Merge branch 'perf/uprobes' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/uprobes

158 files changed, 1863 insertions, 1394 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index f62251e82ffa..3bb7ffeae3bc 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <asm/barrier.h>
+#include <asm/cmpxchg.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -168,73 +169,6 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 	return result;
 }
 
-/*
- * Atomic exchange routines.
- */
-
-#define __ASM__MB
-#define ____xchg(type, args...)		__xchg ## type ## _local(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
-#include <asm/xchg.h>
-
-#define xchg_local(ptr,x)						\
-  ({									\
-     __typeof__(*(ptr)) _x_ = (x);					\
-     (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
-				       sizeof(*(ptr)));			\
-  })
-
-#define cmpxchg_local(ptr, o, n)					\
-  ({									\
-     __typeof__(*(ptr)) _o_ = (o);					\
-     __typeof__(*(ptr)) _n_ = (n);					\
-     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
-					  (unsigned long)_n_,		\
-					  sizeof(*(ptr)));		\
-  })
-
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-
-#ifdef CONFIG_SMP
-#undef __ASM__MB
-#define __ASM__MB	"\tmb\n"
-#endif
-#undef ____xchg
-#undef ____cmpxchg
-#define ____xchg(type, args...)		__xchg ##type(args)
-#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
-#include <asm/xchg.h>
-
-#define xchg(ptr,x)							\
-  ({									\
-     __typeof__(*(ptr)) _x_ = (x);					\
-     (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
-				 sizeof(*(ptr)));			\
-  })
-
-#define cmpxchg(ptr, o, n)						\
-  ({									\
-     __typeof__(*(ptr)) _o_ = (o);					\
-     __typeof__(*(ptr)) _n_ = (n);					\
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		\
-				    (unsigned long)_n_,	sizeof(*(ptr)));\
-  })
-
-#define cmpxchg64(ptr, o, n)						\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
-  })
-
-#undef __ASM__MB
-#undef ____cmpxchg
-
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..429e8cd0d78e
--- /dev/null
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -0,0 +1,71 @@
+#ifndef _ALPHA_CMPXCHG_H
+#define _ALPHA_CMPXCHG_H
+
+/*
+ * Atomic exchange routines.
+ */
+
+#define __ASM__MB
+#define ____xchg(type, args...)		__xchg ## type ## _local(args)
+#define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
+#include <asm/xchg.h>
+
+#define xchg_local(ptr, x)						\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_,	\
+				       sizeof(*(ptr)));			\
+})
+
+#define cmpxchg_local(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	\
+					  (unsigned long)_n_,		\
+					  sizeof(*(ptr)));		\
+})
+
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+})
+
+#ifdef CONFIG_SMP
+#undef __ASM__MB
+#define __ASM__MB	"\tmb\n"
+#endif
+#undef ____xchg
+#undef ____cmpxchg
+#define ____xchg(type, args...)		__xchg ##type(args)
+#define ____cmpxchg(type, args...)	__cmpxchg ##type(args)
+#include <asm/xchg.h>
+
+#define xchg(ptr, x)							\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_,		\
+				 sizeof(*(ptr)));			\
+})
+
+#define cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,	\
+				    (unsigned long)_n_,	sizeof(*(ptr)));\
+})
+
+#define cmpxchg64(ptr, o, n)						\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+})
+
+#undef __ASM__MB
+#undef ____cmpxchg
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+#endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h
index 1d1b436fbff2..0ca9724597c1 100644
--- a/arch/alpha/include/asm/xchg.h
+++ b/arch/alpha/include/asm/xchg.h
@@ -1,10 +1,10 @@
-#ifndef _ALPHA_ATOMIC_H
+#ifndef _ALPHA_CMPXCHG_H
 #error Do not include xchg.h directly!
 #else
 /*
  * xchg/xchg_local and cmpxchg/cmpxchg_local share the same code
  * except that local version do not have the expensive memory barrier.
- * So this file is included twice from asm/system.h.
+ * So this file is included twice from asm/cmpxchg.h.
  */
 
 /*
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 0dae252f7a33..d821b17047e0 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -824,7 +824,6 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 
 	idx = la_ptr;
 
-	perf_sample_data_init(&data, 0);
 	for (j = 0; j < cpuc->n_events; j++) {
 		if (cpuc->current_idx[j] == idx)
 			break;
@@ -848,7 +847,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 
 	hwc = &event->hw;
 	alpha_perf_event_update(event, hwc, idx, alpha_pmu->pmc_max_period[idx]+1);
-	data.period = event->hw.last_period;
+	perf_sample_data_init(&data, 0, hwc->last_period);
 
 	if (alpha_perf_event_set_period(event, hwc, idx)) {
 		if (perf_event_overflow(event, &data, regs)) {
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index 6ce11c481178..797f04bedb47 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -77,6 +77,8 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 		} else if (atag->hdr.tag == ATAG_MEM) {
 			if (memcount >= sizeof(mem_reg_property)/4)
 				continue;
+			if (!atag->u.mem.size)
+				continue;
 			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
 			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
 		} else if (atag->hdr.tag == ATAG_INITRD2) {
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 5f6045f1766c..dc7e8ce8e6be 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -273,7 +273,7 @@ restart:	adr	r0, LC0
 		add	r0, r0, #0x100
 		mov	r1, r6
 		sub	r2, sp, r6
-		blne	atags_to_fdt
+		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
 		sub	sp, sp, #0x10000
diff --git a/arch/arm/boot/dts/at91sam9g20.dtsi b/arch/arm/boot/dts/at91sam9g20.dtsi
index 799ad1889b51..773ef484037a 100644
--- a/arch/arm/boot/dts/at91sam9g20.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20.dtsi
@@ -55,7 +55,6 @@
 				#interrupt-cells = <2>;
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
-				interrupt-parent;
 				reg = <0xfffff000 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index 9e6eb6ecea0e..c8042147eaa2 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -56,7 +56,6 @@
 				#interrupt-cells = <2>;
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
-				interrupt-parent;
 				reg = <0xfffff000 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 70ab3a4e026f..dd4ed748469a 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -54,7 +54,6 @@
 				#interrupt-cells = <2>;
 				compatible = "atmel,at91rm9200-aic";
 				interrupt-controller;
-				interrupt-parent;
 				reg = <0xfffff000 0x200>;
 			};
 
diff --git a/arch/arm/boot/dts/db8500.dtsi b/arch/arm/boot/dts/db8500.dtsi
index d73dce645667..14bc30705099 100644
--- a/arch/arm/boot/dts/db8500.dtsi
+++ b/arch/arm/boot/dts/db8500.dtsi
@@ -24,7 +24,6 @@
 			#interrupt-cells = <3>;
 			#address-cells = <1>;
 			interrupt-controller;
-			interrupt-parent;
 			reg = <0xa0411000 0x1000>,
 			      <0xa0410100 0x100>;
 		};
diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts
index 37c0ff9c8b90..83e72294aefb 100644
--- a/arch/arm/boot/dts/highbank.dts
+++ b/arch/arm/boot/dts/highbank.dts
@@ -89,7 +89,6 @@
 			#size-cells = <0>;
 			#address-cells = <1>;
 			interrupt-controller;
-			interrupt-parent;
 			reg = <0xfff11000 0x1000>,
 			      <0xfff10100 0x100>;
 		};
diff --git a/arch/arm/common/vic.c b/arch/arm/common/vic.c
index 7a66311f3066..7e288f96cedf 100644
--- a/arch/arm/common/vic.c
+++ b/arch/arm/common/vic.c
@@ -427,19 +427,18 @@ int __init vic_of_init(struct device_node *node, struct device_node *parent)
 
 /*
  * Handle each interrupt in a single VIC.  Returns non-zero if we've
- * handled at least one interrupt.  This does a single read of the
- * status register and handles all interrupts in order from LSB first.
+ * handled at least one interrupt.  This reads the status register
+ * before handling each interrupt, which is necessary given that
+ * handle_IRQ may briefly re-enable interrupts for soft IRQ handling.
  */
 static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs)
 {
 	u32 stat, irq;
 	int handled = 0;
 
-	stat = readl_relaxed(vic->base + VIC_IRQ_STATUS);
-	while (stat) {
+	while ((stat = readl_relaxed(vic->base + VIC_IRQ_STATUS))) {
 		irq = ffs(stat) - 1;
 		handle_IRQ(irq_find_mapping(vic->domain, irq), regs);
-		stat &= ~(1 << irq);
 		handled = 1;
 	}
 
diff --git a/arch/arm/configs/bcmring_defconfig b/arch/arm/configs/bcmring_defconfig
index 795374d48f81..9e6a8fe13164 100644
--- a/arch/arm/configs/bcmring_defconfig
+++ b/arch/arm/configs/bcmring_defconfig
@@ -11,7 +11,7 @@ CONFIG_KALLSYMS_EXTRA_PASS=y
 # CONFIG_TIMERFD is not set
 # CONFIG_EVENTFD is not set
 # CONFIG_AIO is not set
-CONFIG_PERF_COUNTERS=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index b5ac644e12af..6b31cb60daab 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -112,6 +112,7 @@ CONFIG_WATCHDOG=y
 CONFIG_IMX2_WDT=y
 CONFIG_MFD_MC13XXX=y
 CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_MC13783=y
 CONFIG_REGULATOR_MC13892=y
 CONFIG_FB=y
diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig
index 889d73ac1ae1..7e84f453e8a6 100644
--- a/arch/arm/configs/u8500_defconfig
+++ b/arch/arm/configs/u8500_defconfig
@@ -8,8 +8,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_LBDAF is not set
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_ARCH_U8500=y
-CONFIG_UX500_SOC_DB5500=y
-CONFIG_UX500_SOC_DB8500=y
 CONFIG_MACH_HREFV60=y
 CONFIG_MACH_SNOWBALL=y
 CONFIG_MACH_U5500=y
@@ -39,7 +37,6 @@ CONFIG_CAIF=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_MISC_DEVICES=y
 CONFIG_AB8500_PWM=y
 CONFIG_SENSORS_BH1780=y
 CONFIG_NETDEVICES=y
@@ -65,16 +62,18 @@ CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_NOMADIK=y
-CONFIG_I2C=y
-CONFIG_I2C_NOMADIK=y
 CONFIG_SPI=y
 CONFIG_SPI_PL022=y
 CONFIG_GPIO_STMPE=y
 CONFIG_GPIO_TC3589X=y
+CONFIG_POWER_SUPPLY=y
+CONFIG_AB8500_BM=y
+CONFIG_AB8500_BATTERY_THERM_ON_BATCTRL=y
 CONFIG_MFD_STMPE=y
 CONFIG_MFD_TC3589X=y
 CONFIG_AB5500_CORE=y
 CONFIG_AB8500_CORE=y
+CONFIG_REGULATOR=y
 CONFIG_REGULATOR_AB8500=y
 # CONFIG_HID_SUPPORT is not set
 CONFIG_USB_GADGET=y
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index 5c5ca2ea62b0..bfc198c75913 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -14,7 +14,7 @@
 #define JUMP_LABEL_NOP	"nop"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:\n\t"
 		 JUMP_LABEL_NOP "\n\t"
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index b78af0cc6ef3..ab627a740fa3 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -489,8 +489,6 @@ armv6pmu_handle_irq(int irq_num,
 	 */
 	armv6_pmcr_write(pmcr);
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -509,7 +507,7 @@ armv6pmu_handle_irq(int irq_num,
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 00755d82e2f2..d3c536068162 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1077,8 +1077,6 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	 */
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -1097,7 +1095,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 71a21e6712f5..e34e7254e652 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -248,8 +248,6 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -263,7 +261,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
@@ -588,8 +586,6 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
@@ -603,7 +599,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 
 		hwc = &event->hw;
 		armpmu_event_update(event, hwc, idx);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!armpmu_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b91411371ae1..ebfac782593f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -523,7 +523,21 @@ int __init arm_add_memory(phys_addr_t start, unsigned long size)
 	 */
 	size -= start & ~PAGE_MASK;
 	bank->start = PAGE_ALIGN(start);
-	bank->size  = size & PAGE_MASK;
+
+#ifndef CONFIG_LPAE
+	if (bank->start + size < bank->start) {
+		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
+			"32-bit physical address space\n", (long long)start);
+		/*
+		 * To ensure bank->start + bank->size is representable in
+		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
+		 * This means we lose a page after masking.
+		 */
+		size = ULONG_MAX - bank->start;
+	}
+#endif
+
+	bank->size = size & PAGE_MASK;
 
 	/*
 	 * Check whether this memory region has non-zero size or
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index fef42b21cecb..5b150afb995b 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -118,10 +118,14 @@ static int twd_cpufreq_transition(struct notifier_block *nb,
 	 * The twd clock events must be reprogrammed to account for the new
 	 * frequency.  The timer is local to a cpu, so cross-call to the
 	 * changing cpu.
+	 *
+	 * Only wait for it to finish, if the cpu is active to avoid
+	 * deadlock when cpu1 is spinning on while(!cpu_active(cpu1)) during
+	 * booting of that cpu.
 	 */
 	if (state == CPUFREQ_POSTCHANGE || state == CPUFREQ_RESUMECHANGE)
 		smp_call_function_single(freqs->cpu, twd_update_frequency,
-			NULL, 1);
+					 NULL, cpu_active(freqs->cpu));
 
 	return NOTIFY_OK;
 }
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index 99ce5c955e39..05774e5b1cba 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -1173,7 +1173,6 @@ void __init at91_add_device_serial(void)
 		printk(KERN_INFO "AT91: No default serial console defined.\n");
 }
 #else
-void __init __deprecated at91_init_serial(struct at91_uart_config *config) {}
 void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins) {}
 void __init at91_set_serial_console(unsigned portnr) {}
 void __init at91_add_device_serial(void) {}
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index dd7f782b0b91..104ca40d8d18 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/clockchips.h>
+#include <linux/export.h>
 
 #include <asm/mach/time.h>
 
@@ -176,6 +177,7 @@ static struct clock_event_device clkevt = {
 };
 
 void __iomem *at91_st_base;
+EXPORT_SYMBOL_GPL(at91_st_base);
 
 void __init at91rm9200_ioremap_st(u32 addr)
 {
diff --git a/arch/arm/mach-at91/board-rm9200ek.c b/arch/arm/mach-at91/board-rm9200ek.c
index 11cbaa8946fe..b2e4fe21f346 100644
--- a/arch/arm/mach-at91/board-rm9200ek.c
+++ b/arch/arm/mach-at91/board-rm9200ek.c
@@ -117,7 +117,7 @@ static struct i2c_board_info __initdata ek_i2c_devices[] = {
 };
 
 #define EK_FLASH_BASE	AT91_CHIPSELECT_0
-#define EK_FLASH_SIZE	SZ_2M
+#define EK_FLASH_SIZE	SZ_8M
 
 static struct physmap_flash_data ek_flash_data = {
 	.width		= 2,
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index c3f994462864..065fed342424 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -85,8 +85,6 @@ static struct resource dm9000_resource[] = {
 		.flags	= IORESOURCE_MEM
 	},
 	[2] = {
-		.start	= AT91_PIN_PC11,
-		.end	= AT91_PIN_PC11,
 		.flags	= IORESOURCE_IRQ
 			| IORESOURCE_IRQ_LOWEDGE | IORESOURCE_IRQ_HIGHEDGE,
 	}
@@ -130,6 +128,8 @@ static struct sam9_smc_config __initdata dm9000_smc_config = {
 
 static void __init ek_add_device_dm9000(void)
 {
+	struct resource *r = &dm9000_resource[2];
+
 	/* Configure chip-select 2 (DM9000) */
 	sam9_smc_configure(0, 2, &dm9000_smc_config);
 
@@ -139,6 +139,7 @@ static void __init ek_add_device_dm9000(void)
 	/* Configure Interrupt pin as input, no pull-up */
 	at91_set_gpio_input(AT91_PIN_PC11, 0);
 
+	r->start = r->end = gpio_to_irq(AT91_PIN_PC11);
 	platform_device_register(&dm9000_device);
 }
 #else
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index a0f4d7424cdc..6b692824c988 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -35,6 +35,7 @@
 #include "generic.h"
 
 void __iomem *at91_pmc_base;
+EXPORT_SYMBOL_GPL(at91_pmc_base);
 
 /*
  * There's a lot more which can be done with clocks, including cpufreq
diff --git a/arch/arm/mach-at91/include/mach/at91_pmc.h b/arch/arm/mach-at91/include/mach/at91_pmc.h
index 36604782a78f..ea2c57a86ca6 100644
--- a/arch/arm/mach-at91/include/mach/at91_pmc.h
+++ b/arch/arm/mach-at91/include/mach/at91_pmc.h
@@ -25,7 +25,7 @@ extern void __iomem *at91_pmc_base;
 #define at91_pmc_write(field, value) \
 	__raw_writel(value, at91_pmc_base + field)
 #else
-.extern at91_aic_base
+.extern at91_pmc_base
 #endif
 
 #define	AT91_PMC_SCER		0x00			/* System Clock Enable Register */
diff --git a/arch/arm/mach-at91/setup.c b/arch/arm/mach-at91/setup.c
index 97cc04dc8073..f44a2e7272e3 100644
--- a/arch/arm/mach-at91/setup.c
+++ b/arch/arm/mach-at91/setup.c
@@ -54,6 +54,7 @@ void __init at91_init_interrupts(unsigned int *priority)
 }
 
 void __iomem *at91_ramc_base[2];
+EXPORT_SYMBOL_GPL(at91_ramc_base);
 
 void __init at91_ioremap_ramc(int id, u32 addr, u32 size)
 {
@@ -292,6 +293,7 @@ void __init at91_ioremap_rstc(u32 base_addr)
 }
 
 void __iomem *at91_matrix_base;
+EXPORT_SYMBOL_GPL(at91_matrix_base);
 
 void __init at91_ioremap_matrix(u32 base_addr)
 {
diff --git a/arch/arm/mach-bcmring/core.c b/arch/arm/mach-bcmring/core.c
index 22e4e0a28ad1..adbfb1994582 100644
--- a/arch/arm/mach-bcmring/core.c
+++ b/arch/arm/mach-bcmring/core.c
@@ -52,8 +52,8 @@
 #include <mach/csp/chipcHw_inline.h>
 #include <mach/csp/tmrHw_reg.h>
 
-static AMBA_APB_DEVICE(uartA, "uarta", MM_ADDR_IO_UARTA, { IRQ_UARTA }, NULL);
-static AMBA_APB_DEVICE(uartB, "uartb", MM_ADDR_IO_UARTB, { IRQ_UARTB }, NULL);
+static AMBA_APB_DEVICE(uartA, "uartA", 0, MM_ADDR_IO_UARTA, {IRQ_UARTA}, NULL);
+static AMBA_APB_DEVICE(uartB, "uartB", 0, MM_ADDR_IO_UARTB, {IRQ_UARTB}, NULL);
 
 static struct clk pll1_clk = {
 	.name = "PLL1",
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index 0491ceef1cda..e81c35f936b5 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -368,6 +368,7 @@ comment "Flattened Device Tree based board for EXYNOS SoCs"
 
 config MACH_EXYNOS4_DT
 	bool "Samsung Exynos4 Machine using device tree"
+	depends on ARCH_EXYNOS4
 	select CPU_EXYNOS4210
 	select USE_OF
 	select ARM_AMBA
@@ -380,6 +381,7 @@ config MACH_EXYNOS4_DT
 
 config MACH_EXYNOS5_DT
 	bool "SAMSUNG EXYNOS5 Machine using device tree"
+	depends on ARCH_EXYNOS5
 	select SOC_EXYNOS5250
 	select USE_OF
 	select ARM_AMBA
diff --git a/arch/arm/mach-exynos/include/mach/irqs.h b/arch/arm/mach-exynos/include/mach/irqs.h
index 9bee8535d9e0..591e78521a9f 100644
--- a/arch/arm/mach-exynos/include/mach/irqs.h
+++ b/arch/arm/mach-exynos/include/mach/irqs.h
@@ -212,6 +212,8 @@
 #define IRQ_MFC				EXYNOS4_IRQ_MFC
 #define IRQ_SDO				EXYNOS4_IRQ_SDO
 
