct kvm *kvm)
 	struct hrtimer *timer;
 
 	if (kvm->arch.vpit) {
+		kvm_unregister_irq_mask_notifier(kvm, 0,
+					       &kvm->arch.vpit->mask_notifier);
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
 		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
 		hrtimer_cancel(timer);
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 4178022b97a..6acbe4b505d 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -9,6 +9,7 @@ struct kvm_kpit_timer {
 	s64 period; /* unit: ns */
 	s64 scheduled;
 	atomic_t pending;
+	bool reinject;
 };
 
 struct kvm_kpit_channel_state {
@@ -45,6 +46,7 @@ struct kvm_pit {
 	struct kvm *kvm;
 	struct kvm_kpit_state pit_state;
 	int irq_source_id;
+	struct kvm_irq_mask_notifier mask_notifier;
 };
 
 #define KVM_PIT_BASE_ADDRESS	    0x40
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 179dcb0103f..1ccb50c74f1 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -32,11 +32,13 @@
 #include <linux/kvm_host.h>
 
 static void pic_lock(struct kvm_pic *s)
+	__acquires(&s->lock)
 {
 	spin_lock(&s->lock);
 }
 
 static void pic_unlock(struct kvm_pic *s)
+	__releases(&s->lock)
 {
 	struct kvm *kvm = s->kvm;
 	unsigned acks = s->pending_acks;
@@ -49,7 +51,8 @@ static void pic_unlock(struct kvm_pic *s)
 	spin_unlock(&s->lock);
 
 	while (acks) {
-		kvm_notify_acked_irq(kvm, __ffs(acks));
+		kvm_notify_acked_irq(kvm, SELECT_PIC(__ffs(acks)),
+				     __ffs(acks));
 		acks &= acks - 1;
 	}
 
@@ -76,12 +79,13 @@ void kvm_pic_clear_isr_ack(struct kvm *kvm)
 /*
  * set irq level. If an edge is detected, then the IRR is set to 1
  */
-static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
+static inline int pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
 {
-	int mask;
+	int mask, ret = 1;
 	mask = 1 << irq;
 	if (s->elcr & mask)	/* level triggered */
 		if (level) {
+			ret = !(s->irr & mask);
 			s->irr |= mask;
 			s->last_irr |= mask;
 		} else {
@@ -90,11 +94,15 @@ static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level)
 		}
 	else	/* edge triggered */
 		if (level) {
-			if ((s->last_irr & mask) == 0)
+			if ((s->last_irr & mask) == 0) {
+				ret = !(s->irr & mask);
 				s->irr |= mask;
+			}
 			s->last_irr |= mask;
 		} else
 			s->last_irr &= ~mask;
+
+	return (s->imr & mask) ? -1 : ret;
 }
 
 /*
@@ -171,16 +179,19 @@ void kvm_pic_update_irq(struct kvm_pic *s)
 	pic_unlock(s);
 }
 
-void kvm_pic_set_irq(void *opaque, int irq, int level)
+int kvm_pic_set_irq(void *opaque, int irq, int level)
 {
 	struct kvm_pic *s = opaque;
+	int ret = -1;
 
 	pic_lock(s);
 	if (irq >= 0 && irq < PIC_NUM_PINS) {
-		pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
+		ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
 		pic_update_irq(s);
 	}
 	pic_unlock(s);
+
+	return ret;
 }
 
 /*
@@ -232,7 +243,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	}
 	pic_update_irq(s);
 	pic_unlock(s);
-	kvm_notify_acked_irq(kvm, irq);
+	kvm_notify_acked_irq(kvm, SELECT_PIC(irq), irq);
 
 	return intno;
 }
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 82579ee538d..9f593188129 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -32,6 +32,8 @@
 #include "lapic.h"
 
 #define PIC_NUM_PINS 16
+#define SELECT_PIC(irq) \
+	((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE)
 
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
index 8e5ee99551f..ed66e4c078d 100644
--- a/arch/x86/kvm/kvm_svm.h
+++ b/arch/x86/kvm/kvm_svm.h
@@ -18,7 +18,6 @@ static const u32 host_save_user_msrs[] = {
 };
 
 #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
-#define NUM_DB_REGS 4
 
 struct kvm_vcpu;
 
@@ -29,18 +28,23 @@ struct vcpu_svm {
 	struct svm_cpu_data *svm_data;
 	uint64_t asid_generation;
 
-	unsigned long db_regs[NUM_DB_REGS];
-
 	u64 next_rip;
 
 	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
 	u64 host_gs_base;
 	unsigned long host_cr2;
-	unsigned long host_db_regs[NUM_DB_REGS];
-	unsigned long host_dr6;
-	unsigned long host_dr7;
 
 	u32 *msrpm;
+	struct vmcb *hsave;
+	u64 hsave_msr;
+
+	u64 nested_vmcb;
+
+	/* These are the merged vectors */
+	u32 *nested_msrpm;
+
+	/* gpa pointers to the real vectors */
+	u64 nested_vmcb_msrpm;
 };
 
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2d4477c7147..2a36f7f7c4c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -145,11 +145,20 @@ struct kvm_rmap_desc {
 	struct kvm_rmap_desc *more;
 };
 
-struct kvm_shadow_walk {
-	int (*entry)(struct kvm_shadow_walk *walk, struct kvm_vcpu *vcpu,
-		     u64 addr, u64 *spte, int level);
+struct kvm_shadow_walk_iterator {
+	u64 addr;
+	hpa_t shadow_addr;
+	int level;
+	u64 *sptep;
+	unsigned index;
 };
 
+#define for_each_shadow_entry(_vcpu, _addr, _walker)    \
+	for (shadow_walk_init(&(_walker), _vcpu, _addr);	\
+	     shadow_walk_okay(&(_walker));			\
+	     shadow_walk_next(&(_walker)))
+
+
 struct kvm_unsync_walk {
 	int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
 };
@@ -343,7 +352,6 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc,
 
 	BUG_ON(!mc->nobjs);
 	p = mc->objects[--mc->nobjs];
-	memset(p, 0, size);
 	return p;
 }
 
@@ -794,10 +802,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&sp->oos_link);
-	ASSERT(is_empty_shadow_page(sp->spt));
 	bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
 	sp->multimapped = 0;
-	sp->global = 1;
 	sp->parent_pte = parent_pte;
 	--vcpu->kvm->arch.n_free_mmu_pages;
 	return sp;
@@ -983,8 +989,8 @@ struct kvm_mmu_pages {
 	     idx < 512;					\
 	     idx = find_next_bit(bitmap, 512, idx+1))
 
-int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
-		   int idx)
+static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
+			 int idx)
 {
 	int i;
 
@@ -1059,7 +1065,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry(sp, node, bucket, hash_link)
-		if (sp->gfn == gfn && !sp->role.metaphysical
+		if (sp->gfn == gfn && !sp->role.direct
 		    && !sp->role.invalid) {
 			pgprintk("%s: found role %x\n",
 				 __func__, sp->role.word);
@@ -1115,8 +1121,9 @@ struct mmu_page_path {
 			i < pvec.nr && ({ sp = pvec.page[i].sp; 1;});	\
 			i = mmu_pages_next(&pvec, &parents, i))
 
-int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents,
-		   int i)
+static int mmu_pages_next(struct kvm_mmu_pages *pvec,
+			  struct mmu_page_path *parents,
+			  int i)
 {
 	int n;
 
@@ -1135,7 +1142,7 @@ int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents,
 	return n;
 }
 
-void mmu_pages_clear_parents(struct mmu_page_path *parents)
+static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 {
 	struct kvm_mmu_page *sp;
 	unsigned int level = 0;
@@ -1193,7 +1200,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 					     gfn_t gfn,
 					     gva_t gaddr,
 					     unsigned level,
-					     int metaphysical,
+					     int direct,
 					     unsigned access,
 					     u64 *parent_pte)
 {
@@ -1204,10 +1211,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	struct kvm_mmu_page *sp;
 	struct hlist_node *node, *tmp;
 
-	role.word = 0;
-	role.glevels = vcpu->arch.mmu.root_level;
+	role = vcpu->arch.mmu.base_role;
 	role.level = level;
-	role.metaphysical = metaphysical;
+	role.direct = direct;
 	role.access = access;
 	if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
@@ -1242,8 +1248,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
 	sp->gfn = gfn;
 	sp->role = role;
+	sp->global = role.cr4_pge;
 	hlist_add_head(&sp->hash_link, bucket);
-	if (!metaphysical) {
+	if (!direct) {
 		if (rmap_write_protect(vcpu->kvm, gfn))
 			kvm_flush_remote_tlbs(vcpu->kvm);
 		account_shadowed(vcpu->kvm, gfn);
@@ -1255,35 +1262,35 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	return sp;
 }
 
-static int walk_shadow(struct kvm_shadow_walk *walker,
-		       struct kvm_vcpu *vcpu, u64 addr)
+static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
+			     struct kvm_vcpu *vcpu, u64 addr)
 {
-	hpa_t shadow_addr;
-	int level;
-	int r;
-	u64 *sptep;
-	unsigned index;
-
-	shadow_addr = vcpu->arch.mmu.root_hpa;
-	level = vcpu->arch.mmu.shadow_root_level;
-	if (level == PT32E_ROOT_LEVEL) {
-		shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
-		shadow_addr &= PT64_BASE_ADDR_MASK;
-		if (!shadow_addr)
-			return 1;
-		--level;
+	iterator->addr = addr;
+	iterator->shadow_addr = vcpu->arch.mmu.root_hpa;
+	iterator->level = vcpu->arch.mmu.shadow_root_level;
+	if (iterator->level == PT32E_ROOT_LEVEL) {
+		iterator->shadow_addr
+			= vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+		iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
+		--iterator->level;
+		if (!iterator->shadow_addr)
+			iterator->level = 0;
 	}
+}
 
-	while (level >= PT_PAGE_TABLE_LEVEL) {
-		index = SHADOW_PT_INDEX(addr, level);
-		sptep = ((u64 *)__va(shadow_addr)) + index;
-		r = walker->entry(walker, vcpu, addr, sptep, level);
-		if (r)
-			return r;
-		shadow_addr = *sptep & PT64_BASE_ADDR_MASK;
-		--level;
-	}
-	return 0;
+static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
+{
+	if (iterator->level < PT_PAGE_TABLE_LEVEL)
+		return false;
+	iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
+	iterator->sptep	= ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
+	return true;
+}
+
+static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
+{
+	iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK;
+	--iterator->level;
 }
 
 static void kvm_mmu_page_unlink_children(struct kvm *kvm,
@@ -1388,7 +1395,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_page_unlink_children(kvm, sp);
 	kvm_mmu_unlink_parents(kvm, sp);
 	kvm_flush_remote_tlbs(kvm);
-	if (!sp->role.invalid && !sp->role.metaphysical)
+	if (!sp->role.invalid && !sp->role.direct)
 		unaccount_shadowed(kvm, sp->gfn);
 	if (sp->unsync)
 		kvm_unlink_unsync_page(kvm, sp);
@@ -1451,7 +1458,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
-		if (sp->gfn == gfn && !sp->role.metaphysical) {
+		if (sp->gfn == gfn && !sp->role.direct) {
 			pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
 				 sp->role.word);
 			r = 1;
@@ -1463,11 +1470,20 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
 static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 {
+	unsigned index;
+	struct hlist_head *bucket;
 	struct kvm_mmu_page *sp;
+	struct hlist_node *node, *nn;
 
-	while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) {
-		pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word);
-		kvm_mmu_zap_page(kvm, sp);
+	index = kvm_page_table_hashfn(gfn);
+	bucket = &kvm->arch.mmu_page_hash[index];
+	hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) {
+		if (sp->gfn == gfn && !sp->role.direct
+		    && !sp->role.invalid) {
+			pgprintk("%s: zap %lx %x\n",
+				 __func__, gfn, sp->role.word);
+			kvm_mmu_zap_page(kvm, sp);
+		}
 	}
 }
 
@@ -1622,7 +1638,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	/* don't unsync if pagetable is shadowed with multiple roles */
 	hlist_for_each_entry_safe(s, node, n, bucket, hash_link) {
-		if (s->gfn != sp->gfn || s->role.metaphysical)
+		if (s->gfn != sp->gfn || s->role.direct)
 			continue;
 		if (s->role.word != sp->role.word)
 			return 1;
@@ -1669,8 +1685,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	u64 mt_mask = shadow_mt_mask;
 	struct kvm_mmu_page *sp = page_header(__pa(shadow_pte));
 
-	if (!(vcpu->arch.cr4 & X86_CR4_PGE))
-		global = 0;
 	if (!global && sp->global) {
 		sp->global = 0;
 		if (sp->unsync) {
@@ -1777,12 +1791,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 			pgprintk("hfn old %lx new %lx\n",
 				 spte_to_pfn(*shadow_pte), pfn);
 			rmap_remove(vcpu->kvm, shadow_pte);
-		} else {
-			if (largepage)
-				was_rmapped = is_large_pte(*shadow_pte);
-			else
-				was_rmapped = 1;
-		}
+		} else
+			was_rmapped = 1;
 	}
 	if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
 		      dirty, largepage, global, gfn, pfn, speculative, true)) {
@@ -1820,67 +1830,42 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 {
 }
 
-struct direct_shadow_walk {
-	struct kvm_shadow_walk walker;
-	pfn_t pfn;
-	int write;
-	int largepage;
-	int pt_write;
-};
-
-static int direct_map_entry(struct kvm_shadow_walk *_walk,
-			    struct kvm_vcpu *vcpu,
-			    u64 addr, u64 *sptep, int level)
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
+			int largepage, gfn_t gfn, pfn_t pfn)
 {
-	struct direct_shadow_walk *walk =
-		container_of(_walk, struct direct_shadow_walk, walker);
+	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
+	int pt_write = 0;
 	gfn_t pseudo_gfn;
-	gfn_t gfn = addr >> PAGE_SHIFT;
-
-	if (level == PT_PAGE_TABLE_LEVEL
-	    || (walk->largepage && level == PT_DIRECTORY_LEVEL)) {
-		mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL,
-			     0, walk->write, 1, &walk->pt_write,
-			     walk->largepage, 0, gfn, walk->pfn, false);
-		++vcpu->stat.pf_fixed;
-		return 1;
-	}
 
