Merge branch 'gic-fasteoi' of git://linux-arm.org/linux-2.6-wd into devel-stable

23 files changed, 460 insertions, 466 deletions

diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index f70ec7d..4ddd0a6 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -49,7 +49,7 @@ struct gic_chip_data {
  * Default make them NULL.
  */
 struct irq_chip gic_arch_extn = {
-	.irq_ack	= NULL,
+	.irq_eoi	= NULL,
 	.irq_mask	= NULL,
 	.irq_unmask	= NULL,
 	.irq_retrigger	= NULL,
@@ -84,21 +84,12 @@ static inline unsigned int gic_irq(struct irq_data *d)
 /*
  * Routines to acknowledge, disable and enable interrupts
  */
-static void gic_ack_irq(struct irq_data *d)
-{
-	spin_lock(&irq_controller_lock);
-	if (gic_arch_extn.irq_ack)
-		gic_arch_extn.irq_ack(d);
-	writel(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
-	spin_unlock(&irq_controller_lock);
-}
-
 static void gic_mask_irq(struct irq_data *d)
 {
 	u32 mask = 1 << (d->irq % 32);
 
 	spin_lock(&irq_controller_lock);
-	writel(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4);
+	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4);
 	if (gic_arch_extn.irq_mask)
 		gic_arch_extn.irq_mask(d);
 	spin_unlock(&irq_controller_lock);
@@ -111,10 +102,21 @@ static void gic_unmask_irq(struct irq_data *d)
 	spin_lock(&irq_controller_lock);
 	if (gic_arch_extn.irq_unmask)
 		gic_arch_extn.irq_unmask(d);
-	writel(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4);
+	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4);
 	spin_unlock(&irq_controller_lock);
 }
 
+static void gic_eoi_irq(struct irq_data *d)
+{
+	if (gic_arch_extn.irq_eoi) {
+		spin_lock(&irq_controller_lock);
+		gic_arch_extn.irq_eoi(d);
+		spin_unlock(&irq_controller_lock);
+	}
+
+	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
+}
+
 static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
@@ -138,7 +140,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
 
-	val = readl(base + GIC_DIST_CONFIG + confoff);
+	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
 	if (type == IRQ_TYPE_LEVEL_HIGH)
 		val &= ~confmask;
 	else if (type == IRQ_TYPE_EDGE_RISING)
@@ -148,15 +150,15 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	 * As recommended by the spec, disable the interrupt before changing
 	 * the configuration
 	 */
-	if (readl(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
+	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
 		enabled = true;
 	}
 
-	writel(val, base + GIC_DIST_CONFIG + confoff);
+	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
 
 	if (enabled)
-		writel(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
 
 	spin_unlock(&irq_controller_lock);
 
@@ -188,8 +190,8 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 
 	spin_lock(&irq_controller_lock);
 	d->node = cpu;
-	val = readl(reg) & ~mask;
-	writel(val | bit, reg);
+	val = readl_relaxed(reg) & ~mask;
+	writel_relaxed(val | bit, reg);
 	spin_unlock(&irq_controller_lock);
 
 	return 0;
@@ -218,11 +220,10 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 	unsigned int cascade_irq, gic_irq;
 	unsigned long status;
 
-	/* primary controller ack'ing */
-	chip->irq_ack(&desc->irq_data);
+	chained_irq_enter(chip, desc);
 
 	spin_lock(&irq_controller_lock);
-	status = readl(chip_data->cpu_base + GIC_CPU_INTACK);
+	status = readl_relaxed(chip_data->cpu_base + GIC_CPU_INTACK);
 	spin_unlock(&irq_controller_lock);
 
 	gic_irq = (status & 0x3ff);
@@ -236,15 +237,14 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 		generic_handle_irq(cascade_irq);
 
  out:
-	/* primary controller unmasking */
-	chip->irq_unmask(&desc->irq_data);
+	chained_irq_exit(chip, desc);
 }
 
 static struct irq_chip gic_chip = {
 	.name			= "GIC",
-	.irq_ack		= gic_ack_irq,
 	.irq_mask		= gic_mask_irq,
 	.irq_unmask		= gic_unmask_irq,
+	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
 	.irq_retrigger		= gic_retrigger,
 #ifdef CONFIG_SMP
@@ -272,13 +272,13 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
-	writel(0, base + GIC_DIST_CTRL);
+	writel_relaxed(0, base + GIC_DIST_CTRL);
 
 	/*
 	 * Find out how many interrupts are supported.
 	 * The GIC only supports up to 1020 interrupt sources.
 	 */
-	gic_irqs = readl(base + GIC_DIST_CTR) & 0x1f;
+	gic_irqs = readl_relaxed(base + GIC_DIST_CTR) & 0x1f;
 	gic_irqs = (gic_irqs + 1) * 32;
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
@@ -287,26 +287,26 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	 * Set all global interrupts to be level triggered, active low.
 	 */
 	for (i = 32; i < gic_irqs; i += 16)
-		writel(0, base + GIC_DIST_CONFIG + i * 4 / 16);
+		writel_relaxed(0, base + GIC_DIST_CONFIG + i * 4 / 16);
 
 	/*
 	 * Set all global interrupts to this CPU only.
 	 */
 	for (i = 32; i < gic_irqs; i += 4)
-		writel(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
+		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
 	/*
 	 * Set priority on all global interrupts.
 	 */
 	for (i = 32; i < gic_irqs; i += 4)
-		writel(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
 
 	/*
 	 * Disable all interrupts.  Leave the PPI and SGIs alone
 	 * as these enables are banked registers.
 	 */
 	for (i = 32; i < gic_irqs; i += 32)
-		writel(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
+		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
 
 	/*
 	 * Limit number of interrupts registered to the platform maximum
@@ -319,12 +319,12 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 	 * Setup the Linux IRQ subsystem.
 	 */
 	for (i = irq_start; i < irq_limit; i++) {
-		irq_set_chip_and_handler(i, &gic_chip, handle_level_irq);
+		irq_set_chip_and_handler(i, &gic_chip, handle_fasteoi_irq);
 		irq_set_chip_data(i, gic);
 		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
 	}
 
-	writel(1, base + GIC_DIST_CTRL);
+	writel_relaxed(1, base + GIC_DIST_CTRL);
 }
 
 static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
@@ -337,17 +337,17 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	 * Deal with the banked PPI and SGI interrupts - disable all
 	 * PPI interrupts, ensure all SGI interrupts are enabled.
 	 */
-	writel(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
-	writel(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
+	writel_relaxed(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
 
 	/*
 	 * Set priority on PPI and SGI interrupts
 	 */
 	for (i = 0; i < 32; i += 4)
-		writel(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
 