+#define IRQ_I2S0			EXYNOS4_IRQ_I2S0
+
 #define IRQ_ADC				EXYNOS4_IRQ_ADC0
 #define IRQ_TC				EXYNOS4_IRQ_PEN0
 
diff --git a/arch/arm/mach-exynos/include/mach/map.h b/arch/arm/mach-exynos/include/mach/map.h
index 024d38ff1718..6e6d11ff352a 100644
--- a/arch/arm/mach-exynos/include/mach/map.h
+++ b/arch/arm/mach-exynos/include/mach/map.h
@@ -89,6 +89,10 @@
 #define EXYNOS4_PA_MDMA1		0x12840000
 #define EXYNOS4_PA_PDMA0		0x12680000
 #define EXYNOS4_PA_PDMA1		0x12690000
+#define EXYNOS5_PA_MDMA0		0x10800000
+#define EXYNOS5_PA_MDMA1		0x11C10000
+#define EXYNOS5_PA_PDMA0		0x121A0000
+#define EXYNOS5_PA_PDMA1		0x121B0000
 
 #define EXYNOS4_PA_SYSMMU_MDMA		0x10A40000
 #define EXYNOS4_PA_SYSMMU_SSS		0x10A50000
diff --git a/arch/arm/mach-exynos/include/mach/regs-clock.h b/arch/arm/mach-exynos/include/mach/regs-clock.h
index e141c1fd68d8..d9578a58ae7f 100644
--- a/arch/arm/mach-exynos/include/mach/regs-clock.h
+++ b/arch/arm/mach-exynos/include/mach/regs-clock.h
@@ -255,9 +255,15 @@
 
 /* For EXYNOS5250 */
 
+#define EXYNOS5_APLL_LOCK			EXYNOS_CLKREG(0x00000)
 #define EXYNOS5_APLL_CON0			EXYNOS_CLKREG(0x00100)
 #define EXYNOS5_CLKSRC_CPU			EXYNOS_CLKREG(0x00200)
+#define EXYNOS5_CLKMUX_STATCPU			EXYNOS_CLKREG(0x00400)
 #define EXYNOS5_CLKDIV_CPU0			EXYNOS_CLKREG(0x00500)
+#define EXYNOS5_CLKDIV_CPU1			EXYNOS_CLKREG(0x00504)
+#define EXYNOS5_CLKDIV_STATCPU0			EXYNOS_CLKREG(0x00600)
+#define EXYNOS5_CLKDIV_STATCPU1			EXYNOS_CLKREG(0x00604)
+
 #define EXYNOS5_MPLL_CON0			EXYNOS_CLKREG(0x04100)
 #define EXYNOS5_CLKSRC_CORE1			EXYNOS_CLKREG(0x04204)
 
diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c
index 0d26f50081ad..4711c8920e37 100644
--- a/arch/arm/mach-exynos/mach-exynos5-dt.c
+++ b/arch/arm/mach-exynos/mach-exynos5-dt.c
@@ -45,7 +45,7 @@ static const struct of_dev_auxdata exynos5250_auxdata_lookup[] __initconst = {
 				"exynos4210-uart.3", NULL),
 	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA0, "dma-pl330.0", NULL),
 	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA1, "dma-pl330.1", NULL),
-	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_PDMA1, "dma-pl330.2", NULL),
+	OF_DEV_AUXDATA("arm,pl330", EXYNOS5_PA_MDMA1, "dma-pl330.2", NULL),
 	{},
 };
 
diff --git a/arch/arm/mach-exynos/mach-nuri.c b/arch/arm/mach-exynos/mach-nuri.c
index b3982c867c9c..b4f1f902ce6d 100644
--- a/arch/arm/mach-exynos/mach-nuri.c
+++ b/arch/arm/mach-exynos/mach-nuri.c
@@ -307,49 +307,7 @@ static struct i2c_board_info i2c1_devs[] __initdata = {
 };
 
 /* TSP */
-static u8 mxt_init_vals[] = {
-	/* MXT_GEN_COMMAND(6) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_GEN_POWER(7) */
-	0x20, 0xff, 0x32,
-	/* MXT_GEN_ACQUIRE(8) */
-	0x0a, 0x00, 0x05, 0x00, 0x00, 0x00, 0x09, 0x23,
-	/* MXT_TOUCH_MULTI(9) */
-	0x00, 0x00, 0x00, 0x13, 0x0b, 0x00, 0x00, 0x00, 0x02, 0x00,
-	0x00, 0x01, 0x01, 0x0e, 0x0a, 0x0a, 0x0a, 0x0a, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00,
-	/* MXT_TOUCH_KEYARRAY(15) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00,
-	0x00,
-	/* MXT_SPT_GPIOPWM(19) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_PROCI_GRIPFACE(20) */
-	0x07, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x28, 0x04,
-	0x0f, 0x0a,
-	/* MXT_PROCG_NOISE(22) */
-	0x05, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x23, 0x00,
-	0x00, 0x05, 0x0f, 0x19, 0x23, 0x2d, 0x03,
-	/* MXT_TOUCH_PROXIMITY(23) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_PROCI_ONETOUCH(24) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_SPT_SELFTEST(25) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x00, 0x00, 0x00, 0x00,
-	/* MXT_PROCI_TWOTOUCH(27) */
-	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	/* MXT_SPT_CTECONFIG(28) */
-	0x00, 0x00, 0x02, 0x08, 0x10, 0x00,
-};
-
 static struct mxt_platform_data mxt_platform_data = {
-	.config			= mxt_init_vals,
-	.config_length		= ARRAY_SIZE(mxt_init_vals),
-
 	.x_line			= 18,
 	.y_line			= 11,
 	.x_size			= 1024,
@@ -571,7 +529,7 @@ static struct regulator_init_data __initdata max8997_ldo7_data = {
 
 static struct regulator_init_data __initdata max8997_ldo8_data = {
 	.constraints	= {
-		.name		= "VUSB/VDAC_3.3V_C210",
+		.name		= "VUSB+VDAC_3.3V_C210",
 		.min_uV		= 3300000,
 		.max_uV		= 3300000,
 		.valid_ops_mask	= REGULATOR_CHANGE_STATUS,
@@ -1347,6 +1305,7 @@ static struct platform_device *nuri_devices[] __initdata = {
 
 static void __init nuri_map_io(void)
 {
+	clk_xusbxti.rate = 24000000;
 	exynos_init_io(NULL, 0);
 	s3c24xx_init_clocks(24000000);
 	s3c24xx_init_uarts(nuri_uartcfgs, ARRAY_SIZE(nuri_uartcfgs));
@@ -1379,7 +1338,6 @@ static void __init nuri_machine_init(void)
 	nuri_camera_init();
 
 	nuri_ehci_init();
-	clk_xusbxti.rate = 24000000;
 
 	/* Last */
 	platform_add_devices(nuri_devices, ARRAY_SIZE(nuri_devices));
diff --git a/arch/arm/mach-exynos/mach-universal_c210.c b/arch/arm/mach-exynos/mach-universal_c210.c
index 6bb9dbdd73fd..7ebf79c2ab34 100644
--- a/arch/arm/mach-exynos/mach-universal_c210.c
+++ b/arch/arm/mach-exynos/mach-universal_c210.c
@@ -29,6 +29,7 @@
 #include <asm/mach-types.h>
 
 #include <plat/regs-serial.h>
+#include <plat/clock.h>
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/iic.h>
@@ -1057,6 +1058,7 @@ static struct platform_device *universal_devices[] __initdata = {
 
 static void __init universal_map_io(void)
 {
+	clk_xusbxti.rate = 24000000;
 	exynos_init_io(NULL, 0);
 	s3c24xx_init_clocks(24000000);
 	s3c24xx_init_uarts(universal_uartcfgs, ARRAY_SIZE(universal_uartcfgs));
diff --git a/arch/arm/mach-imx/imx27-dt.c b/arch/arm/mach-imx/imx27-dt.c
index 861ceb8232d6..ed38d03c61f2 100644
--- a/arch/arm/mach-imx/imx27-dt.c
+++ b/arch/arm/mach-imx/imx27-dt.c
@@ -35,7 +35,7 @@ static const struct of_dev_auxdata imx27_auxdata_lookup[] __initconst = {
 static int __init imx27_avic_add_irq_domain(struct device_node *np,
 				struct device_node *interrupt_parent)
 {
-	irq_domain_add_simple(np, 0);
+	irq_domain_add_legacy(np, 64, 0, 0, &irq_domain_simple_ops, NULL);
 	return 0;
 }
 
@@ -44,7 +44,9 @@ static int __init imx27_gpio_add_irq_domain(struct device_node *np,
 {
 	static int gpio_irq_base = MXC_GPIO_IRQ_START + ARCH_NR_GPIOS;
 
-	irq_domain_add_simple(np, gpio_irq_base);
+	gpio_irq_base -= 32;
+	irq_domain_add_legacy(np, 32, gpio_irq_base, 0, &irq_domain_simple_ops,
+				NULL);
 
 	return 0;
 }
diff --git a/arch/arm/mach-imx/mm-imx5.c b/arch/arm/mach-imx/mm-imx5.c
index 05250aed61fb..e10f3914fcfe 100644
--- a/arch/arm/mach-imx/mm-imx5.c
+++ b/arch/arm/mach-imx/mm-imx5.c
@@ -35,7 +35,7 @@ static void imx5_idle(void)
 	}
 	clk_enable(gpc_dvfs_clk);
 	mx5_cpu_lp_set(WAIT_UNCLOCKED_POWER_OFF);
-	if (tzic_enable_wake() != 0)
+	if (!tzic_enable_wake())
 		cpu_do_idle();
 	clk_disable(gpc_dvfs_clk);
 }
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index 3698a370d636..26aac363a064 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -86,9 +86,6 @@ static void __init halibut_init(void)
 static void __init halibut_fixup(struct tag *tags, char **cmdline,
 				 struct meminfo *mi)
 {
-	mi->nr_banks=1;
-	mi->bank[0].start = PHYS_OFFSET;
-	mi->bank[0].size = (101*1024*1024);
 }
 
 static void __init halibut_map_io(void)
diff --git a/arch/arm/mach-msm/board-trout-panel.c b/arch/arm/mach-msm/board-trout-panel.c
index 25105c1027fe..89bf6b426699 100644
--- a/arch/arm/mach-msm/board-trout-panel.c
+++ b/arch/arm/mach-msm/board-trout-panel.c
@@ -12,6 +12,7 @@
 
 #include <asm/io.h>
 #include <asm/mach-types.h>
+#include <asm/system_info.h>
 
 #include <mach/msm_fb.h>
 #include <mach/vreg.h>
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 5414f76ec0a9..d4060a37e23d 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/clkdev.h>
 
+#include <asm/system_info.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-msm/proc_comm.c b/arch/arm/mach-msm/proc_comm.c
index 67e701c7f183..9980dc736e7b 100644
--- a/arch/arm/mach-msm/proc_comm.c
+++ b/arch/arm/mach-msm/proc_comm.c
@@ -121,7 +121,7 @@ int msm_proc_comm(unsigned cmd, unsigned *data1, unsigned *data2)
  * and unknown state. This function should be called early to
  * wait on the ARM9.
  */
-void __init proc_comm_boot_wait(void)
+void __devinit proc_comm_boot_wait(void)
 {
 	void __iomem *base = MSM_SHARED_RAM_BASE;
  
diff --git a/arch/arm/mach-omap1/mux.c b/arch/arm/mach-omap1/mux.c
index 087dba0df47e..e9cc52d4cb28 100644
--- a/arch/arm/mach-omap1/mux.c
+++ b/arch/arm/mach-omap1/mux.c
@@ -27,6 +27,7 @@
 #include <linux/io.h>
 #include <linux/spinlock.h>
 
+#include <mach/hardware.h>
 
 #include <plat/mux.h>
 
diff --git a/arch/arm/mach-omap1/timer.c b/arch/arm/mach-omap1/timer.c
index 6e90665a7c47..fb202af01d0d 100644
--- a/arch/arm/mach-omap1/timer.c
+++ b/arch/arm/mach-omap1/timer.c
@@ -47,9 +47,9 @@ static int omap1_dm_timer_set_src(struct platform_device *pdev,
 	int n = (pdev->id - 1) << 1;
 	u32 l;
 
-	l = __raw_readl(MOD_CONF_CTRL_1) & ~(0x03 << n);
+	l = omap_readl(MOD_CONF_CTRL_1) & ~(0x03 << n);
 	l |= source << n;
-	__raw_writel(l, MOD_CONF_CTRL_1);
+	omap_writel(l, MOD_CONF_CTRL_1);
 
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index a39fc4bbd2b8..130ab00c09a2 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -20,6 +20,7 @@
 #include <linux/usb/otg.h>
 #include <linux/spi/spi.h>
 #include <linux/i2c/twl.h>
+#include <linux/mfd/twl6040.h>
 #include <linux/gpio_keys.h>
 #include <linux/regulator/machine.h>
 #include <linux/regulator/fixed.h>
@@ -560,7 +561,7 @@ static struct regulator_init_data sdp4430_vusim = {
 	},
 };
 
-static struct twl4030_codec_data twl6040_codec = {
+static struct twl6040_codec_data twl6040_codec = {
 	/* single-step ramp for headset and handsfree */
 	.hs_left_step	= 0x0f,
 	.hs_right_step	= 0x0f,
@@ -568,7 +569,7 @@ static struct twl4030_codec_data twl6040_codec = {
 	.hf_right_step	= 0x1d,
 };
 
-static struct twl4030_vibra_data twl6040_vibra = {
+static struct twl6040_vibra_data twl6040_vibra = {
 	.vibldrv_res = 8,
 	.vibrdrv_res = 3,
 	.viblmotor_res = 10,
@@ -577,16 +578,14 @@ static struct twl4030_vibra_data twl6040_vibra = {
 	.vddvibr_uV = 0,	/* fixed volt supply - VBAT */
 };
 
-static struct twl4030_audio_data twl6040_audio = {
+static struct twl6040_platform_data twl6040_data = {
 	.codec		= &twl6040_codec,
 	.vibra		= &twl6040_vibra,
 	.audpwron_gpio	= 127,
-	.naudint_irq	= OMAP44XX_IRQ_SYS_2N,
 	.irq_base	= TWL6040_CODEC_IRQ_BASE,
 };
 
 static struct twl4030_platform_data sdp4430_twldata = {
-	.audio		= &twl6040_audio,
 	/* Regulators */
 	.vusim		= &sdp4430_vusim,
 	.vaux1		= &sdp4430_vaux1,
@@ -617,7 +616,8 @@ static int __init omap4_i2c_init(void)
 			TWL_COMMON_REGULATOR_VCXIO |
 			TWL_COMMON_REGULATOR_VUSB |
 			TWL_COMMON_REGULATOR_CLK32KG);
-	omap4_pmic_init("twl6030", &sdp4430_twldata);
+	omap4_pmic_init("twl6030", &sdp4430_twldata,
+			&twl6040_data, OMAP44XX_IRQ_SYS_2N);
 	omap_register_i2c_bus(2, 400, NULL, 0);
 	omap_register_i2c_bus(3, 400, sdp4430_i2c_3_boardinfo,
 				ARRAY_SIZE(sdp4430_i2c_3_boardinfo));
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 74e1687b5170..098d183a0086 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -137,7 +137,7 @@ static struct twl4030_platform_data sdp4430_twldata = {
 
 static void __init omap4_i2c_init(void)
 {
-	omap4_pmic_init("twl6030", &sdp4430_twldata);
+	omap4_pmic_init("twl6030", &sdp4430_twldata, NULL, 0);
 }
 
 static void __init omap4_init(void)
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index d8c0e89f0126..1b782ba53433 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -25,6 +25,7 @@
 #include <linux/gpio.h>
 #include <linux/usb/otg.h>
 #include <linux/i2c/twl.h>
+#include <linux/mfd/twl6040.h>
 #include <linux/regulator/machine.h>
 #include <linux/regulator/fixed.h>
 #include <linux/wl12xx.h>
@@ -284,7 +285,7 @@ static int __init omap4_twl6030_hsmmc_init(struct omap2_hsmmc_info *controllers)
 	return 0;
 }
 
-static struct twl4030_codec_data twl6040_codec = {
+static struct twl6040_codec_data twl6040_codec = {
 	/* single-step ramp for headset and handsfree */
 	.hs_left_step	= 0x0f,
 	.hs_right_step	= 0x0f,
@@ -292,17 +293,14 @@ static struct twl4030_codec_data twl6040_codec = {
 	.hf_right_step	= 0x1d,
 };
 
-static struct twl4030_audio_data twl6040_audio = {
+static struct twl6040_platform_data twl6040_data = {
 	.codec		= &twl6040_codec,
 	.audpwron_gpio	= 127,
-	.naudint_irq	= OMAP44XX_IRQ_SYS_2N,
 	.irq_base	= TWL6040_CODEC_IRQ_BASE,
 };
 
 /* Panda board uses the common PMIC configuration */
-static struct twl4030_platform_data omap4_panda_twldata = {
-	.audio		= &twl6040_audio,
-};
+static struct twl4030_platform_data omap4_panda_twldata;
 
 /*
  * Display monitor features are burnt in their EEPROM as EDID data. The EEPROM
@@ -326,7 +324,8 @@ static int __init omap4_panda_i2c_init(void)
 			TWL_COMMON_REGULATOR_VCXIO |
 			TWL_COMMON_REGULATOR_VUSB |
 			TWL_COMMON_REGULATOR_CLK32KG);
-	omap4_pmic_init("twl6030", &omap4_panda_twldata);
+	omap4_pmic_init("twl6030", &omap4_panda_twldata,
+			&twl6040_data, OMAP44XX_IRQ_SYS_2N);
 	omap_register_i2c_bus(2, 400, NULL, 0);
 	/*
 	 * Bus 3 is attached to the DVI port where devices like the pico DLP
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index 7072e0d651b1..3d9d746b221a 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -165,83 +165,3 @@ int omap2_select_table_rate(struct clk *clk, unsigned long rate)
 
 	return 0;
 }
-
-#ifdef CONFIG_CPU_FREQ
-/*
- * Walk PRCM rate table and fillout cpufreq freq_table
- * XXX This should be replaced by an OPP layer in the near future
- */
-static struct cpufreq_frequency_table *freq_table;
-
-void omap2_clk_init_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	const struct prcm_config *prcm;
-	int i = 0;
-	int tbl_sz = 0;
-
-	if (!cpu_is_omap24xx())
-		return;
-
-	for (prcm = rate_table; prcm->mpu_speed; prcm++) {
-		if (!(prcm->flags & cpu_mask))
-			continue;
-		if (prcm->xtal_speed != sclk->rate)
-			continue;
-
-		/* don't put bypass rates in table */
-		if (prcm->dpll_speed == prcm->xtal_speed)
-			continue;
-
-		tbl_sz++;
-	}
-
-	/*
-	 * XXX Ensure that we're doing what CPUFreq expects for this error
-	 * case and the following one
-	 */
-	if (tbl_sz == 0) {
-		pr_warning("%s: no matching entries in rate_table\n",
-			   __func__);
-		return;
-	}
-
-	/* Include the CPUFREQ_TABLE_END terminator entry */
-	tbl_sz++;
-
-	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) * tbl_sz,
-			     GFP_ATOMIC);
-	if (!freq_table) {
-		pr_err("%s: could not kzalloc frequency table\n", __func__);
-		return;
-	}
-
-	for (prcm = rate_table; prcm->mpu_speed; prcm++) {
-		if (!(prcm->flags & cpu_mask))
-			continue;
-		if (prcm->xtal_speed != sclk->rate)
-			continue;
-
-		/* don't put bypass rates in table */
-		if (prcm->dpll_speed == prcm->xtal_speed)
-			continue;
-
-		freq_table[i].index = i;
-		freq_table[i].frequency = prcm->mpu_speed / 1000;
-		i++;
-	}
-
-	freq_table[i].index = i;
-	freq_table[i].frequency = CPUFREQ_TABLE_END;
-
-	*table = &freq_table[0];
-}
-
-void omap2_clk_exit_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	if (!cpu_is_omap24xx())
-		return;
-
-	kfree(freq_table);
-}
-
-#endif
diff --git a/arch/arm/mach-omap2/clock.c b/arch/arm/mach-omap2/clock.c
index f57ed5baeccf..d9f4931513f9 100644
--- a/arch/arm/mach-omap2/clock.c
+++ b/arch/arm/mach-omap2/clock.c
@@ -536,10 +536,5 @@ struct clk_functions omap2_clk_functions = {
 	.clk_set_rate		= omap2_clk_set_rate,
 	.clk_set_parent		= omap2_clk_set_parent,
 	.clk_disable_unused	= omap2_clk_disable_unused,
-#ifdef CONFIG_CPU_FREQ
-	/* These will be removed when the OPP code is integrated */
-	.clk_init_cpufreq_table	= omap2_clk_init_cpufreq_table,
-	.clk_exit_cpufreq_table	= omap2_clk_exit_cpufreq_table,
-#endif
 };
 
diff --git a/arch/arm/mach-omap2/clock.h b/arch/arm/mach-omap2/clock.h
index b8c2a686481c..a1bb23a23351 100644
--- a/arch/arm/mach-omap2/clock.h
+++ b/arch/arm/mach-omap2/clock.h
@@ -146,14 +146,6 @@ extern const struct clksel_rate gpt_sys_rates[];
 extern const struct clksel_rate gfx_l3_rates[];
 extern const struct clksel_rate dsp_ick_rates[];
 