-	if (*sptep == shadow_trap_nonpresent_pte) {
-		pseudo_gfn = (addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
-		sp = kvm_mmu_get_page(vcpu, pseudo_gfn, (gva_t)addr, level - 1,
-				      1, ACC_ALL, sptep);
-		if (!sp) {
-			pgprintk("nonpaging_map: ENOMEM\n");
-			kvm_release_pfn_clean(walk->pfn);
-			return -ENOMEM;
+	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
+		if (iterator.level == PT_PAGE_TABLE_LEVEL
+		    || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) {
+			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL,
+				     0, write, 1, &pt_write,
+				     largepage, 0, gfn, pfn, false);
+			++vcpu->stat.pf_fixed;
+			break;
 		}
 
-		set_shadow_pte(sptep,
-			       __pa(sp->spt)
-			       | PT_PRESENT_MASK | PT_WRITABLE_MASK
-			       | shadow_user_mask | shadow_x_mask);
-	}
-	return 0;
-}
+		if (*iterator.sptep == shadow_trap_nonpresent_pte) {
+			pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT;
+			sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
+					      iterator.level - 1,
+					      1, ACC_ALL, iterator.sptep);
+			if (!sp) {
+				pgprintk("nonpaging_map: ENOMEM\n");
+				kvm_release_pfn_clean(pfn);
+				return -ENOMEM;
+			}
 
-static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
-			int largepage, gfn_t gfn, pfn_t pfn)
-{
-	int r;
-	struct direct_shadow_walk walker = {
-		.walker = { .entry = direct_map_entry, },
-		.pfn = pfn,
-		.largepage = largepage,
-		.write = write,
-		.pt_write = 0,
-	};
-
-	r = walk_shadow(&walker.walker, vcpu, gfn << PAGE_SHIFT);
-	if (r < 0)
-		return r;
-	return walker.pt_write;
+			set_shadow_pte(iterator.sptep,
+				       __pa(sp->spt)
+				       | PT_PRESENT_MASK | PT_WRITABLE_MASK
+				       | shadow_user_mask | shadow_x_mask);
+		}
+	}
+	return pt_write;
 }
 
 static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
@@ -1962,7 +1947,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 	int i;
 	gfn_t root_gfn;
 	struct kvm_mmu_page *sp;
-	int metaphysical = 0;
+	int direct = 0;
 
 	root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
 
@@ -1971,18 +1956,18 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 
 		ASSERT(!VALID_PAGE(root));
 		if (tdp_enabled)
-			metaphysical = 1;
+			direct = 1;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
-				      PT64_ROOT_LEVEL, metaphysical,
+				      PT64_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		vcpu->arch.mmu.root_hpa = root;
 		return;
 	}
-	metaphysical = !is_paging(vcpu);
+	direct = !is_paging(vcpu);
 	if (tdp_enabled)
-		metaphysical = 1;
+		direct = 1;
 	for (i = 0; i < 4; ++i) {
 		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
@@ -1996,7 +1981,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		} else if (vcpu->arch.mmu.root_level == 0)
 			root_gfn = 0;
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
-				      PT32_ROOT_LEVEL, metaphysical,
+				      PT32_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
@@ -2251,17 +2236,23 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 
 static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
+	int r;
+
 	ASSERT(vcpu);
 	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
 	if (!is_paging(vcpu))
-		return nonpaging_init_context(vcpu);
+		r = nonpaging_init_context(vcpu);
 	else if (is_long_mode(vcpu))
-		return paging64_init_context(vcpu);
+		r = paging64_init_context(vcpu);
 	else if (is_pae(vcpu))
-		return paging32E_init_context(vcpu);
+		r = paging32E_init_context(vcpu);
 	else
-		return paging32_init_context(vcpu);
+		r = paging32_init_context(vcpu);
+
+	vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level;
+
+	return r;
 }
 
 static int init_kvm_mmu(struct kvm_vcpu *vcpu)
@@ -2492,7 +2483,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
-		if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid)
+		if (sp->gfn != gfn || sp->role.direct || sp->role.invalid)
 			continue;
 		pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
 		misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
@@ -3130,7 +3121,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 
 	list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) {
-		if (sp->role.metaphysical)
+		if (sp->role.direct)
 			continue;
 
 		gfn = unalias_gfn(vcpu->kvm, sp->gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 258e5d56298..eaab2145f62 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -54,7 +54,7 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 static inline int is_long_mode(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64
-	return vcpu->arch.shadow_efer & EFER_LME;
+	return vcpu->arch.shadow_efer & EFER_LMA;
 #else
 	return 0;
 #endif
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 9fd78b6e17a..6bd70206c56 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -25,7 +25,6 @@
 #if PTTYPE == 64
 	#define pt_element_t u64
 	#define guest_walker guest_walker64
-	#define shadow_walker shadow_walker64
 	#define FNAME(name) paging##64_##name
 	#define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
 	#define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK
@@ -42,7 +41,6 @@
 #elif PTTYPE == 32
 	#define pt_element_t u32
 	#define guest_walker guest_walker32
-	#define shadow_walker shadow_walker32
 	#define FNAME(name) paging##32_##name
 	#define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK
 	#define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK
@@ -73,18 +71,6 @@ struct guest_walker {
 	u32 error_code;
 };
 
-struct shadow_walker {
-	struct kvm_shadow_walk walker;
-	struct guest_walker *guest_walker;
-	int user_fault;
-	int write_fault;
-	int largepage;
-	int *ptwrite;
-	pfn_t pfn;
-	u64 *sptep;
-	gpa_t pte_gpa;
-};
-
 static gfn_t gpte_to_gfn(pt_element_t gpte)
 {
 	return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT;
@@ -283,91 +269,79 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 /*
  * Fetch a shadow pte for a specific level in the paging hierarchy.
  */
-static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw,
-				    struct kvm_vcpu *vcpu, u64 addr,
-				    u64 *sptep, int level)
+static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+			 struct guest_walker *gw,
+			 int user_fault, int write_fault, int largepage,
+			 int *ptwrite, pfn_t pfn)
 {
-	struct shadow_walker *sw =
-		container_of(_sw, struct shadow_walker, walker);
-	struct guest_walker *gw = sw->guest_walker;
 	unsigned access = gw->pt_access;
 	struct kvm_mmu_page *shadow_page;
-	u64 spte;
-	int metaphysical;
+	u64 spte, *sptep;
+	int direct;
 	gfn_t table_gfn;
 	int r;
+	int level;
 	pt_element_t curr_pte;
+	struct kvm_shadow_walk_iterator iterator;
 
-	if (level == PT_PAGE_TABLE_LEVEL
-	    || (sw->largepage && level == PT_DIRECTORY_LEVEL)) {
-		mmu_set_spte(vcpu, sptep, access, gw->pte_access & access,
-			     sw->user_fault, sw->write_fault,
-			     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
-			     sw->ptwrite, sw->largepage,
-			     gw->ptes[gw->level-1] & PT_GLOBAL_MASK,
-			     gw->gfn, sw->pfn, false);
-		sw->sptep = sptep;
-		return 1;
-	}
+	if (!is_present_pte(gw->ptes[gw->level - 1]))
+		return NULL;
 
-	if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep))
-		return 0;
+	for_each_shadow_entry(vcpu, addr, iterator) {
+		level = iterator.level;
+		sptep = iterator.sptep;
+		if (level == PT_PAGE_TABLE_LEVEL
+		    || (largepage && level == PT_DIRECTORY_LEVEL)) {
+			mmu_set_spte(vcpu, sptep, access,
+				     gw->pte_access & access,
+				     user_fault, write_fault,
+				     gw->ptes[gw->level-1] & PT_DIRTY_MASK,
+				     ptwrite, largepage,
+				     gw->ptes[gw->level-1] & PT_GLOBAL_MASK,
+				     gw->gfn, pfn, false);
+			break;
+		}
 
-	if (is_large_pte(*sptep)) {
-		set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
-		kvm_flush_remote_tlbs(vcpu->kvm);
-		rmap_remove(vcpu->kvm, sptep);
-	}
+		if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep))
+			continue;
 
-	if (level == PT_DIRECTORY_LEVEL && gw->level == PT_DIRECTORY_LEVEL) {
-		metaphysical = 1;
-		if (!is_dirty_pte(gw->ptes[level - 1]))
-			access &= ~ACC_WRITE_MASK;
-		table_gfn = gpte_to_gfn(gw->ptes[level - 1]);
-	} else {
-		metaphysical = 0;
-		table_gfn = gw->table_gfn[level - 2];
-	}
-	shadow_page = kvm_mmu_get_page(vcpu, table_gfn, (gva_t)addr, level-1,
-				       metaphysical, access, sptep);
-	if (!metaphysical) {
-		r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 2],
-					  &curr_pte, sizeof(curr_pte));
-		if (r || curr_pte != gw->ptes[level - 2]) {
-			kvm_mmu_put_page(shadow_page, sptep);
-			kvm_release_pfn_clean(sw->pfn);
-			sw->sptep = NULL;
-			return 1;
+		if (is_large_pte(*sptep)) {
+			rmap_remove(vcpu->kvm, sptep);
+			set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
+			kvm_flush_remote_tlbs(vcpu->kvm);
 		}
-	}
 
-	spte = __pa(shadow_page->spt) | PT_PRESENT_MASK | PT_ACCESSED_MASK
-		| PT_WRITABLE_MASK | PT_USER_MASK;
-	*sptep = spte;
-	return 0;
-}
-
-static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
-			 struct guest_walker *guest_walker,
-			 int user_fault, int write_fault, int largepage,
-			 int *ptwrite, pfn_t pfn)
-{
-	struct shadow_walker walker = {
-		.walker = { .entry = FNAME(shadow_walk_entry), },
-		.guest_walker = guest_walker,
-		.user_fault = user_fault,
-		.write_fault = write_fault,
-		.largepage = largepage,
-		.ptwrite = ptwrite,
-		.pfn = pfn,
-	};
-
-	if (!is_present_pte(guest_walker->ptes[guest_walker->level - 1]))
-		return NULL;
+		if (level == PT_DIRECTORY_LEVEL
+		    && gw->level == PT_DIRECTORY_LEVEL) {
+			direct = 1;
+			if (!is_dirty_pte(gw->ptes[level - 1]))
+				access &= ~ACC_WRITE_MASK;
+			table_gfn = gpte_to_gfn(gw->ptes[level - 1]);
+		} else {
+			direct = 0;
+			table_gfn = gw->table_gfn[level - 2];
+		}
+		shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1,
+					       direct, access, sptep);
+		if (!direct) {
+			r = kvm_read_guest_atomic(vcpu->kvm,
+						  gw->pte_gpa[level - 2],
+						  &curr_pte, sizeof(curr_pte));
+			if (r || curr_pte != gw->ptes[level - 2]) {
+				kvm_mmu_put_page(shadow_page, sptep);
+				kvm_release_pfn_clean(pfn);
+				sptep = NULL;
+				break;
+			}
+		}
 
-	walk_shadow(&walker.walker, vcpu, addr);
+		spte = __pa(shadow_page->spt)
+			| PT_PRESENT_MASK | PT_ACCESSED_MASK
+			| PT_WRITABLE_MASK | PT_USER_MASK;
+		*sptep = spte;
+	}
 
-	return walker.sptep;
+	return sptep;
 }
 
 /*
@@ -465,54 +439,56 @@ out_unlock:
 	return 0;
 }
 
-static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw,
-				      struct kvm_vcpu *vcpu, u64 addr,
-				      u64 *sptep, int level)
+static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	struct shadow_walker *sw =
-		container_of(_sw, struct shadow_walker, walker);
-
-	/* FIXME: properly handle invlpg on large guest pages */
-	if (level == PT_PAGE_TABLE_LEVEL ||
-	    ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
-		struct kvm_mmu_page *sp = page_header(__pa(sptep));
+	struct kvm_shadow_walk_iterator iterator;
+	pt_element_t gpte;
+	gpa_t pte_gpa = -1;
+	int level;
+	u64 *sptep;
+	int need_flush = 0;
 
-		sw->pte_gpa = (sp->gfn << PAGE_SHIFT);
-		sw->pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
+	spin_lock(&vcpu->kvm->mmu_lock);
 
-		if (is_shadow_present_pte(*sptep)) {
-			rmap_remove(vcpu->kvm, sptep);
-			if (is_large_pte(*sptep))
-				--vcpu->kvm->stat.lpages;
+	for_each_shadow_entry(vcpu, gva, iterator) {
+		level = iterator.level;
+		sptep = iterator.sptep;
+
+		/* FIXME: properly handle invlpg on large guest pages */
+		if (level == PT_PAGE_TABLE_LEVEL ||
+		    ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
+			struct kvm_mmu_page *sp = page_header(__pa(sptep));
+
+			pte_gpa = (sp->gfn << PAGE_SHIFT);
+			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
+
+			if (is_shadow_present_pte(*sptep)) {
+				rmap_remove(vcpu->kvm, sptep);
+				if (is_large_pte(*sptep))
+					--vcpu->kvm->stat.lpages;
+				need_flush = 1;
+			}
+			set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
+			break;
 		}
-		set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
-		return 1;
-	}
-	if (!is_shadow_present_pte(*sptep))
-		return 1;
-	return 0;
-}
 
-static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
-{
-	pt_element_t gpte;
-	struct shadow_walker walker = {
-		.walker = { .entry = FNAME(shadow_invlpg_entry), },
-		.pte_gpa = -1,
-	};
+		if (!is_shadow_present_pte(*sptep))
+			break;
+	}
 
-	spin_lock(&vcpu->kvm->mmu_lock);
-	walk_shadow(&walker.walker, vcpu, gva);
+	if (need_flush)
+		kvm_flush_remote_tlbs(vcpu->kvm);
 	spin_unlock(&vcpu->kvm->mmu_lock);
-	if (walker.pte_gpa == -1)
+
+	if (pte_gpa == -1)
 		return;
-	if (kvm_read_guest_atomic(vcpu->kvm, walker.pte_gpa, &gpte,
+	if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
 				  sizeof(pt_element_t)))
 		return;
 	if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) {
 		if (mmu_topup_memory_caches(vcpu))
 			return;
-		kvm_mmu_pte_write(vcpu, walker.pte_gpa, (const u8 *)&gpte,
+		kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte,
 				  sizeof(pt_element_t), 0);
 	}
 }
@@ -540,7 +516,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
 	pt_element_t pt[256 / sizeof(pt_element_t)];
 	gpa_t pte_gpa;
 