-	writel(0xf0, base + GIC_CPU_PRIMASK);
-	writel(1, base + GIC_CPU_CTRL);
+	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
+	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
 void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
@@ -391,7 +391,13 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	unsigned long map = *cpus_addr(*mask);
 
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	dsb();
+
 	/* this always happens on GIC0 */
-	writel(map << 16 | irq, gic_data[0].dist_base + GIC_DIST_SOFTINT);
+	writel_relaxed(map << 16 | irq, gic_data[0].dist_base + GIC_DIST_SOFTINT);
 }
 #endif
diff --git a/arch/arm/configs/at91x40_defconfig b/arch/arm/configs/at91x40_defconfig
new file mode 100644
index 0000000..c55e921
--- /dev/null
+++ b/arch/arm/configs/at91x40_defconfig
@@ -0,0 +1,48 @@
+CONFIG_EXPERIMENTAL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_EMBEDDED=y
+# CONFIG_HOTPLUG is not set
+# CONFIG_ELF_CORE is not set
+# CONFIG_FUTEX is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
+CONFIG_ARCH_AT91=y
+CONFIG_ARCH_AT91X40=y
+CONFIG_MACH_AT91EB01=y
+CONFIG_AT91_EARLY_USART0=y
+CONFIG_CPU_ARM7TDMI=y
+CONFIG_SET_MEM_PARAM=y
+CONFIG_DRAM_BASE=0x01000000
+CONFIG_DRAM_SIZE=0x00400000
+CONFIG_FLASH_MEM_BASE=0x01400000
+CONFIG_PROCESSOR_ID=0x14000040
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_BINFMT_FLAT=y
+# CONFIG_SUSPEND is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_MTD=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_RAM=y
+CONFIG_MTD_ROM=y
+CONFIG_BLK_DEV_RAM=y
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_DEVKMEM is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_DNOTIFY is not set
+CONFIG_ROMFS_FS=y
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 2bf27f3..8182f45 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -767,12 +767,20 @@ long arch_ptrace(struct task_struct *child, long request,
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		case PTRACE_GETHBPREGS:
+			if (ptrace_get_breakpoints(child) < 0)
+				return -ESRCH;
+
 			ret = ptrace_gethbpregs(child, addr,
 						(unsigned long __user *)data);
+			ptrace_put_breakpoints(child);
 			break;
 		case PTRACE_SETHBPREGS:
+			if (ptrace_get_breakpoints(child) < 0)
+				return -ESRCH;
+
 			ret = ptrace_sethbpregs(child, addr,
 						(unsigned long __user *)data);
+			ptrace_put_breakpoints(child);
 			break;
 #endif
 
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 1939023..2d299bf 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -83,6 +83,7 @@ config ARCH_AT91CAP9
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
+	select HAVE_NET_MACB
 
 config ARCH_AT572D940HF
 	bool "AT572D940HF"
diff --git a/arch/arm/mach-at91/board-eb01.c b/arch/arm/mach-at91/board-eb01.c
index 1f9d3cb..d8df59a 100644
--- a/arch/arm/mach-at91/board-eb01.c
+++ b/arch/arm/mach-at91/board-eb01.c
@@ -30,6 +30,11 @@
 #include <mach/board.h>
 #include "generic.h"
 
+static void __init at91eb01_init_irq(void)
+{
+	at91x40_init_interrupts(NULL);
+}
+
 static void __init at91eb01_map_io(void)
 {
 	at91x40_initialize(40000000);
@@ -38,7 +43,7 @@ static void __init at91eb01_map_io(void)
 MACHINE_START(AT91EB01, "Atmel AT91 EB01")
 	/* Maintainer: Greg Ungerer <gerg@snapgear.com> */
 	.timer		= &at91x40_timer,
-	.init_irq	= at91x40_init_interrupts,
+	.init_irq	= at91eb01_init_irq,
 	.map_io		= at91eb01_map_io,
 MACHINE_END
 
diff --git a/arch/arm/mach-at91/include/mach/cpu.h b/arch/arm/mach-at91/include/mach/cpu.h
index 3bef931..0700f21 100644
--- a/arch/arm/mach-at91/include/mach/cpu.h
+++ b/arch/arm/mach-at91/include/mach/cpu.h
@@ -27,6 +27,7 @@
 #define ARCH_ID_AT91SAM9G45	0x819b05a0
 #define ARCH_ID_AT91SAM9G45MRL	0x819b05a2	/* aka 9G45-ES2 & non ES lots */
 #define ARCH_ID_AT91SAM9G45ES	0x819b05a1	/* 9G45-ES (Engineering Sample) */
+#define ARCH_ID_AT91SAM9X5	0x819a05a0
 #define ARCH_ID_AT91CAP9	0x039A03A0
 
 #define ARCH_ID_AT91SAM9XE128	0x329973a0
@@ -55,6 +56,12 @@ static inline unsigned long at91_cpu_fully_identify(void)
 #define ARCH_EXID_AT91SAM9G46	0x00000003
 #define ARCH_EXID_AT91SAM9G45	0x00000004
 
+#define ARCH_EXID_AT91SAM9G15	0x00000000
+#define ARCH_EXID_AT91SAM9G35	0x00000001
+#define ARCH_EXID_AT91SAM9X35	0x00000002
+#define ARCH_EXID_AT91SAM9G25	0x00000003
+#define ARCH_EXID_AT91SAM9X25	0x00000004
+
 static inline unsigned long at91_exid_identify(void)
 {
 	return at91_sys_read(AT91_DBGU_EXID);
@@ -143,6 +150,27 @@ static inline unsigned long at91cap9_rev_identify(void)
 #define cpu_is_at91sam9m11()	(0)
 #endif
 
+#ifdef CONFIG_ARCH_AT91SAM9X5
+#define cpu_is_at91sam9x5()	(at91_cpu_identify() == ARCH_ID_AT91SAM9X5)
+#define cpu_is_at91sam9g15()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9G15))
+#define cpu_is_at91sam9g35()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9G35))
+#define cpu_is_at91sam9x35()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9X35))
+#define cpu_is_at91sam9g25()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9G25))
+#define cpu_is_at91sam9x25()	(cpu_is_at91sam9x5() && \
+				(at91_exid_identify() == ARCH_EXID_AT91SAM9X25))
+#else
+#define cpu_is_at91sam9x5()	(0)
+#define cpu_is_at91sam9g15()	(0)
+#define cpu_is_at91sam9g35()	(0)
+#define cpu_is_at91sam9x35()	(0)
+#define cpu_is_at91sam9g25()	(0)
+#define cpu_is_at91sam9x25()	(0)
+#endif
+
 #ifdef CONFIG_ARCH_AT91CAP9
 #define cpu_is_at91cap9()	(at91_cpu_identify() == ARCH_ID_AT91CAP9)
 #define cpu_is_at91cap9_revB()	(at91cap9_rev_identify() == ARCH_REVISION_CAP9_B)
diff --git a/arch/arm/mach-exynos4/irq-combiner.c b/arch/arm/mach-exynos4/irq-combiner.c
index f488b66..5a2758a 100644
--- a/arch/arm/mach-exynos4/irq-combiner.c
+++ b/arch/arm/mach-exynos4/irq-combiner.c
@@ -59,8 +59,7 @@ static void combiner_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 	unsigned int cascade_irq, combiner_irq;
 	unsigned long status;
 