-#if defined(CONFIG_ARCH_OMAP2) && defined(CONFIG_CPU_FREQ)
-extern void omap2_clk_init_cpufreq_table(struct cpufreq_frequency_table **table);
-extern void omap2_clk_exit_cpufreq_table(struct cpufreq_frequency_table **table);
-#else
-#define omap2_clk_init_cpufreq_table	0
-#define omap2_clk_exit_cpufreq_table	0
-#endif
-
 extern const struct clkops clkops_omap2_iclk_dflt_wait;
 extern const struct clkops clkops_omap2_iclk_dflt;
 extern const struct clkops clkops_omap2_iclk_idle_only;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 2c27fdb61e66..7144ae651d3d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1422,6 +1422,9 @@ static int _ocp_softreset(struct omap_hwmod *oh)
 		goto dis_opt_clks;
 	_write_sysconfig(v, oh);
 
+	if (oh->class->sysc->srst_udelay)
+		udelay(oh->class->sysc->srst_udelay);
+
 	if (oh->class->sysc->sysc_flags & SYSS_HAS_RESET_STATUS)
 		omap_test_timeout((omap_hwmod_read(oh,
 						    oh->class->sysc->syss_offs)
@@ -1903,10 +1906,20 @@ void omap_hwmod_write(u32 v, struct omap_hwmod *oh, u16 reg_offs)
  */
 int omap_hwmod_softreset(struct omap_hwmod *oh)
 {
-	if (!oh)
+	u32 v;
+	int ret;
+
+	if (!oh || !(oh->_sysc_cache))
 		return -EINVAL;
 
-	return _ocp_softreset(oh);
+	v = oh->_sysc_cache;
+	ret = _set_softreset(oh, &v);
+	if (ret)
+		goto error;
+	_write_sysconfig(v, oh);
+
+error:
+	return ret;
 }
 
 /**
diff --git a/arch/arm/mach-omap2/omap_hwmod_2420_data.c b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
index a5409ce3f323..a6bde34e443a 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2420_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
@@ -1000,7 +1000,6 @@ static struct omap_hwmod_ocp_if omap2420_l4_core__dss_venc = {
 			.flags	= OMAP_FIREWALL_L4,
 		}
 	},
-	.flags		= OCPIF_SWSUP_IDLE,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index c4f56cb60d7d..04a3885f4475 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -1049,7 +1049,6 @@ static struct omap_hwmod_ocp_if omap2430_l4_core__dss_venc = {
 	.slave		= &omap2430_dss_venc_hwmod,
 	.clk		= "dss_ick",
 	.addr		= omap2_dss_venc_addrs,
-	.flags		= OCPIF_SWSUP_IDLE,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 34b9766d1d23..db86ce90c69f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1676,7 +1676,6 @@ static struct omap_hwmod_ocp_if omap3xxx_l4_core__dss_venc = {
 			.flags	= OMAP_FIREWALL_L4,
 		}
 	},
-	.flags		= OCPIF_SWSUP_IDLE,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index cc9bd106a854..6abc75753e42 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2594,6 +2594,15 @@ static struct omap_hwmod omap44xx_ipu_hwmod = {
 static struct omap_hwmod_class_sysconfig omap44xx_iss_sysc = {
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
+	/*
+	 * ISS needs 100 OCP clk cycles delay after a softreset before
+	 * accessing sysconfig again.
+	 * The lowest frequency at the moment for L3 bus is 100 MHz, so
+	 * 1usec delay is needed. Add an x2 margin to be safe (2 usecs).
+	 *
+	 * TODO: Indicate errata when available.
+	 */
+	.srst_udelay	= 2,
 	.sysc_flags	= (SYSC_HAS_MIDLEMODE | SYSC_HAS_RESET_STATUS |
 			   SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
 	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
diff --git a/arch/arm/mach-omap2/serial.c b/arch/arm/mach-omap2/serial.c
index 0cdd359a128e..9fc2f44188cb 100644
--- a/arch/arm/mach-omap2/serial.c
+++ b/arch/arm/mach-omap2/serial.c
@@ -108,8 +108,14 @@ static void omap_uart_set_noidle(struct platform_device *pdev)
 static void omap_uart_set_smartidle(struct platform_device *pdev)
 {
 	struct omap_device *od = to_omap_device(pdev);
+	u8 idlemode;
 
-	omap_hwmod_set_slave_idlemode(od->hwmods[0], HWMOD_IDLEMODE_SMART);
+	if (od->hwmods[0]->class->sysc->idlemodes & SIDLE_SMART_WKUP)
+		idlemode = HWMOD_IDLEMODE_SMART_WKUP;
+	else
+		idlemode = HWMOD_IDLEMODE_SMART;
+
+	omap_hwmod_set_slave_idlemode(od->hwmods[0], idlemode);
 }
 
 #else
@@ -120,124 +126,8 @@ static void omap_uart_set_smartidle(struct platform_device *pdev) {}
 #endif /* CONFIG_PM */
 
 #ifdef CONFIG_OMAP_MUX
-static struct omap_device_pad default_uart1_pads[] __initdata = {
-	{
-		.name	= "uart1_cts.uart1_cts",
-		.enable	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart1_rts.uart1_rts",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart1_tx.uart1_tx",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart1_rx.uart1_rx",
-		.flags	= OMAP_DEVICE_PAD_REMUX | OMAP_DEVICE_PAD_WAKEUP,
-		.enable	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-		.idle	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-	},
-};
-
-static struct omap_device_pad default_uart2_pads[] __initdata = {
-	{
-		.name	= "uart2_cts.uart2_cts",
-		.enable	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart2_rts.uart2_rts",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart2_tx.uart2_tx",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart2_rx.uart2_rx",
-		.flags	= OMAP_DEVICE_PAD_REMUX | OMAP_DEVICE_PAD_WAKEUP,
-		.enable	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-		.idle	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-	},
-};
-
-static struct omap_device_pad default_uart3_pads[] __initdata = {
-	{
-		.name	= "uart3_cts_rctx.uart3_cts_rctx",
-		.enable	= OMAP_PIN_INPUT_PULLUP | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart3_rts_sd.uart3_rts_sd",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart3_tx_irtx.uart3_tx_irtx",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart3_rx_irrx.uart3_rx_irrx",
-		.flags	= OMAP_DEVICE_PAD_REMUX | OMAP_DEVICE_PAD_WAKEUP,
-		.enable	= OMAP_PIN_INPUT | OMAP_MUX_MODE0,
-		.idle	= OMAP_PIN_INPUT | OMAP_MUX_MODE0,
-	},
-};
-
-static struct omap_device_pad default_omap36xx_uart4_pads[] __initdata = {
-	{
-		.name   = "gpmc_wait2.uart4_tx",
-		.enable = OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "gpmc_wait3.uart4_rx",
-		.flags	= OMAP_DEVICE_PAD_REMUX | OMAP_DEVICE_PAD_WAKEUP,
-		.enable	= OMAP_PIN_INPUT | OMAP_MUX_MODE2,
-		.idle	= OMAP_PIN_INPUT | OMAP_MUX_MODE2,
-	},
-};
-
-static struct omap_device_pad default_omap4_uart4_pads[] __initdata = {
-	{
-		.name	= "uart4_tx.uart4_tx",
-		.enable	= OMAP_PIN_OUTPUT | OMAP_MUX_MODE0,
-	},
-	{
-		.name	= "uart4_rx.uart4_rx",
-		.flags	= OMAP_DEVICE_PAD_REMUX | OMAP_DEVICE_PAD_WAKEUP,
-		.enable	= OMAP_PIN_INPUT | OMAP_MUX_MODE0,
-		.idle	= OMAP_PIN_INPUT | OMAP_MUX_MODE0,
-	},
-};
-
 static void omap_serial_fill_default_pads(struct omap_board_data *bdata)
 {
-	switch (bdata->id) {
-	case 0:
-		bdata->pads = default_uart1_pads;
-		bdata->pads_cnt = ARRAY_SIZE(default_uart1_pads);
-		break;
-	case 1:
-		bdata->pads = default_uart2_pads;
-		bdata->pads_cnt = ARRAY_SIZE(default_uart2_pads);
-		break;
-	case 2:
-		bdata->pads = default_uart3_pads;
-		bdata->pads_cnt = ARRAY_SIZE(default_uart3_pads);
-		break;
-	case 3:
-		if (cpu_is_omap44xx()) {
-			bdata->pads = default_omap4_uart4_pads;
-			bdata->pads_cnt =
-				ARRAY_SIZE(default_omap4_uart4_pads);
-		} else if (cpu_is_omap3630()) {
-			bdata->pads = default_omap36xx_uart4_pads;
-			bdata->pads_cnt =
-				ARRAY_SIZE(default_omap36xx_uart4_pads);
-		}
-		break;
-	default:
-		break;
-	}
 }
 #else
 static void omap_serial_fill_default_pads(struct omap_board_data *bdata) {}
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index 4b57757bf9d1..7a7b89304c48 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -37,6 +37,16 @@ static struct i2c_board_info __initdata pmic_i2c_board_info = {
 	.flags		= I2C_CLIENT_WAKE,
 };
 
+static struct i2c_board_info __initdata omap4_i2c1_board_info[] = {
+	{
+		.addr		= 0x48,
+		.flags		= I2C_CLIENT_WAKE,
+	},
+	{
+		I2C_BOARD_INFO("twl6040", 0x4b),
+	},
+};
+
 void __init omap_pmic_init(int bus, u32 clkrate,
 			   const char *pmic_type, int pmic_irq,
 			   struct twl4030_platform_data *pmic_data)
@@ -49,14 +59,31 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
+void __init omap4_pmic_init(const char *pmic_type,
+		    struct twl4030_platform_data *pmic_data,
+		    struct twl6040_platform_data *twl6040_data, int twl6040_irq)
+{
+	/* PMIC part*/
+	strncpy(omap4_i2c1_board_info[0].type, pmic_type,
+		sizeof(omap4_i2c1_board_info[0].type));
+	omap4_i2c1_board_info[0].irq = OMAP44XX_IRQ_SYS_1N;
+	omap4_i2c1_board_info[0].platform_data = pmic_data;
+
+	/* TWL6040 audio IC part */
+	omap4_i2c1_board_info[1].irq = twl6040_irq;
+	omap4_i2c1_board_info[1].platform_data = twl6040_data;
+
+	omap_register_i2c_bus(1, 400, omap4_i2c1_board_info, 2);
+
+}
+
 void __init omap_pmic_late_init(void)
 {
 	/* Init the OMAP TWL parameters (if PMIC has been registerd) */
-	if (!pmic_i2c_board_info.irq)
-		return;
-
-	omap3_twl_init();
-	omap4_twl_init();
+	if (pmic_i2c_board_info.irq)
+		omap3_twl_init();
+	if (omap4_i2c1_board_info[0].irq)
+		omap4_twl_init();
 }
 
 #if defined(CONFIG_ARCH_OMAP3)
diff --git a/arch/arm/mach-omap2/twl-common.h b/arch/arm/mach-omap2/twl-common.h
index 275dde8cb27a..09627483a57f 100644
--- a/arch/arm/mach-omap2/twl-common.h
+++ b/arch/arm/mach-omap2/twl-common.h
@@ -29,6 +29,7 @@
 
 
 struct twl4030_platform_data;
+struct twl6040_platform_data;
 
 void omap_pmic_init(int bus, u32 clkrate, const char *pmic_type, int pmic_irq,
 		    struct twl4030_platform_data *pmic_data);
@@ -46,12 +47,9 @@ static inline void omap3_pmic_init(const char *pmic_type,
 	omap_pmic_init(1, 2600, pmic_type, INT_34XX_SYS_NIRQ, pmic_data);
 }
 
-static inline void omap4_pmic_init(const char *pmic_type,
-				   struct twl4030_platform_data *pmic_data)
-{
-	/* Phoenix Audio IC needs I2C1 to start with 400 KHz or less */
-	omap_pmic_init(1, 400, pmic_type, OMAP44XX_IRQ_SYS_1N, pmic_data);
-}
+void omap4_pmic_init(const char *pmic_type,
+		    struct twl4030_platform_data *pmic_data,
+		    struct twl6040_platform_data *audio_data, int twl6040_irq);
 
 void omap3_pmic_get_config(struct twl4030_platform_data *pmic_data,
 			   u32 pdata_flags, u32 regulators_flags);
diff --git a/arch/arm/mach-s5pv210/dma.c b/arch/arm/mach-s5pv210/dma.c
index 86ce62f66190..b8337e248b09 100644
--- a/arch/arm/mach-s5pv210/dma.c
+++ b/arch/arm/mach-s5pv210/dma.c
@@ -33,8 +33,6 @@
 #include <mach/irqs.h>
 #include <mach/dma.h>
 
-static u64 dma_dmamask = DMA_BIT_MASK(32);
-
 static u8 pdma0_peri[] = {
 	DMACH_UART0_RX,
 	DMACH_UART0_TX,
diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c
index a9ea64e0da0d..48d018f2332b 100644
--- a/arch/arm/mach-s5pv210/mach-aquila.c
+++ b/arch/arm/mach-s5pv210/mach-aquila.c
@@ -484,8 +484,8 @@ static struct wm8994_pdata wm8994_platform_data = {
 	.gpio_defaults[8] = 0x0100,
 	.gpio_defaults[9] = 0x0100,
 	.gpio_defaults[10] = 0x0100,
-	.ldo[0]	= { S5PV210_MP03(6), NULL, &wm8994_ldo1_data },	/* XM0FRNB_2 */
-	.ldo[1]	= { 0, NULL, &wm8994_ldo2_data },
+	.ldo[0]	= { S5PV210_MP03(6), &wm8994_ldo1_data },	/* XM0FRNB_2 */
+	.ldo[1]	= { 0, &wm8994_ldo2_data },
 };
 
 /* GPIO I2C PMIC */
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index 2cf5ed75f390..a8933de3d627 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -674,8 +674,8 @@ static struct wm8994_pdata wm8994_platform_data = {
 	.gpio_defaults[8] = 0x0100,
 	.gpio_defaults[9] = 0x0100,
 	.gpio_defaults[10] = 0x0100,
-	.ldo[0]	= { S5PV210_MP03(6), NULL, &wm8994_ldo1_data },	/* XM0FRNB_2 */
-	.ldo[1]	= { 0, NULL, &wm8994_ldo2_data },
+	.ldo[0]	= { S5PV210_MP03(6), &wm8994_ldo1_data },	/* XM0FRNB_2 */
+	.ldo[1]	= { 0, &wm8994_ldo2_data },
 };
 
 /* GPIO I2C PMIC */
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 880d02ec89d4..ef7099eea0f2 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -17,6 +17,7 @@ config UX500_SOC_DB5500
 config UX500_SOC_DB8500
 	bool
 	select MFD_DB8500_PRCMU
+	select REGULATOR
 	select REGULATOR_DB8500_PRCMU
 	select CPU_FREQ_TABLE if CPU_FREQ
 
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index d2058ef8345f..eff5842f6232 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -99,7 +99,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 */
 	write_pen_release(cpu_logical_map(cpu));
 
-	gic_raise_softirq(cpumask_of(cpu), 1);
+	smp_send_reschedule(cpu);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7edef9121632..7c8a7d8467bf 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -723,7 +723,7 @@ config CPU_HIGH_VECTOR
 	bool "Select the High exception vector"
 	help
 	  Say Y here to select high exception vector(0xFFFF0000~).
-	  The exception vector can be vary depending on the platform
+	  The exception vector can vary depending on the platform
 	  design in nommu mode. If your platform needs to select
 	  high exception vector, say Y.
 	  Otherwise or if you are unsure, say N, and the low exception
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 9055b5a84ec5..f07467533365 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -320,7 +320,7 @@ retry:
 	 */
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+	if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) {
 		if (fault & VM_FAULT_MAJOR) {
 			tsk->maj_flt++;
 			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 6486d2f253cd..d51225f90ae2 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -13,6 +13,7 @@
 #include <asm/sections.h>
 #include <asm/page.h>
 #include <asm/setup.h>
+#include <asm/traps.h>
 #include <asm/mach/arch.h>
 
 #include "mm.h"
@@ -39,6 +40,7 @@ void __init sanity_check_meminfo(void)
  */
 void __init paging_init(struct machine_desc *mdesc)
 {
+	early_trap_init((void *)CONFIG_VECTORS_BASE);
 	bootmem_init();
 }
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index f1c8486f7501..c2e2b66f72b5 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -255,6 +255,18 @@ __v7_setup:
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
+#ifndef CONFIG_ARM_THUMBEE
+	mrc	p15, 0, r0, c0, c1, 0		@ read ID_PFR0 for ThumbEE
+	and	r0, r0, #(0xf << 12)		@ ThumbEE enabled field
+	teq	r0, #(1 << 12)			@ check if ThumbEE is present
+	bne	1f
+	mov	r5, #0
+	mcr	p14, 6, r5, c1, c0, 0		@ Initialize TEEHBR to 0
+	mrc	p14, 6, r0, c0, c0, 0		@ load TEECR
+	orr	r0, r0, #1			@ set the 1st bit in order to
+	mcr	p14, 6, r0, c0, c0, 0		@ stop userspace TEEHBR access
+1:
+#endif
 	adr	r5, v7_crval
 	ldmia	r5, {r5, r6}
 #ifdef CONFIG_CPU_ENDIAN_BE8
diff --git a/arch/arm/plat-omap/clock.c b/arch/arm/plat-omap/clock.c
index 8506cbb7fea4..62ec5c452792 100644
--- a/arch/arm/plat-omap/clock.c
+++ b/arch/arm/plat-omap/clock.c
@@ -398,32 +398,6 @@ struct clk dummy_ck = {
 	.ops	= &clkops_null,
 };
 
-#ifdef CONFIG_CPU_FREQ
-void clk_init_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	unsigned long flags;
-
-	if (!arch_clock || !arch_clock->clk_init_cpufreq_table)
-		return;
-
-	spin_lock_irqsave(&clockfw_lock, flags);
-	arch_clock->clk_init_cpufreq_table(table);
-	spin_unlock_irqrestore(&clockfw_lock, flags);
-}
-
-void clk_exit_cpufreq_table(struct cpufreq_frequency_table **table)
-{
-	unsigned long flags;
-
-	if (!arch_clock || !arch_clock->clk_exit_cpufreq_table)
-		return;
-
-	spin_lock_irqsave(&clockfw_lock, flags);
-	arch_clock->clk_exit_cpufreq_table(table);
-	spin_unlock_irqrestore(&clockfw_lock, flags);
-}
-#endif
-
 /*
  *
  */
diff --git a/arch/arm/plat-omap/include/plat/clock.h b/arch/arm/plat-omap/include/plat/clock.h
index 240a7b9fd946..d0ef57c1d71b 100644
--- a/arch/arm/plat-omap/include/plat/clock.h
+++ b/arch/arm/plat-omap/include/plat/clock.h
@@ -272,8 +272,6 @@ struct clk {
 #endif
 };
 