-	if (sp->role.metaphysical
+	if (sp->role.direct
 	    || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) {
 		nonpaging_prefetch_page(vcpu, sp);
 		return;
@@ -619,7 +595,6 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 #undef pt_element_t
 #undef guest_walker
-#undef shadow_walker
 #undef FNAME
 #undef PT_BASE_ADDR_MASK
 #undef PT_INDEX
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a9e769e4e25..1821c207819 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -38,9 +38,6 @@ MODULE_LICENSE("GPL");
 #define IOPM_ALLOC_ORDER 2
 #define MSRPM_ALLOC_ORDER 1
 
-#define DR7_GD_MASK (1 << 13)
-#define DR6_BD_MASK (1 << 13)
-
 #define SEG_TYPE_LDT 2
 #define SEG_TYPE_BUSY_TSS16 3
 
@@ -50,6 +47,15 @@ MODULE_LICENSE("GPL");
 
 #define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
 
+/* Turn on to get debugging output*/
+/* #define NESTED_DEBUG */
+
+#ifdef NESTED_DEBUG
+#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args)
+#else
+#define nsvm_printk(fmt, args...) do {} while(0)
+#endif
+
 /* enable NPT for AMD64 and X86 with PAE */
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 static bool npt_enabled = true;
@@ -60,14 +66,29 @@ static int npt = 1;
 
 module_param(npt, int, S_IRUGO);
 
+static int nested = 0;
+module_param(nested, int, S_IRUGO);
+
 static void kvm_reput_irq(struct vcpu_svm *svm);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 
+static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override);
+static int nested_svm_vmexit(struct vcpu_svm *svm);
+static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
+			     void *arg2, void *opaque);
+static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
+				      bool has_error_code, u32 error_code);
+
 static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 {
 	return container_of(vcpu, struct vcpu_svm, vcpu);
 }
 
+static inline bool is_nested(struct vcpu_svm *svm)
+{
+	return svm->nested_vmcb;
+}
+
 static unsigned long iopm_base;
 
 struct kvm_ldttss_desc {
@@ -157,32 +178,6 @@ static inline void kvm_write_cr2(unsigned long val)
 	asm volatile ("mov %0, %%cr2" :: "r" (val));
 }
 
-static inline unsigned long read_dr6(void)
-{
-	unsigned long dr6;
-
-	asm volatile ("mov %%dr6, %0" : "=r" (dr6));
-	return dr6;
-}
-
-static inline void write_dr6(unsigned long val)
-{
-	asm volatile ("mov %0, %%dr6" :: "r" (val));
-}
-
-static inline unsigned long read_dr7(void)
-{
-	unsigned long dr7;
-
-	asm volatile ("mov %%dr7, %0" : "=r" (dr7));
-	return dr7;
-}
-
-static inline void write_dr7(unsigned long val)
-{
-	asm volatile ("mov %0, %%dr7" :: "r" (val));
-}
-
 static inline void force_new_asid(struct kvm_vcpu *vcpu)
 {
 	to_svm(vcpu)->asid_generation--;
@@ -198,7 +193,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	if (!npt_enabled && !(efer & EFER_LMA))
 		efer &= ~EFER_LME;
 
-	to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK;
+	to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
 	vcpu->arch.shadow_efer = efer;
 }
 
@@ -207,6 +202,11 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	/* If we are within a nested VM we'd better #VMEXIT and let the
+	   guest handle the exception */
+	if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
+		return;
+
 	svm->vmcb->control.event_inj = nr
 		| SVM_EVTINJ_VALID
 		| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
@@ -242,7 +242,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	kvm_rip_write(vcpu, svm->next_rip);
 	svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK;
 
-	vcpu->arch.interrupt_window_open = 1;
+	vcpu->arch.interrupt_window_open = (svm->vcpu.arch.hflags & HF_GIF_MASK);
 }
 
 static int has_svm(void)
@@ -250,7 +250,7 @@ static int has_svm(void)
 	const char *msg;
 
 	if (!cpu_has_svm(&msg)) {
-		printk(KERN_INFO "has_svn: %s\n", msg);
+		printk(KERN_INFO "has_svm: %s\n", msg);
 		return 0;
 	}
 
@@ -292,7 +292,7 @@ static void svm_hardware_enable(void *garbage)
 	svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
 	rdmsrl(MSR_EFER, efer);
-	wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK);
+	wrmsrl(MSR_EFER, efer | EFER_SVME);
 
 	wrmsrl(MSR_VM_HSAVE_PA,
 	       page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
@@ -417,6 +417,14 @@ static __init int svm_hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
+	if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
+		kvm_enable_efer_bits(EFER_FFXSR);
+
+	if (nested) {
+		printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
+		kvm_enable_efer_bits(EFER_SVME);
+	}
+
 	for_each_online_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
@@ -559,7 +567,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
 	init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
 
-	save->efer = MSR_EFER_SVME_MASK;
+	save->efer = EFER_SVME;
 	save->dr6 = 0xffff0ff0;
 	save->dr7 = 0x400;
 	save->rflags = 2;
@@ -591,6 +599,9 @@ static void init_vmcb(struct vcpu_svm *svm)
 		save->cr4 = 0;
 	}
 	force_new_asid(&svm->vcpu);
+
+	svm->nested_vmcb = 0;
+	svm->vcpu.arch.hflags = HF_GIF_MASK;
 }
 
 static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
@@ -615,6 +626,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	struct vcpu_svm *svm;
 	struct page *page;
 	struct page *msrpm_pages;
+	struct page *hsave_page;
+	struct page *nested_msrpm_pages;
 	int err;
 
 	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
@@ -637,14 +650,25 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
 		goto uninit;
+
+	nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+	if (!nested_msrpm_pages)
+		goto uninit;
+
 	svm->msrpm = page_address(msrpm_pages);
 	svm_vcpu_init_msrpm(svm->msrpm);
 
+	hsave_page = alloc_page(GFP_KERNEL);
+	if (!hsave_page)
+		goto uninit;
+	svm->hsave = page_address(hsave_page);
+
+	svm->nested_msrpm = page_address(nested_msrpm_pages);
+
 	svm->vmcb = page_address(page);
 	clear_page(svm->vmcb);
 	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	svm->asid_generation = 0;
-	memset(svm->db_regs, 0, sizeof(svm->db_regs));
 	init_vmcb(svm);
 
 	fx_init(&svm->vcpu);
@@ -669,6 +693,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 
 	__free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
+	__free_page(virt_to_page(svm->hsave));
+	__free_pages(virt_to_page(svm->nested_msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
 }
@@ -718,6 +744,16 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
+static void svm_set_vintr(struct vcpu_svm *svm)
+{
+	svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR;
+}
+
+static void svm_clear_vintr(struct vcpu_svm *svm)
+{
+	svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR);
+}
+
 static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg)
 {
 	struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
@@ -760,20 +796,37 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
 	var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
 
-	/*
-	 * SVM always stores 0 for the 'G' bit in the CS selector in
-	 * the VMCB on a VMEXIT. This hurts cross-vendor migration:
-	 * Intel's VMENTRY has a check on the 'G' bit.
-	 */
-	if (seg == VCPU_SREG_CS)
+	switch (seg) {
+	case VCPU_SREG_CS:
+		/*
+		 * SVM always stores 0 for the 'G' bit in the CS selector in
+		 * the VMCB on a VMEXIT. This hurts cross-vendor migration:
+		 * Intel's VMENTRY has a check on the 'G' bit.
+		 */
 		var->g = s->limit > 0xfffff;
-
-	/*
-	 * Work around a bug where the busy flag in the tr selector
-	 * isn't exposed
-	 */
-	if (seg == VCPU_SREG_TR)
+		break;
+	case VCPU_SREG_TR:
+		/*
+		 * Work around a bug where the busy flag in the tr selector
+		 * isn't exposed
+		 */
 		var->type |= 0x2;
+		break;
+	case VCPU_SREG_DS:
+	case VCPU_SREG_ES:
+	case VCPU_SREG_FS:
+	case VCPU_SREG_GS:
+		/*
+		 * The accessed bit must always be set in the segment
+		 * descriptor cache, although it can be cleared in the
+		 * descriptor, the cached bit always remains at 1. Since
+		 * Intel has a check on this, set it here to support
+		 * cross-vendor migration.
+		 */
+		if (!var->unusable)
+			var->type |= 0x1;
+		break;
+	}
 
 	var->unusable = !var->present;
 }
@@ -905,9 +958,37 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 
 }
 
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	return -EOPNOTSUPP;
+	int old_debug = vcpu->guest_debug;
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	vcpu->guest_debug = dbg->control;
+
+	svm->vmcb->control.intercept_exceptions &=
+		~((1 << DB_VECTOR) | (1 << BP_VECTOR));
+	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			svm->vmcb->control.intercept_exceptions |=
+				1 << DB_VECTOR;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			svm->vmcb->control.intercept_exceptions |=
+				1 << BP_VECTOR;
+	} else
+		vcpu->guest_debug = 0;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+		svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
+	else
+		svm->vmcb->save.dr7 = vcpu->arch.dr7;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
+		svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+
+	return 0;
 }
 
 static int svm_get_irq(struct kvm_vcpu *vcpu)
@@ -949,7 +1030,29 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
 
 static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
 {
-	unsigned long val = to_svm(vcpu)->db_regs[dr];
+	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned long val;
+
+	switch (dr) {
+	case 0 ... 3:
+		val = vcpu->arch.db[dr];
+		break;
+	case 6:
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+			val = vcpu->arch.dr6;
+		else
+			val = svm->vmcb->save.dr6;
+		break;
+	case 7:
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+			val = vcpu->arch.dr7;
+		else
+			val = svm->vmcb->save.dr7;
+		break;
+	default:
+		val = 0;
+	}
+
 	KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
 	return val;
 }
@@ -959,33 +1062,40 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	*exception = 0;
+	KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)value, handler);
 
-	if (svm->vmcb->save.dr7 & DR7_GD_MASK) {
-		svm->vmcb->save.dr7 &= ~DR7_GD_MASK;
-		svm->vmcb->save.dr6 |= DR6_BD_MASK;
-		*exception = DB_VECTOR;
-		return;
-	}
+	*exception = 0;
 
 	switch (dr) {
 	case 0 ... 3:
-		svm->db_regs[dr] = value;
+		vcpu->arch.db[dr] = value;
+		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+			vcpu->arch.eff_db[dr] = value;
 		return;
 	case 4 ... 5:
-		if (vcpu->arch.cr4 & X86_CR4_DE) {
+		if (vcpu->arch.cr4 & X86_CR4_DE)
 			*exception = UD_VECTOR;
+		return;
+	case 6:
+		if (value & 0xffffffff00000000ULL) {
+			*exception = GP_VECTOR;
 			return;
 		}
-	case 7: {
-		if (value & ~((1ULL << 32) - 1)) {
+		vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
+		return;
+	case 7:
+		if (value & 0xffffffff00000000ULL) {
 			*exception = GP_VECTOR;
 			return;
 		}
-		svm->vmcb->save.dr7 = value;
+		vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
+		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+			svm->vmcb->save.dr7 = vcpu->arch.dr7;
+			vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
+		}
 		return;
-	}
 	default:
+		/* FIXME: Possible case? */
 		printk(KERN_DEBUG "%s: unexpected dr %u\n",
 		       __func__, dr);
 		*exception = UD_VECTOR;
@@ -1031,6 +1141,27 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
+static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	if (!(svm->vcpu.guest_debug &
+	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
+		return 1;
+	}
+	kvm_run->exit_reason = KVM_EXIT_DEBUG;
+	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
+	kvm_run->debug.arch.exception = DB_VECTOR;
+	return 0;
+}
+
+static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	kvm_run->exit_reason = KVM_EXIT_DEBUG;
+	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
+	kvm_run->debug.arch.exception = BP_VECTOR;
+	return 0;
+}
+
 static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	int er;
@@ -1080,7 +1211,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 {
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
-	int size, down, in, string, rep;
+	int size, in, string;
 	unsigned port;
 