-	/* primary controller ack'ing */
-	chip->irq_ack(&desc->irq_data);
+	chained_irq_enter(chip, desc);
 
 	spin_lock(&irq_controller_lock);
 	status = __raw_readl(chip_data->base + COMBINER_INT_STATUS);
@@ -79,8 +78,7 @@ static void combiner_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 		generic_handle_irq(cascade_irq);
 
  out:
-	/* primary controller unmasking */
-	chip->irq_unmask(&desc->irq_data);
+	chained_irq_exit(chip, desc);
 }
 
 static struct irq_chip combiner_chip = {
diff --git a/arch/arm/mach-msm/gpio-v2.c b/arch/arm/mach-msm/gpio-v2.c
index 56a964e..cc9c4fd 100644
--- a/arch/arm/mach-msm/gpio-v2.c
+++ b/arch/arm/mach-msm/gpio-v2.c
@@ -27,6 +27,9 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
+
+#include <asm/mach/irq.h>
+
 #include <mach/msm_iomap.h>
 #include "gpiomux.h"
 
@@ -309,8 +312,10 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int flow_type)
  */
 static void msm_summary_irq_handler(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_data *data = irq_desc_get_irq_data(desc);
 	unsigned long i;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	chained_irq_enter(chip, desc);
 
 	for (i = find_first_bit(msm_gpio.enabled_irqs, NR_GPIO_IRQS);
 	     i < NR_GPIO_IRQS;
@@ -319,7 +324,8 @@ static void msm_summary_irq_handler(unsigned int irq, struct irq_desc *desc)
 			generic_handle_irq(msm_gpio_to_irq(&msm_gpio.gpio_chip,
 							   i));
 	}
-	data->chip->irq_ack(data);
+
+	chained_irq_exit(chip, desc);
 }
 
 static int msm_gpio_irq_set_wake(struct irq_data *d, unsigned int on)
diff --git a/arch/arm/mach-tegra/Makefile b/arch/arm/mach-tegra/Makefile
index 1afe050..823c703 100644
--- a/arch/arm/mach-tegra/Makefile
+++ b/arch/arm/mach-tegra/Makefile
@@ -1,7 +1,7 @@
 obj-y                                   += common.o
 obj-y                                   += devices.o
 obj-y                                   += io.o
-obj-y                                   += irq.o legacy_irq.o
+obj-y                                   += irq.o
 obj-y                                   += clock.o
 obj-y                                   += timer.o
 obj-y                                   += gpio.o
diff --git a/arch/arm/mach-tegra/gpio.c b/arch/arm/mach-tegra/gpio.c
index 65a1aba..919d638 100644
--- a/arch/arm/mach-tegra/gpio.c
+++ b/arch/arm/mach-tegra/gpio.c
@@ -24,6 +24,8 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 
+#include <asm/mach/irq.h>
+
 #include <mach/iomap.h>
 #include <mach/suspend.h>
 
@@ -221,8 +223,9 @@ static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 	int port;
 	int pin;
 	int unmasked = 0;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 
-	desc->irq_data.chip->irq_ack(&desc->irq_data);
+	chained_irq_enter(chip, desc);
 
 	bank = irq_get_handler_data(irq);
 
@@ -241,7 +244,7 @@ static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 			 */
 			if (lvl & (0x100 << pin)) {
 				unmasked = 1;
-				desc->irq_data.chip->irq_unmask(&desc->irq_data);
+				chained_irq_exit(chip, desc);
 			}
 
 			generic_handle_irq(gpio_to_irq(gpio + pin));
@@ -249,7 +252,7 @@ static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 	}
 
 	if (!unmasked)
-		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+		chained_irq_exit(chip, desc);
 
 }
 
diff --git a/arch/arm/mach-tegra/include/mach/legacy_irq.h b/arch/arm/mach-tegra/include/mach/legacy_irq.h
deleted file mode 100644
index d898c0e..0000000
--- a/arch/arm/mach-tegra/include/mach/legacy_irq.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * arch/arm/mach-tegra/include/mach/legacy_irq.h
- *
- * Copyright (C) 2010 Google, Inc.
- * Author: Colin Cross <ccross@android.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- *
- */
-
-#ifndef _ARCH_ARM_MACH_TEGRA_LEGARY_IRQ_H
-#define _ARCH_ARM_MACH_TEGRA_LEGARY_IRQ_H
-
-void tegra_legacy_mask_irq(unsigned int irq);
-void tegra_legacy_unmask_irq(unsigned int irq);
-void tegra_legacy_select_fiq(unsigned int irq, bool fiq);
-void tegra_legacy_force_irq_set(unsigned int irq);
-void tegra_legacy_force_irq_clr(unsigned int irq);
-int tegra_legacy_force_irq_status(unsigned int irq);
-void tegra_legacy_select_fiq(unsigned int irq, bool fiq);
-unsigned long tegra_legacy_vfiq(int nr);
-unsigned long tegra_legacy_class(int nr);
-int tegra_legacy_irq_set_wake(int irq, int enable);
-void tegra_legacy_irq_set_lp1_wake_mask(void);
-void tegra_legacy_irq_restore_mask(void);
-void tegra_init_legacy_irq(void);
-
-#endif
diff --git a/arch/arm/mach-tegra/irq.c b/arch/arm/mach-tegra/irq.c
index 4330d89..4956c3c 100644
--- a/arch/arm/mach-tegra/irq.c
+++ b/arch/arm/mach-tegra/irq.c
@@ -1,8 +1,8 @@
 /*
- * Copyright (C) 2010 Google, Inc.
+ * Copyright (C) 2011 Google, Inc.
  *
  * Author:
- *	Colin Cross <ccross@google.com>
+ *	Colin Cross <ccross@android.com>
  *
  * Copyright (C) 2010, NVIDIA Corporation
  *
@@ -18,8 +18,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/io.h>
@@ -27,134 +25,110 @@
 #include <asm/hardware/gic.h>
 
 #include <mach/iomap.h>
-#include <mach/legacy_irq.h>
-#include <mach/suspend.h>
 
 #include "board.h"
 