-struct cpufreq_frequency_table;
-
 struct clk_functions {
 	int		(*clk_enable)(struct clk *clk);
 	void		(*clk_disable)(struct clk *clk);
@@ -283,10 +281,6 @@ struct clk_functions {
 	void		(*clk_allow_idle)(struct clk *clk);
 	void		(*clk_deny_idle)(struct clk *clk);
 	void		(*clk_disable_unused)(struct clk *clk);
-#ifdef CONFIG_CPU_FREQ
-	void		(*clk_init_cpufreq_table)(struct cpufreq_frequency_table **);
-	void		(*clk_exit_cpufreq_table)(struct cpufreq_frequency_table **);
-#endif
 };
 
 extern int mpurate;
@@ -301,10 +295,6 @@ extern void recalculate_root_clocks(void);
 extern unsigned long followparent_recalc(struct clk *clk);
 extern void clk_enable_init_clocks(void);
 unsigned long omap_fixed_divisor_recalc(struct clk *clk);
-#ifdef CONFIG_CPU_FREQ
-extern void clk_init_cpufreq_table(struct cpufreq_frequency_table **table);
-extern void clk_exit_cpufreq_table(struct cpufreq_frequency_table **table);
-#endif
 extern struct clk *omap_clk_get_by_name(const char *name);
 extern int omap_clk_enable_autoidle_all(void);
 extern int omap_clk_disable_autoidle_all(void);
diff --git a/arch/arm/plat-omap/include/plat/omap_hwmod.h b/arch/arm/plat-omap/include/plat/omap_hwmod.h
index 8070145ccb98..3f26db4ee8e6 100644
--- a/arch/arm/plat-omap/include/plat/omap_hwmod.h
+++ b/arch/arm/plat-omap/include/plat/omap_hwmod.h
@@ -305,6 +305,7 @@ struct omap_hwmod_sysc_fields {
  * @rev_offs: IP block revision register offset (from module base addr)
  * @sysc_offs: OCP_SYSCONFIG register offset (from module base addr)
  * @syss_offs: OCP_SYSSTATUS register offset (from module base addr)
+ * @srst_udelay: Delay needed after doing a softreset in usecs
  * @idlemodes: One or more of {SIDLE,MSTANDBY}_{OFF,FORCE,SMART}
  * @sysc_flags: SYS{C,S}_HAS* flags indicating SYSCONFIG bits supported
  * @clockact: the default value of the module CLOCKACTIVITY bits
@@ -330,9 +331,10 @@ struct omap_hwmod_class_sysconfig {
 	u16 sysc_offs;
 	u16 syss_offs;
 	u16 sysc_flags;
+	struct omap_hwmod_sysc_fields *sysc_fields;
+	u8 srst_udelay;
 	u8 idlemodes;
 	u8 clockact;
-	struct omap_hwmod_sysc_fields *sysc_fields;
 };
 
 /**
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index eec98afa0f83..f9a8c5341ee9 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -348,7 +348,6 @@ u32 omap3_configure_core_dpll(u32 m2, u32 unlock_dll, u32 f, u32 inc,
 			sdrc_actim_ctrl_b_1, sdrc_mr_1);
 }
 
-#ifdef CONFIG_PM
 void omap3_sram_restore_context(void)
 {
 	omap_sram_ceil = omap_sram_base + omap_sram_size;
@@ -358,17 +357,18 @@ void omap3_sram_restore_context(void)
 			       omap3_sram_configure_core_dpll_sz);
 	omap_push_sram_idle();
 }
-#endif /* CONFIG_PM */
-
-#endif /* CONFIG_ARCH_OMAP3 */
 
 static inline int omap34xx_sram_init(void)
 {
-#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
 	omap3_sram_restore_context();
-#endif
 	return 0;
 }
+#else
+static inline int omap34xx_sram_init(void)
+{
+	return 0;
+}
+#endif /* CONFIG_ARCH_OMAP3 */
 
 static inline int am33xx_sram_init(void)
 {
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 71553f410016..a0ffc77da809 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -302,6 +302,7 @@ comment "Power management"
 config SAMSUNG_PM_DEBUG
 	bool "S3C2410 PM Suspend debug"
 	depends on PM
+	select DEBUG_LL
 	help
 	  Say Y here if you want verbose debugging from the PM Suspend and
 	  Resume code. See <file:Documentation/arm/Samsung-S3C24XX/Suspend.txt>
diff --git a/arch/c6x/include/asm/irq.h b/arch/c6x/include/asm/irq.h
index f13b78d5e1ca..ab4577f93d96 100644
--- a/arch/c6x/include/asm/irq.h
+++ b/arch/c6x/include/asm/irq.h
@@ -42,10 +42,6 @@
 /* This number is used when no interrupt has been assigned */
 #define NO_IRQ		0
 
-struct irq_data;
-extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
-extern irq_hw_number_t virq_to_hw(unsigned int virq);
-
 extern void __init init_pic_c64xplus(void);
 
 extern void init_IRQ(void);
diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c
index 65b8ddf54b44..c90fb5e82ad7 100644
--- a/arch/c6x/kernel/irq.c
+++ b/arch/c6x/kernel/irq.c
@@ -130,16 +130,3 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
 	return 0;
 }
-
-irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-EXPORT_SYMBOL_GPL(irqd_to_hwirq);
-
-irq_hw_number_t virq_to_hw(unsigned int virq)
-{
-	struct irq_data *irq_data = irq_get_irq_data(virq);
-	return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
-}
-EXPORT_SYMBOL_GPL(virq_to_hw);
diff --git a/arch/ia64/include/asm/cmpxchg.h b/arch/ia64/include/asm/cmpxchg.h
index 4c96187e2049..4f37dbbb8640 100644
--- a/arch/ia64/include/asm/cmpxchg.h
+++ b/arch/ia64/include/asm/cmpxchg.h
@@ -1 +1,147 @@
-#include <asm/intrinsics.h>
+#ifndef _ASM_IA64_CMPXCHG_H
+#define _ASM_IA64_CMPXCHG_H
+
+/*
+ * Compare/Exchange, forked from asm/intrinsics.h
+ * which was:
+ *
+ *	Copyright (C) 2002-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+/* include compiler specific intrinsics */
+#include <asm/ia64regs.h>
+#ifdef __INTEL_COMPILER
+# include <asm/intel_intrin.h>
+#else
+# include <asm/gcc_intrin.h>
+#endif
+
+/*
+ * This function doesn't exist, so you'll get a linker error if
+ * something tries to do an invalid xchg().
+ */
+extern void ia64_xchg_called_with_bad_pointer(void);
+
+#define __xchg(x, ptr, size)						\
+({									\
+	unsigned long __xchg_result;					\
+									\
+	switch (size) {							\
+	case 1:								\
+		__xchg_result = ia64_xchg1((__u8 *)ptr, x);		\
+		break;							\
+									\
+	case 2:								\
+		__xchg_result = ia64_xchg2((__u16 *)ptr, x);		\
+		break;							\
+									\
+	case 4:								\
+		__xchg_result = ia64_xchg4((__u32 *)ptr, x);		\
+		break;							\
+									\
+	case 8:								\
+		__xchg_result = ia64_xchg8((__u64 *)ptr, x);		\
+		break;							\
+	default:							\
+		ia64_xchg_called_with_bad_pointer();			\
+	}								\
+	__xchg_result;							\
+})
+
+#define xchg(ptr, x)							\
+((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr))))
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern long ia64_cmpxchg_called_with_bad_pointer(void);
+
+#define ia64_cmpxchg(sem, ptr, old, new, size)				\
+({									\
+	__u64 _o_, _r_;							\
+									\
+	switch (size) {							\
+	case 1:								\
+		_o_ = (__u8) (long) (old);				\
+		break;							\
+	case 2:								\
+		_o_ = (__u16) (long) (old);				\
+		break;							\
+	case 4:								\
+		_o_ = (__u32) (long) (old);				\
+		break;							\
+	case 8:								\
+		_o_ = (__u64) (long) (old);				\
+		break;							\
+	default:							\
+		break;							\
+	}								\
+	switch (size) {							\
+	case 1:								\
+		_r_ = ia64_cmpxchg1_##sem((__u8 *) ptr, new, _o_);	\
+		break;							\
+									\
+	case 2:								\
+		_r_ = ia64_cmpxchg2_##sem((__u16 *) ptr, new, _o_);	\
+		break;							\
+									\
+	case 4:								\
+		_r_ = ia64_cmpxchg4_##sem((__u32 *) ptr, new, _o_);	\
+		break;							\
+									\
+	case 8:								\
+		_r_ = ia64_cmpxchg8_##sem((__u64 *) ptr, new, _o_);	\
+		break;							\
+									\
+	default:							\
+		_r_ = ia64_cmpxchg_called_with_bad_pointer();		\
+		break;							\
+	}								\
+	(__typeof__(old)) _r_;						\
+})
+
+#define cmpxchg_acq(ptr, o, n)	\
+	ia64_cmpxchg(acq, (ptr), (o), (n), sizeof(*(ptr)))
+#define cmpxchg_rel(ptr, o, n)	\
+	ia64_cmpxchg(rel, (ptr), (o), (n), sizeof(*(ptr)))
+
+/* for compatibility with other platforms: */
+#define cmpxchg(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
+
+#define cmpxchg_local		cmpxchg
+#define cmpxchg64_local		cmpxchg64
+
+#ifdef CONFIG_IA64_DEBUG_CMPXCHG
+# define CMPXCHG_BUGCHECK_DECL	int _cmpxchg_bugcheck_count = 128;
+# define CMPXCHG_BUGCHECK(v)						\
+do {									\
+	if (_cmpxchg_bugcheck_count-- <= 0) {				\
+		void *ip;						\
+		extern int printk(const char *fmt, ...);		\
+		ip = (void *) ia64_getreg(_IA64_REG_IP);		\
+		printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));\
+		break;							\
+	}								\
+} while (0)
+#else /* !CONFIG_IA64_DEBUG_CMPXCHG */
+# define CMPXCHG_BUGCHECK_DECL
+# define CMPXCHG_BUGCHECK(v)
+#endif /* !CONFIG_IA64_DEBUG_CMPXCHG */
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_IA64_CMPXCHG_H */
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index 0ab82cc2dc8f..d2bf1fd5e44f 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -106,15 +106,16 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	{
-		register unsigned long r8 __asm ("r8") = 0;
+		register unsigned long r8 __asm ("r8");
 		unsigned long prev;
 		__asm__ __volatile__(
 			"	mf;;					\n"
-			"	mov ar.ccv=%3;;				\n"
-			"[1:]	cmpxchg4.acq %0=[%1],%2,ar.ccv		\n"
+			"	mov %0=r0				\n"
+			"	mov ar.ccv=%4;;				\n"
+			"[1:]	cmpxchg4.acq %1=[%2],%3,ar.ccv		\n"
 			"	.xdata4 \"__ex_table\", 1b-., 2f-.	\n"
 			"[2:]"
-			: "=r" (prev)
+			: "=r" (r8), "=r" (prev)
 			: "r" (uaddr), "r" (newval),
 			  "rO" ((long) (unsigned) oldval)
 			: "memory");
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index e4076b511829..d129e367e764 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -18,6 +18,7 @@
 #else
 # include <asm/gcc_intrin.h>
 #endif
+#include <asm/cmpxchg.h>
 
 #define ia64_native_get_psr_i()	(ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I)
 
@@ -81,119 +82,6 @@ extern unsigned long __bad_increment_for_ia64_fetch_and_add (void);
 
 #define ia64_fetch_and_add(i,v)	(ia64_fetchadd(i, v, rel) + (i)) /* return new value */
 
-/*
- * This function doesn't exist, so you'll get a linker error if
- * something tries to do an invalid xchg().
- */
-extern void ia64_xchg_called_with_bad_pointer (void);
-
-#define __xchg(x,ptr,size)						\
-({									\
-	unsigned long __xchg_result;					\
-									\
-	switch (size) {							\
-	      case 1:							\
-		__xchg_result = ia64_xchg1((__u8 *)ptr, x);		\
-		break;							\
-									\
-	      case 2:							\
-		__xchg_result = ia64_xchg2((__u16 *)ptr, x);		\
-		break;							\
-									\
-	      case 4:							\
-		__xchg_result = ia64_xchg4((__u32 *)ptr, x);		\
-		break;							\
-									\
-	      case 8:							\
-		__xchg_result = ia64_xchg8((__u64 *)ptr, x);		\
-		break;							\
-	      default:							\
-		ia64_xchg_called_with_bad_pointer();			\
-	}								\
-	__xchg_result;							\
-})
-
-#define xchg(ptr,x)							     \
-  ((__typeof__(*(ptr))) __xchg ((unsigned long) (x), (ptr), sizeof(*(ptr))))
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-
-#define __HAVE_ARCH_CMPXCHG 1
-
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid cmpxchg().
- */
-extern long ia64_cmpxchg_called_with_bad_pointer (void);
-
-#define ia64_cmpxchg(sem,ptr,old,new,size)						\
-({											\
-	__u64 _o_, _r_;									\
-											\
-	switch (size) {									\
-	      case 1: _o_ = (__u8 ) (long) (old); break;				\
-	      case 2: _o_ = (__u16) (long) (old); break;				\
-	      case 4: _o_ = (__u32) (long) (old); break;				\
-	      case 8: _o_ = (__u64) (long) (old); break;				\
-	      default: break;								\
-	}										\
-	switch (size) {									\
-	      case 1:									\
-	      	_r_ = ia64_cmpxchg1_##sem((__u8 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      case 2:									\
-	       _r_ = ia64_cmpxchg2_##sem((__u16 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      case 4:									\
-	      	_r_ = ia64_cmpxchg4_##sem((__u32 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      case 8:									\
-		_r_ = ia64_cmpxchg8_##sem((__u64 *) ptr, new, _o_);			\
-		break;									\
-											\
-	      default:									\
-		_r_ = ia64_cmpxchg_called_with_bad_pointer();				\
-		break;									\
-	}										\
-	(__typeof__(old)) _r_;								\
-})
-
-#define cmpxchg_acq(ptr, o, n)	\
-	ia64_cmpxchg(acq, (ptr), (o), (n), sizeof(*(ptr)))
-#define cmpxchg_rel(ptr, o, n)	\
-	ia64_cmpxchg(rel, (ptr), (o), (n), sizeof(*(ptr)))
-
-/* for compatibility with other platforms: */
-#define cmpxchg(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
-#define cmpxchg64(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
-
-#define cmpxchg_local		cmpxchg
-#define cmpxchg64_local		cmpxchg64
-
-#ifdef CONFIG_IA64_DEBUG_CMPXCHG
-# define CMPXCHG_BUGCHECK_DECL	int _cmpxchg_bugcheck_count = 128;
-# define CMPXCHG_BUGCHECK(v)							\
-  do {										\
-	if (_cmpxchg_bugcheck_count-- <= 0) {					\
-		void *ip;							\
-		extern int printk(const char *fmt, ...);			\
-		ip = (void *) ia64_getreg(_IA64_REG_IP);			\
-		printk("CMPXCHG_BUGCHECK: stuck at %p on word %p\n", ip, (v));	\
-		break;								\
-	}									\
-  } while (0)
-#else /* !CONFIG_IA64_DEBUG_CMPXCHG */
-# define CMPXCHG_BUGCHECK_DECL
-# define CMPXCHG_BUGCHECK(v)
-#endif /* !CONFIG_IA64_DEBUG_CMPXCHG */
-
 #endif
 
 #ifdef __KERNEL__
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 9d0fd7d5bb82..f00ba025375d 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -604,12 +604,6 @@ pfm_unprotect_ctx_ctxsw(pfm_context_t *x, unsigned long f)
 	spin_unlock(&(x)->ctx_lock);
 }
 
-static inline unsigned int
-pfm_do_munmap(struct mm_struct *mm, unsigned long addr, size_t len, int acct)
-{
-	return do_munmap(mm, addr, len);
-}
-
 static inline unsigned long 
 pfm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, unsigned long exec)
 {
@@ -1458,8 +1452,9 @@ pfm_unreserve_session(pfm_context_t *ctx, int is_syswide, unsigned int cpu)
  * a PROTECT_CTX() section.
  */
 static int
-pfm_remove_smpl_mapping(struct task_struct *task, void *vaddr, unsigned long size)
+pfm_remove_smpl_mapping(void *vaddr, unsigned long size)
 {
+	struct task_struct *task = current;
 	int r;
 
 	/* sanity checks */
@@ -1473,13 +1468,8 @@ pfm_remove_smpl_mapping(struct task_struct *task, void *vaddr, unsigned long siz
 	/*
 	 * does the actual unmapping
 	 */
-	down_write(&task->mm->mmap_sem);
+	r = vm_munmap((unsigned long)vaddr, size);
 
-	DPRINT(("down_write done smpl_vaddr=%p size=%lu\n", vaddr, size));
-
-	r = pfm_do_munmap(task->mm, (unsigned long)vaddr, size, 0);
-
-	up_write(&task->mm->mmap_sem);
 	if (r !=0) {
 		printk(KERN_ERR "perfmon: [%d] unable to unmap sampling buffer @%p size=%lu\n", task_pid_nr(task), vaddr, size);
 	}
@@ -1945,7 +1935,7 @@ pfm_flush(struct file *filp, fl_owner_t id)
 	 * because some VM function reenables interrupts.
 	 *
 	 */
-	if (smpl_buf_vaddr) pfm_remove_smpl_mapping(current, smpl_buf_vaddr, smpl_buf_size);
+	if (smpl_buf_vaddr) pfm_remove_smpl_mapping(smpl_buf_vaddr, smpl_buf_size);
 
 	return 0;
 }
diff --git a/arch/m68k/configs/m5275evb_defconfig b/arch/m68k/configs/m5275evb_defconfig
index 33c32aeca12b..a1230e82bb1e 100644
--- a/arch/m68k/configs/m5275evb_defconfig
+++ b/arch/m68k/configs/m5275evb_defconfig
@@ -49,7 +49,6 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_NETDEVICES=y
 CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-CONFIG_FEC2=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
diff --git a/arch/m68k/platform/527x/config.c b/arch/m68k/platform/527x/config.c
index 7ed848c3b848..f91a53294c35 100644
--- a/arch/m68k/platform/527x/config.c
+++ b/arch/m68k/platform/527x/config.c
@@ -74,9 +74,7 @@ static void __init m527x_fec_init(void)
 	writew(par | 0xf00, MCF_IPSBAR + 0x100082);
 	v = readb(MCF_IPSBAR + 0x100078);
 	writeb(v | 0xc0, MCF_IPSBAR + 0x100078);
-#endif
 
-#ifdef CONFIG_FEC2
 	/* Set multi-function pins to ethernet mode for fec1 */
 	par = readw(MCF_IPSBAR + 0x100082);
 	writew(par | 0xa0, MCF_IPSBAR + 0x100082);
diff --git a/arch/m68k/platform/68EZ328/Makefile b/arch/m68k/platform/68EZ328/Makefile
index ee97735a242c..b44d799b1115 100644
--- a/arch/m68k/platform/68EZ328/Makefile
+++ b/arch/m68k/platform/68EZ328/Makefile
@@ -3,9 +3,3 @@
 #
 
 obj-y := config.o
-
-extra-y := bootlogo.rh
-
-$(obj)/bootlogo.rh: $(src)/bootlogo.h
-	perl $(src)/../68328/bootlogo.pl < $(src)/bootlogo.h \
-		> $(obj)/bootlogo.rh
diff --git a/arch/m68k/platform/68VZ328/Makefile b/arch/m68k/platform/68VZ328/Makefile
index 447ffa0fd7c7..a49d75e65489 100644
--- a/arch/m68k/platform/68VZ328/Makefile
+++ b/arch/m68k/platform/68VZ328/Makefile
@@ -3,14 +3,9 @@
 #
 
 obj-y		:= config.o
-logo-$(UCDIMM)	:= bootlogo.rh
-logo-$(DRAGEN2)	:= screen.h
-extra-y		:= $(logo-y)
-
-$(obj)/bootlogo.rh: $(src)/../68EZ328/bootlogo.h
-	perl $(src)/bootlogo.pl < $(src)/../68328/bootlogo.h > $(obj)/bootlogo.rh
+extra-$(DRAGEN2):= screen.h
 
 $(obj)/screen.h: $(src)/screen.xbm $(src)/xbm2lcd.pl
 	perl $(src)/xbm2lcd.pl < $(src)/screen.xbm > $(obj)/screen.h
 