 	++svm->vcpu.stat.io_exits;
@@ -1099,8 +1230,6 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
-	rep = (io_info & SVM_IOIO_REP_MASK) != 0;
-	down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0;
 
 	skip_emulated_instruction(&svm->vcpu);
 	return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
@@ -1139,6 +1268,567 @@ static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int nested_svm_check_permissions(struct vcpu_svm *svm)
+{
+	if (!(svm->vcpu.arch.shadow_efer & EFER_SVME)
+	    || !is_paging(&svm->vcpu)) {
+		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	if (svm->vmcb->save.cpl) {
+		kvm_inject_gp(&svm->vcpu, 0);
+		return 1;
+	}
+
+       return 0;
+}
+
+static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
+				      bool has_error_code, u32 error_code)
+{
+	if (is_nested(svm)) {
+		svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
+		svm->vmcb->control.exit_code_hi = 0;
+		svm->vmcb->control.exit_info_1 = error_code;
+		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
+		if (nested_svm_exit_handled(svm, false)) {
+			nsvm_printk("VMexit -> EXCP 0x%x\n", nr);
+
+			nested_svm_vmexit(svm);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int nested_svm_intr(struct vcpu_svm *svm)
+{
+	if (is_nested(svm)) {
+		if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
+			return 0;
+
+		if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
+			return 0;
+
+		svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+
+		if (nested_svm_exit_handled(svm, false)) {
+			nsvm_printk("VMexit -> INTR\n");
+			nested_svm_vmexit(svm);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa)
+{
+	struct page *page;
+
+	down_read(&current->mm->mmap_sem);
+	page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
+	up_read(&current->mm->mmap_sem);
+
+	if (is_error_page(page)) {
+		printk(KERN_INFO "%s: could not find page at 0x%llx\n",
+		       __func__, gpa);
+		kvm_release_page_clean(page);
+		kvm_inject_gp(&svm->vcpu, 0);
+		return NULL;
+	}
+	return page;
+}
+
+static int nested_svm_do(struct vcpu_svm *svm,
+			 u64 arg1_gpa, u64 arg2_gpa, void *opaque,
+			 int (*handler)(struct vcpu_svm *svm,
+					void *arg1,
+					void *arg2,
+					void *opaque))
+{
+	struct page *arg1_page;
+	struct page *arg2_page = NULL;
+	void *arg1;
+	void *arg2 = NULL;
+	int retval;
+
+	arg1_page = nested_svm_get_page(svm, arg1_gpa);
+	if(arg1_page == NULL)
+		return 1;
+
+	if (arg2_gpa) {
+		arg2_page = nested_svm_get_page(svm, arg2_gpa);
+		if(arg2_page == NULL) {
+			kvm_release_page_clean(arg1_page);
+			return 1;
+		}
+	}
+
+	arg1 = kmap_atomic(arg1_page, KM_USER0);
+	if (arg2_gpa)
+		arg2 = kmap_atomic(arg2_page, KM_USER1);
+
+	retval = handler(svm, arg1, arg2, opaque);
+
+	kunmap_atomic(arg1, KM_USER0);
+	if (arg2_gpa)
+		kunmap_atomic(arg2, KM_USER1);
+
+	kvm_release_page_dirty(arg1_page);
+	if (arg2_gpa)
+		kvm_release_page_dirty(arg2_page);
+
+	return retval;
+}
+
+static int nested_svm_exit_handled_real(struct vcpu_svm *svm,
+					void *arg1,
+					void *arg2,
+					void *opaque)
+{
+	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+	bool kvm_overrides = *(bool *)opaque;
+	u32 exit_code = svm->vmcb->control.exit_code;
+
+	if (kvm_overrides) {
+		switch (exit_code) {
+		case SVM_EXIT_INTR:
+		case SVM_EXIT_NMI:
+			return 0;
+		/* For now we are always handling NPFs when using them */
+		case SVM_EXIT_NPF:
+			if (npt_enabled)
+				return 0;
+			break;
+		/* When we're shadowing, trap PFs */
+		case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+			if (!npt_enabled)
+				return 0;
+			break;
+		default:
+			break;
+		}
+	}
+
+	switch (exit_code) {
+	case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
+		u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
+		if (nested_vmcb->control.intercept_cr_read & cr_bits)
+			return 1;
+		break;
+	}
+	case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: {
+		u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0);
+		if (nested_vmcb->control.intercept_cr_write & cr_bits)
+			return 1;
+		break;
+	}
+	case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: {
+		u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0);
+		if (nested_vmcb->control.intercept_dr_read & dr_bits)
+			return 1;
+		break;
+	}
+	case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: {
+		u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0);
+		if (nested_vmcb->control.intercept_dr_write & dr_bits)
+			return 1;
+		break;
+	}
+	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
+		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
+		if (nested_vmcb->control.intercept_exceptions & excp_bits)
+			return 1;
+		break;
+	}
+	default: {
+		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
+		nsvm_printk("exit code: 0x%x\n", exit_code);
+		if (nested_vmcb->control.intercept & exit_bits)
+			return 1;
+	}
+	}
+
+	return 0;
+}
+
+static int nested_svm_exit_handled_msr(struct vcpu_svm *svm,
+				       void *arg1, void *arg2,
+				       void *opaque)
+{
+	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+	u8 *msrpm = (u8 *)arg2;
+        u32 t0, t1;
+	u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+	u32 param = svm->vmcb->control.exit_info_1 & 1;
+
+	if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+		return 0;
+
+	switch(msr) {
+	case 0 ... 0x1fff:
+		t0 = (msr * 2) % 8;
+		t1 = msr / 8;
+		break;
+	case 0xc0000000 ... 0xc0001fff:
+		t0 = (8192 + msr - 0xc0000000) * 2;
+		t1 = (t0 / 8);
+		t0 %= 8;
+		break;
+	case 0xc0010000 ... 0xc0011fff:
+		t0 = (16384 + msr - 0xc0010000) * 2;
+		t1 = (t0 / 8);
+		t0 %= 8;
+		break;
+	default:
+		return 1;
+		break;
+	}
+	if (msrpm[t1] & ((1 << param) << t0))
+		return 1;
+
+	return 0;
+}
+
+static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override)
+{
+	bool k = kvm_override;
+
+	switch (svm->vmcb->control.exit_code) {
+	case SVM_EXIT_MSR:
+		return nested_svm_do(svm, svm->nested_vmcb,
+				     svm->nested_vmcb_msrpm, NULL,
+				     nested_svm_exit_handled_msr);
+	default: break;
+	}
+
+	return nested_svm_do(svm, svm->nested_vmcb, 0, &k,
+			     nested_svm_exit_handled_real);
+}
+
+static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
+				  void *arg2, void *opaque)
+{
+	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+	struct vmcb *hsave = svm->hsave;
+	u64 nested_save[] = { nested_vmcb->save.cr0,
+			      nested_vmcb->save.cr3,
+			      nested_vmcb->save.cr4,
+			      nested_vmcb->save.efer,
+			      nested_vmcb->control.intercept_cr_read,
+			      nested_vmcb->control.intercept_cr_write,
+			      nested_vmcb->control.intercept_dr_read,
+			      nested_vmcb->control.intercept_dr_write,
+			      nested_vmcb->control.intercept_exceptions,
+			      nested_vmcb->control.intercept,
+			      nested_vmcb->control.msrpm_base_pa,
+			      nested_vmcb->control.iopm_base_pa,
+			      nested_vmcb->control.tsc_offset };
+
+	/* Give the current vmcb to the guest */
+	memcpy(nested_vmcb, svm->vmcb, sizeof(struct vmcb));
+	nested_vmcb->save.cr0 = nested_save[0];
+	if (!npt_enabled)
+		nested_vmcb->save.cr3 = nested_save[1];
+	nested_vmcb->save.cr4 = nested_save[2];
+	nested_vmcb->save.efer = nested_save[3];
+	nested_vmcb->control.intercept_cr_read = nested_save[4];
+	nested_vmcb->control.intercept_cr_write = nested_save[5];
+	nested_vmcb->control.intercept_dr_read = nested_save[6];
+	nested_vmcb->control.intercept_dr_write = nested_save[7];
+	nested_vmcb->control.intercept_exceptions = nested_save[8];
+	nested_vmcb->control.intercept = nested_save[9];
+	nested_vmcb->control.msrpm_base_pa = nested_save[10];
+	nested_vmcb->control.iopm_base_pa = nested_save[11];
+	nested_vmcb->control.tsc_offset = nested_save[12];
+
+	/* We always set V_INTR_MASKING and remember the old value in hflags */
+	if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
+		nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
+
+	if ((nested_vmcb->control.int_ctl & V_IRQ_MASK) &&
+	    (nested_vmcb->control.int_vector)) {
+		nsvm_printk("WARNING: IRQ 0x%x still enabled on #VMEXIT\n",
+				nested_vmcb->control.int_vector);
+	}
+
+	/* Restore the original control entries */
+	svm->vmcb->control = hsave->control;
+
+	/* Kill any pending exceptions */
+	if (svm->vcpu.arch.exception.pending == true)
+		nsvm_printk("WARNING: Pending Exception\n");
+	svm->vcpu.arch.exception.pending = false;
+
+	/* Restore selected save entries */
+	svm->vmcb->save.es = hsave->save.es;
+	svm->vmcb->save.cs = hsave->save.cs;
+	svm->vmcb->save.ss = hsave->save.ss;
+	svm->vmcb->save.ds = hsave->save.ds;
+	svm->vmcb->save.gdtr = hsave->save.gdtr;
+	svm->vmcb->save.idtr = hsave->save.idtr;
+	svm->vmcb->save.rflags = hsave->save.rflags;
+	svm_set_efer(&svm->vcpu, hsave->save.efer);
+	svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE);
+	svm_set_cr4(&svm->vcpu, hsave->save.cr4);
+	if (npt_enabled) {
+		svm->vmcb->save.cr3 = hsave->save.cr3;
+		svm->vcpu.arch.cr3 = hsave->save.cr3;
+	} else {
+		kvm_set_cr3(&svm->vcpu, hsave->save.cr3);
+	}
+	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax);
+	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp);
+	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip);
+	svm->vmcb->save.dr7 = 0;
+	svm->vmcb->save.cpl = 0;
+	svm->vmcb->control.exit_int_info = 0;
+
+	svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+	/* Exit nested SVM mode */
+	svm->nested_vmcb = 0;
+
+	return 0;
+}
+
+static int nested_svm_vmexit(struct vcpu_svm *svm)
+{
+	nsvm_printk("VMexit\n");
+	if (nested_svm_do(svm, svm->nested_vmcb, 0,
+			  NULL, nested_svm_vmexit_real))
+		return 1;
+
+	kvm_mmu_reset_context(&svm->vcpu);
+	kvm_mmu_load(&svm->vcpu);
+
+	return 0;
+}
+
+static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1,
+				  void *arg2, void *opaque)
+{
+	int i;
+	u32 *nested_msrpm = (u32*)arg1;
+	for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
+		svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+	svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm);
+
+	return 0;
+}
+
+static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
+			    void *arg2, void *opaque)
+{
+	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+	struct vmcb *hsave = svm->hsave;
+
+	/* nested_vmcb is our indicator if nested SVM is activated */
+	svm->nested_vmcb = svm->vmcb->save.rax;
+
+	/* Clear internal status */
+	svm->vcpu.arch.exception.pending = false;
+
+	/* Save the old vmcb, so we don't need to pick what we save, but
+	   can restore everything when a VMEXIT occurs */
+	memcpy(hsave, svm->vmcb, sizeof(struct vmcb));
+	/* We need to remember the original CR3 in the SPT case */
+	if (!npt_enabled)
+		hsave->save.cr3 = svm->vcpu.arch.cr3;
+	hsave->save.cr4 = svm->vcpu.arch.cr4;
+	hsave->save.rip = svm->next_rip;
+
+	if (svm->vmcb->save.rflags & X86_EFLAGS_IF)
+		svm->vcpu.arch.hflags |= HF_HIF_MASK;
+	else
+		svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
+
+	/* Load the nested guest state */
+	svm->vmcb->save.es = nested_vmcb->save.es;
+	svm->vmcb->save.cs = nested_vmcb->save.cs;
+	svm->vmcb->save.ss = nested_vmcb->save.ss;
+	svm->vmcb->save.ds = nested_vmcb->save.ds;
+	svm->vmcb->save.gdtr = nested_vmcb->save.gdtr;
+	svm->vmcb->save.idtr = nested_vmcb->save.idtr;
+	svm->vmcb->save.rflags = nested_vmcb->save.rflags;
+	svm_set_efer(&svm->vcpu, nested_vmcb->save.efer);
+	svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0);
+	svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4);
+	if (npt_enabled) {
+		svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
+		svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
+	} else {
+		kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
+		kvm_mmu_reset_context(&svm->vcpu);
+	}
+	svm->vmcb->save.cr2 = nested_vmcb->save.cr2;
+	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
+	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
+	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+	/* In case we don't even reach vcpu_run, the fields are not updated */
+	svm->vmcb->save.rax = nested_vmcb->save.rax;
+	svm->vmcb->save.rsp = nested_vmcb->save.rsp;
+	svm->vmcb->save.rip = nested_vmcb->save.rip;
+	svm->vmcb->save.dr7 = nested_vmcb->save.dr7;
+	svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
+	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
+
+	/* We don't want a nested guest to be more powerful than the guest,
+	   so all intercepts are ORed */
+	svm->vmcb->control.intercept_cr_read |=
+		nested_vmcb->control.intercept_cr_read;
+	svm->vmcb->control.intercept_cr_write |=
+		nested_vmcb->control.intercept_cr_write;
+	svm->vmcb->control.intercept_dr_read |=
+		nested_vmcb->control.intercept_dr_read;
+	svm->vmcb->control.intercept_dr_write |=
+		nested_vmcb->control.intercept_dr_write;
+	svm->vmcb->control.intercept_exceptions |=
+		nested_vmcb->control.intercept_exceptions;
+
+	svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+	svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
+
+	force_new_asid(&svm->vcpu);
+	svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info;
+	svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err;
+	svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
+	if (nested_vmcb->control.int_ctl & V_IRQ_MASK) {
+		nsvm_printk("nSVM Injecting Interrupt: 0x%x\n",
+				nested_vmcb->control.int_ctl);
+	}
+	if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
+		svm->vcpu.arch.hflags |= HF_VINTR_MASK;
+	else
+		svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
+
+	nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n",
+			nested_vmcb->control.exit_int_info,
+			nested_vmcb->control.int_state);
+
+	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
+	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
+	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
+	if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID)
+		nsvm_printk("Injecting Event: 0x%x\n",
+				nested_vmcb->control.event_inj);
+	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
+	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
+
+	svm->vcpu.arch.hflags |= HF_GIF_MASK;
+
+	return 0;
+}
+
+static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+{
+	to_vmcb->save.fs = from_vmcb->save.fs;
+	to_vmcb->save.gs = from_vmcb->save.gs;
+	to_vmcb->save.tr = from_vmcb->save.tr;
+	to_vmcb->save.ldtr = from_vmcb->save.ldtr;
+	to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base;
+	to_vmcb->save.star = from_vmcb->save.star;
+	to_vmcb->save.lstar = from_vmcb->save.lstar;
+	to_vmcb->save.cstar = from_vmcb->save.cstar;
+	to_vmcb->save.sfmask = from_vmcb->save.sfmask;
+	to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs;
+	to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp;
+	to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
+
+	return 1;
+}
+
+static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb,
+			     void *arg2, void *opaque)
+{
+	return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb);
+}
+
+static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
+			     void *arg2, void *opaque)
+{
+	return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb);
+}
+
+static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	if (nested_svm_check_permissions(svm))
+		return 1;
+
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
+	nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload);
+
+	return 1;
+}
+
+static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	if (nested_svm_check_permissions(svm))
+		return 1;
+
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
+	nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave);
+
+	return 1;
+}
+
+static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	nsvm_printk("VMrun\n");
+	if (nested_svm_check_permissions(svm))
+		return 1;
+
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
+	if (nested_svm_do(svm, svm->vmcb->save.rax, 0,
+			  NULL, nested_svm_vmrun))
+		return 1;
+
+	if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0,
+		      NULL, nested_svm_vmrun_msrpm))
+		return 1;
+
+	return 1;
+}
+
+static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	if (nested_svm_check_permissions(svm))
+		return 1;
+
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
+	svm->vcpu.arch.hflags |= HF_GIF_MASK;
+
+	return 1;
+}
+
+static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	if (nested_svm_check_permissions(svm))
+		return 1;
+
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
+	svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+
+	/* After a CLGI no interrupts should come */
+	svm_clear_vintr(svm);
+	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
+
+	return 1;
+}
+
 static int invalid_op_interception(struct vcpu_svm *svm,
 				   struct kvm_run *kvm_run)
 {
@@ -1250,6 +1940,15 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	case MSR_IA32_LASTINTTOIP:
 		*data = svm->vmcb->save.last_excp_to;
 		break;
+	case MSR_VM_HSAVE_PA:
+		*data = svm->hsave_msr;
+		break;
+	case MSR_VM_CR:
+		*data = 0;
+		break;
+	case MSR_IA32_UCODE_REV:
+		*data = 0x01000065;
+		break;
 	default:
 		return kvm_get_msr_common(vcpu, ecx, data);
 	}
@@ -1344,6 +2043,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", ecx, data);
 
 		break;
+	case MSR_VM_HSAVE_PA:
+		svm->hsave_msr = data;
+		break;
 	default:
 		return kvm_set_msr_common(vcpu, ecx, data);
 	}
@@ -1380,7 +2082,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm,
 {
 	KVMTRACE_0D(PEND_INTR, &svm->vcpu, handler);
 