-#define PMC_CTRL		0x0
-#define PMC_CTRL_LATCH_WAKEUPS	(1 << 5)
-#define PMC_WAKE_MASK		0xc
-#define PMC_WAKE_LEVEL		0x10
-#define PMC_WAKE_STATUS		0x14
-#define PMC_SW_WAKE_STATUS	0x18
-#define PMC_DPD_SAMPLE		0x20
+#define INT_SYS_NR	(INT_GPIO_BASE - INT_PRI_BASE)
+#define INT_SYS_SZ	(INT_SEC_BASE - INT_PRI_BASE)
+#define PPI_NR		((INT_SYS_NR+INT_SYS_SZ-1)/INT_SYS_SZ)
+
+#define ICTLR_CPU_IEP_VFIQ	0x08
+#define ICTLR_CPU_IEP_FIR	0x14
+#define ICTLR_CPU_IEP_FIR_SET	0x18
+#define ICTLR_CPU_IEP_FIR_CLR	0x1c
+
+#define ICTLR_CPU_IER		0x20
+#define ICTLR_CPU_IER_SET	0x24
+#define ICTLR_CPU_IER_CLR	0x28
+#define ICTLR_CPU_IEP_CLASS	0x2C
+
+#define ICTLR_COP_IER		0x30
+#define ICTLR_COP_IER_SET	0x34
+#define ICTLR_COP_IER_CLR	0x38
+#define ICTLR_COP_IEP_CLASS	0x3c
+
+#define NUM_ICTLRS 4
+#define FIRST_LEGACY_IRQ 32
+
+static void __iomem *ictlr_reg_base[] = {
+	IO_ADDRESS(TEGRA_PRIMARY_ICTLR_BASE),
+	IO_ADDRESS(TEGRA_SECONDARY_ICTLR_BASE),
+	IO_ADDRESS(TEGRA_TERTIARY_ICTLR_BASE),
+	IO_ADDRESS(TEGRA_QUATERNARY_ICTLR_BASE),
+};
 
-static void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE);
+static inline void tegra_irq_write_mask(unsigned int irq, unsigned long reg)
+{
+	void __iomem *base;
+	u32 mask;
 
-static u32 tegra_lp0_wake_enb;
-static u32 tegra_lp0_wake_level;
-static u32 tegra_lp0_wake_level_any;
+	BUG_ON(irq < FIRST_LEGACY_IRQ ||
+		irq >= FIRST_LEGACY_IRQ + NUM_ICTLRS * 32);
 
-static void (*tegra_gic_mask_irq)(struct irq_data *d);
-static void (*tegra_gic_unmask_irq)(struct irq_data *d);
-static void (*tegra_gic_ack_irq)(struct irq_data *d);
+	base = ictlr_reg_base[(irq - FIRST_LEGACY_IRQ) / 32];
+	mask = BIT((irq - FIRST_LEGACY_IRQ) % 32);
 
-/* ensures that sufficient time is passed for a register write to
- * serialize into the 32KHz domain */
-static void pmc_32kwritel(u32 val, unsigned long offs)
-{
-	writel(val, pmc + offs);
-	udelay(130);
+	__raw_writel(mask, base + reg);
 }
 
-int tegra_set_lp1_wake(int irq, int enable)
+static void tegra_mask(struct irq_data *d)
 {
-	return tegra_legacy_irq_set_wake(irq, enable);
+	if (d->irq < FIRST_LEGACY_IRQ)
+		return;
+
+	tegra_irq_write_mask(d->irq, ICTLR_CPU_IER_CLR);
 }
 
-void tegra_set_lp0_wake_pads(u32 wake_enb, u32 wake_level, u32 wake_any)
+static void tegra_unmask(struct irq_data *d)
 {
-	u32 temp;
-	u32 status;
-	u32 lvl;
-
-	wake_level &= wake_enb;
-	wake_any &= wake_enb;
+	if (d->irq < FIRST_LEGACY_IRQ)
+		return;
 
-	wake_level |= (tegra_lp0_wake_level & tegra_lp0_wake_enb);
-	wake_any |= (tegra_lp0_wake_level_any & tegra_lp0_wake_enb);
-
-	wake_enb |= tegra_lp0_wake_enb;
-
-	pmc_32kwritel(0, PMC_SW_WAKE_STATUS);
-	temp = readl(pmc + PMC_CTRL);
-	temp |= PMC_CTRL_LATCH_WAKEUPS;
-	pmc_32kwritel(temp, PMC_CTRL);
-	temp &= ~PMC_CTRL_LATCH_WAKEUPS;
-	pmc_32kwritel(temp, PMC_CTRL);
-	status = readl(pmc + PMC_SW_WAKE_STATUS);
-	lvl = readl(pmc + PMC_WAKE_LEVEL);
-
-	/* flip the wakeup trigger for any-edge triggered pads
-	 * which are currently asserting as wakeups */
-	lvl ^= status;
-	lvl &= wake_any;
-
-	wake_level |= lvl;
-
-	writel(wake_level, pmc + PMC_WAKE_LEVEL);
-	/* Enable DPD sample to trigger sampling pads data and direction
-	 * in which pad will be driven during lp0 mode*/
-	writel(0x1, pmc + PMC_DPD_SAMPLE);
-
-	writel(wake_enb, pmc + PMC_WAKE_MASK);
+	tegra_irq_write_mask(d->irq, ICTLR_CPU_IER_SET);
 }
 
-static void tegra_mask(struct irq_data *d)
+static void tegra_ack(struct irq_data *d)
 {
-	tegra_gic_mask_irq(d);
-	tegra_legacy_mask_irq(d->irq);
-}
+	if (d->irq < FIRST_LEGACY_IRQ)
+		return;
 
-static void tegra_unmask(struct irq_data *d)
-{
-	tegra_gic_unmask_irq(d);
-	tegra_legacy_unmask_irq(d->irq);
+	tegra_irq_write_mask(d->irq, ICTLR_CPU_IEP_FIR_CLR);
 }
 
-static void tegra_ack(struct irq_data *d)
+static void tegra_eoi(struct irq_data *d)
 {
-	tegra_legacy_force_irq_clr(d->irq);
-	tegra_gic_ack_irq(d);
+	if (d->irq < FIRST_LEGACY_IRQ)
+		return;
+
+	tegra_irq_write_mask(d->irq, ICTLR_CPU_IEP_FIR_CLR);
 }
 
 static int tegra_retrigger(struct irq_data *d)
 {
-	tegra_legacy_force_irq_set(d->irq);
+	if (d->irq < FIRST_LEGACY_IRQ)
+		return 0;
+
+	tegra_irq_write_mask(d->irq, ICTLR_CPU_IEP_FIR_SET);
+
 	return 1;
 }
 
-static struct irq_chip tegra_irq = {
-	.name			= "PPI",
-	.irq_ack		= tegra_ack,
-	.irq_mask		= tegra_mask,
-	.irq_unmask		= tegra_unmask,
-	.irq_retrigger		= tegra_retrigger,
-};
-
 void __init tegra_init_irq(void)
 {
-	struct irq_chip *gic;
-	unsigned int i;
-	int irq;
+	int i;
 