-clean-files := $(obj)/screen.h $(obj)/bootlogo.rh
+clean-files := $(obj)/screen.h
diff --git a/arch/m68k/platform/68EZ328/bootlogo.h b/arch/m68k/platform/68VZ328/bootlogo.h
index e842bdae5839..b38e2b255142 100644
--- a/arch/m68k/platform/68EZ328/bootlogo.h
+++ b/arch/m68k/platform/68VZ328/bootlogo.h
@@ -1,6 +1,6 @@
 #define splash_width 640
 #define splash_height 480
-static unsigned char splash_bits[] = {
+unsigned char __attribute__ ((aligned(16))) bootlogo_bits[] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
diff --git a/arch/m68k/platform/coldfire/device.c b/arch/m68k/platform/coldfire/device.c
index fa50c48292ff..7af97362b95c 100644
--- a/arch/m68k/platform/coldfire/device.c
+++ b/arch/m68k/platform/coldfire/device.c
@@ -114,7 +114,7 @@ static struct resource mcf_fec1_resources[] = {
 
 static struct platform_device mcf_fec1 = {
 	.name			= "fec",
-	.id			= 0,
+	.id			= 1,
 	.num_resources		= ARRAY_SIZE(mcf_fec1_resources),
 	.resource		= mcf_fec1_resources,
 };
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 811084f4e422..ab73fa2fb9b5 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1325,7 +1325,7 @@ static int mipsxx_pmu_handle_shared_irq(void)
 
 	regs = get_irq_regs();
 
-	perf_sample_data_init(&data, 0);
+	perf_sample_data_init(&data, 0, 0);
 
 	switch (counters) {
 #define HANDLE_COUNTER(n)						\
diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig
index f104ccde6b53..b1f9597fe312 100644
--- a/arch/powerpc/configs/chroma_defconfig
+++ b/arch/powerpc/configs/chroma_defconfig
@@ -32,7 +32,7 @@ CONFIG_RD_LZMA=y
 CONFIG_INITRAMFS_COMPRESSION_GZIP=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
-CONFIG_PERF_COUNTERS=y
+CONFIG_PERF_EVENTS=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig
index e74d3a483705..9ef2cc13e1b4 100644
--- a/arch/powerpc/configs/gamecube_defconfig
+++ b/arch/powerpc/configs/gamecube_defconfig
@@ -8,7 +8,7 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
-CONFIG_PERF_COUNTERS=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 175295fbf4f3..1e2b7d062aa4 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -9,7 +9,7 @@ CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_ELF_CORE is not set
-CONFIG_PERF_COUNTERS=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index cf417e510736..e648af92ced1 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -33,8 +33,6 @@ extern atomic_t ppc_n_lost_interrupts;
 /* Same thing, used by the generic IRQ code */
 #define NR_IRQS_LEGACY		NUM_ISA_INTERRUPTS
 
-struct irq_data;
-extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
 
 /**
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3e57a00b8cba..ba3aeb4bc06a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -206,40 +206,43 @@ reenable_mmu:				/* re-enable mmu so we can */
 	andi.	r10,r10,MSR_EE		/* Did EE change? */
 	beq	1f
 
-	/* Save handler and return address into the 2 unused words
-	 * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
-	 * else can be recovered from the pt_regs except r3 which for
-	 * normal interrupts has been set to pt_regs and for syscalls
-	 * is an argument, so we temporarily use ORIG_GPR3 to save it
-	 */
-	stw	r9,8(r1)
-	stw	r11,12(r1)
-	stw	r3,ORIG_GPR3(r1)
 	/*
 	 * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
 	 * If from user mode there is only one stack frame on the stack, and
 	 * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
 	 * stack frame to make trace_hardirqs_off happy.
+	 *
+	 * This is handy because we also need to save a bunch of GPRs,
+	 * r3 can be different from GPR3(r1) at this point, r9 and r11
+	 * contains the old MSR and handler address respectively,
+	 * r4 & r5 can contain page fault arguments that need to be passed
+	 * along as well. r12, CCR, CTR, XER etc... are left clobbered as
+	 * they aren't useful past this point (aren't syscall arguments),
+	 * the rest is restored from the exception frame.
 	 */
+	stwu	r1,-32(r1)
+	stw	r9,8(r1)
+	stw	r11,12(r1)
+	stw	r3,16(r1)
+	stw	r4,20(r1)
+	stw	r5,24(r1)
 	andi.	r12,r12,MSR_PR
-	beq	11f
-	stwu	r1,-16(r1)
+	b	11f
 	bl	trace_hardirqs_off
-	addi	r1,r1,16
 	b	12f
-
 11:
 	bl	trace_hardirqs_off
 12:
+	lwz	r5,24(r1)
+	lwz	r4,20(r1)
+	lwz	r3,16(r1)
+	lwz	r11,12(r1)
+	lwz	r9,8(r1)
+	addi	r1,r1,32
 	lwz	r0,GPR0(r1)
-	lwz	r3,ORIG_GPR3(r1)
-	lwz	r4,GPR4(r1)
-	lwz	r5,GPR5(r1)
 	lwz	r6,GPR6(r1)
 	lwz	r7,GPR7(r1)
 	lwz	r8,GPR8(r1)
-	lwz	r9,8(r1)
-	lwz	r11,12(r1)
 1:	mtctr	r11
 	mtlr	r9
 	bctr				/* jump to handler */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 243dbabfe74d..5ec1b2354ca6 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -560,12 +560,6 @@ void do_softirq(void)
 	local_irq_restore(flags);
 }
 
-irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-EXPORT_SYMBOL_GPL(irqd_to_hwirq);
-
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(virq);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f88698c0f332..4937c9690090 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1235,7 +1235,7 @@ void __ppc64_runlatch_on(void)
 	ctrl |= CTRL_RUNLATCH;
 	mtspr(SPRN_CTRLT, ctrl);
 
-	ti->local_flags |= TLF_RUNLATCH;
+	ti->local_flags |= _TLF_RUNLATCH;
 }
 
 /* Called with hard IRQs off */
@@ -1244,7 +1244,7 @@ void __ppc64_runlatch_off(void)
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
 
-	ti->local_flags &= ~TLF_RUNLATCH;
+	ti->local_flags &= ~_TLF_RUNLATCH;
 
 	ctrl = mfspr(SPRN_CTRLF);
 	ctrl &= ~CTRL_RUNLATCH;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 02aee03e713c..8f84bcba18da 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1299,8 +1299,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, ~0ULL);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
 
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 0a6d2a9d569c..106c53354675 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -613,8 +613,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, 0);
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (perf_event_overflow(event, &data, regs))
 			fsl_emb_pmu_stop(event, 0);
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index db360fc4cf0e..d09f3e8e6867 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -392,7 +392,7 @@ static int axon_msi_probe(struct platform_device *device)
 	}
 	memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
 
-	msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic);
+	msic->irq_domain = irq_domain_add_nomap(dn, 0, &msic_host_ops, msic);
 	if (!msic->irq_domain) {
 		printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n",
 		       dn->full_name);
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index e5c3a2c6090d..f9a48af335cb 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -239,7 +239,7 @@ void __init beatic_init_IRQ(void)
 	ppc_md.get_irq = beatic_get_irq;
 
 	/* Allocate an irq host */
-	beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL);
+	beatic_host = irq_domain_add_nomap(NULL, 0, &beatic_pic_host_ops, NULL);
 	BUG_ON(beatic_host == NULL);
 	irq_set_default_host(beatic_host);
 }
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index a81e5a88fbdf..b4ddaa3fbb29 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -192,7 +192,7 @@ static int psurge_secondary_ipi_init(void)
 {
 	int rc = -ENOMEM;
 
-	psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL);
+	psurge_host = irq_domain_add_nomap(NULL, 0, &psurge_host_ops, NULL);
 
 	if (psurge_host)
 		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 2a4ff86cc21f..5f3b23220b8e 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -753,9 +753,8 @@ void __init ps3_init_IRQ(void)
 	unsigned cpu;
 	struct irq_domain *host;
 
-	host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL);
+	host = irq_domain_add_nomap(NULL, PS3_PLUG_MAX + 1, &ps3_host_ops, NULL);
 	irq_set_default_host(host);
-	irq_set_virq_count(PS3_PLUG_MAX + 1);
 
 	for_each_possible_cpu(cpu) {
 		struct ps3_private *pd = &per_cpu(ps3_private, cpu);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 2b7c0fbe578e..9015060919a0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -90,7 +90,6 @@ config S390
 	select HAVE_KERNEL_XZ
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
-	select HAVE_RCU_TABLE_FREE if SMP
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 6cf8e26b3137..1957a9dd256d 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,8 +1,12 @@
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_FHANDLE=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_AUDIT=y
-CONFIG_RCU_TRACE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
@@ -14,16 +18,22 @@ CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
+CONFIG_NAMESPACES=y
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_RD_XZ=y
+CONFIG_RD_LZO=y
+CONFIG_EXPERT=y
 # CONFIG_COMPAT_BRK is not set
-CONFIG_SLAB=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -34,18 +44,15 @@ CONFIG_KSM=y
 CONFIG_BINFMT_MISC=m
 CONFIG_CMM=m
 CONFIG_HZ_100=y
-CONFIG_KEXEC=y
-CONFIG_PM=y
+CONFIG_CRASH_DUMP=y
 CONFIG_HIBERNATION=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_NET_KEY=y
-CONFIG_AFIUCV=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 # CONFIG_INET_LRO is not set
 CONFIG_IPV6=y
-CONFIG_NET_SCTPPROBE=m
 CONFIG_L2TP=m
 CONFIG_L2TP_DEBUGFS=m
 CONFIG_VLAN_8021Q=y
@@ -84,15 +91,14 @@ CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
 CONFIG_ZFCP=y
-CONFIG_ZFCP_DIF=y
 CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
 CONFIG_BONDING=m
+CONFIG_DUMMY=m
 CONFIG_EQUALIZER=m
 CONFIG_TUN=m
-CONFIG_NET_ETHERNET=y
 CONFIG_VIRTIO_NET=y
 CONFIG_RAW_DRIVER=m
+CONFIG_VIRTIO_BALLOON=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
@@ -103,27 +109,21 @@ CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_TIMER_STATS=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_PROVE_RCU=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
-CONFIG_DEBUG_SPINLOCK_SLEEP=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_NOTIFIERS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_RCU_TRACE=y
 CONFIG_KPROBES_SANITY_TEST=y
 CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
 CONFIG_LATENCYTOP=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_DEBUG_PAGEALLOC=y
-# CONFIG_FTRACE is not set
+CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
@@ -173,4 +173,3 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRC7=m
-CONFIG_VIRTIO_BALLOON=y
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 1e5b27edc0c9..2ee66a65f2d4 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -38,12 +38,11 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	unsigned long nr;
 
 	preempt_disable();
-	S390_lowcore.stfl_fac_list = 0;
 	asm volatile(
 		"	.insn s,0xb2b10000,0(0)\n" /* stfl */
 		"0:\n"
 		EX_TABLE(0b, 0b)
-		: "=m" (S390_lowcore.stfl_fac_list));
+		: "+m" (S390_lowcore.stfl_fac_list));
 	nr = 4; /* bytes stored by stfl */
 	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
 	if (S390_lowcore.stfl_fac_list & 0x01000000) {
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 8eef9b5b3cf4..78e3041919de 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -22,10 +22,7 @@ void crst_table_free(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
-void __tlb_remove_table(void *_table);
-#endif
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
diff --git a/arch/s390/include/asm/swab.h b/arch/s390/include/asm/swab.h
index 6bdee21c077e..a3e4ebb32090 100644
--- a/arch/s390/include/asm/swab.h
+++ b/arch/s390/include/asm/swab.h
@@ -77,7 +77,7 @@ static inline __u16 __arch_swab16p(const __u16 *x)
 	
 	asm volatile(
 #ifndef __s390x__
-		"	icm	%0,2,%O+1(%R1)\n"
+		"	icm	%0,2,%O1+1(%R1)\n"
 		"	ic	%0,%1\n"
 		: "=&d" (result) : "Q" (*x) : "cc");
 #else /* __s390x__ */
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index c687a2c83462..775a5eea8f9e 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -30,14 +30,10 @@
 
 struct mmu_gather {
 	struct mm_struct *mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch *batch;
-#endif
 	unsigned int fullmm;
-	unsigned int need_flush;
 };
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 struct mmu_table_batch {
 	struct rcu_head		rcu;
 	unsigned int		nr;
@@ -49,7 +45,6 @@ struct mmu_table_batch {
 
 extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-#endif
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 				  struct mm_struct *mm,
@@ -57,29 +52,20 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 {
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
-	tlb->need_flush = 0;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
-#endif
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
 }
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->need_flush)
-		return;
-	tlb->need_flush = 0;
-	__tlb_flush_mm(tlb->mm);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
-#endif
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
-	tlb_flush_mmu(tlb);
+	tlb_table_flush(tlb);
 }
 
 /*
@@ -105,10 +91,8 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				unsigned long address)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	if (!tlb->fullmm)
 		return page_table_free_rcu(tlb, (unsigned long *) pte);
-#endif
 	page_table_free(tlb->mm, (unsigned long *) pte);
 }
 
@@ -125,10 +109,8 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 31))
 		return;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	if (!tlb->fullmm)
 		return tlb_remove_table(tlb, pmd);
-#endif
 	crst_table_free(tlb->mm, (unsigned long *) pmd);
 #endif
 }
@@ -146,10 +128,8 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 42))
 		return;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	if (!tlb->fullmm)
 		return tlb_remove_table(tlb, pud);
-#endif
 	crst_table_free(tlb->mm, (unsigned long *) pud);
 #endif
 }
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index c27a0727f930..adccd908ebc7 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -474,9 +474,9 @@ ENTRY(startup_kdump)
 	stck	__LC_LAST_UPDATE_CLOCK
 	spt	5f-.LPG0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13)
+	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 #ifndef CONFIG_MARCH_G5
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
-	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 	.insn	s,0xb2b10000,__LC_STFL_FAC_LIST	# store facility list
 	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
 	jz	0f
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 1c2cdd59ccd0..8a22c27219dd 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -118,9 +118,10 @@ asmlinkage void do_softirq(void)
 				         "a" (__do_softirq)
 				     : "0", "1", "2", "3", "4", "5", "14",
 				       "cc", "memory" );
-		} else
+		} else {
 			/* We are already on the async stack. */
 			__do_softirq();
+		}
 	}
 
 	local_irq_restore(flags);
@@ -192,11 +193,12 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 	int index = ext_hash(code);
 
 	spin_lock_irqsave(&ext_int_hash_lock, flags);
-	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
+	list_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
 		if (p->code == code && p->handler == handler) {
 			list_del_rcu(&p->entry);
 			kfree_rcu(p, rcu);
 		}
+	}
 	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
@@ -211,9 +213,10 @@ void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code,
 
 	old_regs = set_irq_regs(regs);
 	irq_enter();
-	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
+	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) {
 		/* Serve timer interrupts first. */
 		clock_comparator_work();
+	}
 	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
 	if (ext_code.code != 0x1004)
 		__get_cpu_var(s390_idle).nohz_delay = 1;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 46405086479c..cb019f429e88 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -178,7 +178,7 @@ static void cpumf_pmu_enable(struct pmu *pmu)
 	err = lcctl(cpuhw->state);
 	if (err) {
 		pr_err("Enabling the performance measuring unit "
-		       "failed with rc=%lx\n", err);
+		       "failed with rc=%x\n", err);
 		return;
 	}
 
@@ -203,7 +203,7 @@ static void cpumf_pmu_disable(struct pmu *pmu)
 	err = lcctl(inactive);
 	if (err) {
 		pr_err("Disabling the performance measuring unit "
-		       "failed with rc=%lx\n", err);
+		       "failed with rc=%x\n", err);
 		return;
 	}
 
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 7bb15fcca75e..e1335dc2b1b7 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -61,21 +61,14 @@ long probe_kernel_write(void *dst, const void *src, size_t size)
 	return copied < 0 ? -EFAULT : 0;
 }
 
-/*
- * Copy memory in real mode (kernel to kernel)
- */
-int memcpy_real(void *dest, void *src, size_t count)
+static int __memcpy_real(void *dest, void *src, size_t count)
 {
 	register unsigned long _dest asm("2") = (unsigned long) dest;
 	register unsigned long _len1 asm("3") = (unsigned long) count;
 	register unsigned long _src  asm("4") = (unsigned long) src;
 	register unsigned long _len2 asm("5") = (unsigned long) count;
-	unsigned long flags;
 	int rc = -EFAULT;
 
-	if (!count)
-		return 0;
-	flags = __arch_local_irq_stnsm(0xf8UL);
 	asm volatile (
 		"0:	mvcle	%1,%2,0x0\n"
 		"1:	jo	0b\n"
@@ -86,7 +79,23 @@ int memcpy_real(void *dest, void *src, size_t count)
 		  "+d" (_len2), "=m" (*((long *) dest))
 		: "m" (*((long *) src))
 		: "cc", "memory");
-	arch_local_irq_restore(flags);
+	return rc;
+}
+
+/*
+ * Copy memory in real mode (kernel to kernel)
+ */
+int memcpy_real(void *dest, void *src, size_t count)
+{
+	unsigned long flags;
+	int rc;
+
+	if (!count)
+		return 0;
+	local_irq_save(flags);
+	__arch_local_irq_stnsm(0xfbUL);
+	rc = __memcpy_real(dest, src, count);
+	local_irq_restore(flags);
 	return rc;
 }
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 373adf69b01c..6e765bf00670 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -678,8 +678,6 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	}
 }
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-
 static void __page_table_free_rcu(void *table, unsigned bit)
 {
 	struct page *page;
@@ -733,7 +731,66 @@ void __tlb_remove_table(void *_table)
 		free_pages((unsigned long) table, ALLOC_ORDER);
 }
 
-#endif
+static void tlb_remove_table_smp_sync(void *arg)
+{
+	/* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+	/*
+	 * This isn't an RCU grace period and hence the page-tables cannot be
+	 * assumed to be actually RCU-freed.
+	 *
+	 * It is however sufficient for software page-table walkers that rely
+	 * on IRQ disabling. See the comment near struct mmu_table_batch.
+	 */
+	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	__tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+	struct mmu_table_batch *batch;
+	int i;
+
+	batch = container_of(head, struct mmu_table_batch, rcu);
+
+	for (i = 0; i < batch->nr; i++)
+		__tlb_remove_table(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	if (*batch) {
+		__tlb_flush_mm(tlb->mm);
+		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+		*batch = NULL;
+	}
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	if (*batch == NULL) {
+		*batch = (struct mmu_table_batch *)
+			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		if (*batch == NULL) {
+			__tlb_flush_mm(tlb->mm);
+			tlb_remove_table_one(table);
+			return;
+		}
+		(*batch)->nr = 0;
+	}
+	(*batch)->tables[(*batch)->nr++] = table;
+	if ((*batch)->nr == MAX_TABLE_BATCH)
+		tlb_table_flush(tlb);
+}
 
 /*
  * switch on pgstes for its userspace process (for kvm)
diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig
index 7b9c696ac5e0..9bdcf72ec06a 100644
--- a/arch/sh/configs/sh7785lcr_32bit_defconfig
+++ b/arch/sh/configs/sh7785lcr_32bit_defconfig
@@ -5,7 +5,7 @@ CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=16
-CONFIG_PERF_COUNTERS=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 3c1e85807403..9d8521b8c854 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -5,7 +5,7 @@ CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_PERF_COUNTERS=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLAB=y
 CONFIG_PROFILING=y
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index fea13c7b1aee..b93c2c9ccb1d 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1264,4 +1264,4 @@ static int __init ds_init(void)
 	return vio_register_driver(&ds_driver);
 }
 
-subsys_initcall(ds_init);
+fs_initcall(ds_init);
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index aba6b958b2a5..19f56058742b 100644
--- a/arch/sparc/kernel/leon_pci.c
+++ b/arch/sparc/kernel/leon_pci.c
@@ -45,7 +45,6 @@ void leon_pci_init(struct platform_device *ofdev, struct leon_pci_info *info)
 
 void __devinit pcibios_fixup_bus(struct pci_bus *pbus)
 {
-	struct leon_pci_info *info = pbus->sysdata;
 	struct pci_dev *dev;
 	int i, has_io, has_mem;
 	u16 cmd;
@@ -111,18 +110,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return pci_enable_resources(dev, mask);
 }
 