-	svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR);
+	svm_clear_vintr(svm);
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	/*
 	 * If the user space waits to inject interrupts, exit as soon as
@@ -1417,6 +2119,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_WRITE_DR3]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR5]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR7]			= emulate_on_interception,
+	[SVM_EXIT_EXCP_BASE + DB_VECTOR]	= db_interception,
+	[SVM_EXIT_EXCP_BASE + BP_VECTOR]	= bp_interception,
 	[SVM_EXIT_EXCP_BASE + UD_VECTOR]	= ud_interception,
 	[SVM_EXIT_EXCP_BASE + PF_VECTOR] 	= pf_interception,
 	[SVM_EXIT_EXCP_BASE + NM_VECTOR] 	= nm_interception,
@@ -1436,12 +2140,12 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_MSR]				= msr_interception,
 	[SVM_EXIT_TASK_SWITCH]			= task_switch_interception,
 	[SVM_EXIT_SHUTDOWN]			= shutdown_interception,
-	[SVM_EXIT_VMRUN]			= invalid_op_interception,
+	[SVM_EXIT_VMRUN]			= vmrun_interception,
 	[SVM_EXIT_VMMCALL]			= vmmcall_interception,
-	[SVM_EXIT_VMLOAD]			= invalid_op_interception,
-	[SVM_EXIT_VMSAVE]			= invalid_op_interception,
-	[SVM_EXIT_STGI]				= invalid_op_interception,
-	[SVM_EXIT_CLGI]				= invalid_op_interception,
+	[SVM_EXIT_VMLOAD]			= vmload_interception,
+	[SVM_EXIT_VMSAVE]			= vmsave_interception,
+	[SVM_EXIT_STGI]				= stgi_interception,
+	[SVM_EXIT_CLGI]				= clgi_interception,
 	[SVM_EXIT_SKINIT]			= invalid_op_interception,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
 	[SVM_EXIT_MONITOR]			= invalid_op_interception,
@@ -1457,6 +2161,17 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	KVMTRACE_3D(VMEXIT, vcpu, exit_code, (u32)svm->vmcb->save.rip,
 		    (u32)((u64)svm->vmcb->save.rip >> 32), entryexit);
 
+	if (is_nested(svm)) {
+		nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n",
+			    exit_code, svm->vmcb->control.exit_info_1,
+			    svm->vmcb->control.exit_info_2, svm->vmcb->save.rip);
+		if (nested_svm_exit_handled(svm, true)) {
+			nested_svm_vmexit(svm);
+			nsvm_printk("-> #VMEXIT\n");
+			return 1;
+		}
+	}
+
 	if (npt_enabled) {
 		int mmu_reload = 0;
 		if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
@@ -1544,6 +2259,8 @@ static void svm_set_irq(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	nested_svm_intr(svm);
+
 	svm_inject_irq(svm, irq);
 }
 
@@ -1589,11 +2306,17 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
 	if (!kvm_cpu_has_interrupt(vcpu))
 		goto out;
 
+	if (nested_svm_intr(svm))
+		goto out;
+
+	if (!(svm->vcpu.arch.hflags & HF_GIF_MASK))
+		goto out;
+
 	if (!(vmcb->save.rflags & X86_EFLAGS_IF) ||
 	    (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
 	    (vmcb->control.event_inj & SVM_EVTINJ_VALID)) {
 		/* unable to deliver irq, set pending irq */
-		vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR);
+		svm_set_vintr(svm);
 		svm_inject_irq(svm, 0x0);
 		goto out;
 	}
@@ -1615,7 +2338,8 @@ static void kvm_reput_irq(struct vcpu_svm *svm)
 	}
 
 	svm->vcpu.arch.interrupt_window_open =
-		!(control->int_state & SVM_INTERRUPT_SHADOW_MASK);
+		!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+		 (svm->vcpu.arch.hflags & HF_GIF_MASK);
 }
 
 static void svm_do_inject_vector(struct vcpu_svm *svm)
@@ -1637,9 +2361,13 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb_control_area *control = &svm->vmcb->control;
 
+	if (nested_svm_intr(svm))
+		return;
+
 	svm->vcpu.arch.interrupt_window_open =
 		(!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		 (svm->vmcb->save.rflags & X86_EFLAGS_IF));
+		 (svm->vmcb->save.rflags & X86_EFLAGS_IF) &&
+		 (svm->vcpu.arch.hflags & HF_GIF_MASK));
 
 	if (svm->vcpu.arch.interrupt_window_open && svm->vcpu.arch.irq_summary)
 		/*
@@ -1652,9 +2380,9 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
 	 */
 	if (!svm->vcpu.arch.interrupt_window_open &&
 	    (svm->vcpu.arch.irq_summary || kvm_run->request_interrupt_window))
-		control->intercept |= 1ULL << INTERCEPT_VINTR;
-	 else
-		control->intercept &= ~(1ULL << INTERCEPT_VINTR);
+		svm_set_vintr(svm);
+	else
+		svm_clear_vintr(svm);
 }
 
 static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
@@ -1662,22 +2390,6 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	return 0;
 }
 
-static void save_db_regs(unsigned long *db_regs)
-{
-	asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0]));
-	asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1]));
-	asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2]));
-	asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3]));
-}
-
-static void load_db_regs(unsigned long *db_regs)
-{
-	asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0]));
-	asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1]));
-	asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2]));
-	asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3]));
-}
-
 static void svm_flush_tlb(struct kvm_vcpu *vcpu)
 {
 	force_new_asid(vcpu);
@@ -1736,19 +2448,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	gs_selector = kvm_read_gs();
 	ldt_selector = kvm_read_ldt();
 	svm->host_cr2 = kvm_read_cr2();
-	svm->host_dr6 = read_dr6();
-	svm->host_dr7 = read_dr7();
-	svm->vmcb->save.cr2 = vcpu->arch.cr2;
+	if (!is_nested(svm))
+		svm->vmcb->save.cr2 = vcpu->arch.cr2;
 	/* required for live migration with NPT */
 	if (npt_enabled)
 		svm->vmcb->save.cr3 = vcpu->arch.cr3;
 
-	if (svm->vmcb->save.dr7 & 0xff) {
-		write_dr7(0);
-		save_db_regs(svm->host_db_regs);
-		load_db_regs(svm->db_regs);
-	}
-
 	clgi();
 
 	local_irq_enable();
@@ -1824,16 +2529,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 #endif
 		);
 
-	if ((svm->vmcb->save.dr7 & 0xff))
-		load_db_regs(svm->host_db_regs);
-
 	vcpu->arch.cr2 = svm->vmcb->save.cr2;
 	vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
-	write_dr6(svm->host_dr6);
-	write_dr7(svm->host_dr7);
 	kvm_write_cr2(svm->host_cr2);
 
 	kvm_load_fs(fs_selector);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7611af57682..bb481330716 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -91,6 +91,7 @@ struct vcpu_vmx {
 	} rmode;
 	int vpid;
 	bool emulation_required;
+	enum emulation_result invalid_state_emulation_result;
 
 	/* Support for vnmi-less CPUs */
 	int soft_vnmi_blocked;
@@ -189,21 +190,21 @@ static inline int is_page_fault(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
 }
 
 static inline int is_no_device(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
 }
 
 static inline int is_invalid_opcode(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
 }
 
 static inline int is_external_interrupt(u32 intr_info)
@@ -480,8 +481,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR);
 	if (!vcpu->fpu_active)
 		eb |= 1u << NM_VECTOR;
-	if (vcpu->guest_debug.enabled)
-		eb |= 1u << DB_VECTOR;
+	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			eb |= 1u << DB_VECTOR;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			eb |= 1u << BP_VECTOR;
+	}
 	if (vcpu->arch.rmode.active)
 		eb = ~0;
 	if (vm_need_ept())
@@ -747,29 +753,33 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 				bool has_error_code, u32 error_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
-	if (has_error_code)
+	if (has_error_code) {
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
 
 	if (vcpu->arch.rmode.active) {
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = nr;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
-		if (nr == BP_VECTOR)
+		if (nr == BP_VECTOR || nr == OF_VECTOR)
 			vmx->rmode.irq.rip++;
-		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-			     nr | INTR_TYPE_SOFT_INTR
-			     | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
-			     | INTR_INFO_VALID_MASK);
+		intr_info |= INTR_TYPE_SOFT_INTR;
+		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
 		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
 		kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
 		return;
 	}
 
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-		     nr | INTR_TYPE_EXCEPTION
-		     | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
-		     | INTR_INFO_VALID_MASK);
+	if (nr == BP_VECTOR || nr == OF_VECTOR) {
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	} else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
 }
 
 static bool vmx_exception_injected(struct kvm_vcpu *vcpu)
@@ -856,11 +866,8 @@ static u64 guest_read_tsc(void)
  * writes 'guest_tsc' into guest's timestamp counter "register"
  * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc
  */
-static void guest_write_tsc(u64 guest_tsc)
+static void guest_write_tsc(u64 guest_tsc, u64 host_tsc)
 {
-	u64 host_tsc;
-
-	rdtscll(host_tsc);
 	vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc);
 }
 
@@ -925,14 +932,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct kvm_msr_entry *msr;
+	u64 host_tsc;
 	int ret = 0;
 
 	switch (msr_index) {
-#ifdef CONFIG_X86_64
 	case MSR_EFER:
 		vmx_load_host_state(vmx);
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
 		break;
+#ifdef CONFIG_X86_64
 	case MSR_FS_BASE:
 		vmcs_writel(GUEST_FS_BASE, data);
 		break;
@@ -950,7 +958,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_TIME_STAMP_COUNTER:
-		guest_write_tsc(data);
+		rdtscll(host_tsc);
+		guest_write_tsc(data, host_tsc);
 		break;
 	case MSR_P6_PERFCTR0:
 	case MSR_P6_PERFCTR1:
@@ -999,40 +1008,28 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	}
 }
 
-static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	unsigned long dr7 = 0x400;
-	int old_singlestep;
-
-	old_singlestep = vcpu->guest_debug.singlestep;
-
-	vcpu->guest_debug.enabled = dbg->enabled;
-	if (vcpu->guest_debug.enabled) {
-		int i;
+	int old_debug = vcpu->guest_debug;
+	unsigned long flags;
 
-		dr7 |= 0x200;  /* exact */
-		for (i = 0; i < 4; ++i) {
-			if (!dbg->breakpoints[i].enabled)
-				continue;
-			vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
-			dr7 |= 2 << (i*2);    /* global enable */
-			dr7 |= 0 << (i*4+16); /* execution breakpoint */
-		}
+	vcpu->guest_debug = dbg->control;
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
+		vcpu->guest_debug = 0;
 
-		vcpu->guest_debug.singlestep = dbg->singlestep;
-	} else
-		vcpu->guest_debug.singlestep = 0;
-
-	if (old_singlestep && !vcpu->guest_debug.singlestep) {
-		unsigned long flags;
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+		vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
+	else
+		vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
 
-		flags = vmcs_readl(GUEST_RFLAGS);
+	flags = vmcs_readl(GUEST_RFLAGS);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
 		flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-		vmcs_writel(GUEST_RFLAGS, flags);
-	}
+	vmcs_writel(GUEST_RFLAGS, flags);
 
 	update_exception_bitmap(vcpu);
-	vmcs_writel(GUEST_DR7, dr7);
 
 	return 0;
 }
@@ -1433,6 +1430,29 @@ continue_rmode:
 	init_rmode(vcpu->kvm);
 }
 
+static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
+
+	vcpu->arch.shadow_efer = efer;
+	if (!msr)
+		return;
+	if (efer & EFER_LMA) {
+		vmcs_write32(VM_ENTRY_CONTROLS,
+			     vmcs_read32(VM_ENTRY_CONTROLS) |
+			     VM_ENTRY_IA32E_MODE);
+		msr->data = efer;
+	} else {
+		vmcs_write32(VM_ENTRY_CONTROLS,
+			     vmcs_read32(VM_ENTRY_CONTROLS) &
+			     ~VM_ENTRY_IA32E_MODE);
+
+		msr->data = efer & ~EFER_LME;
+	}
+	setup_msrs(vmx);
+}
+
 #ifdef CONFIG_X86_64
 
 static void enter_lmode(struct kvm_vcpu *vcpu)
@@ -1447,13 +1467,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 			     (guest_tr_ar & ~AR_TYPE_MASK)
 			     | AR_TYPE_BUSY_64_TSS);
 	}
-
 	vcpu->arch.shadow_efer |= EFER_LMA;
-
-	find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME;
-	vmcs_write32(VM_ENTRY_CONTROLS,
-		     vmcs_read32(VM_ENTRY_CONTROLS)
-		     | VM_ENTRY_IA32E_MODE);
+	vmx_set_efer(vcpu, vcpu->arch.shadow_efer);
 }
 
 static void exit_lmode(struct kvm_vcpu *vcpu)
@@ -1612,30 +1627,6 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vmcs_writel(GUEST_CR4, hw_cr4);
 }
 