-	tegra_init_legacy_irq();
+	for (i = 0; i < NUM_ICTLRS; i++) {
+		void __iomem *ictlr = ictlr_reg_base[i];
+		writel(~0, ictlr + ICTLR_CPU_IER_CLR);
+		writel(0, ictlr + ICTLR_CPU_IEP_CLASS);
+	}
+
+	gic_arch_extn.irq_ack = tegra_ack;
+	gic_arch_extn.irq_eoi = tegra_eoi;
+	gic_arch_extn.irq_mask = tegra_mask;
+	gic_arch_extn.irq_unmask = tegra_unmask;
+	gic_arch_extn.irq_retrigger = tegra_retrigger;
 
 	gic_init(0, 29, IO_ADDRESS(TEGRA_ARM_INT_DIST_BASE),
 		 IO_ADDRESS(TEGRA_ARM_PERIF_BASE + 0x100));
-
-	gic = irq_get_chip(29);
-	tegra_gic_unmask_irq = gic->irq_unmask;
-	tegra_gic_mask_irq = gic->irq_mask;
-	tegra_gic_ack_irq = gic->irq_ack;
-#ifdef CONFIG_SMP
-	tegra_irq.irq_set_affinity = gic->irq_set_affinity;
-#endif
-
-	for (i = 0; i < INT_MAIN_NR; i++) {
-		irq = INT_PRI_BASE + i;
-		irq_set_chip_and_handler(irq, &tegra_irq, handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID);
-	}
 }
diff --git a/arch/arm/mach-tegra/legacy_irq.c b/arch/arm/mach-tegra/legacy_irq.c
deleted file mode 100644
index 38eb719..0000000
--- a/arch/arm/mach-tegra/legacy_irq.c
+++ /dev/null
@@ -1,215 +0,0 @@
-/*
- * arch/arm/mach-tegra/legacy_irq.c
- *
- * Copyright (C) 2010 Google, Inc.
- * Author: Colin Cross <ccross@android.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- *
- */
-
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <mach/iomap.h>
-#include <mach/irqs.h>
-#include <mach/legacy_irq.h>
-
-#define INT_SYS_NR	(INT_GPIO_BASE - INT_PRI_BASE)
-#define INT_SYS_SZ	(INT_SEC_BASE - INT_PRI_BASE)
-#define PPI_NR		((INT_SYS_NR+INT_SYS_SZ-1)/INT_SYS_SZ)
-
-#define ICTLR_CPU_IEP_VFIQ	0x08
-#define ICTLR_CPU_IEP_FIR	0x14
-#define ICTLR_CPU_IEP_FIR_SET	0x18
-#define ICTLR_CPU_IEP_FIR_CLR	0x1c
-
-#define ICTLR_CPU_IER		0x20
-#define ICTLR_CPU_IER_SET	0x24
-#define ICTLR_CPU_IER_CLR	0x28
-#define ICTLR_CPU_IEP_CLASS	0x2C
-
-#define ICTLR_COP_IER		0x30
-#define ICTLR_COP_IER_SET	0x34
-#define ICTLR_COP_IER_CLR	0x38
-#define ICTLR_COP_IEP_CLASS	0x3c
-
-#define NUM_ICTLRS 4
-
-static void __iomem *ictlr_reg_base[] = {
-	IO_ADDRESS(TEGRA_PRIMARY_ICTLR_BASE),
-	IO_ADDRESS(TEGRA_SECONDARY_ICTLR_BASE),
-	IO_ADDRESS(TEGRA_TERTIARY_ICTLR_BASE),
-	IO_ADDRESS(TEGRA_QUATERNARY_ICTLR_BASE),
-};
-
-static u32 tegra_legacy_wake_mask[4];
-static u32 tegra_legacy_saved_mask[4];
-
-/* When going into deep sleep, the CPU is powered down, taking the GIC with it
-   In order to wake, the wake interrupts need to be enabled in the legacy
-   interrupt controller. */
-void tegra_legacy_unmask_irq(unsigned int irq)
-{
-	void __iomem *base;
-	pr_debug("%s: %d\n", __func__, irq);
-
-	irq -= 32;
-	base = ictlr_reg_base[irq>>5];
-	writel(1 << (irq & 31), base + ICTLR_CPU_IER_SET);
-}
-
-void tegra_legacy_mask_irq(unsigned int irq)
-{
-	void __iomem *base;
-	pr_debug("%s: %d\n", __func__, irq);
-
-	irq -= 32;
-	base = ictlr_reg_base[irq>>5];
-	writel(1 << (irq & 31), base + ICTLR_CPU_IER_CLR);
-}
-
-void tegra_legacy_force_irq_set(unsigned int irq)
-{
-	void __iomem *base;
-	pr_debug("%s: %d\n", __func__, irq);
-
-	irq -= 32;
-	base = ictlr_reg_base[irq>>5];
-	writel(1 << (irq & 31), base + ICTLR_CPU_IEP_FIR_SET);
-}
-
-void tegra_legacy_force_irq_clr(unsigned int irq)
-{
-	void __iomem *base;
-	pr_debug("%s: %d\n", __func__, irq);
-
-	irq -= 32;
-	base = ictlr_reg_base[irq>>5];
-	writel(1 << (irq & 31), base + ICTLR_CPU_IEP_FIR_CLR);
-}
-
-int tegra_legacy_force_irq_status(unsigned int irq)
-{
-	void __iomem *base;
-	pr_debug("%s: %d\n", __func__, irq);
-
-	irq -= 32;
-	base = ictlr_reg_base[irq>>5];
-	return !!(readl(base + ICTLR_CPU_IEP_FIR) & (1 << (irq & 31)));
-}
-
-void tegra_legacy_select_fiq(unsigned int irq, bool fiq)
-{
-	void __iomem *base;
-	pr_debug("%s: %d\n", __func__, irq);
-
-	irq -= 32;
-	base = ictlr_reg_base[irq>>5];
-	writel(fiq << (irq & 31), base + ICTLR_CPU_IEP_CLASS);
-}
-
-unsigned long tegra_legacy_vfiq(int nr)
-{
-	void __iomem *base;
-	base = ictlr_reg_base[nr];
-	return readl(base + ICTLR_CPU_IEP_VFIQ);
-}
-
-unsigned long tegra_legacy_class(int nr)
-{
-	void __iomem *base;
-	base = ictlr_reg_base[nr];
-	return readl(base + ICTLR_CPU_IEP_CLASS);
-}
-
-int tegra_legacy_irq_set_wake(int irq, int enable)
-{
-	irq -= 32;
-	if (enable)
-		tegra_legacy_wake_mask[irq >> 5] |= 1 << (irq & 31);
-	else
-		tegra_legacy_wake_mask[irq >> 5] &= ~(1 << (irq & 31));
-
-	return 0;
-}
-
-void tegra_legacy_irq_set_lp1_wake_mask(void)
-{
-	void __iomem *base;
-	int i;
-
-	for (i = 0; i < NUM_ICTLRS; i++) {
-		base = ictlr_reg_base[i];
-		tegra_legacy_saved_mask[i] = readl(base + ICTLR_CPU_IER);
-		writel(tegra_legacy_wake_mask[i], base + ICTLR_CPU_IER);
-	}
-}
-
-void tegra_legacy_irq_restore_mask(void)
-{
-	void __iomem *base;
-	int i;
-
-	for (i = 0; i < NUM_ICTLRS; i++) {
-		base = ictlr_reg_base[i];
-		writel(tegra_legacy_saved_mask[i], base + ICTLR_CPU_IER);
-	}
-}
-
-void tegra_init_legacy_irq(void)
-{
-	int i;
-
-	for (i = 0; i < NUM_ICTLRS; i++) {
-		void __iomem *ictlr = ictlr_reg_base[i];
-		writel(~0, ictlr + ICTLR_CPU_IER_CLR);
-		writel(0, ictlr + ICTLR_CPU_IEP_CLASS);
-	}
-}
-
-#ifdef CONFIG_PM
-static u32 cop_ier[NUM_ICTLRS];
-static u32 cpu_ier[NUM_ICTLRS];
-static u32 cpu_iep[NUM_ICTLRS];
-
-void tegra_irq_suspend(void)
-{
-	unsigned long flags;
-	int i;
-
-	local_irq_save(flags);
-	for (i = 0; i < NUM_ICTLRS; i++) {
-		void __iomem *ictlr = ictlr_reg_base[i];
-		cpu_ier[i] = readl(ictlr + ICTLR_CPU_IER);
-		cpu_iep[i] = readl(ictlr + ICTLR_CPU_IEP_CLASS);
-		cop_ier[i] = readl(ictlr + ICTLR_COP_IER);
-		writel(~0, ictlr + ICTLR_COP_IER_CLR);
-	}
-	local_irq_restore(flags);
-}
-
-void tegra_irq_resume(void)
-{
-	unsigned long flags;
-	int i;
-
-	local_irq_save(flags);
-	for (i = 0; i < NUM_ICTLRS; i++) {
-		void __iomem *ictlr = ictlr_reg_base[i];
-		writel(cpu_iep[i], ictlr + ICTLR_CPU_IEP_CLASS);
-		writel(~0ul, ictlr + ICTLR_CPU_IER_CLR);
-		writel(cpu_ier[i], ictlr + ICTLR_CPU_IER_SET);
-		writel(0, ictlr + ICTLR_COP_IEP_CLASS);
-		writel(~0ul, ictlr + ICTLR_COP_IER_CLR);
-		writel(cop_ier[i], ictlr + ICTLR_COP_IER_SET);
-	}
-	local_irq_restore(flags);
-}
-#endif
diff --git a/arch/arm/plat-nomadik/gpio.c b/arch/arm/plat-nomadik/gpio.c
index f49748e..307b813 100644
--- a/arch/arm/plat-nomadik/gpio.c
+++ b/arch/arm/plat-nomadik/gpio.c
@@ -23,6 +23,8 @@
 #include <linux/irq.h>
 #include <linux/slab.h>
 
