Merge branch 'x86/numa' into x86-mm

Merge reason: Pick up x86-32 remap allocator cleanup changes - 14
commits, 3fe14ab541^..993ba1585c.

  3fe14ab541: x86-32, numa: Fix failure condition check in alloc_remap()
  993ba1585c: x86-32, numa: Update remap allocator comments

Scheduled NUMA init 32/64bit unification changes depend on them.

Signed-off-by: Tejun Heo <tj@kernel.org>

44 files changed, 220 insertions, 417 deletions

diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index d770b00..30edd61 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -386,8 +386,12 @@
 #define __NR_fanotify_init	368
 #define __NR_fanotify_mark	369
 #define __NR_prlimit64		370
+#define __NR_name_to_handle_at	371
+#define __NR_open_by_handle_at	372
+#define __NR_clock_adjtime	373
+#define __NR_syncfs		374
 
-#define __NR_syscalls		371
+#define __NR_syscalls		375
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile
index f0cb5c2..494b63b 100644
--- a/arch/microblaze/kernel/Makefile
+++ b/arch/microblaze/kernel/Makefile
@@ -10,6 +10,7 @@ CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_selfmod.o = -pg
 CFLAGS_REMOVE_heartbeat.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_process.o = -pg
 endif
 
 extra-y := head.o vmlinux.lds
diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c
index 515feb4..357d56a 100644
--- a/arch/microblaze/kernel/ftrace.c
+++ b/arch/microblaze/kernel/ftrace.c
@@ -51,6 +51,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 			: "r" (parent), "r" (return_hooker)
 	);
 
+	flush_dcache_range((u32)parent, (u32)parent + 4);
+	flush_icache_range((u32)parent, (u32)parent + 4);
+
 	if (unlikely(faulted)) {
 		ftrace_graph_stop();
 		WARN_ON(1);
@@ -95,6 +98,9 @@ static int ftrace_modify_code(unsigned long addr, unsigned int value)
 	if (unlikely(faulted))
 		return -EFAULT;
 
+	flush_dcache_range(addr, addr + 4);
+	flush_icache_range(addr, addr + 4);
+
 	return 0;
 }
 
@@ -195,8 +201,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	ret += ftrace_modify_code((unsigned long)&ftrace_caller,
 				  MICROBLAZE_NOP);
 
-	/* All changes are done - lets do caches consistent */
-	flush_icache();
 	return ret;
 }
 
@@ -210,7 +214,6 @@ int ftrace_enable_ftrace_graph_caller(void)
 
 	old_jump = *(unsigned int *)ip; /* save jump over instruction */
 	ret = ftrace_modify_code(ip, MICROBLAZE_NOP);
-	flush_icache();
 
 	pr_debug("%s: Replace instruction: 0x%x\n", __func__, old_jump);
 	return ret;
@@ -222,7 +225,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 	unsigned long ip = (unsigned long)(&ftrace_call_graph);
 
 	ret = ftrace_modify_code(ip, old_jump);
-	flush_icache();
 
 	pr_debug("%s\n", __func__);
 	return ret;
diff --git a/arch/microblaze/kernel/intc.c b/arch/microblaze/kernel/intc.c
index 5ba7e16..c88f066 100644
--- a/arch/microblaze/kernel/intc.c
+++ b/arch/microblaze/kernel/intc.c
@@ -158,11 +158,11 @@ void __init init_IRQ(void)
 	for (i = 0; i < nr_irq; ++i) {
 		if (intr_type & (0x00000001 << i)) {
 			irq_set_chip_and_handler_name(i, &intc_dev,
-				handle_edge_irq, intc_dev.name);
+				handle_edge_irq, "edge");
 			irq_clear_status_flags(i, IRQ_LEVEL);
 		} else {
 			irq_set_chip_and_handler_name(i, &intc_dev,
-				handle_level_irq, intc_dev.name);
+				handle_level_irq, "level");
 			irq_set_status_flags(i, IRQ_LEVEL);
 		}
 	}
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index e88a930..85cea81 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -375,3 +375,7 @@ ENTRY(sys_call_table)
 	.long sys_fanotify_init
 	.long sys_fanotify_mark
 	.long sys_prlimit64	/* 370 */
+	.long sys_name_to_handle_at
+	.long sys_open_by_handle_at
+	.long sys_clock_adjtime
+	.long sys_syncfs
diff --git a/arch/microblaze/lib/Makefile b/arch/microblaze/lib/Makefile
index f1fcbff..10c320a 100644
--- a/arch/microblaze/lib/Makefile
+++ b/arch/microblaze/lib/Makefile
@@ -2,6 +2,12 @@
 # Makefile
 #
 
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_ashldi3.o = -pg
+CFLAGS_REMOVE_ashrdi3.o = -pg
+CFLAGS_REMOVE_lshrdi3.o = -pg
+endif
+
 lib-y :=  memset.o
 
 ifeq ($(CONFIG_OPT_LIB_ASM),y)
diff --git a/arch/powerpc/boot/dts/p1020rdb.dts b/arch/powerpc/boot/dts/p1020rdb.dts
index 22f64b6..e0668f8 100644
--- a/arch/powerpc/boot/dts/p1020rdb.dts
+++ b/arch/powerpc/boot/dts/p1020rdb.dts
@@ -1,7 +1,7 @@
 /*
  * P1020 RDB Device Tree Source
  *
- * Copyright 2009 Freescale Semiconductor Inc.
+ * Copyright 2009-2011 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -553,7 +553,7 @@
 		reg = <0 0xffe09000 0 0x1000>;
 		bus-range = <0 255>;
 		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc30000 0x0 0x10000>;
+			  0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <16 2>;
@@ -580,8 +580,8 @@
 		#address-cells = <3>;
 		reg = <0 0xffe0a000 0 0x1000>;
 		bus-range = <0 255>;
-		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+		ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <16 2>;
@@ -590,8 +590,8 @@
 			#size-cells = <2>;
 			#address-cells = <3>;
 			device_type = "pci";
-			ranges = <0x2000000 0x0 0xc0000000
-				  0x2000000 0x0 0xc0000000
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
 				  0x0 0x20000000
 