-static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
-
-	vcpu->arch.shadow_efer = efer;
-	if (!msr)
-		return;
-	if (efer & EFER_LMA) {
-		vmcs_write32(VM_ENTRY_CONTROLS,
-				     vmcs_read32(VM_ENTRY_CONTROLS) |
-				     VM_ENTRY_IA32E_MODE);
-		msr->data = efer;
-
-	} else {
-		vmcs_write32(VM_ENTRY_CONTROLS,
-				     vmcs_read32(VM_ENTRY_CONTROLS) &
-				     ~VM_ENTRY_IA32E_MODE);
-
-		msr->data = efer & ~EFER_LME;
-	}
-	setup_msrs(vmx);
-}
-
 static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
@@ -1653,7 +1644,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 	var->limit = vmcs_read32(sf->limit);
 	var->selector = vmcs_read16(sf->selector);
 	ar = vmcs_read32(sf->ar_bytes);
-	if (ar & AR_UNUSABLE_MASK)
+	if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
 		ar = 0;
 	var->type = ar & 15;
 	var->s = (ar >> 4) & 1;
@@ -1788,14 +1779,16 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
 	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
 	cs_rpl = cs.selector & SELECTOR_RPL_MASK;
 
+	if (cs.unusable)
+		return false;
 	if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
 		return false;
 	if (!cs.s)
 		return false;
-	if (!(~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK))) {
+	if (cs.type & AR_TYPE_WRITEABLE_MASK) {
 		if (cs.dpl > cs_rpl)
 			return false;
-	} else if (cs.type & AR_TYPE_CODE_MASK) {
+	} else {
 		if (cs.dpl != cs_rpl)
 			return false;
 	}
@@ -1814,7 +1807,9 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu)
 	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
 	ss_rpl = ss.selector & SELECTOR_RPL_MASK;
 
-	if ((ss.type != 3) || (ss.type != 7))
+	if (ss.unusable)
+		return true;
+	if (ss.type != 3 && ss.type != 7)
 		return false;
 	if (!ss.s)
 		return false;
@@ -1834,6 +1829,8 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
 	vmx_get_segment(vcpu, &var, seg);
 	rpl = var.selector & SELECTOR_RPL_MASK;
 
+	if (var.unusable)
+		return true;
 	if (!var.s)
 		return false;
 	if (!var.present)
@@ -1855,9 +1852,11 @@ static bool tr_valid(struct kvm_vcpu *vcpu)
 
 	vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);
 
+	if (tr.unusable)
+		return false;
 	if (tr.selector & SELECTOR_TI_MASK)	/* TI = 1 */
 		return false;
-	if ((tr.type != 3) || (tr.type != 11)) /* TODO: Check if guest is in IA32e mode */
+	if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
 		return false;
 	if (!tr.present)
 		return false;
@@ -1871,6 +1870,8 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu)
 
 	vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);
 
+	if (ldtr.unusable)
+		return true;
 	if (ldtr.selector & SELECTOR_TI_MASK)	/* TI = 1 */
 		return false;
 	if (ldtr.type != 2)
@@ -2112,7 +2113,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 {
 	u32 host_sysenter_cs, msr_low, msr_high;
 	u32 junk;
-	u64 host_pat;
+	u64 host_pat, tsc_this, tsc_base;
 	unsigned long a;
 	struct descriptor_table dt;
 	int i;
@@ -2240,6 +2241,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
 	vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
 
+	tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
+	rdtscll(tsc_this);
+	if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc)
+		tsc_base = tsc_this;
+
+	guest_write_tsc(0, tsc_base);
 
 	return 0;
 }
@@ -2319,7 +2326,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		kvm_rip_write(vcpu, 0);
 	kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
 
-	/* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */
 	vmcs_writel(GUEST_DR7, 0x400);
 
 	vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -2332,8 +2338,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
 	vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
 
-	guest_write_tsc(0);
-
 	/* Special registers */
 	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 
@@ -2486,6 +2490,11 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
 {
 	vmx_update_window_states(vcpu);
 
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+				GUEST_INTR_STATE_STI |
+				GUEST_INTR_STATE_MOV_SS);
+
 	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
 		if (vcpu->arch.interrupt.pending) {
 			enable_nmi_window(vcpu);
@@ -2536,24 +2545,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	return 0;
 }
 
-static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
-{
-	struct kvm_guest_debug *dbg = &vcpu->guest_debug;
-
-	set_debugreg(dbg->bp[0], 0);
-	set_debugreg(dbg->bp[1], 1);
-	set_debugreg(dbg->bp[2], 2);
-	set_debugreg(dbg->bp[3], 3);
-
-	if (dbg->singlestep) {
-		unsigned long flags;
-
-		flags = vmcs_readl(GUEST_RFLAGS);
-		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
-		vmcs_writel(GUEST_RFLAGS, flags);
-	}
-}
-
 static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 				  int vec, u32 err_code)
 {
@@ -2570,9 +2561,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	 *        the required debugging infrastructure rework.
 	 */
 	switch (vec) {
-	case DE_VECTOR:
 	case DB_VECTOR:
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return 0;
+		kvm_queue_exception(vcpu, vec);
+		return 1;
 	case BP_VECTOR:
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return 0;
+		/* fall through */
+	case DE_VECTOR:
 	case OF_VECTOR:
 	case BR_VECTOR:
 	case UD_VECTOR:
@@ -2589,8 +2588,8 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 intr_info, error_code;
-	unsigned long cr2, rip;
+	u32 intr_info, ex_no, error_code;
+	unsigned long cr2, rip, dr6;
 	u32 vect_info;
 	enum emulation_result er;
 
@@ -2649,14 +2648,30 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		return 1;
 	}
 
-	if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) ==
-	    (INTR_TYPE_EXCEPTION | 1)) {
+	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
+	switch (ex_no) {
+	case DB_VECTOR:
+		dr6 = vmcs_readl(EXIT_QUALIFICATION);
+		if (!(vcpu->guest_debug &
+		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+			vcpu->arch.dr6 = dr6 | DR6_FIXED_1;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			return 1;
+		}
+		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
+		/* fall through */
+	case BP_VECTOR:
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		return 0;
+		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+		kvm_run->debug.arch.exception = ex_no;
+		break;
+	default:
+		kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
+		kvm_run->ex.exception = ex_no;
+		kvm_run->ex.error_code = error_code;
+		break;
 	}
-	kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
-	kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK;
-	kvm_run->ex.error_code = error_code;
 	return 0;
 }
 
@@ -2677,7 +2692,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	unsigned long exit_qualification;
-	int size, down, in, string, rep;
+	int size, in, string;
 	unsigned port;
 
 	++vcpu->stat.io_exits;
@@ -2693,8 +2708,6 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	size = (exit_qualification & 7) + 1;
 	in = (exit_qualification & 8) != 0;
-	down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0;
-	rep = (exit_qualification & 32) != 0;
 	port = exit_qualification >> 16;
 
 	skip_emulated_instruction(vcpu);
@@ -2795,21 +2808,44 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	unsigned long val;
 	int dr, reg;
 
-	/*
-	 * FIXME: this code assumes the host is debugging the guest.
-	 *        need to deal with guest debugging itself too.
-	 */
+	dr = vmcs_readl(GUEST_DR7);
+	if (dr & DR7_GD) {
+		/*
+		 * As the vm-exit takes precedence over the debug trap, we
+		 * need to emulate the latter, either for the host or the
+		 * guest debugging itself.
+		 */
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
+			kvm_run->debug.arch.dr6 = vcpu->arch.dr6;
+			kvm_run->debug.arch.dr7 = dr;
+			kvm_run->debug.arch.pc =
+				vmcs_readl(GUEST_CS_BASE) +
+				vmcs_readl(GUEST_RIP);
+			kvm_run->debug.arch.exception = DB_VECTOR;
+			kvm_run->exit_reason = KVM_EXIT_DEBUG;
+			return 0;
+		} else {
+			vcpu->arch.dr7 &= ~DR7_GD;
+			vcpu->arch.dr6 |= DR6_BD;
+			vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			return 1;
+		}
+	}
+
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	dr = exit_qualification & 7;
-	reg = (exit_qualification >> 8) & 15;
-	if (exit_qualification & 16) {
-		/* mov from dr */
+	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
+	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
+	if (exit_qualification & TYPE_MOV_FROM_DR) {
 		switch (dr) {
+		case 0 ... 3:
+			val = vcpu->arch.db[dr];
+			break;
 		case 6:
-			val = 0xffff0ff0;
+			val = vcpu->arch.dr6;
 			break;
 		case 7:
-			val = 0x400;
+			val = vcpu->arch.dr7;
 			break;
 		default:
 			val = 0;
@@ -2817,7 +2853,38 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_register_write(vcpu, reg, val);
 		KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
 	} else {
-		/* mov to dr */
+		val = vcpu->arch.regs[reg];
+		switch (dr) {
+		case 0 ... 3:
+			vcpu->arch.db[dr] = val;
+			if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+				vcpu->arch.eff_db[dr] = val;
+			break;
+		case 4 ... 5:
+			if (vcpu->arch.cr4 & X86_CR4_DE)
+				kvm_queue_exception(vcpu, UD_VECTOR);
+			break;
+		case 6:
+			if (val & 0xffffffff00000000ULL) {
+				kvm_queue_exception(vcpu, GP_VECTOR);
+				break;
+			}
+			vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+			break;
+		case 7:
+			if (val & 0xffffffff00000000ULL) {
+				kvm_queue_exception(vcpu, GP_VECTOR);
+				break;
+			}
+			vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
+			if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+				vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
+				vcpu->arch.switch_db_regs =
+					(val & DR7_BP_EN_MASK);
+			}
+			break;
+		}
+		KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler);
 	}
 	skip_emulated_instruction(vcpu);
 	return 1;
@@ -2968,17 +3035,25 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 	tss_selector = exit_qualification;
 
-	return kvm_task_switch(vcpu, tss_selector, reason);
+	if (!kvm_task_switch(vcpu, tss_selector, reason))
+		return 0;
+
+	/* clear all local breakpoint enable flags */
+	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
+
+	/*
+	 * TODO: What about debug traps on tss switch?
+	 *       Are we supposed to inject them and update dr6?
+	 */
+
+	return 1;
 }
 
 static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u64 exit_qualification;
-	enum emulation_result er;
 	gpa_t gpa;
-	unsigned long hva;
 	int gla_validity;
-	int r;
 
 	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
 
@@ -3001,32 +3076,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
-	hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT);
-	if (!kvm_is_error_hva(hva)) {
-		r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
-		if (r < 0) {
-			printk(KERN_ERR "EPT: Not enough memory!\n");
-			return -ENOMEM;
-		}
-		return 1;
-	} else {
-		/* must be MMIO */
-		er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
-
-		if (er == EMULATE_FAIL) {
-			printk(KERN_ERR
-			 "EPT: Fail to handle EPT violation vmexit!er is %d\n",
-			 er);
-			printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
-			 (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
-			 (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS));
-			printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
-				(long unsigned int)exit_qualification);
-			return -ENOTSUPP;
-		} else if (er == EMULATE_DO_MMIO)
-			return 0;
-	}
-	return 1;
+	return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
 }
 
 static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -3046,7 +3096,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 				struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int err;
+	enum emulation_result err = EMULATE_DONE;
 
 	preempt_enable();
 	local_irq_enable();
@@ -3071,10 +3121,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 	local_irq_disable();
 	preempt_disable();
 
-	/* Guest state should be valid now except if we need to
-	 * emulate an MMIO */
-	if (guest_state_valid(vcpu))
-		vmx->emulation_required = 0;
+	vmx->invalid_state_emulation_result = err;
 }
 
 /*
@@ -3123,8 +3170,11 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	/* If we need to emulate an MMIO from handle_invalid_guest_state
 	 * we just return 0 */
-	if (vmx->emulation_required && emulate_invalid_guest_state)
-		return 0;
+	if (vmx->emulation_required && emulate_invalid_guest_state) {
+		if (guest_state_valid(vcpu))
+			vmx->emulation_required = 0;
+		return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO;
+	}
 
 	/* Access CR3 don't cause VMExit in paging mode, so we need
 	 * to sync with guest real CR3. */
@@ -3238,7 +3288,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
 			vmx->vcpu.arch.nmi_injected = false;
 	}
 	kvm_clear_exception_queue(&vmx->vcpu);
-	if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) {
+	if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION ||
+				type == INTR_TYPE_SOFT_EXCEPTION)) {
 		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
 			error = vmcs_read32(IDT_VECTORING_ERROR_CODE);
 			kvm_queue_exception_e(&vmx->vcpu, vector, error);
@@ -3259,6 +3310,11 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
 
 	vmx_update_window_states(vcpu);
 
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+				GUEST_INTR_STATE_STI |
+				GUEST_INTR_STATE_MOV_SS);
+
 	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
 		if (vcpu->arch.interrupt.pending) {
 			enable_nmi_window(vcpu);
@@ -3347,6 +3403,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	 */
 	vmcs_writel(HOST_CR0, read_cr0());
 
+	set_debugreg(vcpu->arch.dr6, 6);
+
 	asm(
 		/* Store host registers */
 		"push %%"R"dx; push %%"R"bp;"
@@ -3441,6 +3499,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
 	vcpu->arch.regs_dirty = 0;
 
+	get_debugreg(vcpu->arch.dr6, 6);
+
 	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 	if (vmx->rmode.irq.pending)
 		fixup_rmode_irq(vmx);
@@ -3595,7 +3655,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.vcpu_put = vmx_vcpu_put,
 
 	.set_guest_debug = set_guest_debug,
-	.guest_debug_pre = kvm_guest_debug_pre,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 758b7a155ae..8ca100a9eca 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -36,6 +36,7 @@
 #include <linux/highmem.h>
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
+#include <linux/cpufreq.h>
 
 #include <asm/uaccess.h>
 #include <asm/msr.h>
@@ -69,6 +70,8 @@ static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
 
 static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 				    struct kvm_cpuid_entry2 __user *entries);
+struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
+					      u32 function, u32 index);
 
 struct kvm_x86_ops *kvm_x86_ops;
 EXPORT_SYMBOL_GPL(kvm_x86_ops);
@@ -173,6 +176,7 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
 			   u32 error_code)
 {
 	++vcpu->stat.pf_guest;
+
 	if (vcpu->arch.exception.pending) {
 		if (vcpu->arch.exception.nr == PF_VECTOR) {
 			printk(KERN_DEBUG "kvm: inject_page_fault:"
@@ -361,6 +365,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	}
 	kvm_x86_ops->set_cr4(vcpu, cr4);
 	vcpu->arch.cr4 = cr4;
+	vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
 	kvm_mmu_sync_global(vcpu);
 	kvm_mmu_reset_context(vcpu);
 }
@@ -442,6 +447,11 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_cr8);
 
+static inline u32 bit(int bitno)
+{
+	return 1 << (bitno & 31);
+}
+
 /*
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
@@ -456,7 +466,7 @@ static u32 msrs_to_save[] = {
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
 	MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-	MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT
+	MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
 };
 
 static unsigned num_msrs_to_save;
@@ -481,6 +491,28 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 		return;
 	}
 
+	if (efer & EFER_FFXSR) {
+		struct kvm_cpuid_entry2 *feat;
+
+		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
+			printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
+			kvm_inject_gp(vcpu, 0);
+			return;
+		}
+	}
+
+	if (efer & EFER_SVME) {
+		struct kvm_cpuid_entry2 *feat;
+
+		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
+			printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
+			kvm_inject_gp(vcpu, 0);
+			return;
+		}
+	}
+
 	kvm_x86_ops->set_efer(vcpu, efer);
 
 	efer &= ~EFER_LMA;
@@ -586,6 +618,8 @@ static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *
 		 hv_clock->tsc_to_system_mul);
 }
 
+static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
+
 static void kvm_write_guest_time(struct kvm_vcpu *v)
 {
 	struct timespec ts;
@@ -596,9 +630,9 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	if ((!vcpu->time_page))
 		return;
 
-	if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
-		kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
-		vcpu->hv_clock_tsc_khz = tsc_khz;
+	if (unlikely(vcpu->hv_clock_tsc_khz != __get_cpu_var(cpu_tsc_khz))) {
+		kvm_set_time_scale(__get_cpu_var(cpu_tsc_khz), &vcpu->hv_clock);
+		vcpu->hv_clock_tsc_khz = __get_cpu_var(cpu_tsc_khz);
 	}
 
 	/* Keep irq disabled to prevent changes to the clock */
@@ -629,6 +663,16 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
 }
 
+static int kvm_request_guest_time_update(struct kvm_vcpu *v)
+{
+	struct kvm_vcpu_arch *vcpu = &v->arch;
+
+	if (!vcpu->time_page)
+		return 0;
+	set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests);
+	return 1;
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
 	switch (msr) {
@@ -722,6 +766,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		break;
 	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_UCODE_WRITE:
+	case MSR_VM_HSAVE_PA:
 		break;
 	case 0x200 ... 0x2ff:
 		return set_msr_mtrr(vcpu, msr, data);
@@ -758,7 +803,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			vcpu->arch.time_page = NULL;
 		}
 
-		kvm_write_guest_time(vcpu);
+		kvm_request_guest_time_update(vcpu);
 		break;
 	}
 	default:
@@ -843,6 +888,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_LASTBRANCHTOIP:
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
+	case MSR_VM_HSAVE_PA:
 		data = 0;
 		break;
 	case MSR_MTRRcap:
@@ -967,10 +1013,13 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_SYNC_MMU:
+	case KVM_CAP_REINJECT_CONTROL:
+	case KVM_CAP_IRQ_INJECT_STATUS:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -991,9 +1040,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IOMMU:
 		r = iommu_found();
 		break;
-	case KVM_CAP_CLOCKSOURCE:
-		r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC);
-		break;
 	default:
 		r = 0;
 		break;
@@ -1044,7 +1090,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
 		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
-			cpuid_arg->entries);
+						      cpuid_arg->entries);
 		if (r)
 			goto out;
 
@@ -1064,7 +1110,7 @@ out:
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
-	kvm_write_guest_time(vcpu);
+	kvm_request_guest_time_update(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1142,8 +1188,8 @@ out:
 }
 
 static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
-				    struct kvm_cpuid2 *cpuid,
-				    struct kvm_cpuid_entry2 __user *entries)
+				     struct kvm_cpuid2 *cpuid,
+				     struct kvm_cpuid_entry2 __user *entries)
 {
 	int r;
 
@@ -1162,8 +1208,8 @@ out:
 }
 
 static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
-				    struct kvm_cpuid2 *cpuid,
-				    struct kvm_cpuid_entry2 __user *entries)
+				     struct kvm_cpuid2 *cpuid,
+				     struct kvm_cpuid_entry2 __user *entries)
 {
 	int r;
 
@@ -1172,7 +1218,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
 		goto out;
 	r = -EFAULT;
 	if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
-			   vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
+			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
 		goto out;
 	return 0;
 
@@ -1181,18 +1227,13 @@ out:
 	return r;
 }
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
-			  u32 index)
+			   u32 index)
 {
 	entry->function = function;
 	entry->index = index;
 	cpuid_count(entry->function, entry->index,
-		&entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
+		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
 	entry->flags = 0;
 }
 
@@ -1222,15 +1263,17 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 #ifdef CONFIG_X86_64
 		bit(X86_FEATURE_LM) |
 #endif
+		bit(X86_FEATURE_FXSR_OPT) |
 		bit(X86_FEATURE_MMXEXT) |
 		bit(X86_FEATURE_3DNOWEXT) |
 		bit(X86_FEATURE_3DNOW);
 	const u32 kvm_supported_word3_x86_features =
 		bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16);
 	const u32 kvm_supported_word6_x86_features =
-		bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY);
+		bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY) |
+		bit(X86_FEATURE_SVM);
 
-	/* all func 2 cpuid_count() should be called on the same cpu */
+	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 	do_cpuid_1_ent(entry, function, index);
 	++*nent;
@@ -1304,7 +1347,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 }
 
 static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				    struct kvm_cpuid_entry2 __user *entries)
+				     struct kvm_cpuid_entry2 __user *entries)
 {
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	int limit, nent = 0, r = -E2BIG;
@@ -1321,7 +1364,7 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	limit = cpuid_entries[0].eax;
 	for (func = 1; func <= limit && nent < cpuid->nent; ++func)
 		do_cpuid_ent(&cpuid_entries[nent], func, 0,
-				&nent, cpuid->nent);
+			     &nent, cpuid->nent);
 	r = -E2BIG;
 	if (nent >= cpuid->nent)
 		goto out_free;
@@ -1330,10 +1373,10 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	limit = cpuid_entries[nent - 1].eax;
 	for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
 		do_cpuid_ent(&cpuid_entries[nent], func, 0,
-			       &nent, cpuid->nent);
+			     &nent, cpuid->nent);
 	r = -EFAULT;
 	if (copy_to_user(entries, cpuid_entries,
-			nent * sizeof(struct kvm_cpuid_entry2)))
+			 nent * sizeof(struct kvm_cpuid_entry2)))
 		goto out_free;
 	cpuid->nent = nent;
 	r = 0;
@@ -1477,7 +1520,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
 		r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
-				cpuid_arg->entries);
+					      cpuid_arg->entries);
 		if (r)
 			goto out;
 		break;
@@ -1490,7 +1533,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
 		r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
-				cpuid_arg->entries);
+					      cpuid_arg->entries);
 		if (r)
 			goto out;
 		r = -EFAULT;
@@ -1710,6 +1753,15 @@ static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 	return r;
 }
 
+static int kvm_vm_ioctl_reinject(struct kvm *kvm,
+				 struct kvm_reinject_control *control)
+{
+	if (!kvm->arch.vpit)
+		return -ENXIO;
+	kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
+	return 0;
+}
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -1807,13 +1859,26 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			}
 		} else
 			goto out;
+		r = kvm_setup_default_irq_routing(kvm);
+		if (r) {
+			kfree(kvm->arch.vpic);
+			kfree(kvm->arch.vioapic);
+			goto out;
+		}
 		break;
 	case KVM_CREATE_PIT:
+		mutex_lock(&kvm->lock);
+		r = -EEXIST;
+		if (kvm->arch.vpit)
+			goto create_pit_unlock;
 		r = -ENOMEM;
 		kvm->arch.vpit = kvm_create_pit(kvm);
 		if (kvm->arch.vpit)
 			r = 0;
+	create_pit_unlock:
+		mutex_unlock(&kvm->lock);
 		break;
+	case KVM_IRQ_LINE_STATUS:
 	case KVM_IRQ_LINE: {
 		struct kvm_irq_level irq_event;
 
@@ -1821,10 +1886,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
+			__s32 status;
 			mutex_lock(&kvm->lock);
-			kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
-				    irq_event.irq, irq_event.level);
+			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+					irq_event.irq, irq_event.level);
 			mutex_unlock(&kvm->lock);
+			if (ioctl == KVM_IRQ_LINE_STATUS) {
+				irq_event.status = status;
+				if (copy_to_user(argp, &irq_event,
+							sizeof irq_event))
+					goto out;
+			}
 			r = 0;
 		}
 		break;
@@ -1907,6 +1979,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_REINJECT_CONTROL: {
+		struct kvm_reinject_control control;
+		r =  -EFAULT;
+		if (copy_from_user(&control, argp, sizeof(control)))
+			goto out;
+		r = kvm_vm_ioctl_reinject(kvm, &control);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	default:
 		;
 	}
@@ -1960,10 +2043,38 @@ static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
 	return dev;
 }
 
-int emulator_read_std(unsigned long addr,
-			     void *val,
-			     unsigned int bytes,
-			     struct kvm_vcpu *vcpu)
+static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
+			       struct kvm_vcpu *vcpu)
+{
+	void *data = val;
+	int r = X86EMUL_CONTINUE;
+
+	while (bytes) {
+		gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+		unsigned offset = addr & (PAGE_SIZE-1);
+		unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
+		int ret;
+
+		if (gpa == UNMAPPED_GVA) {
+			r = X86EMUL_PROPAGATE_FAULT;
+			goto out;
+		}
+		ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
+		if (ret < 0) {
+			r = X86EMUL_UNHANDLEABLE;
+			goto out;
+		}
+
+		bytes -= toread;
+		data += toread;
+		addr += toread;
+	}
+out:
+	return r;
+}
+
+static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
+				struct kvm_vcpu *vcpu)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
@@ -1971,27 +2082,27 @@ int emulator_read_std(unsigned long addr,
 	while (bytes) {
 		gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
 		unsigned offset = addr & (PAGE_SIZE-1);
-		unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset);
+		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
 
 		if (gpa == UNMAPPED_GVA) {
 			r = X86EMUL_PROPAGATE_FAULT;
 			goto out;
 		}
-		ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy);
+		ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite);
 		if (ret < 0) {
 			r = X86EMUL_UNHANDLEABLE;
 			goto out;
 		}
 
-		bytes -= tocopy;
-		data += tocopy;
-		addr += tocopy;
+		bytes -= towrite;
+		data += towrite;
+		addr += towrite;
 	}
 out:
 	return r;
 }
-EXPORT_SYMBOL_GPL(emulator_read_std);
+
 
 static int emulator_read_emulated(unsigned long addr,
 				  void *val,
@@ -2013,8 +2124,8 @@ static int emulator_read_emulated(unsigned long addr,
 	if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
 		goto mmio;
 
-	if (emulator_read_std(addr, val, bytes, vcpu)
-			== X86EMUL_CONTINUE)
+	if (kvm_read_guest_virt(addr, val, bytes, vcpu)
+				== X86EMUL_CONTINUE)
 		return X86EMUL_CONTINUE;
 	if (gpa == UNMAPPED_GVA)
 		return X86EMUL_PROPAGATE_FAULT;
@@ -2217,7 +2328,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 
 	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
 
-	emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu);
+	kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu);
 
 	printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
 	       context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
@@ -2225,7 +2336,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
 
 static struct x86_emulate_ops emulate_ops = {
-	.read_std            = emulator_read_std,
+	.read_std            = kvm_read_guest_virt,
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
 	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
@@ -2327,40 +2438,19 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(emulate_instruction);
 
-static void free_pio_guest_pages(struct kvm_vcpu *vcpu)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i)
-		if (vcpu->arch.pio.guest_pages[i]) {
-			kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]);
-			vcpu->arch.pio.guest_pages[i] = NULL;
-		}
-}
-
 static int pio_copy_data(struct kvm_vcpu *vcpu)
 {
 	void *p = vcpu->arch.pio_data;
-	void *q;
+	gva_t q = vcpu->arch.pio.guest_gva;
 	unsigned bytes;
-	int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1;
+	int ret;
 
-	q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE,
-		 PAGE_KERNEL);
-	if (!q) {
-		free_pio_guest_pages(vcpu);
-		return -ENOMEM;
-	}
-	q += vcpu->arch.pio.guest_page_offset;
 	bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
 	if (vcpu->arch.pio.in)
-		memcpy(q, p, bytes);
+		ret = kvm_write_guest_virt(q, p, bytes, vcpu);
 	else
-		memcpy(p, q, bytes);
-	q -= vcpu->arch.pio.guest_page_offset;
-	vunmap(q);
-	free_pio_guest_pages(vcpu);
-	return 0;
+		ret = kvm_read_guest_virt(q, p, bytes, vcpu);
+	return ret;
 }
 
 int complete_pio(struct kvm_vcpu *vcpu)
@@ -2471,7 +2561,6 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->arch.pio.in = in;
 	vcpu->arch.pio.string = 0;
 	vcpu->arch.pio.down = 0;
-	vcpu->arch.pio.guest_page_offset = 0;
 	vcpu->arch.pio.rep = 0;
 
 	if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
@@ -2499,9 +2588,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 		  gva_t address, int rep, unsigned port)
 {
 	unsigned now, in_page;
-	int i, ret = 0;
-	int nr_pages = 1;
-	struct page *page;
+	int ret = 0;
 	struct kvm_io_device *pio_dev;
 
 	vcpu->run->exit_reason = KVM_EXIT_IO;
@@ -2513,7 +2600,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->arch.pio.in = in;
 	vcpu->arch.pio.string = 1;
 	vcpu->arch.pio.down = down;
-	vcpu->arch.pio.guest_page_offset = offset_in_page(address);
 	vcpu->arch.pio.rep = rep;
 
 	if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
@@ -2533,15 +2619,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	else
 		in_page = offset_in_page(address) + size;
 	now = min(count, (unsigned long)in_page / size);
-	if (!now) {
-		/*
-		 * String I/O straddles page boundary.  Pin two guest pages
-		 * so that we satisfy atomicity constraints.  Do just one
-		 * transaction to avoid complexity.
-		 */
-		nr_pages = 2;
+	if (!now)
 		now = 1;
-	}
 	if (down) {
 		/*
 		 * String I/O in reverse.  Yuck.  Kill the guest, fix later.
@@ -2556,15 +2635,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
 		kvm_x86_ops->skip_emulated_instruction(vcpu);
 