+#include <asm/mach/irq.h>
+
 #include <plat/pincfg.h>
 #include <mach/hardware.h>
 #include <mach/gpio.h>
@@ -681,13 +683,7 @@ static void __nmk_gpio_irq_handler(unsigned int irq, struct irq_desc *desc,
 	struct irq_chip *host_chip = irq_get_chip(irq);
 	unsigned int first_irq;
 
-	if (host_chip->irq_mask_ack)
-		host_chip->irq_mask_ack(&desc->irq_data);
-	else {
-		host_chip->irq_mask(&desc->irq_data);
-		if (host_chip->irq_ack)
-			host_chip->irq_ack(&desc->irq_data);
-	}
+	chained_irq_enter(host_chip, desc);
 
 	nmk_chip = irq_get_handler_data(irq);
 	first_irq = NOMADIK_GPIO_TO_IRQ(nmk_chip->chip.base);
@@ -698,7 +694,7 @@ static void __nmk_gpio_irq_handler(unsigned int irq, struct irq_desc *desc,
 		status &= ~BIT(bit);
 	}
 
-	host_chip->irq_unmask(&desc->irq_data);
+	chained_irq_exit(host_chip, desc);
 }
 
 static void nmk_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c
index d2adcdd..a2478eb 100644
--- a/arch/arm/plat-omap/gpio.c
+++ b/arch/arm/plat-omap/gpio.c
@@ -1137,8 +1137,9 @@ static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 	struct gpio_bank *bank;
 	u32 retrigger = 0;
 	int unmasked = 0;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 
-	desc->irq_data.chip->irq_ack(&desc->irq_data);
+	chained_irq_enter(chip, desc);
 
 	bank = irq_get_handler_data(irq);
 #ifdef CONFIG_ARCH_OMAP1
@@ -1195,7 +1196,7 @@ static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 		configured, we could unmask GPIO bank interrupt immediately */
 		if (!level_mask && !unmasked) {
 			unmasked = 1;
-			desc->irq_data.chip->irq_unmask(&desc->irq_data);
+			chained_irq_exit(chip, desc);
 		}
 
 		isr |= retrigger;
@@ -1231,7 +1232,7 @@ static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 	interrupt */
 exit:
 	if (!unmasked)
-		desc->irq_data.chip->irq_unmask(&desc->irq_data);
+		chained_irq_exit(chip, desc);
 }
 
 static void gpio_irq_shutdown(struct irq_data *d)
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 55613e3..a6ae1cf 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -933,12 +933,16 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	if (data && !(data & DABR_TRANSLATION))
 		return -EIO;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
+	if (ptrace_get_breakpoints(task) < 0)
+		return -ESRCH;
+
 	bp = thread->ptrace_bps[0];
 	if ((!data) || !(data & (DABR_DATA_WRITE | DABR_DATA_READ))) {
 		if (bp) {
 			unregister_hw_breakpoint(bp);
 			thread->ptrace_bps[0] = NULL;
 		}
+		ptrace_put_breakpoints(task);
 		return 0;
 	}
 	if (bp) {
@@ -948,9 +952,12 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 					(DABR_DATA_WRITE | DABR_DATA_READ),
 							&attr.bp_type);
 		ret =  modify_user_hw_breakpoint(bp, &attr);
-		if (ret)
+		if (ret) {
+			ptrace_put_breakpoints(task);
 			return ret;
+		}
 		thread->ptrace_bps[0] = bp;
+		ptrace_put_breakpoints(task);
 		thread->dabr = data;
 		return 0;
 	}
@@ -965,9 +972,12 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 							ptrace_triggered, task);
 	if (IS_ERR(bp)) {
 		thread->ptrace_bps[0] = NULL;
+		ptrace_put_breakpoints(task);
 		return PTR_ERR(bp);
 	}
 