-struct device_node *pci_device_to_OF_node(struct pci_dev *pdev)
-{
-	/*
-	 * Currently the OpenBoot nodes are not connected with the PCI device,
-	 * this is because the LEON PROM does not create PCI nodes. Eventually
-	 * this will change and the same approach as pcic.c can be used to
-	 * match PROM nodes with pci devices.
-	 */
-	return NULL;
-}
-EXPORT_SYMBOL(pci_device_to_OF_node);
-
 void __devinit pcibios_update_irq(struct pci_dev *dev, int irq)
 {
 #ifdef CONFIG_PCI_DEBUG
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 1210fde18740..160cac9c4036 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -23,6 +23,7 @@
 #include <linux/pm.h>
 #include <linux/delay.h>
 #include <linux/gfp.h>
+#include <linux/cpu.h>
 
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
@@ -78,6 +79,8 @@ void __cpuinit leon_callin(void)
 	local_flush_tlb_all();
 	leon_configure_cache_smp();
 
+	notify_cpu_starting(cpuid);
+
 	/* Get our local ticker going. */
 	smp_setup_percpu_timer();
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 28559ce5eeb5..5713957dcb8a 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1296,8 +1296,6 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	/* If the PMU has the TOE IRQ enable bits, we need to do a
@@ -1321,7 +1319,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 		if (val & (1ULL << 31))
 			continue;
 
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 		if (!sparc_perf_event_set_period(event, hwc, idx))
 			continue;
 
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 77f1b95e0806..9171fc238def 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -20,11 +20,6 @@
 
 		.text
 		.align			32
-__handle_softirq:
-		call			do_softirq
-		 nop
-		ba,a,pt			%xcc, __handle_softirq_continue
-		 nop
 __handle_preemption:
 		call			schedule
 		 wrpr			%g0, RTRAP_PSTATE, %pstate
@@ -89,9 +84,7 @@ rtrap:
 		cmp			%l1, 0
 
 		/* mm/ultra.S:xcall_report_regs KNOWS about this load. */
-		bne,pn			%icc, __handle_softirq
 		 ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
-__handle_softirq_continue:
 rtrap_xcall:
 		sethi			%hi(0xf << 20), %l4
 		and			%l1, %l4, %l4
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 232df9949530..3ee51f189a55 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -566,15 +566,10 @@ out:
 
 SYSCALL_DEFINE2(64_munmap, unsigned long, addr, size_t, len)
 {
-	long ret;
-
 	if (invalid_64bit_range(addr, len))
 		return -EINVAL;
 
-	down_write(&current->mm->mmap_sem);
-	ret = do_munmap(current->mm, addr, len);
-	up_write(&current->mm->mmap_sem);
-	return ret;
+	return vm_munmap(addr, len);
 }
 
 extern unsigned long do_mremap(unsigned long addr,
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 7705c6731e28..df3155a17991 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -225,6 +225,8 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	unsigned long g2;
 	int from_user = !(regs->psr & PSR_PS);
 	int fault, code;
+	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+			      (write ? FAULT_FLAG_WRITE : 0));
 
 	if(text_fault)
 		address = regs->pc;
@@ -251,6 +253,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+retry:
 	down_read(&mm->mmap_sem);
 
 	/*
@@ -289,7 +292,11 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -297,13 +304,29 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			current->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+				      1, regs, address);
+		} else {
+			current->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+				      1, regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
 	}
+
 	up_read(&mm->mmap_sem);
 	return;
 
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 504c0622f729..1fe0429b6314 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -279,6 +279,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	unsigned int insn = 0;
 	int si_code, fault_code, fault;
 	unsigned long address, mm_rss;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	fault_code = get_thread_fault_code();
 
@@ -333,6 +334,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			insn = get_fault_insn(regs, insn);
 			goto handle_kernel_fault;
 		}
+
+retry:
 		down_read(&mm->mmap_sem);
 	}
 
@@ -423,7 +426,12 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
+	flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -431,12 +439,27 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			current->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+				      1, regs, address);
+		} else {
+			current->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+				      1, regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
 	}
 	up_read(&mm->mmap_sem);
 
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index 7a9327046404..446a7f52cc11 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -146,7 +146,6 @@ static ctl_table unaligned_table[] = {
 	},
 	{}
 };
-#endif
 
 static struct ctl_path tile_path[] = {
 	{ .procname = "tile" },
@@ -155,10 +154,9 @@ static struct ctl_path tile_path[] = {
 
 static int __init proc_sys_tile_init(void)
 {
-#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
 	register_sysctl_paths(tile_path, unaligned_table);
-#endif
 	return 0;
 }
 
 arch_initcall(proc_sys_tile_init);
+#endif
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 9efbc1391b3c..89529c9f0605 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -346,12 +346,10 @@ void single_step_once(struct pt_regs *regs)
 		}
 
 		/* allocate a cache line of writable, executable memory */
-		down_write(&current->mm->mmap_sem);
-		buffer = (void __user *) do_mmap(NULL, 0, 64,
+		buffer = (void __user *) vm_mmap(NULL, 0, 64,
 					  PROT_EXEC | PROT_READ | PROT_WRITE,
 					  MAP_PRIVATE | MAP_ANONYMOUS,
 					  0);
-		up_write(&current->mm->mmap_sem);
 
 		if (IS_ERR((void __force *)buffer)) {
 			kfree(state);
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index b949edcec200..172aef7d3159 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -196,6 +196,8 @@ void __cpuinit online_secondary(void)
 	/* This must be done before setting cpu_online_mask */
 	wmb();
 
+	notify_cpu_starting(smp_processor_id());
+
 	/*
 	 * We need to hold call_lock, so there is no inconsistency
 	 * between the time smp_call_function() determines number of
diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h
index dc36b222100b..6673508f3426 100644
--- a/arch/um/drivers/cow.h
+++ b/arch/um/drivers/cow.h
@@ -3,41 +3,6 @@
 
 #include <asm/types.h>
 
-#if defined(__KERNEL__)
-
-# include <asm/byteorder.h>
-
-# if defined(__BIG_ENDIAN)
-#	define ntohll(x) (x)
-#	define htonll(x) (x)
-# elif defined(__LITTLE_ENDIAN)
-#	define ntohll(x)  be64_to_cpu(x)
-#	define htonll(x)  cpu_to_be64(x)
-# else
-#	error "Could not determine byte order"
-# endif
-
-#else
-/* For the definition of ntohl, htonl and __BYTE_ORDER */
-#include <endian.h>
-#include <netinet/in.h>
-#if defined(__BYTE_ORDER)
-
-#  if __BYTE_ORDER == __BIG_ENDIAN
-#	define ntohll(x) (x)
-#	define htonll(x) (x)
-#  elif __BYTE_ORDER == __LITTLE_ENDIAN
-#	define ntohll(x)  bswap_64(x)
-#	define htonll(x)  bswap_64(x)
-#  else
-#	error "Could not determine byte order: __BYTE_ORDER uncorrectly defined"
-#  endif
-
-#else  /* ! defined(__BYTE_ORDER) */
-#	error "Could not determine byte order: __BYTE_ORDER not defined"
-#endif
-#endif /* ! defined(__KERNEL__) */
-
 extern int init_cow_file(int fd, char *cow_file, char *backing_file,
 			 int sectorsize, int alignment, int *bitmap_offset_out,
 			 unsigned long *bitmap_len_out, int *data_offset_out);
diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c
index 9cbb426c0b91..0ee9cc6cc4c7 100644
--- a/arch/um/drivers/cow_user.c
+++ b/arch/um/drivers/cow_user.c
@@ -8,11 +8,10 @@
  * that.
  */
 #include <unistd.h>
-#include <byteswap.h>
 #include <errno.h>
 #include <string.h>
 #include <arpa/inet.h>
-#include <asm/types.h>
+#include <endian.h>
 #include "cow.h"
 #include "cow_sys.h"
 
@@ -214,8 +213,8 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 			   "header\n");
 		goto out;
 	}
-	header->magic = htonl(COW_MAGIC);
-	header->version = htonl(COW_VERSION);
+	header->magic = htobe32(COW_MAGIC);
+	header->version = htobe32(COW_VERSION);
 
 	err = -EINVAL;
 	if (strlen(backing_file) > sizeof(header->backing_file) - 1) {
@@ -246,10 +245,10 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 		goto out_free;
 	}
 
-	header->mtime = htonl(modtime);
-	header->size = htonll(*size);
-	header->sectorsize = htonl(sectorsize);
-	header->alignment = htonl(alignment);
+	header->mtime = htobe32(modtime);
+	header->size = htobe64(*size);
+	header->sectorsize = htobe32(sectorsize);
+	header->alignment = htobe32(alignment);
 	header->cow_format = COW_BITMAP;
 
 	err = cow_write_file(fd, header, sizeof(*header));
@@ -301,8 +300,8 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 	magic = header->v1.magic;
 	if (magic == COW_MAGIC)
 		version = header->v1.version;
-	else if (magic == ntohl(COW_MAGIC))
-		version = ntohl(header->v1.version);
+	else if (magic == be32toh(COW_MAGIC))
+		version = be32toh(header->v1.version);
 	/* No error printed because the non-COW case comes through here */
 	else goto out;
 
@@ -327,9 +326,9 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 				   "header\n");
 			goto out;
 		}
-		*mtime_out = ntohl(header->v2.mtime);
-		*size_out = ntohll(header->v2.size);
-		*sectorsize_out = ntohl(header->v2.sectorsize);
+		*mtime_out = be32toh(header->v2.mtime);
+		*size_out = be64toh(header->v2.size);
+		*sectorsize_out = be32toh(header->v2.sectorsize);
 		*bitmap_offset_out = sizeof(header->v2);
 		*align_out = *sectorsize_out;
 		file = header->v2.backing_file;
@@ -341,10 +340,10 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 				   "header\n");
 			goto out;
 		}
-		*mtime_out = ntohl(header->v3.mtime);
-		*size_out = ntohll(header->v3.size);
-		*sectorsize_out = ntohl(header->v3.sectorsize);
-		*align_out = ntohl(header->v3.alignment);
+		*mtime_out = be32toh(header->v3.mtime);
+		*size_out = be64toh(header->v3.size);
+		*sectorsize_out = be32toh(header->v3.sectorsize);
+		*align_out = be32toh(header->v3.alignment);
 		if (*align_out == 0) {
 			cow_printf("read_cow_header - invalid COW header, "
 				   "align == 0\n");
@@ -366,16 +365,16 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 		 * this was used until Dec2005 - 64bits are needed to represent
 		 * 2038+. I.e. we can safely do this truncating cast.
 		 *
-		 * Additionally, we must use ntohl() instead of ntohll(), since
+		 * Additionally, we must use be32toh() instead of be64toh(), since
 		 * the program used to use the former (tested - I got mtime
 		 * mismatch "0 vs whatever").
 		 *
 		 * Ever heard about bug-to-bug-compatibility ? ;-) */
-		*mtime_out = (time32_t) ntohl(header->v3_b.mtime);
+		*mtime_out = (time32_t) be32toh(header->v3_b.mtime);
 
-		*size_out = ntohll(header->v3_b.size);
-		*sectorsize_out = ntohl(header->v3_b.sectorsize);
-		*align_out = ntohl(header->v3_b.alignment);
+		*size_out = be64toh(header->v3_b.size);
+		*sectorsize_out = be32toh(header->v3_b.sectorsize);
+		*align_out = be32toh(header->v3_b.alignment);
 		if (*align_out == 0) {
 			cow_printf("read_cow_header - invalid COW header, "
 				   "align == 0\n");
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index e672bd6d43e3..43b39d61b538 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -22,6 +22,7 @@
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
+#include <asm/switch_to.h>
 
 #include "init.h"
 #include "irq_kern.h"
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 8419f5cf2ac7..fff24352255d 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,3 +1,4 @@
 generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
 generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
-generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h
+generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
+generic-y += switch_to.h
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 492bc4c1b62b..65a1c3d690ea 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -3,9 +3,10 @@
 # Licensed under the GPL
 #
 
-CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START) \
-                        -DELF_ARCH=$(LDS_ELF_ARCH)        \
-                        -DELF_FORMAT=$(LDS_ELF_FORMAT)
+CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START)		\
+                        -DELF_ARCH=$(LDS_ELF_ARCH)	\
+                        -DELF_FORMAT=$(LDS_ELF_FORMAT)	\
+			$(LDS_EXTRA)
 extra-y := vmlinux.lds
 clean-files :=
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index f386d04a84a5..2b73dedb44ca 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -88,11 +88,8 @@ static inline void set_current(struct task_struct *task)
 
 extern void arch_switch_to(struct task_struct *to);
 
-void *_switch_to(void *prev, void *next, void *last)
+void *__switch_to(struct task_struct *from, struct task_struct *to)
 {
-	struct task_struct *from = prev;
-	struct task_struct *to = next;
-
 	to->thread.prev_sched = from;
 	set_current(to);
 
@@ -111,7 +108,6 @@ void *_switch_to(void *prev, void *next, void *last)
 	} while (current->thread.saved_task);
 
 	return current->thread.prev_sched;
-
 }
 
 void interrupt_end(void)
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 4947b319f53a..0a49ef0c2bf4 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -103,7 +103,6 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 
 void uml_setup_stubs(struct mm_struct *mm)
 {
-	struct page **pages;
 	int err, ret;
 
 	if (!skas_needs_stub)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 76f5a466547a..8443c50fbbf6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -40,7 +40,6 @@ config X86
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KVM
 	select HAVE_ARCH_KGDB
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 4be406abeefd..36b62bc52638 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -14,6 +14,9 @@ LINK-y			+= $(call cc-option,-m32)
 
 export LDFLAGS
 
+LDS_EXTRA		:= -Ui386
+export LDS_EXTRA
+
 # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y.
 include $(srctree)/arch/x86/Makefile_32.cpu
 
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index d511d951a052..4824fb45560f 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -119,9 +119,7 @@ static void set_brk(unsigned long start, unsigned long end)
 	end = PAGE_ALIGN(end);
 	if (end <= start)
 		return;
-	down_write(&current->mm->mmap_sem);
-	do_brk(start, end - start);
-	up_write(&current->mm->mmap_sem);
+	vm_brk(start, end - start);
 }
 
 #ifdef CORE_DUMP
@@ -332,9 +330,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		pos = 32;
 		map_size = ex.a_text+ex.a_data;
 
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(text_addr & PAGE_MASK, map_size);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(text_addr & PAGE_MASK, map_size);
 
 		if (error != (text_addr & PAGE_MASK)) {
 			send_sig(SIGKILL, current, 0);
@@ -373,9 +369,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
 			loff_t pos = fd_offset;
 
-			down_write(&current->mm->mmap_sem);
-			do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-			up_write(&current->mm->mmap_sem);
+			vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
 			bprm->file->f_op->read(bprm->file,
 					(char __user *)N_TXTADDR(ex),
 					ex.a_text+ex.a_data, &pos);
@@ -385,26 +379,22 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			goto beyond_if;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
+		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
 				PROT_READ | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset);
-		up_write(&current->mm->mmap_sem);
 
 		if (error != N_TXTADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset + ex.a_text);
-		up_write(&current->mm->mmap_sem);
 		if (error != N_DATADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
@@ -476,9 +466,7 @@ static int load_aout_library(struct file *file)
 			error_time = jiffies;
 		}
 #endif
-		down_write(&current->mm->mmap_sem);
-		do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-		up_write(&current->mm->mmap_sem);
+		vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
 
 		file->f_op->read(file, (char __user *)start_addr,
 			ex.a_text + ex.a_data, &pos);
@@ -490,12 +478,10 @@ static int load_aout_library(struct file *file)
 		goto out;
 	}
 	/* Now use mmap to map the library into memory. */
-	down_write(&current->mm->mmap_sem);
-	error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
+	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
 			N_TXTOFF(ex));
-	up_write(&current->mm->mmap_sem);
 	retval = error;
 	if (error != start_addr)
 		goto out;
@@ -503,9 +489,7 @@ static int load_aout_library(struct file *file)
 	len = PAGE_ALIGN(ex.a_text + ex.a_data);
 	bss = ex.a_text + ex.a_data + ex.a_bss;
 	if (bss > len) {
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(start_addr + len, bss - len);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(start_addr + len, bss - len);
 		retval = error;
 		if (error != start_addr + len)
 			goto out;
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index b3b733262909..99480e55973d 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -43,7 +43,7 @@ extern void __add_wrong_size(void)
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
 			asm volatile (lock #op "b %b0, %1\n"		\
-				      : "+r" (__ret), "+m" (*(ptr))	\
+				      : "+q" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
@@ -173,7 +173,7 @@ extern void __add_wrong_size(void)
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
 			asm volatile (lock "addb %b1, %0\n"		\
-				      : "+m" (*(ptr)) : "ri" (inc)	\
+				      : "+m" (*(ptr)) : "qi" (inc)	\
 				      : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 268c783ab1c0..18d9005d9e4f 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -34,6 +34,7 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
+extern int modifying_ftrace_code;
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
@@ -50,6 +51,8 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
+int ftrace_int3_handler(struct pt_regs *regs);
+
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ccb805966f68..957ec87385af 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -134,6 +134,8 @@
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
+#define MSR_AMD64_IBSFETCH_REG_COUNT	3
+#define MSR_AMD64_IBSFETCH_REG_MASK	((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
 #define MSR_AMD64_IBSOPCTL		0xc0011033
 #define MSR_AMD64_IBSOPRIP		0xc0011034
 #define MSR_AMD64_IBSOPDATA		0xc0011035
@@ -141,8 +143,11 @@
 #define MSR_AMD64_IBSOPDATA3		0xc0011037
 #define MSR_AMD64_IBSDCLINAD		0xc0011038
 #define MSR_AMD64_IBSDCPHYSAD		0xc0011039
+#define MSR_AMD64_IBSOP_REG_COUNT	7
+#define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
+#define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 2291895b1836..4e40a64315c9 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -158,6 +158,7 @@ struct x86_pmu_capability {
 #define IBS_CAPS_OPCNT			(1U<<4)
 #define IBS_CAPS_BRNTRGT		(1U<<5)
 #define IBS_CAPS_OPCNTEXT		(1U<<6)
+#define IBS_CAPS_RIPINVALIDCHK		(1U<<7)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\
@@ -170,19 +171,22 @@ struct x86_pmu_capability {
 #define IBSCTL_LVT_OFFSET_VALID		(1ULL<<8)
 #define IBSCTL_LVT_OFFSET_MASK		0x0F
 
-/* IbsFetchCtl bits/masks */
+/* ibs fetch bits/masks */
 #define IBS_FETCH_RAND_EN	(1ULL<<57)
 #define IBS_FETCH_VAL		(1ULL<<49)
 #define IBS_FETCH_ENABLE	(1ULL<<48)
 #define IBS_FETCH_CNT		0xFFFF0000ULL
 #define IBS_FETCH_MAX_CNT	0x0000FFFFULL
 
-/* IbsOpCtl bits */
+/* ibs op bits/masks */
+/* lower 4 bits of the current count are ignored: */
+#define IBS_OP_CUR_CNT		(0xFFFF0ULL<<32)
 #define IBS_OP_CNT_CTL		(1ULL<<19)
 #define IBS_OP_VAL		(1ULL<<18)
 #define IBS_OP_ENABLE		(1ULL<<17)
 #define IBS_OP_MAX_CNT		0x0000FFFFULL
 #define IBS_OP_MAX_CNT_EXT	0x007FFFFFULL	/* not a register bit mask */
+#define IBS_RIP_INVALID		(1ULL<<38)
 
 extern u32 get_ibs_caps(void);
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8be5f54d9360..e0544597cfe7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; };
 
 extern unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
+extern __must_check long
+strncpy_from_user(char *dst, const char __user *src, long count);
 
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 566e803cc602..8084bc73b18c 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
 	return n;
 }
 
-long __must_check strncpy_from_user(char *dst, const char __user *src,
-				    long count);
-long __must_check __strncpy_from_user(char *dst,
-				      const char __user *src, long count);
-
 /**
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 1c66d30971ad..fcd4b6f3ef02 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 }
 
-__must_check long
-strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long
-__strncpy_from_user(char *dst, const char __user *src, long count);
 __must_check long strnlen_user(const char __user *str, long n);
 __must_check long __strnlen_user(const char __user *str, long n);
 __must_check long strlen_user(const char __user *str);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index bb8e03407e18..e049d6da0183 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -484,9 +484,6 @@ static int __x86_pmu_event_init(struct perf_event *event)
 