-	for (i = 0; i < nr_pages; ++i) {
-		page = gva_to_page(vcpu, address + i * PAGE_SIZE);
-		vcpu->arch.pio.guest_pages[i] = page;
-		if (!page) {
-			kvm_inject_gp(vcpu, 0);
-			free_pio_guest_pages(vcpu);
-			return 1;
-		}
-	}
+	vcpu->arch.pio.guest_gva = address;
 
 	pio_dev = vcpu_find_pio_dev(vcpu, port,
 				    vcpu->arch.pio.cur_count,
@@ -2572,7 +2643,11 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	if (!vcpu->arch.pio.in) {
 		/* string PIO write */
 		ret = pio_copy_data(vcpu);
-		if (ret >= 0 && pio_dev) {
+		if (ret == X86EMUL_PROPAGATE_FAULT) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+		if (ret == 0 && pio_dev) {
 			pio_string_write(pio_dev, vcpu);
 			complete_pio(vcpu);
 			if (vcpu->arch.pio.count == 0)
@@ -2587,9 +2662,72 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
 
+static void bounce_off(void *info)
+{
+	/* nothing */
+}
+
+static unsigned int  ref_freq;
+static unsigned long tsc_khz_ref;
+
+static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				     void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct kvm *kvm;
+	struct kvm_vcpu *vcpu;
+	int i, send_ipi = 0;
+
+	if (!ref_freq)
+		ref_freq = freq->old;
+
+	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
+		return 0;
+	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
+		return 0;
+	per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+			vcpu = kvm->vcpus[i];
+			if (!vcpu)
+				continue;
+			if (vcpu->cpu != freq->cpu)
+				continue;
+			if (!kvm_request_guest_time_update(vcpu))
+				continue;
+			if (vcpu->cpu != smp_processor_id())
+				send_ipi++;
+		}
+	}
+	spin_unlock(&kvm_lock);
+
+	if (freq->old < freq->new && send_ipi) {
+		/*
+		 * We upscale the frequency.  Must make the guest
+		 * doesn't see old kvmclock values while running with
+		 * the new frequency, otherwise we risk the guest sees
+		 * time go backwards.
+		 *
+		 * In case we update the frequency for another cpu
+		 * (which might be in guest context) send an interrupt
+		 * to kick the cpu out of guest context.  Next time
+		 * guest context is entered kvmclock will be updated,
+		 * so the guest will not see stale values.
+		 */
+		smp_call_function_single(freq->cpu, bounce_off, NULL, 1);
+	}
+	return 0;
+}
+
+static struct notifier_block kvmclock_cpufreq_notifier_block = {
+        .notifier_call  = kvmclock_cpufreq_notifier
+};
+
 int kvm_arch_init(void *opaque)
 {
-	int r;
+	int r, cpu;
 	struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
 
 	if (kvm_x86_ops) {
@@ -2620,6 +2758,15 @@ int kvm_arch_init(void *opaque)
 	kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0, 0);
+
+	for_each_possible_cpu(cpu)
+		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		tsc_khz_ref = tsc_khz;
+		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
+					  CPUFREQ_TRANSITION_NOTIFIER);
+	}
+
 	return 0;
 
 out:
@@ -2827,25 +2974,20 @@ static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e,
 	if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index)
 		return 0;
 	if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) &&
-		!(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
+	    !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
 		return 0;
 	return 1;
 }
 
-void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
+struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
+					      u32 function, u32 index)
 {
 	int i;
-	u32 function, index;
-	struct kvm_cpuid_entry2 *e, *best;
+	struct kvm_cpuid_entry2 *best = NULL;
 
-	function = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	index = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, 0);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, 0);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
-	best = NULL;
 	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
+		struct kvm_cpuid_entry2 *e;
+
 		e = &vcpu->arch.cpuid_entries[i];
 		if (is_matching_cpuid_entry(e, function, index)) {
 			if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC)
@@ -2860,6 +3002,21 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 			if (!best || e->function > best->function)
 				best = e;
 	}
+	return best;
+}
+
+void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
+{
+	u32 function, index;
+	struct kvm_cpuid_entry2 *best;
+
+	function = kvm_register_read(vcpu, VCPU_REGS_RAX);
+	index = kvm_register_read(vcpu, VCPU_REGS_RCX);
+	kvm_register_write(vcpu, VCPU_REGS_RAX, 0);
+	kvm_register_write(vcpu, VCPU_REGS_RBX, 0);
+	kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
+	kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
+	best = kvm_find_cpuid_entry(vcpu, function, index);
 	if (best) {
 		kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
 		kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
@@ -2945,6 +3102,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
 			__kvm_migrate_timers(vcpu);
+		if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests))
+			kvm_write_guest_time(vcpu);
 		if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests))
 			kvm_mmu_sync_roots(vcpu);
 		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
@@ -2979,9 +3138,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		goto out;
 	}
 
-	if (vcpu->guest_debug.enabled)
-		kvm_x86_ops->guest_debug_pre(vcpu);
-
 	vcpu->guest_mode = 1;
 	/*
 	 * Make sure that guest_mode assignment won't happen after
@@ -3002,10 +3158,34 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	kvm_guest_enter();
 
+	get_debugreg(vcpu->arch.host_dr6, 6);
+	get_debugreg(vcpu->arch.host_dr7, 7);
+	if (unlikely(vcpu->arch.switch_db_regs)) {
+		get_debugreg(vcpu->arch.host_db[0], 0);
+		get_debugreg(vcpu->arch.host_db[1], 1);
+		get_debugreg(vcpu->arch.host_db[2], 2);
+		get_debugreg(vcpu->arch.host_db[3], 3);
+
+		set_debugreg(0, 7);
+		set_debugreg(vcpu->arch.eff_db[0], 0);
+		set_debugreg(vcpu->arch.eff_db[1], 1);
+		set_debugreg(vcpu->arch.eff_db[2], 2);
+		set_debugreg(vcpu->arch.eff_db[3], 3);
+	}
 
 	KVMTRACE_0D(VMENTRY, vcpu, entryexit);
 	kvm_x86_ops->run(vcpu, kvm_run);
 
+	if (unlikely(vcpu->arch.switch_db_regs)) {
+		set_debugreg(0, 7);
+		set_debugreg(vcpu->arch.host_db[0], 0);
+		set_debugreg(vcpu->arch.host_db[1], 1);
+		set_debugreg(vcpu->arch.host_db[2], 2);
+		set_debugreg(vcpu->arch.host_db[3], 3);
+	}
+	set_debugreg(vcpu->arch.host_dr6, 6);
+	set_debugreg(vcpu->arch.host_dr7, 7);
+
 	vcpu->guest_mode = 0;
 	local_irq_enable();
 
@@ -3192,7 +3372,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	/*
 	 * Don't leak debug flags in case they were set for guest debugging
 	 */
-	if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep)
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
 
 	vcpu_put(vcpu);
@@ -3811,15 +3991,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
-				    struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
-	int r;
+	int i, r;
 
 	vcpu_load(vcpu);
 
+	if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) ==
+	    (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) {
+		for (i = 0; i < KVM_NR_DB_REGS; ++i)
+			vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
+		vcpu->arch.switch_db_regs =
+			(dbg->arch.debugreg[7] & DR7_BP_EN_MASK);
+	} else {
+		for (i = 0; i < KVM_NR_DB_REGS; i++)
+			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+		vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
+	}
+
 	r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
 
+	if (dbg->control & KVM_GUESTDBG_INJECT_DB)
+		kvm_queue_exception(vcpu, DB_VECTOR);
+	else if (dbg->control & KVM_GUESTDBG_INJECT_BP)
+		kvm_queue_exception(vcpu, BP_VECTOR);
+
 	vcpu_put(vcpu);
 
 	return r;
@@ -4007,6 +4204,11 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.nmi_pending = false;
 	vcpu->arch.nmi_injected = false;
 
+	vcpu->arch.switch_db_regs = 0;
+	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
+	vcpu->arch.dr6 = DR6_FIXED_1;
+	vcpu->arch.dr7 = DR7_FIXED_1;
+
 	return kvm_x86_ops->vcpu_reset(vcpu);
 }
 
@@ -4100,6 +4302,8 @@ struct  kvm *kvm_arch_create_vm(void)
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
 
+	rdtscll(kvm->arch.vm_init_tsc);
+
 	return kvm;
 }
 
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index d174db7a337..ca91749d208 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -178,7 +178,7 @@ static u32 opcode_table[256] = {
 	0, ImplicitOps | Stack, 0, 0,
 	ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov,
 	/* 0xC8 - 0xCF */
-	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, ImplicitOps | Stack, 0, 0, 0, 0,
 	/* 0xD0 - 0xD7 */
 	ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM,
 	ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM,
@@ -1136,18 +1136,19 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt)
 }
 
 static int emulate_pop(struct x86_emulate_ctxt *ctxt,
-		       struct x86_emulate_ops *ops)
+		       struct x86_emulate_ops *ops,
+		       void *dest, int len)
 {
 	struct decode_cache *c = &ctxt->decode;
 	int rc;
 
 	rc = ops->read_emulated(register_address(c, ss_base(ctxt),
 						 c->regs[VCPU_REGS_RSP]),
-				&c->src.val, c->src.bytes, ctxt->vcpu);
+				dest, len, ctxt->vcpu);
 	if (rc != 0)
 		return rc;
 
-	register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->src.bytes);
+	register_address_increment(c, &c->regs[VCPU_REGS_RSP], len);
 	return rc;
 }
 
@@ -1157,11 +1158,9 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
 	struct decode_cache *c = &ctxt->decode;
 	int rc;
 
-	c->src.bytes = c->dst.bytes;
-	rc = emulate_pop(ctxt, ops);
+	rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes);
 	if (rc != 0)
 		return rc;
-	c->dst.val = c->src.val;
 	return 0;
 }
 
@@ -1279,6 +1278,25 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 	return 0;
 }
 
+static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
+			   struct x86_emulate_ops *ops)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int rc;
+	unsigned long cs;
+
+	rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes);
+	if (rc)
+		return rc;
+	if (c->op_bytes == 4)
+		c->eip = (u32)c->eip;
+	rc = emulate_pop(ctxt, ops, &cs, c->op_bytes);
+	if (rc)
+		return rc;
+	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, 1, VCPU_SREG_CS);
+	return rc;
+}
+
 static inline int writeback(struct x86_emulate_ctxt *ctxt,
 			    struct x86_emulate_ops *ops)
 {
@@ -1467,11 +1485,9 @@ special_insn:
 		break;
 	case 0x58 ... 0x5f: /* pop reg */
 	pop_instruction:
-		c->src.bytes = c->op_bytes;
-		rc = emulate_pop(ctxt, ops);
+		rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes);
 		if (rc != 0)
 			goto done;
-		c->dst.val = c->src.val;
 		break;
 	case 0x63:		/* movsxd */
 		if (ctxt->mode != X86EMUL_MODE_PROT64)
@@ -1738,6 +1754,11 @@ special_insn:
 	mov:
 		c->dst.val = c->src.val;
 		break;
+	case 0xcb:		/* ret far */
+		rc = emulate_ret_far(ctxt, ops);
+		if (rc)
+			goto done;
+		break;
 	case 0xd0 ... 0xd1:	/* Grp2 */
 		c->src.val = 1;
 		emulate_grp2(ctxt);
@@ -1908,11 +1929,16 @@ twobyte_insn:
 			c->dst.type = OP_NONE;
 			break;
 		case 3: /* lidt/vmmcall */
-			if (c->modrm_mod == 3 && c->modrm_rm == 1) {
-				rc = kvm_fix_hypercall(ctxt->vcpu);
-				if (rc)
-					goto done;
-				kvm_emulate_hypercall(ctxt->vcpu);
+			if (c->modrm_mod == 3) {
+				switch (c->modrm_rm) {
+				case 1:
+					rc = kvm_fix_hypercall(ctxt->vcpu);
+					if (rc)
+						goto done;
+					break;
+				default:
+					goto cannot_emulate;
+				}
 			} else {
 				rc = read_descriptor(ctxt, ops, c->src.ptr,
 						     &size, &address,
diff --git a/arch/xtensa/include/asm/socket.h b/arch/xtensa/include/asm/socket.h
index 6100682b1da..dd1a7a4a1ce 100644
--- a/arch/xtensa/include/asm/socket.h
+++ b/arch/xtensa/include/asm/socket.h
@@ -65,4 +65,7 @@
 
 #define SO_MARK			36
 
+#define SO_TIMESTAMPING		37
+#define SCM_TIMESTAMPING	SO_TIMESTAMPING
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/arch/xtensa/include/asm/swab.h b/arch/xtensa/include/asm/swab.h
index f50b697eb60..226a3916231 100644
--- a/arch/xtensa/include/asm/swab.h
+++ b/arch/xtensa/include/asm/swab.h
@@ -11,7 +11,7 @@
 #ifndef _XTENSA_SWAB_H
 #define _XTENSA_SWAB_H
 
-#include <asm/types.h>
+#include <linux/types.h>
 #include <linux/compiler.h>
 
 #define __SWAB_64_THRU_32__
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 5fbcde59a92..f3b66fba5b8 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -99,7 +99,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);