+	ptrace_put_breakpoints(task);
+
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
 	/* Move contents to the DABR register */
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 2130ca6..3d7b209 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -117,7 +117,11 @@ void user_enable_single_step(struct task_struct *child)
 
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 
+	if (ptrace_get_breakpoints(child) < 0)
+		return;
+
 	set_single_step(child, pc);
+	ptrace_put_breakpoints(child);
 }
 
 void user_disable_single_step(struct task_struct *child)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3532d3b..bb9eb29 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -698,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
  */
 
 const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
 			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
 EXPORT_SYMBOL_GPL(amd_erratum_400);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e61539b..447a28d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -184,26 +184,23 @@ static __initconst const u64 snb_hw_cache_event_ids
 	},
  },
  [ C(LL  ) ] = {
-	/*
-	 * TBD: Need Off-core Response Performance Monitoring support
-	 */
 	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_WRITE) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -285,26 +282,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	/*
 	 * Use RFO, not WRITEBACK, because a write miss would typically occur
 	 * on RFO.
 	 */
 	[ C(OP_WRITE) ] = {
-		/* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
-		[ C(RESULT_ACCESS) ] = 0x01bb,
-		/* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
 		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+		/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01bb,
+		/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
  [ C(DTLB) ] = {
@@ -352,16 +349,36 @@ static __initconst const u64 westmere_hw_cache_event_ids
 };
 
 /*
- * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
  */
 
-#define DMND_DATA_RD     (1 << 0)
-#define DMND_RFO         (1 << 1)
-#define DMND_WB          (1 << 3)
-#define PF_DATA_RD       (1 << 4)
-#define PF_DATA_RFO      (1 << 5)
-#define RESP_UNCORE_HIT  (1 << 8)
-#define RESP_MISS        (0xf600) /* non uncore hit */
+#define NHM_DMND_DATA_RD	(1 << 0)
+#define NHM_DMND_RFO		(1 << 1)
+#define NHM_DMND_IFETCH		(1 << 2)
+#define NHM_DMND_WB		(1 << 3)
+#define NHM_PF_DATA_RD		(1 << 4)
+#define NHM_PF_DATA_RFO		(1 << 5)
+#define NHM_PF_IFETCH		(1 << 6)
+#define NHM_OFFCORE_OTHER	(1 << 7)
+#define NHM_UNCORE_HIT		(1 << 8)
+#define NHM_OTHER_CORE_HIT_SNP	(1 << 9)
+#define NHM_OTHER_CORE_HITM	(1 << 10)
+        			/* reserved */
+#define NHM_REMOTE_CACHE_FWD	(1 << 12)
+#define NHM_REMOTE_DRAM		(1 << 13)
+#define NHM_LOCAL_DRAM		(1 << 14)
+#define NHM_NON_DRAM		(1 << 15)
+
+#define NHM_ALL_DRAM		(NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+
+#define NHM_DMND_READ		(NHM_DMND_DATA_RD)
+#define NHM_DMND_WRITE		(NHM_DMND_RFO|NHM_DMND_WB)
+#define NHM_DMND_PREFETCH	(NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
+
+#define NHM_L3_HIT	(NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
+#define NHM_L3_MISS	(NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_ACCESS	(NHM_L3_HIT|NHM_L3_MISS)
 
 static __initconst const u64 nehalem_hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -370,16 +387,16 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
 {
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = DMND_DATA_RD|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_READ|NHM_L3_MISS,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = DMND_RFO|DMND_WB|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_WRITE|NHM_L3_MISS,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
-		[ C(RESULT_MISS)   ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+		[ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
 	},
  }
 };
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 45892dc..f65e5b5 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -608,6 +608,9 @@ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
 	unsigned len, type;
 	struct perf_event *bp;
 
+	if (ptrace_get_breakpoints(tsk) < 0)
+		return -ESRCH;
+
 	data &= ~DR_CONTROL_RESERVED;
 	old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
 restore:
@@ -655,6 +658,9 @@ restore:
 		}
 		goto restore;
 	}
+
+	ptrace_put_breakpoints(tsk);
+
 	return ((orig_ret < 0) ? orig_ret : rc);
 }
 
@@ -668,10 +674,17 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 
 	if (n < HBP_NUM) {
 		struct perf_event *bp;
+
+		if (ptrace_get_breakpoints(tsk) < 0)
+			return -ESRCH;
+
 		bp = thread->ptrace_bps[n];
 		if (!bp)
-			return 0;
-		val = bp->hw.info.address;
+			val = 0;
+		else
+			val = bp->hw.info.address;
+
+		ptrace_put_breakpoints(tsk);
 	} else if (n == 6) {
 		val = thread->debugreg6;
 	 } else if (n == 7) {
@@ -686,6 +699,10 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 	struct perf_event *bp;
 	struct thread_struct *t = &tsk->thread;
 	struct perf_event_attr attr;
+	int err = 0;
+
+	if (ptrace_get_breakpoints(tsk) < 0)
+		return -ESRCH;
 
 	if (!t->ptrace_bps[nr]) {
 		ptrace_breakpoint_init(&attr);
@@ -709,24 +726,23 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
 		 * writing for the user. And anyway this is the previous
 		 * behaviour.
 		 */
-		if (IS_ERR(bp))
-			return PTR_ERR(bp);
+		if (IS_ERR(bp)) {
+			err = PTR_ERR(bp);
+			goto put;
+		}
 
 		t->ptrace_bps[nr] = bp;
 	} else {
-		int err;
-
 		bp = t->ptrace_bps[nr];
 
 		attr = bp->attr;
 		attr.bp_addr = addr;
 		err = modify_user_hw_breakpoint(bp, &attr);
-		if (err)
-			return err;
 	}
 
-
-	return 0;
+put:
+	ptrace_put_breakpoints(tsk);
+	return err;
 }
 
 /*
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S
index 29092b3..1d5c46d 100644
--- a/arch/x86/kernel/reboot_32.S
+++ b/arch/x86/kernel/reboot_32.S
@@ -21,26 +21,26 @@ r_base = .
 	/* Get our own relocated address */
 	call	1f
 1:	popl	%ebx
-	subl	$1b, %ebx
+	subl	$(1b - r_base), %ebx
 