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
-
-	/* mark not used */
-	event->hw.extra_reg.idx = EXTRA_REG_NONE;
 	event->hw.branch_reg.idx = EXTRA_REG_NONE;
 
 	return x86_pmu.hw_config(event);
@@ -1186,8 +1183,6 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	/*
@@ -1222,7 +1217,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 		 * event overflow
 		 */
 		handled++;
-		data.period	= event->hw.last_period;
+		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (!x86_perf_event_set_period(event))
 			continue;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 95e7fe1c5f0b..65652265fffd 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -134,8 +134,13 @@ static u64 amd_pmu_event_map(int hw_event)
 
 static int amd_pmu_hw_config(struct perf_event *event)
 {
-	int ret = x86_pmu_hw_config(event);
+	int ret;
 
+	/* pass precise event sampling to ibs: */
+	if (event->attr.precise_ip && get_ibs_caps())
+		return -ENOENT;
+
+	ret = x86_pmu_hw_config(event);
 	if (ret)
 		return ret;
 
@@ -205,10 +210,8 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	 * when we come here
 	 */
 	for (i = 0; i < x86_pmu.num_counters; i++) {
-		if (nb->owners[i] == event) {
-			cmpxchg(nb->owners+i, event, NULL);
+		if (cmpxchg(nb->owners + i, event, NULL) == event)
 			break;
-		}
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 3b8a2d30d14e..da9bcdcd9856 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -9,6 +9,7 @@
 #include <linux/perf_event.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/ptrace.h>
 
 #include <asm/apic.h>
 
@@ -16,36 +17,591 @@ static u32 ibs_caps;
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
 
-static struct pmu perf_ibs;
+#include <linux/kprobes.h>
+#include <linux/hardirq.h>
+
+#include <asm/nmi.h>
+
+#define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
+#define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
+
+enum ibs_states {
+	IBS_ENABLED	= 0,
+	IBS_STARTED	= 1,
+	IBS_STOPPING	= 2,
+
+	IBS_MAX_STATES,
+};
+
+struct cpu_perf_ibs {
+	struct perf_event	*event;
+	unsigned long		state[BITS_TO_LONGS(IBS_MAX_STATES)];
+};
+
+struct perf_ibs {
+	struct pmu	pmu;
+	unsigned int	msr;
+	u64		config_mask;
+	u64		cnt_mask;
+	u64		enable_mask;
+	u64		valid_mask;
+	u64		max_period;
+	unsigned long	offset_mask[1];
+	int		offset_max;
+	struct cpu_perf_ibs __percpu *pcpu;
+	u64		(*get_count)(u64 config);
+};
+
+struct perf_ibs_data {
+	u32		size;
+	union {
+		u32	data[0];	/* data buffer starts here */
+		u32	caps;
+	};
+	u64		regs[MSR_AMD64_IBS_REG_COUNT_MAX];
+};
+
+static int
+perf_event_set_period(struct hw_perf_event *hwc, u64 min, u64 max, u64 *hw_period)
+{
+	s64 left = local64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+	int overflow = 0;
+
+	/*
+	 * If we are way outside a reasonable range then just skip forward:
+	 */
+	if (unlikely(left <= -period)) {
+		left = period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		overflow = 1;
+	}
+
+	if (unlikely(left < (s64)min)) {
+		left += period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		overflow = 1;
+	}
+
+	/*
+	 * If the hw period that triggers the sw overflow is too short
+	 * we might hit the irq handler. This biases the results.
+	 * Thus we shorten the next-to-last period and set the last
+	 * period to the max period.
+	 */
+	if (left > max) {
+		left -= max;
+		if (left > max)
+			left = max;
+		else if (left < min)
+			left = min;
+	}
+
+	*hw_period = (u64)left;
+
+	return overflow;
+}
+
+static  int
+perf_event_try_update(struct perf_event *event, u64 new_raw_count, int width)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int shift = 64 - width;
+	u64 prev_raw_count;
+	u64 delta;
+
+	/*
+	 * Careful: an NMI might modify the previous event value.
+	 *
+	 * Our tactic to handle this is to first atomically read and
+	 * exchange a new raw count - then add that new-prev delta
+	 * count to the generic event atomically:
+	 */
+	prev_raw_count = local64_read(&hwc->prev_count);
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+					new_raw_count) != prev_raw_count)
+		return 0;
+
+	/*
+	 * Now we have the new raw value and have updated the prev
+	 * timestamp already. We can now calculate the elapsed delta
+	 * (event-)time and add that to the generic event.
+	 *
+	 * Careful, not all hw sign-extends above the physical width
+	 * of the count.
+	 */
+	delta = (new_raw_count << shift) - (prev_raw_count << shift);
+	delta >>= shift;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+
+	return 1;
+}
+
+static struct perf_ibs perf_ibs_fetch;
+static struct perf_ibs perf_ibs_op;
+
+static struct perf_ibs *get_ibs_pmu(int type)
+{
+	if (perf_ibs_fetch.pmu.type == type)
+		return &perf_ibs_fetch;
+	if (perf_ibs_op.pmu.type == type)
+		return &perf_ibs_op;
+	return NULL;
+}
+
+/*
+ * Use IBS for precise event sampling:
+ *
+ *  perf record -a -e cpu-cycles:p ...    # use ibs op counting cycle count
+ *  perf record -a -e r076:p ...          # same as -e cpu-cycles:p
+ *  perf record -a -e r0C1:p ...          # use ibs op counting micro-ops
+ *
+ * IbsOpCntCtl (bit 19) of IBS Execution Control Register (IbsOpCtl,
+ * MSRC001_1033) is used to select either cycle or micro-ops counting
+ * mode.
+ *
+ * The rip of IBS samples has skid 0. Thus, IBS supports precise
+ * levels 1 and 2 and the PERF_EFLAGS_EXACT is set. In rare cases the
+ * rip is invalid when IBS was not able to record the rip correctly.
+ * We clear PERF_EFLAGS_EXACT and take the rip from pt_regs then.
+ *
+ */
+static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
+{
+	switch (event->attr.precise_ip) {
+	case 0:
+		return -ENOENT;
+	case 1:
+	case 2:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+		switch (event->attr.config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+			*config = 0;
+			return 0;
+		}
+		break;
+	case PERF_TYPE_RAW:
+		switch (event->attr.config) {
+		case 0x0076:
+			*config = 0;
+			return 0;
+		case 0x00C1:
+			*config = IBS_OP_CNT_CTL;
+			return 0;
+		}
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	return -EOPNOTSUPP;
+}
 
 static int perf_ibs_init(struct perf_event *event)
 {
-	if (perf_ibs.type != event->attr.type)
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_ibs *perf_ibs;
+	u64 max_cnt, config;
+	int ret;
+
+	perf_ibs = get_ibs_pmu(event->attr.type);
+	if (perf_ibs) {
+		config = event->attr.config;
+	} else {
+		perf_ibs = &perf_ibs_op;
+		ret = perf_ibs_precise_event(event, &config);
+		if (ret)
+			return ret;
+	}
+
+	if (event->pmu != &perf_ibs->pmu)
 		return -ENOENT;
+
+	if (config & ~perf_ibs->config_mask)
+		return -EINVAL;
+
+	if (hwc->sample_period) {
+		if (config & perf_ibs->cnt_mask)
+			/* raw max_cnt may not be set */
+			return -EINVAL;
+		if (!event->attr.sample_freq && hwc->sample_period & 0x0f)
+			/*
+			 * lower 4 bits can not be set in ibs max cnt,
+			 * but allowing it in case we adjust the
+			 * sample period to set a frequency.
+			 */
+			return -EINVAL;
+		hwc->sample_period &= ~0x0FULL;
+		if (!hwc->sample_period)
+			hwc->sample_period = 0x10;
+	} else {
+		max_cnt = config & perf_ibs->cnt_mask;
+		config &= ~perf_ibs->cnt_mask;
+		event->attr.sample_period = max_cnt << 4;
+		hwc->sample_period = event->attr.sample_period;
+	}
+
+	if (!hwc->sample_period)
+		return -EINVAL;
+
+	/*
+	 * If we modify hwc->sample_period, we also need to update
+	 * hwc->last_period and hwc->period_left.
+	 */
+	hwc->last_period = hwc->sample_period;
+	local64_set(&hwc->period_left, hwc->sample_period);
+
+	hwc->config_base = perf_ibs->msr;
+	hwc->config = config;
+
 	return 0;
 }
 
+static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
+			       struct hw_perf_event *hwc, u64 *period)
+{
+	int overflow;
+
+	/* ignore lower 4 bits in min count: */
+	overflow = perf_event_set_period(hwc, 1<<4, perf_ibs->max_period, period);
+	local64_set(&hwc->prev_count, 0);
+
+	return overflow;
+}
+
+static u64 get_ibs_fetch_count(u64 config)
+{
+	return (config & IBS_FETCH_CNT) >> 12;
+}
+
+static u64 get_ibs_op_count(u64 config)
+{
+	u64 count = 0;
+
+	if (config & IBS_OP_VAL)
+		count += (config & IBS_OP_MAX_CNT) << 4; /* cnt rolled over */
+
+	if (ibs_caps & IBS_CAPS_RDWROPCNT)
+		count += (config & IBS_OP_CUR_CNT) >> 32;
+
+	return count;
+}
+
+static void
+perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event,
+		      u64 *config)
+{
+	u64 count = perf_ibs->get_count(*config);
+
+	/*
+	 * Set width to 64 since we do not overflow on max width but
+	 * instead on max count. In perf_ibs_set_period() we clear
+	 * prev count manually on overflow.
+	 */
+	while (!perf_event_try_update(event, count, 64)) {
+		rdmsrl(event->hw.config_base, *config);
+		count = perf_ibs->get_count(*config);
+	}
+}
+
+static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs,
+					 struct hw_perf_event *hwc, u64 config)
+{
+	wrmsrl(hwc->config_base, hwc->config | config | perf_ibs->enable_mask);
+}
+
+/*
+ * Erratum #420 Instruction-Based Sampling Engine May Generate
+ * Interrupt that Cannot Be Cleared:
+ *
+ * Must clear counter mask first, then clear the enable bit. See
+ * Revision Guide for AMD Family 10h Processors, Publication #41322.
+ */
+static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
+					  struct hw_perf_event *hwc, u64 config)
+{
+	config &= ~perf_ibs->cnt_mask;
+	wrmsrl(hwc->config_base, config);
+	config &= ~perf_ibs->enable_mask;
+	wrmsrl(hwc->config_base, config);
+}
+
+/*
+ * We cannot restore the ibs pmu state, so we always needs to update
+ * the event while stopping it and then reset the state when starting
+ * again. Thus, ignoring PERF_EF_RELOAD and PERF_EF_UPDATE flags in
+ * perf_ibs_start()/perf_ibs_stop() and instead always do it.
+ */
+static void perf_ibs_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
+	u64 period;
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+	hwc->state = 0;
+
+	perf_ibs_set_period(perf_ibs, hwc, &period);
+	set_bit(IBS_STARTED, pcpu->state);
+	perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
+
+	perf_event_update_userpage(event);
+}
+
+static void perf_ibs_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
+	u64 config;
+	int stopping;
+
+	stopping = test_and_clear_bit(IBS_STARTED, pcpu->state);
+
+	if (!stopping && (hwc->state & PERF_HES_UPTODATE))
+		return;
+
+	rdmsrl(hwc->config_base, config);
+
+	if (stopping) {
+		set_bit(IBS_STOPPING, pcpu->state);
+		perf_ibs_disable_event(perf_ibs, hwc, config);
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if (hwc->state & PERF_HES_UPTODATE)
+		return;
+
+	/*
+	 * Clear valid bit to not count rollovers on update, rollovers
+	 * are only updated in the irq handler.
+	 */
+	config &= ~perf_ibs->valid_mask;
+
+	perf_ibs_event_update(perf_ibs, event, &config);
+	hwc->state |= PERF_HES_UPTODATE;
+}
+
 static int perf_ibs_add(struct perf_event *event, int flags)
 {
+	struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
+
+	if (test_and_set_bit(IBS_ENABLED, pcpu->state))
+		return -ENOSPC;
+
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	pcpu->event = event;
+
+	if (flags & PERF_EF_START)
+		perf_ibs_start(event, PERF_EF_RELOAD);
+
 	return 0;
 }
 
 static void perf_ibs_del(struct perf_event *event, int flags)
 {
+	struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
+
+	if (!test_and_clear_bit(IBS_ENABLED, pcpu->state))
+		return;
+
+	perf_ibs_stop(event, PERF_EF_UPDATE);
+
+	pcpu->event = NULL;
+
+	perf_event_update_userpage(event);
 }
 
-static struct pmu perf_ibs = {
-	.event_init= perf_ibs_init,
-	.add= perf_ibs_add,
-	.del= perf_ibs_del,
+static void perf_ibs_read(struct perf_event *event) { }
+
+static struct perf_ibs perf_ibs_fetch = {
+	.pmu = {
+		.task_ctx_nr	= perf_invalid_context,
+
+		.event_init	= perf_ibs_init,
+		.add		= perf_ibs_add,
+		.del		= perf_ibs_del,
+		.start		= perf_ibs_start,
+		.stop		= perf_ibs_stop,
+		.read		= perf_ibs_read,
+	},
+	.msr			= MSR_AMD64_IBSFETCHCTL,
+	.config_mask		= IBS_FETCH_CONFIG_MASK,
+	.cnt_mask		= IBS_FETCH_MAX_CNT,
+	.enable_mask		= IBS_FETCH_ENABLE,
+	.valid_mask		= IBS_FETCH_VAL,
+	.max_period		= IBS_FETCH_MAX_CNT << 4,
+	.offset_mask		= { MSR_AMD64_IBSFETCH_REG_MASK },
+	.offset_max		= MSR_AMD64_IBSFETCH_REG_COUNT,
+
+	.get_count		= get_ibs_fetch_count,
 };
 
+static struct perf_ibs perf_ibs_op = {
+	.pmu = {
+		.task_ctx_nr	= perf_invalid_context,
+
+		.event_init	= perf_ibs_init,
+		.add		= perf_ibs_add,
+		.del		= perf_ibs_del,
+		.start		= perf_ibs_start,
+		.stop		= perf_ibs_stop,
+		.read		= perf_ibs_read,
+	},
+	.msr			= MSR_AMD64_IBSOPCTL,
+	.config_mask		= IBS_OP_CONFIG_MASK,
+	.cnt_mask		= IBS_OP_MAX_CNT,
+	.enable_mask		= IBS_OP_ENABLE,
+	.valid_mask		= IBS_OP_VAL,
+	.max_period		= IBS_OP_MAX_CNT << 4,
+	.offset_mask		= { MSR_AMD64_IBSOP_REG_MASK },
+	.offset_max		= MSR_AMD64_IBSOP_REG_COUNT,
+
+	.get_count		= get_ibs_op_count,
+};
+
+static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
+{
+	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
+	struct perf_event *event = pcpu->event;
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_sample_data data;
+	struct perf_raw_record raw;
+	struct pt_regs regs;
+	struct perf_ibs_data ibs_data;
+	int offset, size, check_rip, offset_max, throttle = 0;
+	unsigned int msr;
+	u64 *buf, *config, period;
+
+	if (!test_bit(IBS_STARTED, pcpu->state)) {
+		/*
+		 * Catch spurious interrupts after stopping IBS: After
+		 * disabling IBS there could be still incomming NMIs
+		 * with samples that even have the valid bit cleared.
+		 * Mark all this NMIs as handled.
+		 */
+		return test_and_clear_bit(IBS_STOPPING, pcpu->state) ? 1 : 0;
+	}
+
+	msr = hwc->config_base;
+	buf = ibs_data.regs;
+	rdmsrl(msr, *buf);
+	if (!(*buf++ & perf_ibs->valid_mask))
+		return 0;
+
+	config = &ibs_data.regs[0];
+	perf_ibs_event_update(perf_ibs, event, config);
+	perf_sample_data_init(&data, 0, hwc->last_period);
+	if (!perf_ibs_set_period(perf_ibs, hwc, &period))
+		goto out;	/* no sw counter overflow */
+
+	ibs_data.caps = ibs_caps;
+	size = 1;
+	offset = 1;
+	check_rip = (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_RIPINVALIDCHK));
+	if (event->attr.sample_type & PERF_SAMPLE_RAW)
+		offset_max = perf_ibs->offset_max;
+	else if (check_rip)
+		offset_max = 2;
+	else
+		offset_max = 1;
+	do {
+		rdmsrl(msr + offset, *buf++);
+		size++;
+		offset = find_next_bit(perf_ibs->offset_mask,
+				       perf_ibs->offset_max,
+				       offset + 1);
+	} while (offset < offset_max);
+	ibs_data.size = sizeof(u64) * size;
+
+	regs = *iregs;
+	if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
+		regs.flags &= ~PERF_EFLAGS_EXACT;
+	} else {
+		instruction_pointer_set(&regs, ibs_data.regs[1]);
+		regs.flags |= PERF_EFLAGS_EXACT;
+	}
+
+	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+		raw.size = sizeof(u32) + ibs_data.size;
+		raw.data = ibs_data.data;
+		data.raw = &raw;
+	}
+
+	throttle = perf_event_overflow(event, &data, &regs);
+out:
+	if (throttle)
+		perf_ibs_disable_event(perf_ibs, hwc, *config);
+	else
+		perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
+
+	perf_event_update_userpage(event);
+
+	return 1;
+}
+
+static int __kprobes
+perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
+{
+	int handled = 0;
+
+	handled += perf_ibs_handle_irq(&perf_ibs_fetch, regs);
+	handled += perf_ibs_handle_irq(&perf_ibs_op, regs);
+
+	if (handled)
+		inc_irq_stat(apic_perf_irqs);
+
+	return handled;
+}
+
+static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
+{
+	struct cpu_perf_ibs __percpu *pcpu;
+	int ret;
+
+	pcpu = alloc_percpu(struct cpu_perf_ibs);
+	if (!pcpu)
+		return -ENOMEM;
+
+	perf_ibs->pcpu = pcpu;
+
+	ret = perf_pmu_register(&perf_ibs->pmu, name, -1);
+	if (ret) {
+		perf_ibs->pcpu = NULL;
+		free_percpu(pcpu);
+	}
+
+	return ret;
+}
+
 static __init int perf_event_ibs_init(void)
 {
 	if (!ibs_caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	perf_pmu_register(&perf_ibs, "ibs", -1);
+	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
+	if (ibs_caps & IBS_CAPS_OPCNT)
+		perf_ibs_op.config_mask |= IBS_OP_CNT_CTL;
+	perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
+	register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
 	printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps);
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 26b3e2fef104..166546ec6aef 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1027,8 +1027,6 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	u64 status;
 	int handled;
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	/*
@@ -1082,7 +1080,7 @@ again:
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (has_branch_stack(event))
 			data.br_stack = &cpuc->lbr_stack;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 7f64df19e7dd..5a3edc27f6e5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -316,8 +316,7 @@ int intel_pmu_drain_bts_buffer(void)
 
 	ds->bts_index = ds->bts_buffer_base;
 
-	perf_sample_data_init(&data, 0);
-	data.period = event->hw.last_period;
+	perf_sample_data_init(&data, 0, event->hw.last_period);
 	regs.ip     = 0;
 
 	/*
@@ -564,8 +563,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	if (!intel_pmu_save_and_restart(event))
 		return;
 
-	perf_sample_data_init(&data, 0);
-	data.period = event->hw.last_period;
+	perf_sample_data_init(&data, 0, event->hw.last_period);
 
 	/*
 	 * We use the interrupt regs as a base because the PEBS record
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index a2dfacfd7103..47124a73dd73 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1005,8 +1005,6 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	perf_sample_data_init(&data, 0);
-
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -1034,10 +1032,12 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 		handled += overflow;
 
 		/* event overflow for sure */
-		data.period = event->hw.last_period;
+		perf_sample_data_init(&data, 0, hwc->last_period);
 
 		if (!x86_perf_event_set_period(event))
 			continue;
+
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c9a281f272fd..4243e8bbdcb1 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -24,40 +24,21 @@
 #include <trace/syscall.h>
 