 				  0x1000000 0x0 0x0
diff --git a/arch/powerpc/boot/dts/p2020rdb.dts b/arch/powerpc/boot/dts/p2020rdb.dts
index da4cb0d..e2d48fd 100644
--- a/arch/powerpc/boot/dts/p2020rdb.dts
+++ b/arch/powerpc/boot/dts/p2020rdb.dts
@@ -1,7 +1,7 @@
 /*
  * P2020 RDB Device Tree Source
  *
- * Copyright 2009 Freescale Semiconductor Inc.
+ * Copyright 2009-2011 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -537,7 +537,7 @@
 		reg = <0 0xffe09000 0 0x1000>;
 		bus-range = <0 255>;
 		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc30000 0x0 0x10000>;
+			  0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <25 2>;
@@ -564,8 +564,8 @@
 		#address-cells = <3>;
 		reg = <0 0xffe0a000 0 0x1000>;
 		bus-range = <0 255>;
-		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+		ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <26 2>;
@@ -574,8 +574,8 @@
 			#size-cells = <2>;
 			#address-cells = <3>;
 			device_type = "pci";
-			ranges = <0x2000000 0x0 0xc0000000
-				  0x2000000 0x0 0xc0000000
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
 				  0x0 0x20000000
 
 				  0x1000000 0x0 0x0
diff --git a/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts b/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts
index 0fe93d0..b69c3a5 100644
--- a/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts
+++ b/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts
@@ -6,7 +6,7 @@
  * This dts file allows core0 to have memory, l2, i2c, spi, gpio, dma1, usb,
  * eth1, eth2, sdhc, crypto, global-util, pci0.
  *
- * Copyright 2009 Freescale Semiconductor Inc.
+ * Copyright 2009-2011 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -342,7 +342,7 @@
 		reg = <0 0xffe09000 0 0x1000>;
 		bus-range = <0 255>;
 		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc30000 0x0 0x10000>;
+			  0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <25 2>;
diff --git a/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts b/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts
index e95a512..7a31d46c 100644
--- a/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts
+++ b/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts
@@ -7,7 +7,7 @@
  *
  * Please note to add "-b 1" for core1's dts compiling.
  *
- * Copyright 2009 Freescale Semiconductor Inc.
+ * Copyright 2009-2011 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -162,8 +162,8 @@
 		#address-cells = <3>;
 		reg = <0 0xffe0a000 0 0x1000>;
 		bus-range = <0 255>;
-		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+		ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <26 2>;
@@ -172,8 +172,8 @@
 			#size-cells = <2>;
 			#address-cells = <3>;
 			device_type = "pci";
-			ranges = <0x2000000 0x0 0xc0000000
-				  0x2000000 0x0 0xc0000000
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
 				  0x0 0x20000000
 
 				  0x1000000 0x0 0x0
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 3d569e2..3d3d416 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -163,7 +163,7 @@ static void crash_kexec_prepare_cpus(int cpu)
 }
 
 /* wait for all the CPUs to hit real mode but timeout if they don't come in */
-#ifdef CONFIG_PPC_STD_MMU_64
+#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP)
 static void crash_kexec_wait_realmode(int cpu)
 {
 	unsigned int msecs;
@@ -188,6 +188,8 @@ static void crash_kexec_wait_realmode(int cpu)
 	}
 	mb();
 }
+#else
+static inline void crash_kexec_wait_realmode(int cpu) {}
 #endif
 
 /*
@@ -344,9 +346,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crash_save_cpu(regs, crashing_cpu);
 	crash_kexec_prepare_cpus(crashing_cpu);
 	cpu_set(crashing_cpu, cpus_in_crash);
-#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP)
 	crash_kexec_wait_realmode(crashing_cpu);
-#endif
 
 	machine_kexec_mask_interrupts();
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index f4adf89..10f0aad 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -203,7 +203,7 @@ void __init free_unused_pacas(void)
 {
 	int new_size;
 
-	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * num_possible_cpus());
+	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
 
 	if (new_size >= paca_size)
 		return;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 9d4882a..21f30cb 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -509,6 +509,9 @@ void __init smp_setup_cpu_maps(void)
 	 */
 	cpu_init_thread_core_maps(nthreads);
 
+	/* Now that possible cpus are set, set nr_cpu_ids for later use */
+	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
+
 	free_unused_pacas();
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 8526bd9..2228151 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -431,7 +431,7 @@ virt_page_table_tlb_miss_fault:
 	 * The thing is, we know that in normal circumstances, this is
 	 * always called as a second level tlb miss for SW load or as a first
 	 * level TLB miss for HW load, so we should be able to peek at the
-	 * relevant informations in the first exception frame in the PACA.
+	 * relevant information in the first exception frame in the PACA.
 	 *
 	 * However, we do need to double check that, because we may just hit
 	 * a stray kernel pointer or a userland attack trying to hit those
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 2057682..f7b0772 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -46,7 +46,7 @@ config PPC_OF_BOOT_TRAMPOLINE
 	help
 	  Support from booting from Open Firmware or yaboot using an
 	  Open Firmware client interface. This enables the kernel to
-	  communicate with open firmware to retrieve system informations
+	  communicate with open firmware to retrieve system information
 	  such as the device tree.
 
 	  In case of doubt, say Y
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c319d04..0007241 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -378,7 +378,7 @@ static int __init pSeries_init_panel(void)
 
 	return 0;
 }
-arch_initcall(pSeries_init_panel);
+machine_arch_initcall(pseries, pSeries_init_panel);
 
 static int pseries_set_dabr(unsigned long dabr)
 {
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index d6479f9..a509c52 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -112,10 +112,10 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 
 	/* Fixup atomic count: it exited inside IRQ handler. */
 	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
-
+#ifdef CONFIG_HOTPLUG_CPU
 	if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE)
 		goto out;
-
+#endif
 	/* 
 	 * If the RTAS start-cpu token does not exist then presume the
 	 * cpu is already spinning.
@@ -130,7 +130,9 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 		return 0;
 	}
 
+#ifdef CONFIG_HOTPLUG_CPU
 out:
+#endif
 	return 1;
 }
 
@@ -144,16 +146,15 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 		vpa_init(cpu);
 
 	cpumask_clear_cpu(cpu, of_spin_mask);
+#ifdef CONFIG_HOTPLUG_CPU
 	set_cpu_current_state(cpu, CPU_STATE_ONLINE);
 	set_default_offline_state(cpu);
-
+#endif
 }
 #endif /* CONFIG_XICS */
 
 static void __devinit smp_pSeries_kick_cpu(int nr)
 {
-	long rc;
-	unsigned long hcpuid;
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
 	if (!smp_startup_cpu(nr))
@@ -165,16 +166,20 @@ static void __devinit smp_pSeries_kick_cpu(int nr)
 	 * the processor will continue on to secondary_start
 	 */
 	paca[nr].cpu_start = 1;
-
+#ifdef CONFIG_HOTPLUG_CPU
 	set_preferred_offline_state(nr, CPU_STATE_ONLINE);
 
 	if (get_cpu_current_state(nr) == CPU_STATE_INACTIVE) {
+		long rc;
+		unsigned long hcpuid;
+
 		hcpuid = get_hard_smp_processor_id(nr);
 		rc = plpar_hcall_norets(H_PROD, hcpuid);
 		if (rc != H_SUCCESS)
 			printk(KERN_ERR "Error: Prod to wake up processor %d "
 						"Ret= %ld\n", nr, rc);
 	}
+#endif
 }
 
 static int smp_pSeries_cpu_bootable(unsigned int nr)
diff --git a/arch/unicore32/Makefile b/arch/unicore32/Makefile
index e08d6d3..76a8bee 100644
--- a/arch/unicore32/Makefile
+++ b/arch/unicore32/Makefile
@@ -48,7 +48,7 @@ ASM_GENERIC_HEADERS	+= bitsperlong.h bug.h bugs.h
 ASM_GENERIC_HEADERS	+= cputime.h current.h
 ASM_GENERIC_HEADERS	+= device.h div64.h
 ASM_GENERIC_HEADERS	+= emergency-restart.h errno.h
-ASM_GENERIC_HEADERS	+= fb.h fcntl.h ftrace.h
+ASM_GENERIC_HEADERS	+= fb.h fcntl.h ftrace.h futex.h
 ASM_GENERIC_HEADERS	+= hardirq.h hw_irq.h
 ASM_GENERIC_HEADERS	+= ioctl.h ioctls.h ipcbuf.h irq_regs.h
 ASM_GENERIC_HEADERS	+= kdebug.h kmap_types.h
diff --git a/arch/unicore32/include/asm/futex.h b/arch/unicore32/include/asm/futex.h
deleted file mode 100644
index 07dea61..0000000
--- a/arch/unicore32/include/asm/futex.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * linux/arch/unicore32/include/asm/futex.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __UNICORE_FUTEX_H__
-#define __UNICORE_FUTEX_H__
-
-#ifdef __KERNEL__
-
-#include <linux/futex.h>
-#include <linux/preempt.h>
-#include <linux/uaccess.h>
-#include <linux/errno.h>
-
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
-	__asm__ __volatile__(					\
-	"1:	ldw.u	%1, [%2]\n"				\
-	"	" insn "\n"					\
-	"2:	stw.u	%0, [%2]\n"				\
-	"	mov	%0, #0\n"				\
-	"3:\n"							\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 4f, 2b, 4f\n"			\
-	"	.popsection\n"					\
-	"	.pushsection .fixup,\"ax\"\n"			\
-	"4:	mov	%0, %4\n"				\
-	"	b	3b\n"					\
-	"	.popsection"					\
-	: "=&r" (ret), "=&r" (oldval)				\
-	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
-
-static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
-{
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
-
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-	pagefault_disable();	/* implies preempt_disable() */
-
-	switch (op) {
-	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
-		break;
-	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
-		break;
-	case FUTEX_OP_OR:
-		__futex_atomic_op("or	%0, %1, %3", ret, oldval, uaddr, oparg);
-		break;
-	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %3",
-				ret, oldval, uaddr, ~oparg);
-		break;
-	case FUTEX_OP_XOR:
-		__futex_atomic_op("xor	%0, %1, %3", ret, oldval, uaddr, oparg);
-		break;
-	default:
-		ret = -ENOSYS;
-	}
-
-	pagefault_enable();	/* subsumes preempt_enable() */
-
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval <  cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval >  cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
-	return ret;
-}
-
-static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
-{
-	int val;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-	pagefault_disable();	/* implies preempt_disable() */
-
-	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldw.u	%0, [%3]\n"
-	"	cmpxor.a	%0, %1\n"
-	"	bne	3f\n"
-	"2:	stw.u	%2, [%3]\n"
-	"3:\n"
-	"	.pushsection __ex_table,\"a\"\n"
-	"	.align	3\n"
-	"	.long	1b, 4f, 2b, 4f\n"
-	"	.popsection\n"
-	"	.pushsection .fixup,\"ax\"\n"
-	"4:	mov	%0, %4\n"
-	"	b	3b\n"
-	"	.popsection"
-	: "=&r" (val)
-	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
-	: "cc", "memory");
-
-	pagefault_enable();	/* subsumes preempt_enable() */
-
-	return val;
-}
-
-#endif /* __KERNEL__ */
-#endif /* __UNICORE_FUTEX_H__ */
diff --git a/arch/unicore32/include/mach/PKUnity.h b/arch/unicore32/include/mach/PKUnity.h
index a18bdc3..8040d57 100644
--- a/arch/unicore32/include/mach/PKUnity.h
+++ b/arch/unicore32/include/mach/PKUnity.h
@@ -24,16 +24,6 @@
 #define PKUNITY_MMIO_BASE		0x80000000 /* 0x80000000 - 0xFFFFFFFF 2GB */
 
 /*
- * PKUNITY Memory Map Addresses: 0x0D000000 - 0x0EFFFFFF (32MB)
- *	0x0D000000 - 0x0DFFFFFF 16MB: for UVC
- *	0x0E000000 - 0x0EFFFFFF 16MB: for UNIGFX
- */
-#define PKUNITY_UVC_MMAP_BASE		0x0D000000
-#define PKUNITY_UVC_MMAP_SIZE		0x01000000 /* 16MB */
-#define PKUNITY_UNIGFX_MMAP_BASE        0x0E000000
-#define PKUNITY_UNIGFX_MMAP_SIZE        0x01000000 /* 16MB */
-
-/*
  * PKUNITY System Bus Addresses (PCI): 0x80000000 - 0xBFFFFFFF (1GB)
  * 0x80000000 - 0x8000000B 12B    PCI Configuration regs
  * 0x80010000 - 0x80010250 592B   PCI Bridge Base
diff --git a/arch/unicore32/include/mach/memory.h b/arch/unicore32/include/mach/memory.h
index 0bf21c9..4be72c2 100644
--- a/arch/unicore32/include/mach/memory.h
+++ b/arch/unicore32/include/mach/memory.h
@@ -50,7 +50,6 @@ void puv3_pci_adjust_zones(unsigned long *size, unsigned long *holes);
 
 /* kuser area */
 #define KUSER_VECPAGE_BASE	(KUSER_BASE + UL(0x3fff0000))
-#define KUSER_UNIGFX_BASE	(PAGE_OFFSET + PKUNITY_UNIGFX_MMAP_BASE)
 /* kuser_vecpage (0xbfff0000) is ro, and vectors page (0xffff0000) is rw */
 #define kuser_vecpage_to_vectors(x)	((x) - (KUSER_VECPAGE_BASE)	\
 					+ (VECTORS_BASE))
diff --git a/arch/unicore32/kernel/puv3-core.c b/arch/unicore32/kernel/puv3-core.c
index 8b1b6be..1a505a7 100644
--- a/arch/unicore32/kernel/puv3-core.c
+++ b/arch/unicore32/kernel/puv3-core.c
@@ -99,11 +99,6 @@ static struct resource puv3_unigfx_resources[] = {
 		.end	= io_v2p(PKUNITY_UNIGFX_BASE) + 0xfff,
 		.flags	= IORESOURCE_MEM,
 	},
-	[1] = {
-		.start	= PKUNITY_UNIGFX_MMAP_BASE,
-		.end	= PKUNITY_UNIGFX_MMAP_BASE + PKUNITY_UNIGFX_MMAP_SIZE,
-		.flags	= IORESOURCE_MEM,
-	},
 };
 
 static struct resource puv3_rtc_resources[] = {
diff --git a/arch/unicore32/kernel/rtc.c b/arch/unicore32/kernel/rtc.c
index c5f0682..8cad70b 100644
--- a/arch/unicore32/kernel/rtc.c
+++ b/arch/unicore32/kernel/rtc.c
@@ -88,11 +88,6 @@ static int puv3_rtc_setpie(struct device *dev, int enabled)
 	return 0;
 }
 
-static int puv3_rtc_setfreq(struct device *dev, int freq)
-{
-	return 0;
-}
-
 /* Time read/write */
 
 static int puv3_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
@@ -214,8 +209,6 @@ static const struct rtc_class_ops puv3_rtcops = {
 	.set_time	= puv3_rtc_settime,
 	.read_alarm	= puv3_rtc_getalarm,
 	.set_alarm	= puv3_rtc_setalarm,
-	.irq_set_freq	= puv3_rtc_setfreq,
-	.irq_set_state	= puv3_rtc_setpie,
 	.proc	        = puv3_rtc_proc,
 };
 
@@ -294,8 +287,6 @@ static int puv3_rtc_probe(struct platform_device *pdev)
 
 	puv3_rtc_enable(pdev, 1);
 
-	puv3_rtc_setfreq(&pdev->dev, 1);
-
 	/* register RTC and exit */
 
 	rtc = rtc_device_register("pkunity", &pdev->dev, &puv3_rtcops,
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
index 1e175a8..471b6bc 100644
--- a/arch/unicore32/kernel/setup.c
+++ b/arch/unicore32/kernel/setup.c
@@ -64,12 +64,6 @@ static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
  */
 static struct resource mem_res[] = {
 	{
-		.name = "Video RAM",
-		.start = 0,
-		.end = 0,
-		.flags = IORESOURCE_MEM
-	},
-	{
 		.name = "Kernel text",
 		.start = 0,
 		.end = 0,
@@ -83,9 +77,8 @@ static struct resource mem_res[] = {
 	}
 };
 
-#define video_ram   mem_res[0]
-#define kernel_code mem_res[1]
-#define kernel_data mem_res[2]
+#define kernel_code mem_res[0]
+#define kernel_data mem_res[1]
 
 /*
  * These functions re-use the assembly code in head.S, which
@@ -224,10 +217,6 @@ request_standard_resources(struct meminfo *mi)
 		    kernel_data.end <= res->end)
 			request_resource(res, &kernel_data);
 	}
-
-	video_ram.start = PKUNITY_UNIGFX_MMAP_BASE;
-	video_ram.end   = PKUNITY_UNIGFX_MMAP_BASE + PKUNITY_UNIGFX_MMAP_SIZE;
-	request_resource(&iomem_resource, &video_ram);
 }
 
 static void (*init_machine)(void) __initdata;
diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c
index 25abbb1..254e36f 100644
--- a/arch/unicore32/kernel/traps.c
+++ b/arch/unicore32/kernel/traps.c
@@ -22,7 +22,6 @@
 #include <linux/delay.h>
 #include <linux/hardirq.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/unistd.h>
 
diff --git a/arch/unicore32/kernel/vmlinux.lds.S b/arch/unicore32/kernel/vmlinux.lds.S
index 0b4eb89..9bf7f7a 100644
--- a/arch/unicore32/kernel/vmlinux.lds.S
+++ b/arch/unicore32/kernel/vmlinux.lds.S
@@ -14,6 +14,7 @@
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/page.h>
+#include <asm/cache.h>
 
 OUTPUT_ARCH(unicore32)
 ENTRY(stext)
@@ -29,7 +30,7 @@ SECTIONS
 	HEAD_TEXT_SECTION
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
-	PERCPU(PAGE_SIZE)
+	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
 	__init_end = .;
 
 	_stext = .;
@@ -45,10 +46,10 @@ SECTIONS
 
 	_sdata = .;
 	RO_DATA_SECTION(PAGE_SIZE)
-	RW_DATA_SECTION(32, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
-	EXCEPTION_TABLE(32)
+	EXCEPTION_TABLE(L1_CACHE_BYTES)
 	NOTES
 
 	BSS_SECTION(0, 0, 0)
diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c
index 7bf3d58..db2d334 100644
--- a/arch/unicore32/mm/mmu.c
+++ b/arch/unicore32/mm/mmu.c
@@ -338,15 +338,6 @@ void __init uc32_mm_memblock_reserve(void)
 	 * and can only be in node 0.
 	 */
 	memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
-
-#ifdef CONFIG_PUV3_UNIGFX
-	/*
-	 * These should likewise go elsewhere.  They pre-reserve the
-	 * screen/video memory region at the 48M~64M of main system memory.
-	 */
-	memblock_reserve(PKUNITY_UNIGFX_MMAP_BASE, PKUNITY_UNIGFX_MMAP_SIZE);
-	memblock_reserve(PKUNITY_UVC_MMAP_BASE, PKUNITY_UVC_MMAP_SIZE);
-#endif
 }
 
 /*
@@ -371,17 +362,6 @@ static void __init devicemaps_init(void)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
-	 * Create a mapping for UniGFX VRAM
-	 */
-#ifdef CONFIG_PUV3_UNIGFX
-	map.pfn = __phys_to_pfn(PKUNITY_UNIGFX_MMAP_BASE);
-	map.virtual = KUSER_UNIGFX_BASE;
-	map.length = PKUNITY_UNIGFX_MMAP_SIZE;
-	map.type = MT_KUSER;
-	create_mapping(&map);
-#endif
-
-	/*
 	 * Create a mapping for the machine vectors at the high-vectors
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a279d98..2b7d573 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_APIC_H
 
 #include <linux/cpumask.h>
-#include <linux/delay.h>
 #include <linux/pm.h>
 
 #include <asm/alternative.h>
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 97b6d81..057099e 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -10,7 +10,6 @@
 
 #include <linux/spinlock.h>	/* And spinlocks */
 #include <asm/io.h>		/* need byte IO */
-#include <linux/delay.h>
 
 #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
 #define dma_outb	outb_p
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 910a708..8dba769 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -95,7 +95,6 @@ extern void setup_node_to_cpumask_map(void);
 #ifdef CONFIG_X86_32
 extern unsigned long node_start_pfn[];
 extern unsigned long node_end_pfn[];
-extern unsigned long node_remap_size[];
 #define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
 
 # define SD_CACHE_NICE_TRIES	1
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 6801959..4c39baa 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,7 +21,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 EXPORT_SYMBOL(amd_nb_misc_ids);
 
 static struct pci_device_id amd_nb_link_ids[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_LINK) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
 	{}
 };
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c4e557a..5260fe9 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -16,6 +16,7 @@
 #include <linux/kprobes.h>
 #include <linux/nmi.h>
 #include <linux/module.h>
+#include <linux/delay.h>
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(void)
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 6273eee..0aced70 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -93,10 +93,6 @@ static inline void numaq_register_node(int node, struct sys_cfg_data *scd)
 						node_end_pfn[node]);
 
 	memory_present(node, node_start_pfn[node], node_end_pfn[node]);
-
-	node_remap_size[node] = node_memmap_size_bytes(node,
-					node_start_pfn[node],
-					node_end_pfn[node]);
 }
 
 /*
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 3c28928..33b10a0 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -23,6 +23,8 @@
 #include <linux/io.h>
 #include <linux/pci.h>
 #include <linux/kdebug.h>
+#include <linux/delay.h>
+#include <linux/crash_dump.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -34,6 +36,7 @@
 #include <asm/ipi.h>
 #include <asm/smp.h>
 #include <asm/x86_init.h>
+#include <asm/emergency-restart.h>
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
@@ -810,4 +813,11 @@ void __init uv_system_init(void)
 
 	/* register Legacy VGA I/O redirection handler */
 	pci_register_set_vga_state(uv_set_vga_state);
+
+	/*
+	 * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
+	 * EFI is not enabled in the kdump kernel.
+	 */
+	if (is_kdump_kernel())
+		reboot_type = BOOT_ACPI;
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 5a05ef6..3385ea2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1626,7 +1626,7 @@ out:
 static unsigned int mce_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_wait, wait);
-	if (rcu_dereference_check_mce(mcelog.next))
+	if (rcu_access_index(mcelog.next))
 		return POLLIN | POLLRDNORM;
 	if (!mce_apei_read_done && apei_check_mce())
 		return POLLIN | POLLRDNORM;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 307dfbb..929739a 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -293,14 +293,24 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 
 	/*
 	 * HACK!
-	 * We use this same function to initialize the mtrrs on boot.
-	 * The state of the boot cpu's mtrrs has been saved, and we want
-	 * to replicate across all the APs.
-	 * If we're doing that @reg is set to something special...
+	 *
+	 * We use this same function to initialize the mtrrs during boot,
+	 * resume, runtime cpu online and on an explicit request to set a
+	 * specific MTRR.
+	 *
+	 * During boot or suspend, the state of the boot cpu's mtrrs has been
+	 * saved, and we want to replicate that across all the cpus that come
+	 * online (either at the end of boot or resume or during a runtime cpu
+	 * online). If we're doing that, @reg is set to something special and on
+	 * this cpu we still do mtrr_if->set_all(). During boot/resume, this
+	 * is unnecessary if at this point we are still on the cpu that started
+	 * the boot/resume sequence. But there is no guarantee that we are still
+	 * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be
+	 * sure that we are in sync with everyone else.
 	 */
 	if (reg != ~0U)
 		mtrr_if->set(reg, base, size, type);
-	else if (!mtrr_aps_delayed_init)
+	else
 		mtrr_if->set_all();
 
 	/* Wait for the others */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 948a31e..1cb0b9f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -8,6 +8,7 @@
 #include <linux/seq_file.h>
 #include <linux/smp.h>
 #include <linux/ftrace.h>
+#include <linux/delay.h>
 
 #include <asm/apic.h>
 #include <asm/io_apic.h>
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 5ed0ab5..f924280 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -550,6 +550,7 @@ static void __exit microcode_exit(void)
 	microcode_dev_exit();
 
 	unregister_hotcpu_notifier(&mc_cpu_notifier);
+	unregister_syscore_ops(&mc_syscore_ops);
 
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index d3ce37e..08c44b0 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -6,6 +6,7 @@
 #include <linux/dmi.h>
 #include <linux/sched.h>
 #include <linux/tboot.h>
+#include <linux/delay.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
 #include <asm/apic.h>
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index bde3906..c757c0a 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -104,13 +104,9 @@ extern unsigned long highend_pfn, highstart_pfn;
 
 #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
 
-unsigned long node_remap_size[MAX_NUMNODES];
 static void *node_remap_start_vaddr[MAX_NUMNODES];
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-static unsigned long kva_start_pfn;
-static unsigned long kva_pages;
-
 int __cpuinit numa_cpu_node(int cpu)
 {
 	return apic->x86_32_numa_cpu_node(cpu);
@@ -129,7 +125,6 @@ int __init get_memcfg_numa_flat(void)
 	node_end_pfn[0] = max_pfn;
 	memblock_x86_register_active_regions(0, 0, max_pfn);
 	memory_present(0, 0, max_pfn);
-	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
 
         /* Indicate there is one node available. */
 	nodes_clear(node_online_map);
@@ -164,9 +159,8 @@ static void __init allocate_pgdat(int nid)
 {
 	char buf[16];
 
-	if (node_has_online_mem(nid) && node_remap_start_vaddr[nid])
-		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
-	else {
+	NODE_DATA(nid) = alloc_remap(nid, ALIGN(sizeof(pg_data_t), PAGE_SIZE));
+	if (!NODE_DATA(nid)) {
 		unsigned long pgdat_phys;
 		pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
 				 max_pfn_mapped<<PAGE_SHIFT,
@@ -182,25 +176,38 @@ static void __init allocate_pgdat(int nid)
 }
 
 /*
- * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel
- * virtual address space (KVA) is reserved and portions of nodes are mapped
- * using it. This is to allow node-local memory to be allocated for
- * structures that would normally require ZONE_NORMAL. The memory is
- * allocated with alloc_remap() and callers should be prepared to allocate
- * from the bootmem allocator instead.
+ * Remap memory allocator
  */
 static unsigned long node_remap_start_pfn[MAX_NUMNODES];
 static void *node_remap_end_vaddr[MAX_NUMNODES];
 static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-static unsigned long node_remap_offset[MAX_NUMNODES];
 
+/**
+ * alloc_remap - Allocate remapped memory
+ * @nid: NUMA node to allocate memory from
+ * @size: The size of allocation
+ *
+ * Allocate @size bytes from the remap area of NUMA node @nid.  The
+ * size of the remap area is predetermined by init_alloc_remap() and
+ * only the callers considered there should call this function.  For
+ * more info, please read the comment on top of init_alloc_remap().
+ *
+ * The caller must be ready to handle allocation failure from this
+ * function and fall back to regular memory allocator in such cases.
+ *
+ * CONTEXT:
+ * Single CPU early boot context.
+ *
+ * RETURNS:
+ * Pointer to the allocated memory on success, %NULL on failure.
+ */
 void *alloc_remap(int nid, unsigned long size)
 {
 	void *allocation = node_remap_alloc_vaddr[nid];
 
 	size = ALIGN(size, L1_CACHE_BYTES);
 
-	if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
+	if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
 		return NULL;
 
 	node_remap_alloc_vaddr[nid] += size;
@@ -209,26 +216,6 @@ void *alloc_remap(int nid, unsigned long size)
 	return allocation;
 }
 
-static void __init remap_numa_kva(void)
-{
-	void *vaddr;
-	unsigned long pfn;
-	int node;
-
-	for_each_online_node(node) {
-		printk(KERN_DEBUG "remap_numa_kva: node %d\n", node);
-		for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
-			vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
-			printk(KERN_DEBUG "remap_numa_kva: %08lx to pfn %08lx\n",
-				(unsigned long)vaddr,
-				node_remap_start_pfn[node] + pfn);
-			set_pmd_pfn((ulong) vaddr, 
-				node_remap_start_pfn[node] + pfn, 
-				PAGE_KERNEL_LARGE);
-		}
-	}
-}
-
 #ifdef CONFIG_HIBERNATION
 /**
  * resume_map_numa_kva - add KVA mapping to the temporary page tables created
@@ -240,15 +227,16 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 	int node;
 
 	for_each_online_node(node) {
-		unsigned long start_va, start_pfn, size, pfn;
+		unsigned long start_va, start_pfn, nr_pages, pfn;
 
 		start_va = (unsigned long)node_remap_start_vaddr[node];
 		start_pfn = node_remap_start_pfn[node];
-		size = node_remap_size[node];
+		nr_pages = (node_remap_end_vaddr[node] -
+			    node_remap_start_vaddr[node]) >> PAGE_SHIFT;
 
 		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
 
-		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+		for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
 			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
 			pgd_t *pgd = pgd_base + pgd_index(vaddr);
 			pud_t *pud = pud_offset(pgd, vaddr);
@@ -264,132 +252,102 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 }
 #endif
 
-static __init unsigned long calculate_numa_remap_pages(void)
+/**
+ * init_alloc_remap - Initialize remap allocator for a NUMA node
+ * @nid: NUMA node to initizlie remap allocator for
+ *
+ * NUMA nodes may end up without any lowmem.  As allocating pgdat and
+ * memmap on a different node with lowmem is inefficient, a special
+ * remap allocator is implemented which can be used by alloc_remap().
+ *
+ * For each node, the amount of memory which will be necessary for
+ * pgdat and memmap is calculated and two memory areas of the size are
+ * allocated - one in the node and the other in lowmem; then, the area
+ * in the node is remapped to the lowmem area.
+ *
+ * As pgdat and memmap must be allocated in lowmem anyway, this
+ * doesn't waste lowmem address space; however, the actual lowmem
+ * which gets remapped over is wasted.  The amount shouldn't be
+ * problematic on machines this feature will be used.
+ *
+ * Initialization failure isn't fatal.  alloc_remap() is used
+ * opportunistically and the callers will fall back to other memory
+ * allocation mechanisms on failure.
+ */
+static __init void init_alloc_remap(int nid)
 {
-	int nid;
-	unsigned long size, reserve_pages = 0;
+	unsigned long size, pfn;
+	u64 node_pa, remap_pa;
+	void *remap_va;
 
-	for_each_online_node(nid) {
-		u64 node_kva_target;
-		u64 node_kva_final;
-
-		/*
-		 * The acpi/srat node info can show hot-add memroy zones
-		 * where memory could be added but not currently present.
-		 */
-		printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
-			nid, node_start_pfn[nid], node_end_pfn[nid]);
-		if (node_start_pfn[nid] > max_pfn)
-			continue;
-		if (!node_end_pfn[nid])
-			continue;
-		if (node_end_pfn[nid] > max_pfn)
-			node_end_pfn[nid] = max_pfn;
-
-		/* ensure the remap includes space for the pgdat. */
-		size = node_remap_size[nid] + sizeof(pg_data_t);
-
-		/* convert size to large (pmd size) pages, rounding up */
-		size = (size + LARGE_PAGE_BYTES - 1) / LARGE_PAGE_BYTES;
-		/* now the roundup is correct, convert to PAGE_SIZE pages */
-		size = size * PTRS_PER_PTE;
-
-		node_kva_target = round_down(node_end_pfn[nid] - size,
-						 PTRS_PER_PTE);
-		node_kva_target <<= PAGE_SHIFT;
-		do {
-			node_kva_final = memblock_find_in_range(node_kva_target,
-					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
-						((u64)size)<<PAGE_SHIFT,
-						LARGE_PAGE_BYTES);
-			node_kva_target -= LARGE_PAGE_BYTES;
-		} while (node_kva_final == MEMBLOCK_ERROR &&
-			 (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
-
-		if (node_kva_final == MEMBLOCK_ERROR)
-			panic("Can not get kva ram\n");
-
-		node_remap_size[nid] = size;
-		node_remap_offset[nid] = reserve_pages;
-		reserve_pages += size;
-		printk(KERN_DEBUG "Reserving %ld pages of KVA for lmem_map of"
-				  " node %d at %llx\n",
-				size, nid, node_kva_final>>PAGE_SHIFT);
-
-		/*
-		 *  prevent kva address below max_low_pfn want it on system
-		 *  with less memory later.
-		 *  layout will be: KVA address , KVA RAM
-		 *
-		 *  we are supposed to only record the one less then max_low_pfn
-		 *  but we could have some hole in high memory, and it will only
-		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
-		 *  to use it as free.
-		 *  So memblock_x86_reserve_range here, hope we don't run out of that array
-		 */
-		memblock_x86_reserve_range(node_kva_final,
-			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
-			      "KVA RAM");
-
-		node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT;
-	}
-	printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n",
-			reserve_pages);
-	return reserve_pages;
-}
+	/*
+	 * The acpi/srat node info can show hot-add memroy zones where
+	 * memory could be added but not currently present.
+	 */
+	printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
+	       nid, node_start_pfn[nid], node_end_pfn[nid]);
+	if (node_start_pfn[nid] > max_pfn)
+		return;
+	if (!node_end_pfn[nid])
+		return;
+	if (node_end_pfn[nid] > max_pfn)
+		node_end_pfn[nid] = max_pfn;
 
-static void init_remap_allocator(int nid)
-{
-	node_remap_start_vaddr[nid] = pfn_to_kaddr(
-			kva_start_pfn + node_remap_offset[nid]);
-	node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] +
-		(node_remap_size[nid] * PAGE_SIZE);
-	node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] +
-		ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-
-	printk(KERN_DEBUG "node %d will remap to vaddr %08lx - %08lx\n", nid,
-		(ulong) node_remap_start_vaddr[nid],
-		(ulong) node_remap_end_vaddr[nid]);
+	/* calculate the necessary space aligned to large page size */
+	size = node_memmap_size_bytes(nid, node_start_pfn[nid],
+				      min(node_end_pfn[nid], max_pfn));
+	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
+	size = ALIGN(size, LARGE_PAGE_BYTES);
+
+	/* allocate node memory and the lowmem remap area */
+	node_pa = memblock_find_in_range(node_start_pfn[nid] << PAGE_SHIFT,
+					 (u64)node_end_pfn[nid] << PAGE_SHIFT,
+					 size, LARGE_PAGE_BYTES);
+	if (node_pa == MEMBLOCK_ERROR) {
+		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
+			   size, nid);
+		return;
+	}
+	memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM");
+
+	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
+					  max_low_pfn << PAGE_SHIFT,
+					  size, LARGE_PAGE_BYTES);
+	if (remap_pa == MEMBLOCK_ERROR) {
+		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
+			   size, nid);
+		memblock_x86_free_range(node_pa, node_pa + size);
+		return;
+	}
+	memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG");
+	remap_va = phys_to_virt(remap_pa);
+
+	/* perform actual remap */
+	for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
+		set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
+			    (node_pa >> PAGE_SHIFT) + pfn,
+			    PAGE_KERNEL_LARGE);
+
+	/* initialize remap allocator parameters */
+	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
+	node_remap_start_vaddr[nid] = remap_va;
+	node_remap_end_vaddr[nid] = remap_va + size;
+	node_remap_alloc_vaddr[nid] = remap_va;
+
+	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
+	       nid, node_pa, node_pa + size, remap_va, remap_va + size);
 }
 
 void __init initmem_init(void)
 {
 	int nid;
-	long kva_target_pfn;
-
-	/*
-	 * When mapping a NUMA machine we allocate the node_mem_map arrays
-	 * from node local memory.  They are then mapped directly into KVA
-	 * between zone normal and vmalloc space.  Calculate the size of
-	 * this space and use it to adjust the boundary between ZONE_NORMAL
-	 * and ZONE_HIGHMEM.
-	 */
 
 	get_memcfg_numa();
 	numa_init_array();
 
-	kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE);
-
-	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
-	do {
-		kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
-					max_low_pfn<<PAGE_SHIFT,
-					kva_pages<<PAGE_SHIFT,
-					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
-		kva_target_pfn -= PTRS_PER_PTE;
-	} while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
-
-	if (kva_start_pfn == MEMBLOCK_ERROR)
-		panic("Can not get kva space\n");
-
-	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
-		kva_start_pfn, max_low_pfn);
-	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
+	for_each_online_node(nid)
+		init_alloc_remap(nid);
 
-	/* avoid clash with initrd */
-	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
-		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
-		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
@@ -409,12 +367,8 @@ void __init initmem_init(void)
 
 	printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(max_low_pfn));
-	for_each_online_node(nid) {
-		init_remap_allocator(nid);
-
+	for_each_online_node(nid)
 		allocate_pgdat(nid);
-	}
-	remap_numa_kva();
 
 	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(highstart_pfn));
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 48651c6..1b9e82c 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -276,7 +276,6 @@ int __init get_memcfg_from_srat(void)
 		unsigned long end = min(node_end_pfn[nid], max_pfn);
 
 		memory_present(nid, start, end);
-		node_remap_size[nid] = node_memmap_size_bytes(nid, start, end);
 	}
 	return 1;
 out_fail:
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 8dace18..cf97500 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -49,6 +49,10 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 	val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0;
 	val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0;
 	val |= (counter_config->unit_mask & 0xFF) << 8;
+	counter_config->extra &= (ARCH_PERFMON_EVENTSEL_INV |
+				  ARCH_PERFMON_EVENTSEL_EDGE |
+				  ARCH_PERFMON_EVENTSEL_CMASK);
+	val |= counter_config->extra;
 	event &= model->event_mask ? model->event_mask : 0xFF;
 	val |= event & 0xFF;
 	val |= (event & 0x0F00) << 24;
@@ -440,6 +444,7 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
 		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
 		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
 		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+		oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
 	}
 
 	return 0;
diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h
index e28398d..0b7b7b1 100644
--- a/arch/x86/oprofile/op_counter.h
+++ b/arch/x86/oprofile/op_counter.h
@@ -22,6 +22,7 @@ struct op_counter_config {
 	unsigned long kernel;
 	unsigned long user;
 	unsigned long unit_mask;
+	unsigned long extra;
 };
 
 extern struct op_counter_config counter_config[];
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index a7b38d3..7cb6424 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -11,6 +11,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 
 #include <asm/mmu_context.h>
 #include <asm/uv/uv.h>