 	/* Compute the equivalent real-mode segment */
 	movl	%ebx, %ecx
 	shrl	$4, %ecx
 	
 	/* Patch post-real-mode segment jump */
-	movw	dispatch_table(%ebx,%eax,2),%ax
-	movw	%ax, 101f(%ebx)
-	movw	%cx, 102f(%ebx)
+	movw	(dispatch_table - r_base)(%ebx,%eax,2),%ax
+	movw	%ax, (101f - r_base)(%ebx)
+	movw	%cx, (102f - r_base)(%ebx)
 
 	/* Set up the IDT for real mode. */
-	lidtl	machine_real_restart_idt(%ebx)
+	lidtl	(machine_real_restart_idt - r_base)(%ebx)
 
 	/*
 	 * Set up a GDT from which we can load segment descriptors for real
 	 * mode.  The GDT is not used in real mode; it is just needed here to
 	 * prepare the descriptors.
 	 */
-	lgdtl	machine_real_restart_gdt(%ebx)
+	lgdtl	(machine_real_restart_gdt - r_base)(%ebx)
 
 	/*
 	 * Load the data segment registers with 16-bit compatible values
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index e8c00cc..85b52fc 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -306,7 +306,7 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 		bi->end = min(bi->end, high);
 
 		/* and there's no empty block */
-		if (bi->start == bi->end) {
+		if (bi->start >= bi->end) {
 			numa_remove_memblk_from(i--, mi);
 			continue;
 		}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index aef7af9..55c965b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1463,6 +1463,119 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 	return ret;
 }
 
+#ifdef CONFIG_X86_64
+static __initdata u64 __last_pgt_set_rw = 0;
+static __initdata u64 __pgt_buf_start = 0;
+static __initdata u64 __pgt_buf_end = 0;
+static __initdata u64 __pgt_buf_top = 0;
+/*
+ * As a consequence of the commit:
+ * 
+ * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
+ * Author: Yinghai Lu <yinghai@kernel.org>
+ * Date:   Fri Dec 17 16:58:28 2010 -0800
+ * 
+ *     x86-64, mm: Put early page table high
+ * 
+ * at some point init_memory_mapping is going to reach the pagetable pages
+ * area and map those pages too (mapping them as normal memory that falls
+ * in the range of addresses passed to init_memory_mapping as argument).
+ * Some of those pages are already pagetable pages (they are in the range
+ * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
+ * everything is fine.
+ * Some of these pages are not pagetable pages yet (they fall in the range
+ * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
+ * are going to be mapped RW.  When these pages become pagetable pages and
+ * are hooked into the pagetable, xen will find that the guest has already
+ * a RW mapping of them somewhere and fail the operation.
+ * The reason Xen requires pagetables to be RO is that the hypervisor needs
+ * to verify that the pagetables are valid before using them. The validation
+ * operations are called "pinning".
+ * 
+ * In order to fix the issue we mark all the pages in the entire range
+ * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
+ * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
+ * init_memory_mapping. Hence the kernel is going to crash as soon as one
+ * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
+ * ranges are RO).
+ * 
+ * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
+ * the init_memory_mapping has completed (in a perfect world we would
+ * call this function from init_memory_mapping, but lets ignore that).
+ * 
+ * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
+ * end,top] have all changed to new values (b/c init_memory_mapping
+ * is called and setting up another new page-table). Hence, the first time
+ * we enter this function, we save away the pgt_buf_start value and update
+ * the pgt_buf_[end,top].
+ * 
+ * When we detect that the "old" pgt_buf_start through pgt_buf_end
+ * PFNs have been reserved (so memblock_x86_reserve_range has been called),
+ * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
+ * 
+ * And then we update those "old" pgt_buf_[end|top] with the new ones
+ * so that we can redo this on the next pagetable.
+ */
+static __init void mark_rw_past_pgt(void) {
+
+	if (pgt_buf_end > pgt_buf_start) {
+		u64 addr, size;
+
+		/* Save it away. */
+		if (!__pgt_buf_start) {
+			__pgt_buf_start = pgt_buf_start;
+			__pgt_buf_end = pgt_buf_end;
+			__pgt_buf_top = pgt_buf_top;
+			return;
+		}
+		/* If we get the range that starts at __pgt_buf_end that means
+		 * the range is reserved, and that in 'init_memory_mapping'
+		 * the 'memblock_x86_reserve_range' has been called with the
+		 * outdated __pgt_buf_start, __pgt_buf_end (the "new"
+		 * pgt_buf_[start|end|top] refer now to a new pagetable.
+		 * Note: we are called _after_ the pgt_buf_[..] have been
+		 * updated.*/
+
+		addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
+						       &size, PAGE_SIZE);
+
+		/* Still not reserved, meaning 'memblock_x86_reserve_range'
+		 * hasn't been called yet. Update the _end and _top.*/
+		if (addr == PFN_PHYS(__pgt_buf_start)) {
+			__pgt_buf_end = pgt_buf_end;
+			__pgt_buf_top = pgt_buf_top;
+			return;
+		}
+
+		/* OK, the area is reserved, meaning it is time for us to
+		 * set RW for the old end->top PFNs. */
+
+		/* ..unless we had already done this. */
+		if (__pgt_buf_end == __last_pgt_set_rw)
+			return;
+
+		addr = PFN_PHYS(__pgt_buf_end);
+		
+		/* set as RW the rest */
+		printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
+			PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
+		
+		while (addr < PFN_PHYS(__pgt_buf_top)) {
+			make_lowmem_page_readwrite(__va(addr));
+			addr += PAGE_SIZE;
+		}
+		/* And update everything so that we are ready for the next
+		 * pagetable (the one created for regions past 4GB) */
+		__last_pgt_set_rw = __pgt_buf_end;
+		__pgt_buf_start = pgt_buf_start;
+		__pgt_buf_end = pgt_buf_end;
+		__pgt_buf_top = pgt_buf_top;
+	}
+	return;
+}
+#else
+static __init void mark_rw_past_pgt(void) { }
+#endif
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
@@ -1489,13 +1602,21 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 	unsigned long pfn = pte_pfn(pte);
 
 	/*
+	 * A bit of optimization. We do not need to call the workaround
+	 * when xen_set_pte_init is called with a PTE with 0 as PFN.
+	 * That is b/c the pagetable at that point are just being populated
+	 * with empty values and we can save some cycles by not calling
+	 * the 'memblock' code.*/
+	if (pfn)
+		mark_rw_past_pgt();
+	/*
 	 * If the new pfn is within the range of the newly allocated
 	 * kernel pagetable, and it isn't being mapped into an
 	 * early_ioremap fixmap slot as a freshly allocated page, make sure
 	 * it is RO.
 	 */
 	if (((!is_early_ioremap_ptep(ptep) &&
-			pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+			pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
 			(is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
 		pte = pte_wrprotect(pte);
 
@@ -1997,6 +2118,8 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
+	mark_rw_past_pgt();
+
 #ifdef CONFIG_XEN_DEBUG
 	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
 #endif