 #include <asm/cacheflush.h>
+#include <asm/kprobes.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
-#include <asm/nmi.h>
-
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-/*
- * modifying_code is set to notify NMIs that they need to use
- * memory barriers when entering or exiting. But we don't want
- * to burden NMIs with unnecessary memory barriers when code
- * modification is not being done (which is most of the time).
- *
- * A mutex is already held when ftrace_arch_code_modify_prepare
- * and post_process are called. No locks need to be taken here.
- *
- * Stop machine will make sure currently running NMIs are done
- * and new NMIs will see the updated variable before we need
- * to worry about NMIs doing memory barriers.
- */
-static int modifying_code __read_mostly;
-static DEFINE_PER_CPU(int, save_modifying_code);
-
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
 	set_all_modules_text_rw();
-	modifying_code = 1;
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
 {
-	modifying_code = 0;
 	set_all_modules_text_ro();
 	set_kernel_text_ro();
 	return 0;
@@ -90,134 +71,6 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-/*
- * Modifying code must take extra care. On an SMP machine, if
- * the code being modified is also being executed on another CPU
- * that CPU will have undefined results and possibly take a GPF.
- * We use kstop_machine to stop other CPUS from exectuing code.
- * But this does not stop NMIs from happening. We still need
- * to protect against that. We separate out the modification of
- * the code to take care of this.
- *
- * Two buffers are added: An IP buffer and a "code" buffer.
- *
- * 1) Put the instruction pointer into the IP buffer
- *    and the new code into the "code" buffer.
- * 2) Wait for any running NMIs to finish and set a flag that says
- *    we are modifying code, it is done in an atomic operation.
- * 3) Write the code
- * 4) clear the flag.
- * 5) Wait for any running NMIs to finish.
- *
- * If an NMI is executed, the first thing it does is to call
- * "ftrace_nmi_enter". This will check if the flag is set to write
- * and if it is, it will write what is in the IP and "code" buffers.
- *
- * The trick is, it does not matter if everyone is writing the same
- * content to the code location. Also, if a CPU is executing code
- * it is OK to write to that code location if the contents being written
- * are the same as what exists.
- */
-
-#define MOD_CODE_WRITE_FLAG (1 << 31)	/* set when NMI should do the write */
-static atomic_t nmi_running = ATOMIC_INIT(0);
-static int mod_code_status;		/* holds return value of text write */
-static void *mod_code_ip;		/* holds the IP to write to */
-static const void *mod_code_newcode;	/* holds the text to write to the IP */
-
-static unsigned nmi_wait_count;
-static atomic_t nmi_update_count = ATOMIC_INIT(0);
-
-int ftrace_arch_read_dyn_info(char *buf, int size)
-{
-	int r;
-
-	r = snprintf(buf, size, "%u %u",
-		     nmi_wait_count,
-		     atomic_read(&nmi_update_count));
-	return r;
-}
-
-static void clear_mod_flag(void)
-{
-	int old = atomic_read(&nmi_running);
-
-	for (;;) {
-		int new = old & ~MOD_CODE_WRITE_FLAG;
-
-		if (old == new)
-			break;
-
-		old = atomic_cmpxchg(&nmi_running, old, new);
-	}
-}
-
-static void ftrace_mod_code(void)
-{
-	/*
-	 * Yes, more than one CPU process can be writing to mod_code_status.
-	 *    (and the code itself)
-	 * But if one were to fail, then they all should, and if one were
-	 * to succeed, then they all should.
-	 */
-	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
-					     MCOUNT_INSN_SIZE);
-
-	/* if we fail, then kill any new writers */
-	if (mod_code_status)
-		clear_mod_flag();
-}
-
-void ftrace_nmi_enter(void)
-{
-	__this_cpu_write(save_modifying_code, modifying_code);
-
-	if (!__this_cpu_read(save_modifying_code))
-		return;
-
-	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
-		smp_rmb();
-		ftrace_mod_code();
-		atomic_inc(&nmi_update_count);
-	}
-	/* Must have previous changes seen before executions */
-	smp_mb();
-}
-
-void ftrace_nmi_exit(void)
-{
-	if (!__this_cpu_read(save_modifying_code))
-		return;
-
-	/* Finish all executions before clearing nmi_running */
-	smp_mb();
-	atomic_dec(&nmi_running);
-}
-
-static void wait_for_nmi_and_set_mod_flag(void)
-{
-	if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG))
-		return;
-
-	do {
-		cpu_relax();
-	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
-
-	nmi_wait_count++;
-}
-
-static void wait_for_nmi(void)
-{
-	if (!atomic_read(&nmi_running))
-		return;
-
-	do {
-		cpu_relax();
-	} while (atomic_read(&nmi_running));
-
-	nmi_wait_count++;
-}
-
 static inline int
 within(unsigned long addr, unsigned long start, unsigned long end)
 {
@@ -238,26 +91,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa(ip));
 
-	mod_code_ip = (void *)ip;
-	mod_code_newcode = new_code;
-
-	/* The buffers need to be visible before we let NMIs write them */
-	smp_mb();
-
-	wait_for_nmi_and_set_mod_flag();
-
-	/* Make sure all running NMIs have finished before we write the code */
-	smp_mb();
-
-	ftrace_mod_code();
-
-	/* Make sure the write happens before clearing the bit */
-	smp_mb();
-
-	clear_mod_flag();
-	wait_for_nmi();
-
-	return mod_code_status;
+	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
 }
 
 static const unsigned char *ftrace_nop_replace(void)
@@ -334,6 +168,347 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
+int modifying_ftrace_code __read_mostly;
+
+/*
+ * A breakpoint was added to the code address we are about to
+ * modify, and this is the handle that will just skip over it.
+ * We are either changing a nop into a trace call, or a trace
+ * call to a nop. While the change is taking place, we treat
+ * it just like it was a nop.
+ */
+int ftrace_int3_handler(struct pt_regs *regs)
+{
+	if (WARN_ON_ONCE(!regs))
+		return 0;
+
+	if (!ftrace_location(regs->ip - 1))
+		return 0;
+
+	regs->ip += MCOUNT_INSN_SIZE - 1;
+
+	return 1;
+}
+
+static int ftrace_write(unsigned long ip, const char *val, int size)
+{
+	/*
+	 * On x86_64, kernel text mappings are mapped read-only with
+	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
+	 * of the kernel text mapping to modify the kernel text.
+	 *
+	 * For 32bit kernels, these mappings are same and we can use
+	 * kernel identity mapping to modify code.
+	 */
+	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
+		ip = (unsigned long)__va(__pa(ip));
+
+	return probe_kernel_write((void *)ip, val, size);
+}
+
+static int add_break(unsigned long ip, const char *old)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	if (ftrace_write(ip, &brk, 1))
+		return -EPERM;
+
+	return 0;
+}
+
+static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned const char *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_call_replace(ip, addr);
+
+	return add_break(rec->ip, old);
+}
+
+
+static int add_brk_on_nop(struct dyn_ftrace *rec)
+{
+	unsigned const char *old;
+
+	old = ftrace_nop_replace();
+
+	return add_break(rec->ip, old);
+}
+
+static int add_breakpoints(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_test_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_brk_on_nop(rec);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_brk_on_call(rec, ftrace_addr);
+	}
+	return 0;
+}
+
+/*
+ * On error, we need to remove breakpoints. This needs to
+ * be done caefully. If the address does not currently have a
+ * breakpoint, we know we are done. Otherwise, we look at the
+ * remaining 4 bytes of the instruction. If it matches a nop
+ * we replace the breakpoint with the nop. Otherwise we replace
+ * it with the call instruction.
+ */
+static int remove_breakpoint(struct dyn_ftrace *rec)
+{
+	unsigned char ins[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+	const unsigned char *nop;
+	unsigned long ftrace_addr;
+	unsigned long ip = rec->ip;
+
+	/* If we fail the read, just give up */
+	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* If this does not have a breakpoint, we are done */
+	if (ins[0] != brk)
+		return -1;
+
+	nop = ftrace_nop_replace();
+
+	/*
+	 * If the last 4 bytes of the instruction do not match
+	 * a nop, then we assume that this is a call to ftrace_addr.
+	 */
+	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
+		/*
+		 * For extra paranoidism, we check if the breakpoint is on
+		 * a call that would actually jump to the ftrace_addr.
+		 * If not, don't touch the breakpoint, we make just create
+		 * a disaster.
+		 */
+		ftrace_addr = (unsigned long)FTRACE_ADDR;
+		nop = ftrace_call_replace(ip, ftrace_addr);
+
+		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
+			return -EINVAL;
+	}
+
+	return probe_kernel_write((void *)ip, &nop[0], 1);
+}
+
+static int add_update_code(unsigned long ip, unsigned const char *new)
+{
+	/* skip breakpoint */
+	ip++;
+	new++;
+	if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1))
+		return -EPERM;
+	return 0;
+}
+
+static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+	return add_update_code(ip, new);
+}
+
+static int add_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+	return add_update_code(ip, new);
+}
+
+static int add_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_test_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_update_nop(rec);
+	}
+
+	return 0;
+}
+
+static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+
+	if (ftrace_write(ip, new, 1))
+		return -EPERM;
+
+	return 0;
+}
+
+static int finish_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+
+	if (ftrace_write(ip, new, 1))
+		return -EPERM;
+	return 0;
+}
+
+static int finish_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_update_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return finish_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return finish_update_nop(rec);
+	}
+
+	return 0;
+}
+
+static void do_sync_core(void *data)
+{
+	sync_core();
+}
+
+static void run_sync(void)
+{
+	int enable_irqs = irqs_disabled();
+
+	/* We may be called with interrupts disbled (on bootup). */
+	if (enable_irqs)
+		local_irq_enable();
+	on_each_cpu(do_sync_core, NULL, 1);
+	if (enable_irqs)
+		local_irq_disable();
+}
+
+static void ftrace_replace_code(int enable)
+{
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	const char *report = "adding breakpoints";
+	int count = 0;
+	int ret;
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_breakpoints(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+		count++;
+	}
+
+	run_sync();
+
+	report = "updating code";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	report = "removing breakpoints";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = finish_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	return;
+
+ remove_breakpoints:
+	ftrace_bug(ret, rec ? rec->ip : 0);
+	printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+		remove_breakpoint(rec);
+	}
+}
+
+void arch_ftrace_update_code(int command)
+{
+	modifying_ftrace_code++;
+
+	if (command & FTRACE_UPDATE_CALLS)
+		ftrace_replace_code(1);
+	else if (command & FTRACE_DISABLE_CALLS)
+		ftrace_replace_code(0);
+
+	if (command & FTRACE_UPDATE_TRACE_FUNC)
+		ftrace_update_ftrace_func(ftrace_trace_function);
+
+	if (command & FTRACE_START_FUNC_RET)
+		ftrace_enable_ftrace_graph_caller();
+	else if (command & FTRACE_STOP_FUNC_RET)
+		ftrace_disable_ftrace_graph_caller();
+
+	modifying_ftrace_code--;
+}
+
 int __init ftrace_dyn_arch_init(void *data)
 {
 	/* The return code is retured via data */
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 47acaf319165..eb1539eac393 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -84,7 +84,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 #define nmi_to_desc(type) (&nmi_desc[type])
 
-static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
+static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
 	struct nmiaction *a;
@@ -209,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
-static notrace __kprobes void
+static __kprobes void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
 	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
@@ -236,7 +236,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
 	outb(reason, NMI_REASON_PORT);
 }
 
-static notrace __kprobes void
+static __kprobes void
 io_check_error(unsigned char reason, struct pt_regs *regs)
 {
 	unsigned long i;
@@ -263,7 +263,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	outb(reason, NMI_REASON_PORT);
 }
 
-static notrace __kprobes void
+static __kprobes void
 unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 {
 	int handled;
@@ -305,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 static DEFINE_PER_CPU(bool, swallow_nmi);
 static DEFINE_PER_CPU(unsigned long, last_nmi_rip);
 
-static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
+static __kprobes void default_do_nmi(struct pt_regs *regs)
 {
 	unsigned char reason = 0;
 	int handled;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ff9281f16029..92d5756d85fc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -50,6 +50,7 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <linux/atomic.h>
+#include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -303,8 +304,13 @@ gp_in_kernel:
 }
 
 /* May run on IST stack. */
-dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
+dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* ftrace must be first, everything else may cause a recursive crash */
+	if (unlikely(modifying_ftrace_code) && ftrace_int3_handler(regs))
+		return;
+#endif
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index f386dc49f988..7515cf0e1805 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -216,9 +216,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	current_thread_info()->sig_on_uaccess_error = 1;
 
 	/*
-	 * 0 is a valid user pointer (in the access_ok sense) on 32-bit and
+	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
 	 * 64-bit, so we don't need to special-case it here.  For all the
-	 * vsyscalls, 0 means "don't write anything" not "write it at
+	 * vsyscalls, NULL means "don't write anything" not "write it at
 	 * address 0".
 	 */
 	ret = -EFAULT;
@@ -247,7 +247,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 		ret = sys_getcpu((unsigned __user *)regs->di,
 				 (unsigned __user *)regs->si,
-				 0);
+				 NULL);
 		break;
 	}
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 173df38dbda5..2e88438ffd83 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -459,17 +459,17 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1);
 
 	if (pmu->version == 1) {
-		pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1;
-		return;
+		pmu->nr_arch_fixed_counters = 0;
+	} else {
+		pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
+				X86_PMC_MAX_FIXED);
+		pmu->counter_bitmask[KVM_PMC_FIXED] =
+			((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
 	}
 
-	pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
-			X86_PMC_MAX_FIXED);
-	pmu->counter_bitmask[KVM_PMC_FIXED] =
-		((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
-	pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1)
-			| (((1ull << pmu->nr_arch_fixed_counters) - 1)
-				<< X86_PMC_IDX_FIXED));
+	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+		(((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED);
+	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ad85adfef843..4ff0ab9bc3c8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2210,9 +2210,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs)
+			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+				preempt_disable();
 				kvm_set_shared_msr(msr->index, msr->data,
 						   msr->mask);
+				preempt_enable();
+			}
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4044ce0bf7c1..91a5e989abcf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6336,13 +6336,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		if (npages && !old.rmap) {
 			unsigned long userspace_addr;
 
-			down_write(&current->mm->mmap_sem);
-			userspace_addr = do_mmap(NULL, 0,
+			userspace_addr = vm_mmap(NULL, 0,
 						 npages * PAGE_SIZE,
 						 PROT_READ | PROT_WRITE,
 						 map_flags,
 						 0);
-			up_write(&current->mm->mmap_sem);
 
 			if (IS_ERR((void *)userspace_addr))
 				return PTR_ERR((void *)userspace_addr);
@@ -6366,10 +6364,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
 		int ret;
 
-		down_write(&current->mm->mmap_sem);
-		ret = do_munmap(current->mm, old.userspace_addr,
+		ret = vm_munmap(old.userspace_addr,
 				old.npages * PAGE_SIZE);
-		up_write(&current->mm->mmap_sem);
 		if (ret < 0)
 			printk(KERN_WARNING
 			       "kvm_vm_ioctl_set_memory_region: "
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 25feb1ae71c5..b1e6c4b2e8eb 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -379,8 +379,8 @@ err_out:
 	return;
 }
 
-/* Decode moffset16/32/64 */
-static void __get_moffset(struct insn *insn)
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
 {
 	switch (insn->addr_bytes) {
 	case 2:
@@ -397,15 +397,19 @@ static void __get_moffset(struct insn *insn)
 		insn->moffset2.value = get_next(int, insn);
 		insn->moffset2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->moffset1.got = insn->moffset2.got = 1;
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v32(Iz) */
-static void __get_immv32(struct insn *insn)
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -417,14 +421,18 @@ static void __get_immv32(struct insn *insn)
 		insn->immediate.value = get_next(int, insn);
 		insn->immediate.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v64(Iv/Ov) */
-static void __get_immv(struct insn *insn)
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -441,15 +449,18 @@ static void __get_immv(struct insn *insn)
 		insn->immediate2.value = get_next(int, insn);
 		insn->immediate2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /* Decode ptr16:16/32(Ap) */
-static void __get_immptr(struct insn *insn)
+static int __get_immptr(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -462,14 +473,17 @@ static void __get_immptr(struct insn *insn)
 		break;
 	case 8:
 		/* ptr16:64 is not exist (no segment) */
-		return;
+		return 0;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate2.value = get_next(unsigned short, insn);
 	insn->immediate2.nbytes = 2;
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /**
@@ -489,7 +503,8 @@ void insn_get_immediate(struct insn *insn)
 		insn_get_displacement(insn);
 
 	if (inat_has_moffset(insn->attr)) {
-		__get_moffset(insn);
+		if (!__get_moffset(insn))
+			goto err_out;
 		goto done;
 	}
 
@@ -517,16 +532,20 @@ void insn_get_immediate(struct insn *insn)
 		insn->immediate2.nbytes = 4;
 		break;
 	case INAT_IMM_PTR:
-		__get_immptr(insn);
+		if (!__get_immptr(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD32:
-		__get_immv32(insn);
+		if (!__get_immv32(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD:
-		__get_immv(insn);
+		if (!__get_immv(insn))
+			goto err_out;
 		break;
 	default:
-		break;
+		/* Here, insn must have an immediate, but failed */
+		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
 		insn->immediate2.value = get_next(char, insn);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 97be9cb54483..d6ae30bbd7bb 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -7,6 +7,8 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 
+#include <asm/word-at-a-time.h>
+
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
  */
@@ -41,3 +43,104 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
+
+static inline unsigned long count_bytes(unsigned long mask)
+{
+	mask = (mask - 1) & ~mask;
+	mask >>= 7;
+	return count_masked_bytes(mask);
+}
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+{
+	long res = 0;
+
+	/*
+	 * Truncate 'max' to the user-specified limit, so that
+	 * we only have one limit we need to check in the loop
+	 */
+	if (max > count)
+		max = count;
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c;
+
+		/* Fall back to byte-at-a-time if we get a page fault */
+		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+			break;
+		/* This can write a few bytes past the NUL character, but that's ok */
+		*(unsigned long *)(dst+res) = c;
+		c = has_zero(c);
+		if (c)
+			return res + count_bytes(c);
+		res += sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+	while (max) {
+		char c;
+
+		if (unlikely(__get_user(c,src+res)))
+			return -EFAULT;
+		dst[res] = c;
+		if (!c)
+			return res;
+		res++;
+		max--;
+	}
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, that's ok - we got as much as the user asked for.
+	 */
+	if (res >= count)
+		return res;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's an EFAULT.
+	 */
+	return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	max_addr = current_thread_info()->addr_limit.seg;
+	src_addr = (unsigned long)src;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strncpy_from_user(dst, src, count, max);
+	}
+	return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index d9b094ca7aaa..ef2a6a5d78e3 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -33,93 +33,6 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 	__movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n))
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst, src, count, res)			   \
-do {									   \
-	int __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testl %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decl %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subl %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movl %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-/**
- * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- * Caller must check the specified block with access_ok() before calling
- * this function.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b7c2849ffb66..0d0326f388c0 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -9,55 +9,6 @@
 #include <asm/uaccess.h>
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst,src,count,res)			   \
-do {									   \
-	long __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testq %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decq %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subq %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movq %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		return __strncpy_from_user(dst, src, count);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
new file mode 100644
index 000000000000..7d01b8c56c00
--- /dev/null
+++ b/arch/x86/um/asm/barrier.h
@@ -0,0 +1,75 @@
+#ifndef _ASM_UM_BARRIER_H_
+#define _ASM_UM_BARRIER_H_
+
+#include <asm/asm.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm/cmpxchg.h>
+#include <asm/nops.h>
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#ifdef CONFIG_X86_32
+
+#define mb()	alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb()	alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb()	alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+
+#else /* CONFIG_X86_32 */
+
+#define mb()	asm volatile("mfence" : : : "memory")
+#define rmb()	asm volatile("lfence" : : : "memory")
+#define wmb()	asm volatile("sfence" : : : "memory")
+
+#endif /* CONFIG_X86_32 */
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+#define smp_rmb()	rmb()
+#else /* CONFIG_X86_PPRO_FENCE */
+#define smp_rmb()	barrier()
+#endif /* CONFIG_X86_PPRO_FENCE */
+
+#ifdef CONFIG_X86_OOSTORE
+#define smp_wmb()	wmb()
+#else /* CONFIG_X86_OOSTORE */
+#define smp_wmb()	barrier()
+#endif /* CONFIG_X86_OOSTORE */
+
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#else /* CONFIG_SMP */
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif
diff --git a/arch/x86/um/asm/system.h b/arch/x86/um/asm/system.h
deleted file mode 100644
index a459fd9b7598..000000000000
--- a/arch/x86/um/asm/system.h
+++ /dev/null
@@ -1,135 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif