Merge commit 'origin/master' into next

124 files changed, 3064 insertions, 1979 deletions

diff --git a/arch/alpha/include/asm/errno.h b/arch/alpha/include/asm/errno.h
index 69e2655249d..98099bda937 100644
--- a/arch/alpha/include/asm/errno.h
+++ b/arch/alpha/include/asm/errno.h
@@ -120,4 +120,6 @@
 #define	EOWNERDEAD	136	/* Owner died */
 #define	ENOTRECOVERABLE	137	/* State not recoverable */
 
+#define	ERFKILL		138	/* Operation not possible due to RF-kill */
+
 #endif
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 442b87476f9..93bb4247b7e 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -536,7 +536,7 @@ setup_rt_frame(int usig, struct k_sigaction *ka, siginfo_t *info,
 	return err;
 }
 
-static inline void restart_syscall(struct pt_regs *regs)
+static inline void setup_syscall_restart(struct pt_regs *regs)
 {
 	regs->ARM_r0 = regs->ARM_ORIG_r0;
 	regs->ARM_pc -= thumb_mode(regs) ? 2 : 4;
@@ -571,7 +571,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 			}
 			/* fallthrough */
 		case -ERESTARTNOINTR:
-			restart_syscall(regs);
+			setup_syscall_restart(regs);
 		}
 	}
 
@@ -695,7 +695,7 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall)
 		if (regs->ARM_r0 == -ERESTARTNOHAND ||
 		    regs->ARM_r0 == -ERESTARTSYS ||
 		    regs->ARM_r0 == -ERESTARTNOINTR) {
-			restart_syscall(regs);
+			setup_syscall_restart(regs);
 		}
 	}
 	single_step_set(current);
diff --git a/arch/arm/mach-pxa/tosa-bt.c b/arch/arm/mach-pxa/tosa-bt.c
index fb0294bd431..c31e601eb49 100644
--- a/arch/arm/mach-pxa/tosa-bt.c
+++ b/arch/arm/mach-pxa/tosa-bt.c
@@ -35,21 +35,25 @@ static void tosa_bt_off(struct tosa_bt_data *data)
 	gpio_set_value(data->gpio_reset, 0);
 }
 
-static int tosa_bt_toggle_radio(void *data, enum rfkill_state state)
+static int tosa_bt_set_block(void *data, bool blocked)
 {
-	pr_info("BT_RADIO going: %s\n",
-			state == RFKILL_STATE_ON ? "on" : "off");
+	pr_info("BT_RADIO going: %s\n", blocked ? "off" : "on");
 
-	if (state == RFKILL_STATE_ON) {
+	if (!blocked) {
 		pr_info("TOSA_BT: going ON\n");
 		tosa_bt_on(data);
 	} else {
 		pr_info("TOSA_BT: going OFF\n");
 		tosa_bt_off(data);
 	}
+
 	return 0;
 }
 
+static const struct rfkill_ops tosa_bt_rfkill_ops = {
+	.set_block = tosa_bt_set_block,
+};
+
 static int tosa_bt_probe(struct platform_device *dev)
 {
 	int rc;
@@ -70,18 +74,14 @@ static int tosa_bt_probe(struct platform_device *dev)
 	if (rc)
 		goto err_pwr_dir;
 
-	rfk = rfkill_allocate(&dev->dev, RFKILL_TYPE_BLUETOOTH);
+	rfk = rfkill_alloc("tosa-bt", &dev->dev, RFKILL_TYPE_BLUETOOTH,
+			   &tosa_bt_rfkill_ops, data);
 	if (!rfk) {
 		rc = -ENOMEM;
 		goto err_rfk_alloc;
 	}
 
-	rfk->name = "tosa-bt";
-	rfk->toggle_radio = tosa_bt_toggle_radio;
-	rfk->data = data;
-#ifdef CONFIG_RFKILL_LEDS
-	rfk->led_trigger.name = "tosa-bt";
-#endif
+	rfkill_set_led_trigger_name(rfk, "tosa-bt");
 
 	rc = rfkill_register(rfk);
 	if (rc)
@@ -92,9 +92,7 @@ static int tosa_bt_probe(struct platform_device *dev)
 	return 0;
 
 err_rfkill:
-	if (rfk)
-		rfkill_free(rfk);
-	rfk = NULL;
+	rfkill_destroy(rfk);
 err_rfk_alloc:
 	tosa_bt_off(data);
 err_pwr_dir:
@@ -113,8 +111,10 @@ static int __devexit tosa_bt_remove(struct platform_device *dev)
 
 	platform_set_drvdata(dev, NULL);
 
-	if (rfk)
+	if (rfk) {
 		rfkill_unregister(rfk);
+		rfkill_destroy(rfk);
+	}
 	rfk = NULL;
 
 	tosa_bt_off(data);
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 168267a5dfb..117ad5920e5 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -31,7 +31,6 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/pda_power.h>
-#include <linux/rfkill.h>
 #include <linux/spi/spi.h>
 
 #include <asm/setup.h>
diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c
index 803d7be0938..27227561bad 100644
--- a/arch/avr32/kernel/signal.c
+++ b/arch/avr32/kernel/signal.c
@@ -212,7 +212,7 @@ out:
 	return err;
 }
 
-static inline void restart_syscall(struct pt_regs *regs)
+static inline void setup_syscall_restart(struct pt_regs *regs)
 {
 	if (regs->r12 == -ERESTART_RESTARTBLOCK)
 		regs->r8 = __NR_restart_syscall;
@@ -296,7 +296,7 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset, int syscall)
 			}
 			/* fall through */
 		case -ERESTARTNOINTR:
-			restart_syscall(regs);
+			setup_syscall_restart(regs);
 		}
 	}
 
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index a60cfe75791..8ea0d942cde 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -6,59 +6,65 @@
 mainmenu "Blackfin Kernel Configuration"
 
 config MMU
-	bool
-	default n
+	def_bool n
 
 config FPU
-	bool
-	default n
+	def_bool n
 
 config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y
+	def_bool y
 
 config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default n
+	def_bool n
 
 config BLACKFIN
-	bool
-	default y
+	def_bool y
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
 	select HAVE_IDE
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_BZIP2
+	select HAVE_KERNEL_LZMA
 	select HAVE_OPROFILE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 
+config GENERIC_BUG
+	def_bool y
+	depends on BUG
+
 config ZONE_DMA
-	bool
-	default y
+	def_bool y
 
 config GENERIC_FIND_NEXT_BIT
-	bool
-	default y
+	def_bool y
 
 config GENERIC_HWEIGHT
-	bool
-	default y
+	def_bool y
 
 config GENERIC_HARDIRQS
-	bool
-	default y
+	def_bool y
 
 config GENERIC_IRQ_PROBE
-	bool
-	default y
+	def_bool y
 
 config GENERIC_GPIO
-	bool
-	default y
+	def_bool y
 
 config FORCE_MAX_ZONEORDER
 	int
 	default "14"
 
 config GENERIC_CALIBRATE_DELAY
-	bool
-	default y
+	def_bool y
+
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config STACKTRACE_SUPPORT
+	def_bool y
+
+config TRACE_IRQFLAGS_SUPPORT
+	def_bool y
 
 source "init/Kconfig"
 
@@ -408,12 +414,12 @@ comment "Clock/PLL Setup"
 
 config CLKIN_HZ
 	int "Frequency of the crystal on the board in Hz"
+	default "10000000" if BFIN532_IP0X
 	default "11059200" if BFIN533_STAMP
+	default "24576000" if PNAV10
+	default "25000000" # most people use this
 	default "27000000" if BFIN533_EZKIT
-	default "25000000" if (BFIN537_STAMP || BFIN527_EZKIT || H8606_HVSISTEMAS || BLACKSTAMP || BFIN526_EZBRD || BFIN538_EZKIT || BFIN518F-EZBRD)
 	default "30000000" if BFIN561_EZKIT
-	default "24576000" if PNAV10
-	default "10000000" if BFIN532_IP0X
 	help
 	  The frequency of CLKIN crystal oscillator on the board in Hz.
 	  Warning: This value should match the crystal on the board. Otherwise,
diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile
index d54c8283825..6f9533c3d75 100644
--- a/arch/blackfin/Makefile
+++ b/arch/blackfin/Makefile
@@ -137,7 +137,7 @@ archclean:
 
 INSTALL_PATH ?= /tftpboot
 boot := arch/$(ARCH)/boot
-BOOT_TARGETS = vmImage
+BOOT_TARGETS = vmImage vmImage.bz2 vmImage.gz vmImage.lzma
 PHONY += $(BOOT_TARGETS) install
 KBUILD_IMAGE := $(boot)/vmImage
 
@@ -150,7 +150,10 @@ install:
 	$(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) install
 
 define archhelp
-  echo  '* vmImage         - Kernel-only image for U-Boot (arch/$(ARCH)/boot/vmImage)'
+  echo  '* vmImage         - Alias to selected kernel format (vmImage.gz by default)'
+  echo  '  vmImage.bz2     - Kernel-only image for U-Boot (arch/$(ARCH)/boot/vmImage.bz2)'
+  echo  '* vmImage.gz      - Kernel-only image for U-Boot (arch/$(ARCH)/boot/vmImage.gz)'
+  echo  '  vmImage.lzma    - Kernel-only image for U-Boot (arch/$(ARCH)/boot/vmImage.lzma)'
   echo  '  install         - Install kernel using'
   echo  '                     (your) ~/bin/$(CROSS_COMPILE)installkernel or'
   echo  '                     (distribution) PATH: $(CROSS_COMPILE)installkernel or'
diff --git a/arch/blackfin/boot/.gitignore b/arch/blackfin/boot/.gitignore
index 3ae03994b88..229e5080867 100644
--- a/arch/blackfin/boot/.gitignore
+++ b/arch/blackfin/boot/.gitignore
@@ -1 +1,2 @@
-+vmImage
+vmImage*
+vmlinux*
diff --git a/arch/blackfin/boot/Makefile b/arch/blackfin/boot/Makefile
index e028d13481a..3ab6f23561d 100644
--- a/arch/blackfin/boot/Makefile
+++ b/arch/blackfin/boot/Makefile
@@ -8,24 +8,41 @@
 
 MKIMAGE := $(srctree)/scripts/mkuboot.sh
 
-targets := vmImage
-extra-y += vmlinux.bin vmlinux.gz
+targets := vmImage vmImage.bz2 vmImage.gz vmImage.lzma
+extra-y += vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma
 
 quiet_cmd_uimage = UIMAGE  $@
       cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A $(ARCH) -O linux -T kernel \
-                   -C gzip -n 'Linux-$(KERNELRELEASE)' -a $(CONFIG_BOOT_LOAD) \
+                   -C $(2) -n 'Linux-$(KERNELRELEASE)' -a $(CONFIG_BOOT_LOAD) \
                    -e $(shell $(NM) vmlinux | awk '$$NF == "__start" {print $$1}') \
                    -d $< $@
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
-$(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
 
-$(obj)/vmImage: $(obj)/vmlinux.gz
-	$(call if_changed,uimage)
-	@$(kecho) 'Kernel: $@ is ready'
+$(obj)/vmlinux.bin.bz2: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,bzip2)
+
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
+
+$(obj)/vmImage.bz2: $(obj)/vmlinux.bin.bz2
+	$(call if_changed,uimage,bzip2)
+
+$(obj)/vmImage.gz: $(obj)/vmlinux.bin.gz
+	$(call if_changed,uimage,gzip)
+
+$(obj)/vmImage.lzma: $(obj)/vmlinux.bin.lzma
+	$(call if_changed,uimage,lzma)
+
+suffix-$(CONFIG_KERNEL_GZIP)  := gz
+suffix-$(CONFIG_KERNEL_BZIP2) := bz2
+suffix-$(CONFIG_KERNEL_LZMA)  := lzma
+$(obj)/vmImage: $(obj)/vmImage.$(suffix-y)
+	@ln -sf $(notdir $<) $@
 
 install:
 	sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(BOOTIMAGE) System.map "$(INSTALL_PATH)"
diff --git a/arch/blackfin/include/asm/atomic.h b/arch/blackfin/include/asm/atomic.h
index 7bbf44e4ddf..b1d92f13ef9 100644
--- a/arch/blackfin/include/asm/atomic.h
+++ b/arch/blackfin/include/asm/atomic.h
@@ -90,7 +90,7 @@ static inline int atomic_test_mask(int mask, atomic_t *v)
 
 static inline void atomic_add(int i, atomic_t *v)
 {
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter += i;
@@ -99,7 +99,7 @@ static inline void atomic_add(int i, atomic_t *v)
 
 static inline void atomic_sub(int i, atomic_t *v)
 {
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter -= i;
@@ -110,7 +110,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	int __temp = 0;
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter += i;
@@ -124,7 +124,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
 	int __temp = 0;
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter -= i;
@@ -136,7 +136,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 
 static inline void atomic_inc(volatile atomic_t *v)
 {
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter++;
@@ -145,7 +145,7 @@ static inline void atomic_inc(volatile atomic_t *v)
 
 static inline void atomic_dec(volatile atomic_t *v)
 {
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter--;
@@ -154,7 +154,7 @@ static inline void atomic_dec(volatile atomic_t *v)
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter &= ~mask;
@@ -163,7 +163,7 @@ static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 
 static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 {
-	long flags;
+	unsigned long flags;
 
 	local_irq_save_hw(flags);
 	v->counter |= mask;
diff --git a/arch/blackfin/include/asm/bfin-global.h b/arch/blackfin/include/asm/bfin-global.h
index daffc0684e7..e39277ea43e 100644
--- a/arch/blackfin/include/asm/bfin-global.h
+++ b/arch/blackfin/include/asm/bfin-global.h
@@ -31,7 +31,7 @@
 
 #ifndef __ASSEMBLY__
 
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
 #include <asm/ptrace.h>
 #include <asm/user.h>
 #include <linux/linkage.h>
@@ -99,15 +99,6 @@ extern const char bfin_board_name[];
 extern unsigned long bfin_sic_iwr[];
 extern unsigned vr_wakeup;
 extern u16 _bfin_swrst; /* shadow for Software Reset Register (SWRST) */
-extern unsigned long _ramstart, _ramend, _rambase;
-extern unsigned long memory_start, memory_end, physical_mem_end;
-extern char _stext_l1[], _etext_l1[], _sdata_l1[], _edata_l1[], _sbss_l1[],
-	_ebss_l1[], _l1_lma_start[], _sdata_b_l1[], _sbss_b_l1[], _ebss_b_l1[],
-	_stext_l2[], _etext_l2[], _sdata_l2[], _edata_l2[], _sbss_l2[],
-	_ebss_l2[], _l2_lma_start[];
-
-/* only used when MTD_UCLINUX */
-extern unsigned long memory_mtd_start, memory_mtd_end, mtd_size;
 
 #ifdef CONFIG_BFIN_ICACHE_LOCK
 extern void cache_grab_lock(int way);
diff --git a/arch/blackfin/include/asm/bitops.h b/arch/blackfin/include/asm/bitops.h
index 21b036eadab..75fee2f7d9f 100644
--- a/arch/blackfin/include/asm/bitops.h
+++ b/arch/blackfin/include/asm/bitops.h
@@ -109,7 +109,8 @@ static inline void clear_bit(int nr, volatile unsigned long *addr)
 
 static inline void change_bit(int nr, volatile unsigned long *addr)
 {
-	int mask, flags;
+	int mask;
+	unsigned long flags;
 	unsigned long *ADDR = (unsigned long *)addr;
 
 	ADDR += nr >> 5;
diff --git a/arch/blackfin/include/asm/bug.h b/arch/blackfin/include/asm/bug.h
index 6d3e11b1fc5..655e49540e4 100644
--- a/arch/blackfin/include/asm/bug.h
+++ b/arch/blackfin/include/asm/bug.h
@@ -2,13 +2,58 @@
 #define _BLACKFIN_BUG_H
 
 #ifdef CONFIG_BUG
-#define HAVE_ARCH_BUG
 
-#define BUG() do { \
-	dump_bfin_trace_buffer(); \
-	printk(KERN_EMERG "BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
-	panic("BUG!"); \
-} while (0)
+#define BFIN_BUG_OPCODE	0xefcd
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+#define _BUG_OR_WARN(flags)						\
+	asm volatile(							\
+		"1:	.hword	%0\n"					\
+		"	.section __bug_table,\"a\",@progbits\n"		\
+		"2:	.long	1b\n"					\
+		"	.long	%1\n"					\
+		"	.short	%2\n"					\
+		"	.short	%3\n"					\
+		"	.org	2b + %4\n"				\
+		"	.previous"					\
+		:							\
+		: "i"(BFIN_BUG_OPCODE), "i"(__FILE__),			\
+		  "i"(__LINE__), "i"(flags),				\
+		  "i"(sizeof(struct bug_entry)))
+
+#else
+
+#define _BUG_OR_WARN(flags)						\
+	asm volatile(							\
+		"1:	.hword	%0\n"					\
+		"	.section __bug_table,\"a\",@progbits\n"		\
+		"2:	.long	1b\n"					\
+		"	.short	%1\n"					\
+		"	.org	2b + %2\n"				\
+		"	.previous"					\
+		:							\
+		: "i"(BFIN_BUG_OPCODE), "i"(flags),			\
+		  "i"(sizeof(struct bug_entry)))
+
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
+#define BUG()								\
+	do {								\
+		_BUG_OR_WARN(0);					\
+		for (;;);						\
+	} while (0)
+
+#define WARN_ON(condition)							\
+	({								\
+		int __ret_warn_on = !!(condition);			\
+		if (unlikely(__ret_warn_on))				\
+			_BUG_OR_WARN(BUGFLAG_WARNING);			\
+		unlikely(__ret_warn_on);				\
+	})
+
+#define HAVE_ARCH_BUG
+#define HAVE_ARCH_WARN_ON
 
 #endif
 
diff --git a/arch/blackfin/include/asm/cache.h b/arch/blackfin/include/asm/cache.h
index 86637814cf2..2ef669ed922 100644
--- a/arch/blackfin/include/asm/cache.h
+++ b/arch/blackfin/include/asm/cache.h
@@ -34,9 +34,13 @@
 #define L1_CACHE_SHIFT_MAX	5
 
 #if defined(CONFIG_SMP) && \
-    !defined(CONFIG_BFIN_CACHE_COHERENT) && \
-    defined(CONFIG_BFIN_DCACHE)
-#define __ARCH_SYNC_CORE_DCACHE
+    !defined(CONFIG_BFIN_CACHE_COHERENT)
+# if defined(CONFIG_BFIN_ICACHE)
+# define __ARCH_SYNC_CORE_ICACHE
+# endif
+# if defined(CONFIG_BFIN_DCACHE)
+# define __ARCH_SYNC_CORE_DCACHE
+# endif
 #ifndef __ASSEMBLY__
 asmlinkage void __raw_smp_mark_barrier_asm(void);
 asmlinkage void __raw_smp_check_barrier_asm(void);
@@ -51,6 +55,7 @@ static inline void smp_check_barrier(void)
 }
 
 void resync_core_dcache(void);
+void resync_core_icache(void);
 #endif
 #endif
 
diff --git a/arch/blackfin/include/asm/cacheflush.h b/arch/blackfin/include/asm/cacheflush.h
index 94697f0f6f4..5c17dee53b5 100644
--- a/arch/blackfin/include/asm/cacheflush.h
+++ b/arch/blackfin/include/asm/cacheflush.h
@@ -37,6 +37,7 @@ extern void blackfin_dcache_flush_range(unsigned long start_address, unsigned lo
 extern void blackfin_dcache_invalidate_range(unsigned long start_address, unsigned long end_address);
 extern void blackfin_dflush_page(void *page);
 extern void blackfin_invalidate_entire_dcache(void);
+extern void blackfin_invalidate_entire_icache(void);
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
@@ -97,7 +98,7 @@ do { memcpy(dst, src, len);						\
 extern unsigned long reserved_mem_dcache_on;
 extern unsigned long reserved_mem_icache_on;
 
-static inline int bfin_addr_dcachable(unsigned long addr)
+static inline int bfin_addr_dcacheable(unsigned long addr)
 {
 #ifdef CONFIG_BFIN_DCACHE
 	if (addr < (_ramend - DMA_UNCACHED_REGION))
diff --git a/arch/blackfin/include/asm/cpu.h b/arch/blackfin/include/asm/cpu.h
index c2594ef877f..565b8136855 100644
--- a/arch/blackfin/include/asm/cpu.h
+++ b/arch/blackfin/include/asm/cpu.h
@@ -34,6 +34,7 @@ struct blackfin_cpudata {
 	unsigned int dmemctl;
 	unsigned long loops_per_jiffy;
 	unsigned long dcache_invld_count;
+	unsigned long icache_invld_count;
 };
 
 DECLARE_PER_CPU(struct blackfin_cpudata, cpu_data);
diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h
index 40a8c178f10..8643680f0f7 100644
--- a/arch/blackfin/include/asm/ftrace.h
+++ b/arch/blackfin/include/asm/ftrace.h
@@ -1 +1,13 @@
-/* empty */
+/*
+ * Blackfin ftrace code
+ *
+ * Copyright 2009 Analog Devices Inc.
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef __ASM_BFIN_FTRACE_H__
+#define __ASM_BFIN_FTRACE_H__
+
+#define MCOUNT_INSN_SIZE	8 /* sizeof mcount call: LINK + CALL */
+
+#endif
diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h
index 51d0bf5e289..bbe1c3726b6 100644
--- a/arch/blackfin/include/asm/ipipe.h
+++ b/arch/blackfin/include/asm/ipipe.h
@@ -35,10 +35,10 @@
 #include <asm/atomic.h>
 #include <asm/traps.h>
 
-#define IPIPE_ARCH_STRING     "1.9-01"
+#define IPIPE_ARCH_STRING     "1.10-00"
 #define IPIPE_MAJOR_NUMBER    1
-#define IPIPE_MINOR_NUMBER    9
-#define IPIPE_PATCH_NUMBER    1
+#define IPIPE_MINOR_NUMBER    10
+#define IPIPE_PATCH_NUMBER    0
 
 #ifdef CONFIG_SMP
 #error "I-pipe/blackfin: SMP not implemented"
@@ -54,10 +54,11 @@ do {						\
 
 #define task_hijacked(p)						\
 	({								\
-		int __x__ = ipipe_current_domain != ipipe_root_domain;	\
-		/* We would need to clear the SYNC flag for the root domain */ \
-		/* over the current processor in SMP mode. */		\
-		local_irq_enable_hw(); __x__;				\
+		int __x__ = __ipipe_root_domain_p;			\
+		__clear_bit(IPIPE_SYNC_FLAG, &ipipe_root_cpudom_var(status)); \
+		if (__x__)						\
+			local_irq_enable_hw();				\
+		!__x__;							\
 	})
 
 struct ipipe_domain;
@@ -179,23 +180,24 @@ static inline unsigned long __ipipe_ffnz(unsigned long ul)
 
 #define __ipipe_run_isr(ipd, irq)					\
 	do {								\
-		if (ipd == ipipe_root_domain) {				\
+		if (!__ipipe_pipeline_head_p(ipd))			\
 			local_irq_enable_hw();				\
-			if (ipipe_virtual_irq_p(irq))			\
+		if (ipd == ipipe_root_domain) {				\
+			if (unlikely(ipipe_virtual_irq_p(irq))) {	\
+				irq_enter();				\
 				ipd->irqs[irq].handler(irq, ipd->irqs[irq].cookie); \
-			else						\
+				irq_exit();				\
+			} else 						\
 				ipd->irqs[irq].handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)); \
-			local_irq_disable_hw();				\
 		} else {						\
 			__clear_bit(IPIPE_SYNC_FLAG, &ipipe_cpudom_var(ipd, status)); \
-			local_irq_enable_nohead(ipd);			\
 			ipd->irqs[irq].handler(irq, ipd->irqs[irq].cookie); \
 			/* Attempt to exit the outer interrupt level before \
 			 * starting the deferred IRQ processing. */	\
-			local_irq_disable_nohead(ipd);			\
 			__ipipe_run_irqtail();				\
 			__set_bit(IPIPE_SYNC_FLAG, &ipipe_cpudom_var(ipd, status)); \
 		}							\
+		local_irq_disable_hw();					\
 	} while (0)
 
 #define __ipipe_syscall_watched_p(p, sc)	\
diff --git a/arch/blackfin/include/asm/irq.h b/arch/blackfin/include/asm/irq.h
index 7645e85a5f6..400bdd52ce8 100644
--- a/arch/blackfin/include/asm/irq.h
+++ b/arch/blackfin/include/asm/irq.h
@@ -17,270 +17,17 @@
 #ifndef _BFIN_IRQ_H_
 #define _BFIN_IRQ_H_
 
-/* SYS_IRQS and NR_IRQS are defined in <mach-bf5xx/irq.h>*/
-#include <mach/irq.h>
-#include <asm/pda.h>
-#include <asm/processor.h>
-
-#ifdef CONFIG_SMP
-/* Forward decl needed due to cdef inter dependencies */
-static inline uint32_t __pure bfin_dspid(void);
-# define blackfin_core_id() (bfin_dspid() & 0xff)
-# define bfin_irq_flags cpu_pda[blackfin_core_id()].imask
-#else
-extern unsigned long bfin_irq_flags;
-#endif
-
-#ifdef CONFIG_IPIPE
-
-#include <linux/ipipe_trace.h>
+#include <linux/irqflags.h>
 
-void __ipipe_unstall_root(void);
-
-void __ipipe_restore_root(unsigned long flags);
-
-#ifdef CONFIG_DEBUG_HWERR
-# define __all_masked_irq_flags 0x3f
-# define __save_and_cli_hw(x) \
-	__asm__ __volatile__( \
-		"cli %0;" \
-		"sti %1;" \
-		: "=&d"(x) \
-		: "d" (0x3F) \
-	)
-#else
-# define __all_masked_irq_flags 0x1f
-# define __save_and_cli_hw(x) \
-	__asm__ __volatile__( \
-		"cli %0;" \
-		: "=&d"(x) \
-	)
-#endif
-
-#define irqs_enabled_from_flags_hw(x)	((x) != __all_masked_irq_flags)
-#define raw_irqs_disabled_flags(flags)	(!irqs_enabled_from_flags_hw(flags))
-#define local_test_iflag_hw(x)		irqs_enabled_from_flags_hw(x)
-
-#define local_save_flags(x)					 \
-	do {							 \
-		(x) = __ipipe_test_root() ?			 \
-			__all_masked_irq_flags : bfin_irq_flags; \
-		barrier();					 \
-	} while (0)
-
-#define local_irq_save(x)					 \
-	do {						 	 \
-		(x) = __ipipe_test_and_stall_root() ?		 \
-			__all_masked_irq_flags : bfin_irq_flags; \
-		barrier();					 \
-	} while (0)
-
-static inline void local_irq_restore(unsigned long x)
-{
-	barrier();
-	__ipipe_restore_root(x == __all_masked_irq_flags);
-}
-
-#define local_irq_disable()			\
-	do {					\
-		__ipipe_stall_root();		\
-		barrier();			\
-	} while (0)
-
-static inline void local_irq_enable(void)
-{
-	barrier();
-	__ipipe_unstall_root();
-}
-
-#define irqs_disabled()		__ipipe_test_root()
-
-#define local_save_flags_hw(x) \
-	__asm__ __volatile__( \
-		"cli %0;" \
-		"sti %0;" \
-		: "=d"(x) \
-	)
-
-#define	irqs_disabled_hw()				\
-	({						\
-		unsigned long flags;			\
-		local_save_flags_hw(flags);		\
-		!irqs_enabled_from_flags_hw(flags);	\
-	})
-
-static inline unsigned long raw_mangle_irq_bits(int virt, unsigned long real)
-{
-	/* Merge virtual and real interrupt mask bits into a single
-	   32bit word. */
-	return (real & ~(1 << 31)) | ((virt != 0) << 31);
-}
-
-static inline int raw_demangle_irq_bits(unsigned long *x)
-{
-	int virt = (*x & (1 << 31)) != 0;
-	*x &= ~(1L << 31);
-	return virt;
-}
-
-#ifdef CONFIG_IPIPE_TRACE_IRQSOFF
-
-#define local_irq_disable_hw()						\
-	do {								\
-		int _tmp_dummy;						\
-		if (!irqs_disabled_hw())				\
-			ipipe_trace_begin(0x80000000);			\
-		__asm__ __volatile__ ("cli %0;" : "=d" (_tmp_dummy) : );	\
-	} while (0)
-
-#define local_irq_enable_hw()						\
-	do {								\
-		if (irqs_disabled_hw())					\
-			ipipe_trace_end(0x80000000);			\
-		__asm__ __volatile__ ("sti %0;" : : "d"(bfin_irq_flags));	\
-	} while (0)
-
-#define local_irq_save_hw(x)				\
-	do {						\
-		__save_and_cli_hw(x);			\
-		if (local_test_iflag_hw(x))		\
-			ipipe_trace_begin(0x80000001);	\
-	} while (0)
-
-#define local_irq_restore_hw(x)				\
-	do {						\
-		if (local_test_iflag_hw(x)) {		\
-			ipipe_trace_end(0x80000001);	\
-			local_irq_enable_hw_notrace();	\
-		}					\
-	} while (0)
-
-#define local_irq_disable_hw_notrace()					\
-	do {								\
-		int _tmp_dummy;						\
-		__asm__ __volatile__ ("cli %0;" : "=d" (_tmp_dummy) : );	\
-	} while (0)
-
-#define local_irq_enable_hw_notrace() \
-	__asm__ __volatile__( \
-		"sti %0;" \
-		: \
-		: "d"(bfin_irq_flags) \
-	)
-
-#define local_irq_save_hw_notrace(x) __save_and_cli_hw(x)
-
-#define local_irq_restore_hw_notrace(x)			\
-	do {						\
-		if (local_test_iflag_hw(x))		\
-			local_irq_enable_hw_notrace();	\
-	} while (0)
-
-#else /* CONFIG_IPIPE_TRACE_IRQSOFF */
-
-#define local_irq_enable_hw() \
-	__asm__ __volatile__( \
-		"sti %0;" \
-		: \
-		: "d"(bfin_irq_flags) \
-	)
-
-#define local_irq_disable_hw()			\
-	do {					\
-		int _tmp_dummy;			\
-		__asm__ __volatile__ (		\
-			"cli %0;"		\
-			: "=d" (_tmp_dummy));	\
-	} while (0)
-
-#define local_irq_restore_hw(x) \
-	do { \
-		if (irqs_enabled_from_flags_hw(x)) \
-			local_irq_enable_hw(); \
-	} while (0)
-
-#define local_irq_save_hw(x)		__save_and_cli_hw(x)
-
-#define local_irq_disable_hw_notrace()	local_irq_disable_hw()
-#define local_irq_enable_hw_notrace()	local_irq_enable_hw()
-#define local_irq_save_hw_notrace(x)	local_irq_save_hw(x)
-#define local_irq_restore_hw_notrace(x)	local_irq_restore_hw(x)
-
-#endif  /* CONFIG_IPIPE_TRACE_IRQSOFF */
-
-#else /* !CONFIG_IPIPE */
-
-/*
- * Interrupt configuring macros.
- */
-#define local_irq_disable() \
-	do { \
-		int __tmp_dummy; \
-		__asm__ __volatile__( \
-			"cli %0;" \
-			: "=d" (__tmp_dummy) \
-		); \
-	} while (0)
-
-#define local_irq_enable() \
-	__asm__ __volatile__( \
-		"sti %0;" \
-		: \
-		: "d" (bfin_irq_flags) \
-	)
-
-#ifdef CONFIG_DEBUG_HWERR
-# define __save_and_cli(x) \
-	__asm__ __volatile__( \
-		"cli %0;" \
-		"sti %1;" \
-		: "=&d" (x) \
-		: "d" (0x3F) \
-	)
-#else
-# define __save_and_cli(x) \
-	__asm__ __volatile__( \
-		"cli %0;" \
-		: "=&d" (x) \
-	)
-#endif
-
-#define local_save_flags(x) \
-	__asm__ __volatile__( \
-		"cli %0;" \
-		"sti %0;" \
-		: "=d" (x) \
-	)
-
-#ifdef CONFIG_DEBUG_HWERR
-#define irqs_enabled_from_flags(x) (((x) & ~0x3f) != 0)
-#else
-#define irqs_enabled_from_flags(x) ((x) != 0x1f)
-#endif
-
-#define local_irq_restore(x) \
-	do { \
-		if (irqs_enabled_from_flags(x)) \
-			local_irq_enable(); \
-	} while (0)
-
-/* For spinlocks etc */
-#define local_irq_save(x) __save_and_cli(x)
-
-#define irqs_disabled()				\
-({						\
-	unsigned long flags;			\
-	local_save_flags(flags);		\
-	!irqs_enabled_from_flags(flags);	\
-})
-
-#define local_irq_save_hw(x)		local_irq_save(x)
-#define local_irq_restore_hw(x)		local_irq_restore(x)
-#define local_irq_enable_hw()		local_irq_enable()
-#define local_irq_disable_hw()		local_irq_disable()
-#define irqs_disabled_hw()		irqs_disabled()
+/* SYS_IRQS and NR_IRQS are defined in <mach-bf5xx/irq.h> */
+#include <mach/irq.h>
 
-#endif /* !CONFIG_IPIPE */
+/* Xenomai IPIPE helpers */
+#define local_irq_restore_hw(x) local_irq_restore(x)
+#define local_irq_save_hw(x)    local_irq_save(x)
+#define local_irq_enable_hw(x)  local_irq_enable(x)
+#define local_irq_disable_hw(x) local_irq_disable(x)
+#define irqs_disabled_hw(x)     irqs_disabled(x)
 
 #if ANOMALY_05000244 && defined(CONFIG_BFIN_ICACHE)
 # define NOP_PAD_ANOMALY_05000244 "nop; nop;"
diff --git a/arch/blackfin/include/asm/irqflags.h b/arch/blackfin/include/asm/irqflags.h
new file mode 100644
index 00000000000..139cba4651b
--- /dev/null
+++ b/arch/blackfin/include/asm/irqflags.h
@@ -0,0 +1,63 @@
+/*
+ * interface to Blackfin CEC
+ *
+ * Copyright 2009 Analog Devices Inc.
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef __ASM_BFIN_IRQFLAGS_H__
+#define __ASM_BFIN_IRQFLAGS_H__
+
+#ifdef CONFIG_SMP
+# include <asm/pda.h>
+# include <asm/processor.h>
+/* Forward decl needed due to cdef inter dependencies */
+static inline uint32_t __pure bfin_dspid(void);
+# define blackfin_core_id() (bfin_dspid() & 0xff)
+# define bfin_irq_flags cpu_pda[blackfin_core_id()].imask
+#else
+extern unsigned long bfin_irq_flags;
+#endif
+
+static inline void bfin_sti(unsigned long flags)
+{
+	asm volatile("sti %0;" : : "d" (flags));
+}
+
+static inline unsigned long bfin_cli(void)
+{
+	unsigned long flags;
+	asm volatile("cli %0;" : "=d" (flags));
+	return flags;
+}
+
+static inline void raw_local_irq_disable(void)
+{
+	bfin_cli();
+}
+static inline void raw_local_irq_enable(void)
+{
+	bfin_sti(bfin_irq_flags);
+}
+
+#define raw_local_save_flags(flags) do { (flags) = bfin_read_IMASK(); } while (0)
+
+#define raw_irqs_disabled_flags(flags) (((flags) & ~0x3f) == 0)
+
+static inline void raw_local_irq_restore(unsigned long flags)
+{
+	if (!raw_irqs_disabled_flags(flags))
+		raw_local_irq_enable();
+}
+
+static inline unsigned long __raw_local_irq_save(void)
+{
+	unsigned long flags = bfin_cli();
+#ifdef CONFIG_DEBUG_HWERR
+	bfin_sti(0x3f);
+#endif
+	return flags;
+}
+#define raw_local_irq_save(flags) do { (flags) = __raw_local_irq_save(); } while (0)
+
+#endif
diff --git a/arch/blackfin/include/asm/mutex-dec.h b/arch/blackfin/include/asm/mutex-dec.h
deleted file mode 100644
index 0134151656a..00000000000
--- a/arch/blackfin/include/asm/mutex-dec.h
+++ /dev/null
@@ -1,112 +0,0 @@
-/*
- * include/asm-generic/mutex-dec.h
- *
- * Generic implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- */
-#ifndef _ASM_GENERIC_MUTEX_DEC_H
-#define _ASM_GENERIC_MUTEX_DEC_H
-
-/**
- *  __mutex_fastpath_lock - try to take the lock by moving the count
- *                          from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function MUST leave the value lower than
- * 1 even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, fastcall void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_dec_return(count) < 0))
-		fail_fn(count);
-	else
-		smp_mb();
-}
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
- * or anything the slow path function returns.
- */
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count, fastcall int (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_dec_return(count) < 0))
-		return fail_fn(count);
-	else {
-		smp_mb();
-		return 0;
-	}
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the count from 0 to 1
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 0
- *
- * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
- * In the failure case, this function is allowed to either set the value to
- * 1, or to set it to a value lower than 1.
- *
- * If the implementation sets it to a value of lower than 1, then the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, fastcall void (*fail_fn)(atomic_t *))
-{
-	smp_mb();
-	if (unlikely(atomic_inc_return(count) <= 0))
-		fail_fn(count);
-}
-
-#define __mutex_slowpath_needs_to_unlock()		1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: fallback function
- *
- * Change the count from 1 to a value lower than 1, and return 0 (failure)
- * if it wasn't 1 originally, or return 1 (success) otherwise. This function
- * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
- * Additionally, if the value was < 0 originally, this function must not leave
- * it to 0 on failure.
- *
- * If the architecture has no effective trylock variant, it should call the
- * <fail_fn> spinlock-based trylock variant unconditionally.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	/*
-	 * We have two variants here. The cmpxchg based one is the best one
-	 * because it never induce a false contention state.  It is included
-	 * here because architectures using the inc/dec algorithms over the
-	 * xchg ones are much more likely to support cmpxchg natively.
-	 *
-	 * If not we fall back to the spinlock based variant - that is
-	 * just as efficient (and simpler) as a 'destructive' probing of
-	 * the mutex state would be.
-	 */
-#ifdef __HAVE_ARCH_CMPXCHG
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1)) {
-		smp_mb();
-		return 1;
-	}
-	return 0;
-#else
-	return fail_fn(count);
-#endif
-}
-
-#endif
diff --git a/arch/blackfin/include/asm/sections.h b/arch/blackfin/include/asm/sections.h
index 1443c3353a8..e7fd0ecd73f 100644
--- a/arch/blackfin/include/asm/sections.h
+++ b/arch/blackfin/include/asm/sections.h
@@ -4,4 +4,15 @@
 /* nothing to see, move along */
 #include <asm-generic/sections.h>
 
+/* only used when MTD_UCLINUX */
+extern unsigned long memory_mtd_start, memory_mtd_end, mtd_size;
+
+extern unsigned long _ramstart, _ramend, _rambase;
+extern unsigned long memory_start, memory_end, physical_mem_end;
+
+extern char _stext_l1[], _etext_l1[], _sdata_l1[], _edata_l1[], _sbss_l1[],
+	_ebss_l1[], _l1_lma_start[], _sdata_b_l1[], _sbss_b_l1[], _ebss_b_l1[],
+	_stext_l2[], _etext_l2[], _sdata_l2[], _edata_l2[], _sbss_l2[],
+	_ebss_l2[], _l2_lma_start[];
+
 #endif
diff --git a/arch/blackfin/include/asm/system.h b/arch/blackfin/include/asm/system.h
index a4c8254bec5..294dbda2416 100644
--- a/arch/blackfin/include/asm/system.h
+++ b/arch/blackfin/include/asm/system.h
@@ -35,10 +35,10 @@
 #define _BLACKFIN_SYSTEM_H
 
 #include <linux/linkage.h>
-#include <linux/compiler.h>
+#include <linux/irqflags.h>
 #include <mach/anomaly.h>
+#include <asm/cache.h>
 #include <asm/pda.h>
-#include <asm/processor.h>
 #include <asm/irq.h>
 
 /*
diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
index cf5066d3efd..da35133c171 100644
--- a/arch/blackfin/include/asm/unistd.h
+++ b/arch/blackfin/include/asm/unistd.h
@@ -380,8 +380,9 @@
 #define __NR_inotify_init1	365
 #define __NR_preadv		366
 #define __NR_pwritev		367
+#define __NR_rt_tgsigqueueinfo	368
 
-#define __NR_syscall		368
+#define __NR_syscall		369
 #define NR_syscalls		__NR_syscall
 
 /* Old optional stuff no one actually uses */
diff --git a/arch/blackfin/kernel/Makefile b/arch/blackfin/kernel/Makefile
index fd4d4328a0f..3731088e181 100644
--- a/arch/blackfin/kernel/Makefile
+++ b/arch/blackfin/kernel/Makefile
@@ -15,6 +15,10 @@ else
     obj-y += time.o
 endif
 
+obj-$(CONFIG_FUNCTION_TRACER)        += ftrace-entry.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)  += ftrace.o
+CFLAGS_REMOVE_ftrace.o = -pg
+
 obj-$(CONFIG_IPIPE)                  += ipipe.o
 obj-$(CONFIG_IPIPE_TRACE_MCOUNT)     += mcount.o
 obj-$(CONFIG_BFIN_GPTIMERS)          += gptimers.o
@@ -23,6 +27,7 @@ obj-$(CONFIG_MODULES)                += module.o
 obj-$(CONFIG_KGDB)                   += kgdb.o
 obj-$(CONFIG_KGDB_TESTS)             += kgdb_test.o
 obj-$(CONFIG_EARLY_PRINTK)           += early_printk.o
+obj-$(CONFIG_STACKTRACE)             += stacktrace.o
 
 # the kgdb test puts code into L2 and without linker
 # relaxation, we need to force long calls to/from it
diff --git a/arch/blackfin/kernel/bfin_dma_5xx.c b/arch/blackfin/kernel/bfin_dma_5xx.c
index 763ed84ba45..e0bf8cc0690 100644
--- a/arch/blackfin/kernel/bfin_dma_5xx.c
+++ b/arch/blackfin/kernel/bfin_dma_5xx.c
@@ -453,10 +453,10 @@ void *dma_memcpy(void *pdst, const void *psrc, size_t size)
 	unsigned long src = (unsigned long)psrc;
 	size_t bulk, rest;
 
-	if (bfin_addr_dcachable(src))
+	if (bfin_addr_dcacheable(src))
 		blackfin_dcache_flush_range(src, src + size);
 
-	if (bfin_addr_dcachable(dst))
+	if (bfin_addr_dcacheable(dst))
 		blackfin_dcache_invalidate_range(dst, dst + size);
 
 	bulk = size & ~0xffff;
diff --git a/arch/blackfin/kernel/bfin_ksyms.c b/arch/blackfin/kernel/bfin_ksyms.c
index 53e893ff708..aa05e638fb7 100644
--- a/arch/blackfin/kernel/bfin_ksyms.c
+++ b/arch/blackfin/kernel/bfin_ksyms.c
@@ -103,3 +103,8 @@ EXPORT_SYMBOL(__raw_smp_mark_barrier_asm);
 EXPORT_SYMBOL(__raw_smp_check_barrier_asm);
 #endif
 #endif
+
+#ifdef CONFIG_FUNCTION_TRACER
+extern void _mcount(void);
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/blackfin/kernel/cplb-mpu/cplbmgr.c b/arch/blackfin/kernel/cplb-mpu/cplbmgr.c
index 87463ce87f5..784923e52a9 100644
--- a/arch/blackfin/kernel/cplb-mpu/cplbmgr.c
+++ b/arch/blackfin/kernel/cplb-mpu/cplbmgr.c
@@ -151,7 +151,7 @@ static noinline int dcplb_miss(unsigned int cpu)
 
 	d_data = CPLB_SUPV_WR | CPLB_VALID | CPLB_DIRTY | PAGE_SIZE_4KB;
 #ifdef CONFIG_BFIN_DCACHE
-	if (bfin_addr_dcachable(addr)) {
+	if (bfin_addr_dcacheable(addr)) {
 		d_data |= CPLB_L1_CHBL | ANOMALY_05000158_WORKAROUND;
 #ifdef CONFIG_BFIN_WT
 		d_data |= CPLB_L1_AOW | CPLB_WT;
diff --git a/arch/blackfin/kernel/cplb-nompu/cplbmgr.c b/arch/blackfin/kernel/cplb-nompu/cplbmgr.c
index 8cbb47c7b66..12b030842fd 100644
--- a/arch/blackfin/kernel/cplb-nompu/cplbmgr.c
+++ b/arch/blackfin/kernel/cplb-nompu/cplbmgr.c
@@ -28,6 +28,7 @@
 #include <asm/cplbinit.h>
 #include <asm/cplb.h>
 #include <asm/mmu_context.h>
+#include <asm/traps.h>
 
 /*
  * WARNING
@@ -100,28 +101,6 @@ static inline void write_icplb_data(int cpu, int idx, unsigned long data,
 #endif
 }
 
-/*
- * Given the contents of the status register, return the index of the
- * CPLB that caused the fault.
- */
-static inline int faulting_cplb_index(int status)
-{
-	int signbits = __builtin_bfin_norm_fr1x32(status & 0xFFFF);
-	return 30 - signbits;
-}
-
-/*
- * Given the contents of the status register and the DCPLB_DATA contents,
- * return true if a write access should be permitted.
- */
-static inline int write_permitted(int status, unsigned long data)
-{
-	if (status & FAULT_USERSUPV)
-		return !!(data & CPLB_SUPV_WR);
-	else
-		return !!(data & CPLB_USER_WR);
-}
-
 /* Counters to implement round-robin replacement.  */
 static int icplb_rr_index[NR_CPUS] PDT_ATTR;
 static int dcplb_rr_index[NR_CPUS] PDT_ATTR;
@@ -245,43 +224,16 @@ MGR_ATTR static int dcplb_miss(int cpu)
 	return CPLB_RELOADED;
 }
 
-MGR_ATTR static noinline int dcplb_protection_fault(int cpu)
-{
-	int status = bfin_read_DCPLB_STATUS();
-
-	nr_dcplb_prot[cpu]++;
-
-	if (likely(status & FAULT_RW)) {
-		int idx = faulting_cplb_index(status);
-		unsigned long regaddr = DCPLB_DATA0 + idx * 4;
-		unsigned long data = bfin_read32(regaddr);
-
-		/* Check if fault is to dirty a clean page */
-		if (!(data & CPLB_WT) && !(data & CPLB_DIRTY) &&
-		    write_permitted(status, data)) {
-
-			dcplb_tbl[cpu][idx].data = data;
-			bfin_write32(regaddr, data);
-			return CPLB_RELOADED;
-		}
-	}
-
-	return CPLB_PROT_VIOL;
-}
-
 MGR_ATTR int cplb_hdr(int seqstat, struct pt_regs *regs)
 {
 	int cause = seqstat & 0x3f;
 	unsigned int cpu = smp_processor_id();
 	switch (cause) {
-	case 0x2C:
+	case VEC_CPLB_I_M:
 		return icplb_miss(cpu);
-	case 0x26:
+	case VEC_CPLB_M:
 		return dcplb_miss(cpu);
 	default:
-		if (unlikely(cause == 0x23))
-			return dcplb_protection_fault(cpu);
-
 		return CPLB_UNKNOWN_ERR;
 	}
 }
diff --git a/arch/blackfin/kernel/early_printk.c b/arch/blackfin/kernel/early_printk.c
index 3302719173c..2ab56811841 100644
--- a/arch/blackfin/kernel/early_printk.c
+++ b/arch/blackfin/kernel/early_printk.c
@@ -202,11 +202,15 @@ asmlinkage void __init init_early_exception_vectors(void)
 asmlinkage void __init early_trap_c(struct pt_regs *fp, void *retaddr)
 {
 	/* This can happen before the uart is initialized, so initialize
-	 * the UART now
+	 * the UART now (but only if we are running on the processor we think
+	 * we are compiled for - otherwise we write to MMRs that don't exist,
+	 * and cause other problems. Nothing comes out the UART, but it does
+	 * end up in the __buf_log.
 	 */
-	if (likely(early_console == NULL))
+	if (likely(early_console == NULL) && CPUID == bfin_cpuid())
 		setup_early_printk(DEFAULT_EARLY_PORT);
 
+	printk(KERN_EMERG "Early panic\n");
 	dump_bfin_mem(fp);
 	show_regs(fp);
 	dump_bfin_trace_buffer();
diff --git a/arch/blackfin/kernel/ftrace-entry.S b/arch/blackfin/kernel/ftrace-entry.S
new file mode 100644
index 00000000000..6980b7a0615
--- /dev/null
+++ b/arch/blackfin/kernel/ftrace-entry.S
@@ -0,0 +1,140 @@
+/*
+ * mcount and friends -- ftrace stuff
+ *
+ * Copyright (C) 2009 Analog Devices Inc.
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+
+.text
+
+/* GCC will have called us before setting up the function prologue, so we
+ * can clobber the normal scratch registers, but we need to make sure to
+ * save/restore the registers used for argument passing (R0-R2) in case
+ * the profiled function is using them.  With data registers, R3 is the
+ * only one we can blow away.  With pointer registers, we have P0-P2.
+ *
+ * Upon entry, the RETS will point to the top of the current profiled
+ * function.  And since GCC setup the frame for us, the previous function
+ * will be waiting there.  mmmm pie.
+ */
+ENTRY(__mcount)
+	/* save third function arg early so we can do testing below */
+	[--sp] = r2;
+
+	/* load the function pointer to the tracer */
+	p0.l = _ftrace_trace_function;
+	p0.h = _ftrace_trace_function;
+	r3 = [p0];
+
+	/* optional micro optimization: don't call the stub tracer */
+	r2.l = _ftrace_stub;
+	r2.h = _ftrace_stub;
+	cc = r2 == r3;
+	if ! cc jump .Ldo_trace;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* if the ftrace_graph_return function pointer is not set to
+	 * the ftrace_stub entry, call prepare_ftrace_return().
+	 */
+	p0.l = _ftrace_graph_return;
+	p0.h = _ftrace_graph_return;
+	r3 = [p0];
+	cc = r2 == r3;
+	if ! cc jump _ftrace_graph_caller;
+
+	/* similarly, if the ftrace_graph_entry function pointer is not
+	 * set to the ftrace_graph_entry_stub entry, ...
+	 */
+	p0.l = _ftrace_graph_entry;
+	p0.h = _ftrace_graph_entry;
+	r2.l = _ftrace_graph_entry_stub;
+	r2.h = _ftrace_graph_entry_stub;
+	r3 = [p0];
+	cc = r2 == r3;
+	if ! cc jump _ftrace_graph_caller;
+#endif
+
+	r2 = [sp++];
+	rts;
+
+.Ldo_trace:
+
+	/* save first/second function arg and the return register */
+	[--sp] = r0;
+	[--sp] = r1;
+	[--sp] = rets;
+
+	/* setup the tracer function */
+	p0 = r3;
+
+	/* tracer(ulong frompc, ulong selfpc):
+	 *  frompc: the pc that did the call to ...
+	 *  selfpc: ... this location
+	 * the selfpc itself will need adjusting for the mcount call
+	 */
+	r1 = rets;
+	r0 = [fp + 4];
+	r1 += -MCOUNT_INSN_SIZE;
+
+	/* call the tracer */
+	call (p0);
+
+	/* restore state and get out of dodge */
+.Lfinish_trace:
+	rets = [sp++];
+	r1 = [sp++];
+	r0 = [sp++];
+	r2 = [sp++];
+
+.globl _ftrace_stub
+_ftrace_stub:
+	rts;
+ENDPROC(__mcount)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/* The prepare_ftrace_return() function is similar to the trace function
+ * except it takes a pointer to the location of the frompc.  This is so
+ * the prepare_ftrace_return() can hijack it temporarily for probing
+ * purposes.
+ */
+ENTRY(_ftrace_graph_caller)
+	/* save first/second function arg and the return register */
+	[--sp] = r0;
+	[--sp] = r1;
+	[--sp] = rets;
+
+	r0 = fp;
+	r1 = rets;
+	r0 += 4;
+	r1 += -MCOUNT_INSN_SIZE;
+	call _prepare_ftrace_return;
+
+	jump .Lfinish_trace;
+ENDPROC(_ftrace_graph_caller)
+
+/* Undo the rewrite caused by ftrace_graph_caller().  The common function
+ * ftrace_return_to_handler() will return the original rets so we can
+ * restore it and be on our way.
+ */
+ENTRY(_return_to_handler)
+	/* make sure original return values are saved */
+	[--sp] = p0;
+	[--sp] = r0;
+	[--sp] = r1;
+
+	/* get original return address */
+	call _ftrace_return_to_handler;
+	rets = r0;
+
+	/* anomaly 05000371 - make sure we have at least three instructions
+	 * between rets setting and the return
+	 */
+	r1 = [sp++];
+	r0 = [sp++];
+	p0 = [sp++];
+	rts;
+ENDPROC(_return_to_handler)
+#endif
diff --git a/arch/blackfin/kernel/ftrace.c b/arch/blackfin/kernel/ftrace.c
new file mode 100644
index 00000000000..905bfc40a00
--- /dev/null
+++ b/arch/blackfin/kernel/ftrace.c
@@ -0,0 +1,42 @@
+/*
+ * ftrace graph code
+ *
+ * Copyright (C) 2009 Analog Devices Inc.
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/ftrace.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+	struct ftrace_graph_ent trace;
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	if (ftrace_push_return_trace(*parent, self_addr, &trace.depth) == -EBUSY)
+		return;
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		return;
+	}
+
+	/* all is well in the world !  hijack RETS ... */
+	*parent = return_hooker;
+}
+
+#endif
diff --git a/arch/blackfin/kernel/ipipe.c b/arch/blackfin/kernel/ipipe.c
index 5fc424803a1..d8cde1fc5cb 100644
--- a/arch/blackfin/kernel/ipipe.c
+++ b/arch/blackfin/kernel/ipipe.c
@@ -99,7 +99,7 @@ void __ipipe_handle_irq(unsigned irq, struct pt_regs *regs)
 	 * interrupt.
 	 */
 	m_ack = (regs == NULL || irq == IRQ_SYSTMR || irq == IRQ_CORETMR);
-	this_domain = ipipe_current_domain;
+	this_domain = __ipipe_current_domain;
 
 	if (unlikely(test_bit(IPIPE_STICKY_FLAG, &this_domain->irqs[irq].control)))
 		head = &this_domain->p_link;
@@ -212,7 +212,9 @@ void __ipipe_unstall_root_raw(void)
 
 int __ipipe_syscall_root(struct pt_regs *regs)
 {
+	struct ipipe_percpu_domain_data *p;
 	unsigned long flags;
+	int ret;
 
 	/*
 	 * We need to run the IRQ tail hook whenever we don't
@@ -231,29 +233,31 @@ int __ipipe_syscall_root(struct pt_regs *regs)
 	/*
 	 * This routine either returns:
 	 * 0 -- if the syscall is to be passed to Linux;
-	 * 1 -- if the syscall should not be passed to Linux, and no
+	 * >0 -- if the syscall should not be passed to Linux, and no
 	 * tail work should be performed;
-	 * -1 -- if the syscall should not be passed to Linux but the
+	 * <0 -- if the syscall should not be passed to Linux but the
 	 * tail work has to be performed (for handling signals etc).
 	 */
 
-	if (__ipipe_event_monitored_p(IPIPE_EVENT_SYSCALL) &&
-	    __ipipe_dispatch_event(IPIPE_EVENT_SYSCALL, regs) > 0) {
-		if (ipipe_root_domain_p && !in_atomic()) {
-			/*
-			 * Sync pending VIRQs before _TIF_NEED_RESCHED
-			 * is tested.
-			 */
-			local_irq_save_hw(flags);
-			if ((ipipe_root_cpudom_var(irqpend_himask) & IPIPE_IRQMASK_VIRT) != 0)
-				__ipipe_sync_pipeline(IPIPE_IRQMASK_VIRT);
-			local_irq_restore_hw(flags);
-			return -1;
-		}
+	if (!__ipipe_event_monitored_p(IPIPE_EVENT_SYSCALL))
+		return 0;
+
+	ret = __ipipe_dispatch_event(IPIPE_EVENT_SYSCALL, regs);
+
+	local_irq_save_hw(flags);
+
+	if (!__ipipe_root_domain_p) {
+		local_irq_restore_hw(flags);
 		return 1;
 	}
 
-	return 0;
+	p = ipipe_root_cpudom_ptr();
+	if ((p->irqpend_himask & IPIPE_IRQMASK_VIRT) != 0)
+		__ipipe_sync_pipeline(IPIPE_IRQMASK_VIRT);
+
+	local_irq_restore_hw(flags);
+
+	return -ret;
 }
 
 unsigned long ipipe_critical_enter(void (*syncfn) (void))
@@ -329,9 +333,7 @@ asmlinkage void __ipipe_sync_root(void)
 
 void ___ipipe_sync_pipeline(unsigned long syncmask)
 {
-	struct ipipe_domain *ipd = ipipe_current_domain;
-
-	if (ipd == ipipe_root_domain) {
+	if (__ipipe_root_domain_p) {
 		if (test_bit(IPIPE_SYNCDEFER_FLAG, &ipipe_root_cpudom_var(status)))
 			return;
 	}
diff --git a/arch/blackfin/kernel/setup.c b/arch/blackfin/kernel/setup.c
index 80447f99c2b..6454babdfaf 100644
--- a/arch/blackfin/kernel/setup.c
+++ b/arch/blackfin/kernel/setup.c
@@ -1098,7 +1098,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 			CPUID, bfin_cpuid());
 
 	seq_printf(m, "model name\t: ADSP-%s %lu(MHz CCLK) %lu(MHz SCLK) (%s)\n"
-		"stepping\t: %d\n",
+		"stepping\t: %d ",
 		cpu, cclk/1000000, sclk/1000000,
 #ifdef CONFIG_MPU
 		"mpu on",
@@ -1107,7 +1107,16 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #endif
 		revid);
 
-	seq_printf(m, "cpu MHz\t\t: %lu.%03lu/%lu.%03lu\n",
+	if (bfin_revid() != bfin_compiled_revid()) {
+		if (bfin_compiled_revid() == -1)
+			seq_printf(m, "(Compiled for Rev none)");
+		else if (bfin_compiled_revid() == 0xffff)
+			seq_printf(m, "(Compiled for Rev any)");
+		else
+			seq_printf(m, "(Compiled for Rev %d)", bfin_compiled_revid());
+	}
+
+	seq_printf(m, "\ncpu MHz\t\t: %lu.%03lu/%lu.%03lu\n",
 		cclk/1000000, cclk%1000000,
 		sclk/1000000, sclk%1000000);
 	seq_printf(m, "bogomips\t: %lu.%02lu\n"
@@ -1172,6 +1181,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #ifdef __ARCH_SYNC_CORE_DCACHE
 	seq_printf(m, "SMP Dcache Flushes\t: %lu\n\n", cpudata->dcache_invld_count);
 #endif
+#ifdef __ARCH_SYNC_CORE_ICACHE
+	seq_printf(m, "SMP Icache Flushes\t: %lu\n\n", cpudata->icache_invld_count);
+#endif
 #ifdef CONFIG_BFIN_ICACHE_LOCK
 	switch ((cpudata->imemctl >> 3) & WAYALL_L) {
 	case WAY0_L:
diff --git a/arch/blackfin/kernel/stacktrace.c b/arch/blackfin/kernel/stacktrace.c
new file mode 100644
index 00000000000..30301e1eace
--- /dev/null
+++ b/arch/blackfin/kernel/stacktrace.c
@@ -0,0 +1,53 @@
+/*
+ * Blackfin stacktrace code (mostly copied from avr32)
+ *
+ * Copyright 2009 Analog Devices Inc.
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+#include <linux/thread_info.h>
+#include <linux/module.h>
+
+register unsigned long current_frame_pointer asm("FP");
+
+struct stackframe {
+	unsigned long fp;
+	unsigned long rets;
+};
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace(struct stack_trace *trace)
+{
+	unsigned long low, high;
+	unsigned long fp;
+	struct stackframe *frame;
+	int skip = trace->skip;
+
+	low = (unsigned long)task_stack_page(current);
+	high = low + THREAD_SIZE;
+	fp = current_frame_pointer;
+
+	while (fp >= low && fp <= (high - sizeof(*frame))) {
+		frame = (struct stackframe *)fp;
+
+		if (skip) {
+			skip--;
+		} else {
+			trace->entries[trace->nr_entries++] = frame->rets;
+			if (trace->nr_entries >= trace->max_entries)
+				break;
+		}
+
+		/*
+		 * The next frame must be at a higher address than the
+		 * current frame.
+		 */
+		low = fp + sizeof(*frame);
+		fp = frame->fp;
+	}
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
diff --git a/arch/blackfin/kernel/traps.c b/arch/blackfin/kernel/traps.c
index aa76dfb0226..d279552fe9b 100644
--- a/arch/blackfin/kernel/traps.c
+++ b/arch/blackfin/kernel/traps.c
@@ -27,6 +27,7 @@
  * 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#include <linux/bug.h>
 #include <linux/uaccess.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -238,6 +239,11 @@ asmlinkage void double_fault_c(struct pt_regs *fp)
 
 }
 
+static int kernel_mode_regs(struct pt_regs *regs)
+{
+	return regs->ipend & 0xffc0;
+}
+
 asmlinkage void trap_c(struct pt_regs *fp)
 {
 #ifdef CONFIG_DEBUG_BFIN_HWTRACE_ON
@@ -246,6 +252,7 @@ asmlinkage void trap_c(struct pt_regs *fp)
 #ifdef CONFIG_DEBUG_HUNT_FOR_ZERO
 	unsigned int cpu = smp_processor_id();
 #endif
+	const char *strerror = NULL;
 	int sig = 0;
 	siginfo_t info;
 	unsigned long trapnr = fp->seqstat & SEQSTAT_EXCAUSE;
@@ -259,27 +266,10 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	 * double faults if the stack has become corrupt
 	 */
 
-	/* If the fault was caused by a kernel thread, or interrupt handler
-	 * we will kernel panic, so the system reboots.
-	 * If KGDB is enabled, don't set this for kernel breakpoints
-	*/
-
-	/* TODO: check to see if we are in some sort of deferred HWERR
-	 * that we should be able to recover from, not kernel panic
-	 */
-	if ((bfin_read_IPEND() & 0xFFC0) && (trapnr != VEC_STEP)
-#ifdef CONFIG_KGDB
-		&& (trapnr != VEC_EXCPT02)
+#ifndef CONFIG_KGDB
+	/* IPEND is skipped if KGDB isn't enabled (see entry code) */
+	fp->ipend = bfin_read_IPEND();
 #endif
-	){
-		console_verbose();
-		oops_in_progress = 1;
-	} else if (current) {
-		if (current->mm == NULL) {
-			console_verbose();
-			oops_in_progress = 1;
-		}
-	}
 
 	/* trap_c() will be called for exceptions. During exceptions
 	 * processing, the pc value should be set with retx value.
@@ -307,15 +297,15 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		sig = SIGTRAP;
 		CHK_DEBUGGER_TRAP_MAYBE();
 		/* Check if this is a breakpoint in kernel space */
-		if (fp->ipend & 0xffc0)
-			return;
+		if (kernel_mode_regs(fp))
+			goto traps_done;
 		else
 			break;
 	/* 0x03 - User Defined, userspace stack overflow */
 	case VEC_EXCPT03:
 		info.si_code = SEGV_STACKFLOW;
 		sig = SIGSEGV;
-		verbose_printk(KERN_NOTICE EXC_0x03(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x03(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x02 - KGDB initial connection and break signal trap */
@@ -324,7 +314,7 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		info.si_code = TRAP_ILLTRAP;
 		sig = SIGTRAP;
 		CHK_DEBUGGER_TRAP();
-		return;
+		goto traps_done;
 #endif
 	/* 0x04 - User Defined */
 	/* 0x05 - User Defined */
@@ -344,7 +334,7 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	case VEC_EXCPT04 ... VEC_EXCPT15:
 		info.si_code = ILL_ILLPARAOP;
 		sig = SIGILL;
-		verbose_printk(KERN_NOTICE EXC_0x04(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x04(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x10 HW Single step, handled here */
@@ -353,15 +343,15 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		sig = SIGTRAP;
 		CHK_DEBUGGER_TRAP_MAYBE();
 		/* Check if this is a single step in kernel space */
-		if (fp->ipend & 0xffc0)
-			return;
+		if (kernel_mode_regs(fp))
+			goto traps_done;
 		else
 			break;
 	/* 0x11 - Trace Buffer Full, handled here */
 	case VEC_OVFLOW:
 		info.si_code = TRAP_TRACEFLOW;
 		sig = SIGTRAP;
-		verbose_printk(KERN_NOTICE EXC_0x11(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x11(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x12 - Reserved, Caught by default */
@@ -381,37 +371,54 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	/* 0x20 - Reserved, Caught by default */
 	/* 0x21 - Undefined Instruction, handled here */
 	case VEC_UNDEF_I:
+#ifdef CONFIG_BUG
+		if (kernel_mode_regs(fp)) {
+			switch (report_bug(fp->pc, fp)) {
+			case BUG_TRAP_TYPE_NONE:
+				break;
+			case BUG_TRAP_TYPE_WARN:
+				dump_bfin_trace_buffer();
+				fp->pc += 2;
+				goto traps_done;
+			case BUG_TRAP_TYPE_BUG:
+				/* call to panic() will dump trace, and it is
+				 * off at this point, so it won't be clobbered
+				 */
+				panic("BUG()");
+			}
+		}
+#endif
 		info.si_code = ILL_ILLOPC;
 		sig = SIGILL;
-		verbose_printk(KERN_NOTICE EXC_0x21(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x21(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x22 - Illegal Instruction Combination, handled here */
 	case VEC_ILGAL_I:
 		info.si_code = ILL_ILLPARAOP;
 		sig = SIGILL;
-		verbose_printk(KERN_NOTICE EXC_0x22(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x22(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x23 - Data CPLB protection violation, handled here */
 	case VEC_CPLB_VL:
 		info.si_code = ILL_CPLB_VI;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE EXC_0x23(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x23(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x24 - Data access misaligned, handled here */
 	case VEC_MISALI_D:
 		info.si_code = BUS_ADRALN;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE EXC_0x24(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x24(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x25 - Unrecoverable Event, handled here */
 	case VEC_UNCOV:
 		info.si_code = ILL_ILLEXCPT;
 		sig = SIGILL;
-		verbose_printk(KERN_NOTICE EXC_0x25(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x25(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x26 - Data CPLB Miss, normal case is handled in _cplb_hdr,
@@ -419,7 +426,7 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	case VEC_CPLB_M:
 		info.si_code = BUS_ADRALN;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE EXC_0x26(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x26(KERN_NOTICE);
 		break;
 	/* 0x27 - Data CPLB Multiple Hits - Linux Trap Zero, handled here */
 	case VEC_CPLB_MHIT:
@@ -427,10 +434,10 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		sig = SIGSEGV;
 #ifdef CONFIG_DEBUG_HUNT_FOR_ZERO
 		if (cpu_pda[cpu].dcplb_fault_addr < FIXED_CODE_START)
-			verbose_printk(KERN_NOTICE "NULL pointer access\n");
+			strerror = KERN_NOTICE "NULL pointer access\n";
 		else
 #endif
-			verbose_printk(KERN_NOTICE EXC_0x27(KERN_NOTICE));
+			strerror = KERN_NOTICE EXC_0x27(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x28 - Emulation Watchpoint, handled here */
@@ -440,8 +447,8 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		pr_debug(EXC_0x28(KERN_DEBUG));
 		CHK_DEBUGGER_TRAP_MAYBE();
 		/* Check if this is a watchpoint in kernel space */
-		if (fp->ipend & 0xffc0)
-			return;
+		if (kernel_mode_regs(fp))
+			goto traps_done;
 		else
 			break;
 #ifdef CONFIG_BF535
@@ -449,7 +456,7 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	case VEC_ISTRU_VL:      /* ADSP-BF535 only (MH) */
 		info.si_code = BUS_OPFETCH;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE "BF535: VEC_ISTRU_VL\n");
+		strerror = KERN_NOTICE "BF535: VEC_ISTRU_VL\n";
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 #else
@@ -459,21 +466,21 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	case VEC_MISALI_I:
 		info.si_code = BUS_ADRALN;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE EXC_0x2A(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x2A(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x2B - Instruction CPLB protection violation, handled here */
 	case VEC_CPLB_I_VL:
 		info.si_code = ILL_CPLB_VI;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE EXC_0x2B(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x2B(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x2C - Instruction CPLB miss, handled in _cplb_hdr */
 	case VEC_CPLB_I_M:
 		info.si_code = ILL_CPLB_MISS;
 		sig = SIGBUS;
-		verbose_printk(KERN_NOTICE EXC_0x2C(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x2C(KERN_NOTICE);
 		break;
 	/* 0x2D - Instruction CPLB Multiple Hits, handled here */
 	case VEC_CPLB_I_MHIT:
@@ -481,17 +488,17 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		sig = SIGSEGV;
 #ifdef CONFIG_DEBUG_HUNT_FOR_ZERO
 		if (cpu_pda[cpu].icplb_fault_addr < FIXED_CODE_START)
-			verbose_printk(KERN_NOTICE "Jump to NULL address\n");
+			strerror = KERN_NOTICE "Jump to NULL address\n";
 		else
 #endif
-			verbose_printk(KERN_NOTICE EXC_0x2D(KERN_NOTICE));
+			strerror = KERN_NOTICE EXC_0x2D(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x2E - Illegal use of Supervisor Resource, handled here */
 	case VEC_ILL_RES:
 		info.si_code = ILL_PRVOPC;
 		sig = SIGILL;
-		verbose_printk(KERN_NOTICE EXC_0x2E(KERN_NOTICE));
+		strerror = KERN_NOTICE EXC_0x2E(KERN_NOTICE);
 		CHK_DEBUGGER_TRAP_MAYBE();
 		break;
 	/* 0x2F - Reserved, Caught by default */
@@ -519,17 +526,17 @@ asmlinkage void trap_c(struct pt_regs *fp)
 		case (SEQSTAT_HWERRCAUSE_SYSTEM_MMR):
 			info.si_code = BUS_ADRALN;
 			sig = SIGBUS;
-			verbose_printk(KERN_NOTICE HWC_x2(KERN_NOTICE));
+			strerror = KERN_NOTICE HWC_x2(KERN_NOTICE);
 			break;
 		/* External Memory Addressing Error */
 		case (SEQSTAT_HWERRCAUSE_EXTERN_ADDR):
 			info.si_code = BUS_ADRERR;
 			sig = SIGBUS;
-			verbose_printk(KERN_NOTICE HWC_x3(KERN_NOTICE));
+			strerror = KERN_NOTICE HWC_x3(KERN_NOTICE);
 			break;
 		/* Performance Monitor Overflow */
 		case (SEQSTAT_HWERRCAUSE_PERF_FLOW):
-			verbose_printk(KERN_NOTICE HWC_x12(KERN_NOTICE));
+			strerror = KERN_NOTICE HWC_x12(KERN_NOTICE);
 			break;
 		/* RAISE 5 instruction */
 		case (SEQSTAT_HWERRCAUSE_RAISE_5):
@@ -546,7 +553,6 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	 * if we get here we hit a reserved one, so panic
 	 */
 	default:
-		oops_in_progress = 1;
 		info.si_code = ILL_ILLPARAOP;
 		sig = SIGILL;
 		verbose_printk(KERN_EMERG "Caught Unhandled Exception, code = %08lx\n",
@@ -557,6 +563,16 @@ asmlinkage void trap_c(struct pt_regs *fp)
 
 	BUG_ON(sig == 0);
 
+	/* If the fault was caused by a kernel thread, or interrupt handler
+	 * we will kernel panic, so the system reboots.
+	 */
+	if (kernel_mode_regs(fp) || (current && !current->mm)) {
+		console_verbose();
+		oops_in_progress = 1;
+		if (strerror)
+			verbose_printk(strerror);
+	}
+
 	if (sig != SIGTRAP) {
 		dump_bfin_process(fp);
 		dump_bfin_mem(fp);
@@ -606,8 +622,8 @@ asmlinkage void trap_c(struct pt_regs *fp)
 	if (ANOMALY_05000461 && trapnr == VEC_HWERR && !access_ok(VERIFY_READ, fp->pc, 8))
 		fp->pc = SAFE_USER_INSTRUCTION;
 
+ traps_done:
 	trace_buffer_restore(j);
-	return;
 }
 
 /* Typical exception handling routines	*/
@@ -792,6 +808,18 @@ void dump_bfin_trace_buffer(void)
 }
 EXPORT_SYMBOL(dump_bfin_trace_buffer);
 
+#ifdef CONFIG_BUG
+int is_valid_bugaddr(unsigned long addr)
+{
+	unsigned short opcode;
+
+	if (!get_instruction(&opcode, (unsigned short *)addr))
+		return 0;
+
+	return opcode == BFIN_BUG_OPCODE;
+}
+#endif
+
 /*
  * Checks to see if the address pointed to is either a
  * 16-bit CALL instruction, or a 32-bit CALL instruction
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 8b67167cb4f..6ac307ca0d8 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -54,6 +54,7 @@ SECTIONS
 		SCHED_TEXT
 #endif
 		LOCK_TEXT
+		IRQENTRY_TEXT
 		KPROBES_TEXT
 		*(.text.*)
 		*(.fixup)
@@ -166,6 +167,20 @@ SECTIONS
 	}
 	PERCPU(4)
 	SECURITY_INIT
+
+	/* we have to discard exit text and such at runtime, not link time, to
+	 * handle embedded cross-section references (alt instructions, bug
+	 * table, eh_frame, etc...)
+	 */
+	.exit.text :
+	{
+		EXIT_TEXT
+	}
+	.exit.data :
+	{
+		EXIT_DATA
+	}
+
 	.init.ramfs :
 	{
 		. = ALIGN(4);
@@ -264,8 +279,6 @@ SECTIONS
 
 	/DISCARD/ :
 	{
-		EXIT_TEXT
-		EXIT_DATA
 		*(.exitcall.exit)
 	}
 }
diff --git a/arch/blackfin/lib/checksum.c b/arch/blackfin/lib/checksum.c
index 762a7f02970..cd605e7d851 100644
--- a/arch/blackfin/lib/checksum.c
+++ b/arch/blackfin/lib/checksum.c
@@ -116,6 +116,7 @@ __sum16 ip_compute_csum(const void *buff, int len)
 {
 	return (__force __sum16)~do_csum(buff, len);
 }
+EXPORT_SYMBOL(ip_compute_csum);
 
 /*
  * copy from fs while checksumming, otherwise like csum_partial
@@ -130,6 +131,7 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
 	memcpy(dst, (__force void *)src, len);
 	return csum_partial(dst, len, sum);
 }
+EXPORT_SYMBOL(csum_partial_copy_from_user);
 
 /*
  * copy from ds while checksumming, otherwise like csum_partial
diff --git a/arch/blackfin/mach-bf518/boards/ezbrd.c b/arch/blackfin/mach-bf518/boards/ezbrd.c
index 62bba09bcce..1382f038235 100644
--- a/arch/blackfin/mach-bf518/boards/ezbrd.c
+++ b/arch/blackfin/mach-bf518/boards/ezbrd.c
@@ -246,7 +246,7 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = {
 		.modalias = "m25p80", /* Name of spi_driver for this device */
 		.max_speed_hz = 25000000,     /* max spi clock (SCK) speed in HZ */
 		.bus_num = 0, /* Framework bus number */
-		.chip_select = 1, /* Framework chip select. On STAMP537 it is SPISSEL1*/
+		.chip_select = 2, /* On BF518F-EZBRD it's SPI0_SSEL2 */
 		.platform_data = &bfin_spi_flash_data,
 		.controller_data = &spi_flash_chip_info,
 		.mode = SPI_MODE_3,
@@ -369,6 +369,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI0,
 		.end   = CH_SPI0,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI0,
+		.end   = IRQ_SPI0,
 		.flags = IORESOURCE_IRQ,
 	},
 };
@@ -399,6 +404,11 @@ static struct resource bfin_spi1_resource[] = {
 	[1] = {
 		.start = CH_SPI1,
 		.end   = CH_SPI1,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI1,
+		.end   = IRQ_SPI1,
 		.flags = IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/blackfin/mach-bf527/boards/cm_bf527.c b/arch/blackfin/mach-bf527/boards/cm_bf527.c
index 6d6f9effa0b..1eaf27ff722 100644
--- a/arch/blackfin/mach-bf527/boards/cm_bf527.c
+++ b/arch/blackfin/mach-bf527/boards/cm_bf527.c
@@ -664,6 +664,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/blackfin/mach-bf527/boards/ezbrd.c b/arch/blackfin/mach-bf527/boards/ezbrd.c
index 1435c5d38cd..9f9c0005dcf 100644
--- a/arch/blackfin/mach-bf527/boards/ezbrd.c
+++ b/arch/blackfin/mach-bf527/boards/ezbrd.c
@@ -467,6 +467,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/blackfin/mach-bf527/boards/ezkit.c b/arch/blackfin/mach-bf527/boards/ezkit.c
index 147edd1eb1a..3e5b7db6b06 100644
--- a/arch/blackfin/mach-bf527/boards/ezkit.c
+++ b/arch/blackfin/mach-bf527/boards/ezkit.c
@@ -723,6 +723,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/blackfin/mach-bf533/boards/H8606.c b/arch/blackfin/mach-bf533/boards/H8606.c
index 895f213ea45..38cf8ffd6d7 100644
--- a/arch/blackfin/mach-bf533/boards/H8606.c
+++ b/arch/blackfin/mach-bf533/boards/H8606.c
@@ -266,6 +266,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c
index 0765872a8ad..9ecdc361fa6 100644
--- a/arch/blackfin/mach-bf533/boards/blackstamp.c
+++ b/arch/blackfin/mach-bf533/boards/blackstamp.c
@@ -162,6 +162,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf533/boards/cm_bf533.c b/arch/blackfin/mach-bf533/boards/cm_bf533.c
index a727e538fa2..1443e92d8b6 100644
--- a/arch/blackfin/mach-bf533/boards/cm_bf533.c
+++ b/arch/blackfin/mach-bf533/boards/cm_bf533.c
@@ -160,6 +160,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf533/boards/ezkit.c b/arch/blackfin/mach-bf533/boards/ezkit.c
index 842f1c9c239..89a5ec4ca04 100644
--- a/arch/blackfin/mach-bf533/boards/ezkit.c
+++ b/arch/blackfin/mach-bf533/boards/ezkit.c
@@ -196,6 +196,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c
index e19c565ade1..a68ade8a3ca 100644
--- a/arch/blackfin/mach-bf533/boards/stamp.c
+++ b/arch/blackfin/mach-bf533/boards/stamp.c
@@ -299,6 +299,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537.c b/arch/blackfin/mach-bf537/boards/cm_bf537.c
index 4fee1967312..2a87d1cfcd0 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537.c
@@ -182,8 +182,13 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
-	}
+	},
 };
 
 /* SPI controller data */
diff --git a/arch/blackfin/mach-bf537/boards/minotaur.c b/arch/blackfin/mach-bf537/boards/minotaur.c
index 3c159819e55..399f81da7b9 100644
--- a/arch/blackfin/mach-bf537/boards/minotaur.c
+++ b/arch/blackfin/mach-bf537/boards/minotaur.c
@@ -184,6 +184,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	},
 };
diff --git a/arch/blackfin/mach-bf537/boards/pnav10.c b/arch/blackfin/mach-bf537/boards/pnav10.c
index 26707ce39f2..838240f151f 100644
--- a/arch/blackfin/mach-bf537/boards/pnav10.c
+++ b/arch/blackfin/mach-bf537/boards/pnav10.c
@@ -398,8 +398,13 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
-	}
+	},
 };
 
 /* SPI controller data */
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index dfb5036f8a6..ff7228caa7d 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -1345,7 +1345,7 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = {
 #if defined(CONFIG_PMIC_ADP5520) || defined(CONFIG_PMIC_ADP5520_MODULE)
 	{
 		I2C_BOARD_INFO("pmic-adp5520", 0x32),
-		.irq = IRQ_PF7,
+		.irq = IRQ_PG0,
 		.platform_data = (void *)&adp5520_pdev_data,
 	},
 #endif
diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
index 28057459120..e523e6e610d 100644
--- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
@@ -182,6 +182,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf538/boards/ezkit.c b/arch/blackfin/mach-bf538/boards/ezkit.c
index e37cb937888..57695b4c3c0 100644
--- a/arch/blackfin/mach-bf538/boards/ezkit.c
+++ b/arch/blackfin/mach-bf538/boards/ezkit.c
@@ -352,6 +352,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI0,
 		.end   = CH_SPI0,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI0,
+		.end   = IRQ_SPI0,
 		.flags = IORESOURCE_IRQ,
 	}
 };
@@ -366,6 +371,11 @@ static struct resource bfin_spi1_resource[] = {
 	[1] = {
 		.start = CH_SPI1,
 		.end   = CH_SPI1,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI1,
+		.end   = IRQ_SPI1,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf548/boards/cm_bf548.c b/arch/blackfin/mach-bf548/boards/cm_bf548.c
index f53ad682530..f5a3c30a41b 100644
--- a/arch/blackfin/mach-bf548/boards/cm_bf548.c
+++ b/arch/blackfin/mach-bf548/boards/cm_bf548.c
@@ -612,6 +612,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI0,
 		.end   = CH_SPI0,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI0,
+		.end   = IRQ_SPI0,
 		.flags = IORESOURCE_IRQ,
 	}
 };
@@ -626,6 +631,11 @@ static struct resource bfin_spi1_resource[] = {
 	[1] = {
 		.start = CH_SPI1,
 		.end   = CH_SPI1,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI1,
+		.end   = IRQ_SPI1,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c
index add5a17452c..805a57b5e65 100644
--- a/arch/blackfin/mach-bf548/boards/ezkit.c
+++ b/arch/blackfin/mach-bf548/boards/ezkit.c
@@ -396,6 +396,8 @@ static struct platform_device bfin_sir3_device = {
 #endif
 
 #if defined(CONFIG_SMSC911X) || defined(CONFIG_SMSC911X_MODULE)
+#include <linux/smsc911x.h>
+
 static struct resource smsc911x_resources[] = {
 	{
 		.name = "smsc911x-memory",
@@ -409,11 +411,22 @@ static struct resource smsc911x_resources[] = {
 		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL,
 	},
 };
+
+static struct smsc911x_platform_config smsc911x_config = {
+	.flags = SMSC911X_USE_32BIT,
+	.irq_polarity = SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
+	.irq_type = SMSC911X_IRQ_TYPE_OPEN_DRAIN,
+	.phy_interface = PHY_INTERFACE_MODE_MII,
+};
+
 static struct platform_device smsc911x_device = {
 	.name = "smsc911x",
 	.id = 0,
 	.num_resources = ARRAY_SIZE(smsc911x_resources),
 	.resource = smsc911x_resources,
+	.dev = {
+		.platform_data = &smsc911x_config,
+	},
 };
 #endif
 
@@ -741,6 +754,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI0,
 		.end   = CH_SPI0,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI0,
+		.end   = IRQ_SPI0,
 		.flags = IORESOURCE_IRQ,
 	}
 };
@@ -755,6 +773,11 @@ static struct resource bfin_spi1_resource[] = {
 	[1] = {
 		.start = CH_SPI1,
 		.end   = CH_SPI1,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI1,
+		.end   = IRQ_SPI1,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index 0dd9685e5d5..0c9d72c5f5b 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -177,8 +177,13 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
-	}
+	},
 };
 
 /* SPI controller data */
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index 0e2178a1aec..b5ef7ff7b7b 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -304,6 +304,11 @@ static struct resource bfin_spi0_resource[] = {
 	[1] = {
 		.start = CH_SPI,
 		.end   = CH_SPI,
+		.flags = IORESOURCE_DMA,
+	},
+	[2] = {
+		.start = IRQ_SPI,
+		.end   = IRQ_SPI,
 		.flags = IORESOURCE_IRQ,
 	}
 };
diff --git a/arch/blackfin/mach-common/cache-c.c b/arch/blackfin/mach-common/cache-c.c
index e6ab1f81512..b59ce3cb380 100644
--- a/arch/blackfin/mach-common/cache-c.c
+++ b/arch/blackfin/mach-common/cache-c.c
@@ -16,9 +16,21 @@
 void blackfin_invalidate_entire_dcache(void)
 {
 	u32 dmem = bfin_read_DMEM_CONTROL();
-	SSYNC();
 	bfin_write_DMEM_CONTROL(dmem & ~0xc);
 	SSYNC();
 	bfin_write_DMEM_CONTROL(dmem);
 	SSYNC();
 }
+
+/* Invalidate the Entire Instruction cache by
+ * clearing IMC bit
+ */
+void blackfin_invalidate_entire_icache(void)
+{
+	u32 imem = bfin_read_IMEM_CONTROL();
+	bfin_write_IMEM_CONTROL(imem & ~0x4);
+	SSYNC();
+	bfin_write_IMEM_CONTROL(imem);
+	SSYNC();
+}
+
diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index da0558ad1b1..31fa313e81c 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -42,6 +42,7 @@
 #include <asm/thread_info.h>  /* TIF_NEED_RESCHED */
 #include <asm/asm-offsets.h>
 #include <asm/trace.h>
+#include <asm/traps.h>
 
 #include <asm/context.S>
 
@@ -84,13 +85,15 @@ ENTRY(_ex_workaround_261)
 	if !cc jump _bfin_return_from_exception;
 	/* fall through */
 	R7 = P4;
-	R6 = 0x26;	/* Data CPLB Miss */
+	R6 = VEC_CPLB_M;	/* Data CPLB Miss */
 	cc = R6 == R7;
 	if cc jump _ex_dcplb_miss (BP);
-	R6 = 0x23;	/* Data CPLB Miss */
+#ifdef CONFIG_MPU
+	R6 = VEC_CPLB_VL;	/* Data CPLB Violation */
 	cc = R6 == R7;
 	if cc jump _ex_dcplb_viol (BP);
-	/* Handle 0x23 Data CPLB Protection Violation
+#endif
+	/* Handle Data CPLB Protection Violation
 	 * and Data CPLB Multiple Hits - Linux Trap Zero
 	 */
 	jump _ex_trap_c;
@@ -270,7 +273,7 @@ ENTRY(_bfin_return_from_exception)
 	r6.l = lo(SEQSTAT_EXCAUSE);
 	r6.h = hi(SEQSTAT_EXCAUSE);
 	r7 = r7 & r6;
-	r6 = 0x25;
+	r6 = VEC_UNCOV;
 	CC = R7 == R6;
 	if CC JUMP _double_fault;
 #endif
@@ -1605,6 +1608,7 @@ ENTRY(_sys_call_table)
 	.long _sys_inotify_init1	/* 365 */
 	.long _sys_preadv
 	.long _sys_pwritev
+	.long _sys_rt_tgsigqueueinfo
 
 	.rept NR_syscalls-(.-_sys_call_table)/4
 	.long _sys_ni_syscall
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 3b8ebaee77f..61840059dfa 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -144,7 +144,7 @@ static void ipi_call_function(unsigned int cpu, struct ipi_message *msg)
 
 static irqreturn_t ipi_handler(int irq, void *dev_instance)
 {
-	struct ipi_message *msg, *mg;
+	struct ipi_message *msg;
 	struct ipi_message_queue *msg_queue;
 	unsigned int cpu = smp_processor_id();
 
@@ -154,7 +154,8 @@ static irqreturn_t ipi_handler(int irq, void *dev_instance)
 	msg_queue->count++;
 
 	spin_lock(&msg_queue->lock);
-	list_for_each_entry_safe(msg, mg, &msg_queue->head, list) {
+	while (!list_empty(&msg_queue->head)) {
+		msg = list_entry(msg_queue->head.next, typeof(*msg), list);
 		list_del(&msg->list);
 		switch (msg->type) {
 		case BFIN_IPI_RESCHEDULE:
@@ -221,7 +222,7 @@ int smp_call_function(void (*func)(void *info), void *info, int wait)
 	for_each_cpu_mask(cpu, callmap) {
 		msg_queue = &per_cpu(ipi_msg_queue, cpu);
 		spin_lock_irqsave(&msg_queue->lock, flags);
-		list_add(&msg->list, &msg_queue->head);
+		list_add_tail(&msg->list, &msg_queue->head);
 		spin_unlock_irqrestore(&msg_queue->lock, flags);
 		platform_send_ipi_cpu(cpu);
 	}
@@ -261,7 +262,7 @@ int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
 
 	msg_queue = &per_cpu(ipi_msg_queue, cpu);
 	spin_lock_irqsave(&msg_queue->lock, flags);
-	list_add(&msg->list, &msg_queue->head);
+	list_add_tail(&msg->list, &msg_queue->head);
 	spin_unlock_irqrestore(&msg_queue->lock, flags);
 	platform_send_ipi_cpu(cpu);
 
@@ -292,7 +293,7 @@ void smp_send_reschedule(int cpu)
 
 	msg_queue = &per_cpu(ipi_msg_queue, cpu);
 	spin_lock_irqsave(&msg_queue->lock, flags);
-	list_add(&msg->list, &msg_queue->head);
+	list_add_tail(&msg->list, &msg_queue->head);
 	spin_unlock_irqrestore(&msg_queue->lock, flags);
 	platform_send_ipi_cpu(cpu);
 
@@ -320,7 +321,7 @@ void smp_send_stop(void)
 	for_each_cpu_mask(cpu, callmap) {
 		msg_queue = &per_cpu(ipi_msg_queue, cpu);
 		spin_lock_irqsave(&msg_queue->lock, flags);
-		list_add(&msg->list, &msg_queue->head);
+		list_add_tail(&msg->list, &msg_queue->head);
 		spin_unlock_irqrestore(&msg_queue->lock, flags);
 		platform_send_ipi_cpu(cpu);
 	}
@@ -468,6 +469,17 @@ void smp_icache_flush_range_others(unsigned long start, unsigned long end)
 }
 EXPORT_SYMBOL_GPL(smp_icache_flush_range_others);
 
+#ifdef __ARCH_SYNC_CORE_ICACHE
+void resync_core_icache(void)
+{
+	unsigned int cpu = get_cpu();
+	blackfin_invalidate_entire_icache();
+	++per_cpu(cpu_data, cpu).icache_invld_count;
+	put_cpu();
+}
+EXPORT_SYMBOL(resync_core_icache);
+#endif
+
 #ifdef __ARCH_SYNC_CORE_DCACHE
 unsigned long barrier_mask __attribute__ ((__section__(".l2.bss")));
 
diff --git a/arch/ia64/mm/extable.c b/arch/ia64/mm/extable.c
index e95d5ad9285..c99a41e29fe 100644
--- a/arch/ia64/mm/extable.c
+++ b/arch/ia64/mm/extable.c
@@ -8,7 +8,7 @@
 #include <linux/sort.h>
 
 #include <asm/uaccess.h>
-#include <asm/module.h>
+#include <linux/module.h>
 
 static int cmp_ex(const void *a, const void *b)
 {
@@ -55,7 +55,7 @@ void sort_extable (struct exception_table_entry *start,
 
 static inline unsigned long ex_to_addr(const struct exception_table_entry *x)
 {
-	return (unsigned long)&x->insn + x->insn;
+	return (unsigned long)&x->addr + x->addr;
 }
 
 #ifdef CONFIG_MODULES
diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig
index 783da855a2e..d6d35b2e5fe 100644
--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
@@ -963,7 +963,7 @@ CONFIG_EEPROM_LEGACY=y
 CONFIG_SENSORS_PCF8574=y
 # CONFIG_PCF8575 is not set
 CONFIG_SENSORS_PCF8591=y
-CONFIG_SENSORS_MAX6875=y
+CONFIG_EEPROM_MAX6875=y
 # CONFIG_SENSORS_TSL2550 is not set
 CONFIG_I2C_DEBUG_CORE=y
 CONFIG_I2C_DEBUG_ALGO=y
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index 8426d3b9501..fadb351d249 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -1849,7 +1849,7 @@ CONFIG_EEPROM_LEGACY=m
 CONFIG_SENSORS_PCF8574=m
 CONFIG_SENSORS_PCA9539=m
 CONFIG_SENSORS_PCF8591=m
-CONFIG_SENSORS_MAX6875=m
+CONFIG_EEPROM_MAX6875=m
 # CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
 # CONFIG_I2C_DEBUG_ALGO is not set
diff --git a/arch/mips/include/asm/errno.h b/arch/mips/include/asm/errno.h
index 3c0d840e457..a0efc73819e 100644
--- a/arch/mips/include/asm/errno.h
+++ b/arch/mips/include/asm/errno.h
@@ -119,6 +119,8 @@
 #define	EOWNERDEAD	165	/* Owner died */
 #define	ENOTRECOVERABLE	166	/* State not recoverable */
 
+#define	ERFKILL		167	/* Operation not possible due to RF-kill */
+
 #define EDQUOT		1133	/* Quota exceeded */
 
 #ifdef __KERNEL__
diff --git a/arch/parisc/include/asm/errno.h b/arch/parisc/include/asm/errno.h
index e2f3ddc796b..9992abdd782 100644
--- a/arch/parisc/include/asm/errno.h
+++ b/arch/parisc/include/asm/errno.h
@@ -120,5 +120,6 @@
 #define EOWNERDEAD	254	/* Owner died */
 #define ENOTRECOVERABLE	255	/* State not recoverable */
 
+#define	ERFKILL		256	/* Operation not possible due to RF-kill */
 
 #endif
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 7d044dfd923..12dc7c40961 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -1808,7 +1808,7 @@ CONFIG_PCF8575=m
 CONFIG_SENSORS_PCA9539=m
 CONFIG_SENSORS_PCF8591=m
 # CONFIG_TPS65010 is not set
-CONFIG_SENSORS_MAX6875=m
+CONFIG_EEPROM_MAX6875=m
 CONFIG_SENSORS_TSL2550=m
 CONFIG_MCU_MPC8349EMITX=m
 # CONFIG_I2C_DEBUG_CORE is not set
diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index e0faf332c9c..157c5ca581c 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -675,6 +675,8 @@ struct ucc_slow_pram {
 #define UCC_GETH_UPSMR_RMM      0x00001000
 #define UCC_GETH_UPSMR_CAM      0x00000400
 #define UCC_GETH_UPSMR_BRO      0x00000200
+#define UCC_GETH_UPSMR_SMM	0x00000080
+#define UCC_GETH_UPSMR_SGMM	0x00000020
 
 /* UCC Transmit On Demand Register (UTODR) */
 #define UCC_SLOW_TOD	0x8000
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 0eb6d7f6224..51fcae41f08 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/fsl_devices.h>
 #include <linux/mdio-bitbang.h>
+#include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 
 #include <asm/io.h>
@@ -115,7 +116,7 @@ static int __devinit ep8248e_mdio_probe(struct of_device *ofdev,
 	struct mii_bus *bus;
 	struct resource res;
 	struct device_node *node;
-	int ret, i;
+	int ret;
 
 	node = of_get_parent(ofdev->node);
 	of_node_put(node);
@@ -130,17 +131,13 @@ static int __devinit ep8248e_mdio_probe(struct of_device *ofdev,
 	if (!bus)
 		return -ENOMEM;
 
-	bus->phy_mask = 0;
 	bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
 
-	for (i = 0; i < PHY_MAX_ADDR; i++)
-		bus->irq[i] = -1;
-
 	bus->name = "ep8248e-mdio-bitbang";
 	bus->parent = &ofdev->dev;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%x", res.start);
 
-	return mdiobus_register(bus);
+	return of_mdiobus_register(bus, ofdev->node);
 }
 
 static int ep8248e_mdio_remove(struct of_device *ofdev)
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 75cc165d5be..3bf546797cb 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -29,7 +29,7 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/phy.h>
-#include <linux/platform_device.h>
+#include <linux/of_mdio.h>
 #include <linux/of_platform.h>
 
 #define DELAY 1
@@ -39,6 +39,7 @@ static void __iomem *gpio_regs;
 struct gpio_priv {
 	int mdc_pin;
 	int mdio_pin;
+	int mdio_irqs[PHY_MAX_ADDR];
 };
 
 #define MDC_PIN(bus)	(((struct gpio_priv *)bus->priv)->mdc_pin)
@@ -218,12 +219,11 @@ static int __devinit gpio_mdio_probe(struct of_device *ofdev,
 				     const struct of_device_id *match)
 {
 	struct device *dev = &ofdev->dev;
-	struct device_node *phy_dn, *np = ofdev->node;
+	struct device_node *np = ofdev->node;
 	struct mii_bus *new_bus;
 	struct gpio_priv *priv;
 	const unsigned int *prop;
 	int err;
-	int i;
 
 	err = -ENOMEM;
 	priv = kzalloc(sizeof(struct gpio_priv), GFP_KERNEL);
@@ -244,27 +244,7 @@ static int __devinit gpio_mdio_probe(struct of_device *ofdev,
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%x", *prop);
 	new_bus->priv = priv;
 
-	new_bus->phy_mask = 0;
-
-	new_bus->irq = kmalloc(sizeof(int)*PHY_MAX_ADDR, GFP_KERNEL);
-
-	if (!new_bus->irq)
-		goto out_free_bus;
-
-	for (i = 0; i < PHY_MAX_ADDR; i++)
-		new_bus->irq[i] = NO_IRQ;
-
-	for (phy_dn = of_get_next_child(np, NULL);
-	     phy_dn != NULL;
-	     phy_dn = of_get_next_child(np, phy_dn)) {
-		const unsigned int *ip, *regp;
-
-		ip = of_get_property(phy_dn, "interrupts", NULL);
-		regp = of_get_property(phy_dn, "reg", NULL);
-		if (!ip || !regp || *regp >= PHY_MAX_ADDR)
-			continue;
-		new_bus->irq[*regp] = irq_create_mapping(NULL, *ip);
-	}
+	new_bus->irq = priv->mdio_irqs;
 
 	prop = of_get_property(np, "mdc-pin", NULL);
 	priv->mdc_pin = *prop;
@@ -275,7 +255,7 @@ static int __devinit gpio_mdio_probe(struct of_device *ofdev,
 	new_bus->parent = dev;
 	dev_set_drvdata(dev, new_bus);
 
-	err = mdiobus_register(new_bus);
+	err = of_mdiobus_register(new_bus, np);
 
 	if (err != 0) {
 		printk(KERN_ERR "%s: Cannot register as MDIO bus, err %d\n",
@@ -286,8 +266,6 @@ static int __devinit gpio_mdio_probe(struct of_device *ofdev,
 	return 0;
 
 out_free_irq:
-	kfree(new_bus->irq);
-out_free_bus:
 	kfree(new_bus);
 out_free_priv:
 	kfree(priv);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 99dc3ded6b4..a14dba0e4d6 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -348,6 +348,9 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
 config ARCH_ENABLE_MEMORY_HOTREMOVE
 	def_bool y
 
+config ARCH_HIBERNATION_POSSIBLE
+       def_bool y if 64BIT
+
 source "mm/Kconfig"
 
 comment "I/O subsystem configuration"
@@ -592,6 +595,12 @@ config SECCOMP
 
 endmenu
 
+menu "Power Management"
+
+source "kernel/power/Kconfig"
+
+endmenu
+
 source "net/Kconfig"
 
 config PCMCIA
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 578c61f15a4..0ff387cebf8 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -88,7 +88,9 @@ LDFLAGS_vmlinux := -e start
 head-y		:= arch/s390/kernel/head.o arch/s390/kernel/init_task.o
 
 core-y		+= arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \
-		   arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/
+		   arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/ \
+		   arch/s390/power/
+
 libs-y		+= arch/s390/lib/
 drivers-y	+= drivers/s390/
 drivers-$(CONFIG_MATHEMU) += arch/s390/math-emu/
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 1dfc7100c7e..264528e4f58 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -5,7 +5,7 @@
  * Exports appldata_register_ops() and appldata_unregister_ops() for the
  * data gathering modules.
  *
- * Copyright IBM Corp. 2003, 2008
+ * Copyright IBM Corp. 2003, 2009
  *
  * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
@@ -26,6 +26,8 @@
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/workqueue.h>
+#include <linux/suspend.h>
+#include <linux/platform_device.h>
 #include <asm/appldata.h>
 #include <asm/timer.h>
 #include <asm/uaccess.h>
@@ -41,6 +43,9 @@
 
 #define TOD_MICRO	0x01000			/* nr. of TOD clock units
 						   for 1 microsecond */
+
+static struct platform_device *appldata_pdev;
+
 /*
  * /proc entries (sysctl)
  */
@@ -86,6 +91,7 @@ static atomic_t appldata_expire_count = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(appldata_timer_lock);
 static int appldata_interval = APPLDATA_CPU_INTERVAL;
 static int appldata_timer_active;
+static int appldata_timer_suspended = 0;
 
 /*
  * Work queue
@@ -475,6 +481,93 @@ void appldata_unregister_ops(struct appldata_ops *ops)
 /********************** module-ops management <END> **************************/
 
 
+/**************************** suspend / resume *******************************/
+static int appldata_freeze(struct device *dev)
+{
+	struct appldata_ops *ops;
+	int rc;
+	struct list_head *lh;
+
+	get_online_cpus();
+	spin_lock(&appldata_timer_lock);
+	if (appldata_timer_active) {
+		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
+		appldata_timer_suspended = 1;
+	}
+	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
+
+	mutex_lock(&appldata_ops_mutex);
+	list_for_each(lh, &appldata_ops_list) {
+		ops = list_entry(lh, struct appldata_ops, list);
+		if (ops->active == 1) {
+			rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
+					(unsigned long) ops->data, ops->size,
+					ops->mod_lvl);
+			if (rc != 0)
+				pr_err("Stopping the data collection for %s "
+				       "failed with rc=%d\n", ops->name, rc);
+		}
+	}
+	mutex_unlock(&appldata_ops_mutex);
+	return 0;
+}
+
+static int appldata_restore(struct device *dev)
+{
+	struct appldata_ops *ops;
+	int rc;
+	struct list_head *lh;
+
+	get_online_cpus();
+	spin_lock(&appldata_timer_lock);
+	if (appldata_timer_suspended) {
+		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
+		appldata_timer_suspended = 0;
+	}
+	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
+
+	mutex_lock(&appldata_ops_mutex);
+	list_for_each(lh, &appldata_ops_list) {
+		ops = list_entry(lh, struct appldata_ops, list);
+		if (ops->active == 1) {
+			ops->callback(ops->data);	// init record
+			rc = appldata_diag(ops->record_nr,
+					APPLDATA_START_INTERVAL_REC,
+					(unsigned long) ops->data, ops->size,
+					ops->mod_lvl);
+			if (rc != 0) {
+				pr_err("Starting the data collection for %s "
+				       "failed with rc=%d\n", ops->name, rc);
+			}
+		}
+	}
+	mutex_unlock(&appldata_ops_mutex);
+	return 0;
+}
+
+static int appldata_thaw(struct device *dev)
+{
+	return appldata_restore(dev);
+}
+
+static struct dev_pm_ops appldata_pm_ops = {
+	.freeze		= appldata_freeze,
+	.thaw		= appldata_thaw,
+	.restore	= appldata_restore,
+};
+
+static struct platform_driver appldata_pdrv = {
+	.driver = {
+		.name	= "appldata",
+		.owner	= THIS_MODULE,
+		.pm	= &appldata_pm_ops,
+	},
+};
+/************************* suspend / resume <END> ****************************/
+
+
 /******************************* init / exit *********************************/
 
 static void __cpuinit appldata_online_cpu(int cpu)
@@ -531,11 +624,23 @@ static struct notifier_block __cpuinitdata appldata_nb = {
  */
 static int __init appldata_init(void)
 {
-	int i;
+	int i, rc;
+
+	rc = platform_driver_register(&appldata_pdrv);
+	if (rc)
+		return rc;
 
+	appldata_pdev = platform_device_register_simple("appldata", -1, NULL,
+							0);
+	if (IS_ERR(appldata_pdev)) {
+		rc = PTR_ERR(appldata_pdev);
+		goto out_driver;
+	}
 	appldata_wq = create_singlethread_workqueue("appldata");
-	if (!appldata_wq)
-		return -ENOMEM;
+	if (!appldata_wq) {
+		rc = -ENOMEM;
+		goto out_device;
+	}
 
 	get_online_cpus();
 	for_each_online_cpu(i)
@@ -547,6 +652,12 @@ static int __init appldata_init(void)
 
 	appldata_sysctl_header = register_sysctl_table(appldata_dir_table);
 	return 0;
+
+out_device:
+	platform_device_unregister(appldata_pdev);
+out_driver:
+	platform_driver_unregister(&appldata_pdrv);
+	return rc;
 }
 
 __initcall(appldata_init);
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index ba007d8df94..2a541955117 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -1,11 +1,9 @@
 /*
- *  include/asm-s390/ccwdev.h
- *  include/asm-s390x/ccwdev.h
+ * Copyright  IBM Corp. 2002, 2009
  *
- *    Copyright (C) 2002 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Arnd Bergmann <arndb@de.ibm.com>
+ * Author(s): Arnd Bergmann <arndb@de.ibm.com>
  *
- *  Interface for CCW device drivers
+ * Interface for CCW device drivers
  */
 #ifndef _S390_CCWDEV_H_
 #define _S390_CCWDEV_H_
@@ -104,6 +102,11 @@ struct ccw_device {
  * @set_offline: called when setting device offline
  * @notify: notify driver of device state changes
  * @shutdown: called at device shutdown
+ * @prepare: prepare for pm state transition
+ * @complete: undo work done in @prepare
+ * @freeze: callback for freezing during hibernation snapshotting
+ * @thaw: undo work done in @freeze
+ * @restore: callback for restoring after hibernation
  * @driver: embedded device driver structure
  * @name: device driver name
  */
@@ -116,6 +119,11 @@ struct ccw_driver {
 	int (*set_offline) (struct ccw_device *);
 	int (*notify) (struct ccw_device *, int);
 	void (*shutdown) (struct ccw_device *);
+	int (*prepare) (struct ccw_device *);
+	void (*complete) (struct ccw_device *);
+	int (*freeze)(struct ccw_device *);
+	int (*thaw) (struct ccw_device *);
+	int (*restore)(struct ccw_device *);
 	struct device_driver driver;
 	char *name;
 };
@@ -184,6 +192,7 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
 #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
 
 extern struct ccw_device *ccw_device_probe_console(void);
+extern int ccw_device_force_console(void);
 
 // FIXME: these have to go
 extern int _ccw_device_get_subchannel_number(struct ccw_device *);
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index a27f68985a7..c79c1e787b8 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -38,6 +38,11 @@ struct ccwgroup_device {
  * @set_online: function called when device is set online
  * @set_offline: function called when device is set offline
  * @shutdown: function called when device is shut down
+ * @prepare: prepare for pm state transition
+ * @complete: undo work done in @prepare
+ * @freeze: callback for freezing during hibernation snapshotting
+ * @thaw: undo work done in @freeze
+ * @restore: callback for restoring after hibernation
  * @driver: embedded driver structure
  */
 struct ccwgroup_driver {
@@ -51,6 +56,11 @@ struct ccwgroup_driver {
 	int (*set_online) (struct ccwgroup_device *);
 	int (*set_offline) (struct ccwgroup_device *);
 	void (*shutdown)(struct ccwgroup_device *);
+	int (*prepare) (struct ccwgroup_device *);
+	void (*complete) (struct ccwgroup_device *);
+	int (*freeze)(struct ccwgroup_device *);
+	int (*thaw) (struct ccwgroup_device *);
+	int (*restore)(struct ccwgroup_device *);
 
 	struct device_driver driver;
 };
diff --git a/arch/s390/include/asm/suspend.h b/arch/s390/include/asm/suspend.h
new file mode 100644
index 00000000000..dc75c616eaf
--- /dev/null
+++ b/arch/s390/include/asm/suspend.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_S390_SUSPEND_H
+#define __ASM_S390_SUSPEND_H
+
+static inline int arch_prepare_suspend(void)
+{
+	return 0;
+}
+
+#endif
+
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index 3a8b26eb1f2..4fb83c1cdb7 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -1,11 +1,7 @@
 /*
- *  include/asm-s390/system.h
+ * Copyright IBM Corp. 1999, 2009
  *
- *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- *
- *  Derived from "include/asm-i386/system.h"
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
 #ifndef __ASM_SYSTEM_H
@@ -469,6 +465,20 @@ extern psw_t sysc_restore_trace_psw;
 extern psw_t io_restore_trace_psw;
 #endif
 
+static inline int tprot(unsigned long addr)
+{
+	int rc = -EFAULT;
+
+	asm volatile(
+		"	tprot	0(%1),0\n"
+		"0:	ipm	%0\n"
+		"	srl	%0,28\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "+d" (rc) : "a" (addr) : "cc");
+	return rc;
+}
+
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index fb263736826..f9b144049dc 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -1,7 +1,7 @@
 /*
  *  arch/s390/kernel/early.c
  *
- *    Copyright IBM Corp. 2007
+ *    Copyright IBM Corp. 2007, 2009
  *    Author(s): Hongjie Yang <hongjie@us.ibm.com>,
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
@@ -210,7 +210,7 @@ static noinline __init void detect_machine_type(void)
 		machine_flags |= MACHINE_FLAG_VM;
 }
 
-static __init void early_pgm_check_handler(void)
+static void early_pgm_check_handler(void)
 {
 	unsigned long addr;
 	const struct exception_table_entry *fixup;
@@ -222,7 +222,7 @@ static __init void early_pgm_check_handler(void)
 	S390_lowcore.program_old_psw.addr = fixup->fixup | PSW_ADDR_AMODE;
 }
 
-static noinline __init void setup_lowcore_early(void)
+void setup_lowcore_early(void)
 {
 	psw_t psw;
 
diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c
index 9872999c66d..559af0d0787 100644
--- a/arch/s390/kernel/mem_detect.c
+++ b/arch/s390/kernel/mem_detect.c
@@ -1,6 +1,7 @@
 /*
- *    Copyright IBM Corp. 2008
- *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ * Copyright IBM Corp. 2008, 2009
+ *
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
 #include <linux/kernel.h>
@@ -9,20 +10,6 @@
 #include <asm/sclp.h>
 #include <asm/setup.h>
 
-static inline int tprot(unsigned long addr)
-{
-	int rc = -EFAULT;
-
-	asm volatile(
-		"	tprot	0(%1),0\n"
-		"0:	ipm	%0\n"
-		"	srl	%0,28\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) : "a" (addr) : "cc");
-	return rc;
-}
-
 #define ADDR2G (1ULL << 31)
 
 static void find_memory_chunks(struct mem_chunk chunk[])
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index cc8c484984e..fd8e3111a4e 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -1,7 +1,7 @@
 /*
  *  arch/s390/kernel/smp.c
  *
- *    Copyright IBM Corp. 1999,2007
+ *    Copyright IBM Corp. 1999, 2009
  *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
  *		 Martin Schwidefsky (schwidefsky@de.ibm.com)
  *		 Heiko Carstens (heiko.carstens@de.ibm.com)
@@ -1031,6 +1031,42 @@ out:
 static SYSDEV_CLASS_ATTR(dispatching, 0644, dispatching_show,
 			 dispatching_store);
 
+/*
+ * If the resume kernel runs on another cpu than the suspended kernel,
+ * we have to switch the cpu IDs in the logical map.
+ */
+void smp_switch_boot_cpu_in_resume(u32 resume_phys_cpu_id,
+				   struct _lowcore *suspend_lowcore)
+{
+	int cpu, suspend_cpu_id, resume_cpu_id;
+	u32 suspend_phys_cpu_id;
+
+	suspend_phys_cpu_id = __cpu_logical_map[suspend_lowcore->cpu_nr];
+	suspend_cpu_id = suspend_lowcore->cpu_nr;
+
+	for_each_present_cpu(cpu) {
+		if (__cpu_logical_map[cpu] == resume_phys_cpu_id) {
+			resume_cpu_id = cpu;
+			goto found;
+		}
+	}
+	panic("Could not find resume cpu in logical map.\n");
+
+found:
+	printk("Resume  cpu ID: %i/%i\n", resume_phys_cpu_id, resume_cpu_id);
+	printk("Suspend cpu ID: %i/%i\n", suspend_phys_cpu_id, suspend_cpu_id);
+
+	__cpu_logical_map[resume_cpu_id] = suspend_phys_cpu_id;
+	__cpu_logical_map[suspend_cpu_id] = resume_phys_cpu_id;
+
+	lowcore_ptr[suspend_cpu_id]->cpu_addr = resume_phys_cpu_id;
+}
+
+u32 smp_get_phys_cpu_id(void)
+{
+	return __cpu_logical_map[smp_processor_id()];
+}
+
 static int __init topology_init(void)
 {
 	int cpu;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4ca8e826bf3..56566720798 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -313,3 +313,22 @@ int s390_enable_sie(void)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+#ifdef CONFIG_HIBERNATION
+bool kernel_page_present(struct page *page)
+{
+	unsigned long addr;
+	int cc;
+
+	addr = page_to_phys(page);
+	asm("lra %1,0(%1)\n"
+	    "ipm %0\n"
+	    "srl %0,28"
+	    :"=d"(cc),"+a"(addr)::"cc");
+	return cc == 0;
+}
+
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
diff --git a/arch/s390/power/Makefile b/arch/s390/power/Makefile
new file mode 100644
index 00000000000..973bb45a8fe
--- /dev/null
+++ b/arch/s390/power/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for s390 PM support
+#
+
+obj-$(CONFIG_HIBERNATION) += suspend.o
+obj-$(CONFIG_HIBERNATION) += swsusp.o
+obj-$(CONFIG_HIBERNATION) += swsusp_64.o
+obj-$(CONFIG_HIBERNATION) += swsusp_asm64.o
diff --git a/arch/s390/power/suspend.c b/arch/s390/power/suspend.c
new file mode 100644
index 00000000000..b3351eceebb
--- /dev/null
+++ b/arch/s390/power/suspend.c
@@ -0,0 +1,40 @@
+/*
+ * Suspend support specific for s390.
+ *
+ * Copyright IBM Corp. 2009
+ *
+ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/reboot.h>
+#include <linux/pfn.h>
+#include <asm/sections.h>
+#include <asm/ipl.h>
+
+/*
+ * References to section boundaries
+ */
+extern const void __nosave_begin, __nosave_end;
+
+/*
+ *  check if given pfn is in the 'nosave' or in the read only NSS section
+ */
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end))
+					>> PAGE_SHIFT;
+	unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1;
+	unsigned long stext_pfn = PFN_DOWN(__pa(&_stext));
+
+	if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn)
+		return 1;
+	if (pfn >= stext_pfn && pfn <= eshared_pfn) {
+		if (ipl_info.type == IPL_TYPE_NSS)
+			return 1;
+	} else if ((tprot(pfn * PAGE_SIZE) && pfn > 0))
+		return 1;
+	return 0;
+}
diff --git a/arch/s390/power/swsusp.c b/arch/s390/power/swsusp.c
new file mode 100644
index 00000000000..e6a4fe9f5f2
--- /dev/null
+++ b/arch/s390/power/swsusp.c
@@ -0,0 +1,30 @@
+/*
+ * Support for suspend and resume on s390
+ *
+ * Copyright IBM Corp. 2009
+ *
+ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com>
+ *
+ */
+
+
+/*
+ * save CPU registers before creating a hibernation image and before
+ * restoring the memory state from it
+ */
+void save_processor_state(void)
+{
+	/* implentation contained in the
+	 * swsusp_arch_suspend function
+	 */
+}
+
+/*
+ * restore the contents of CPU registers
+ */
+void restore_processor_state(void)
+{
+	/* implentation contained in the
+	 * swsusp_arch_resume function
+	 */
+}
diff --git a/arch/s390/power/swsusp_64.c b/arch/s390/power/swsusp_64.c
new file mode 100644
index 00000000000..9516a517d72
--- /dev/null
+++ b/arch/s390/power/swsusp_64.c
@@ -0,0 +1,17 @@
+/*
+ * Support for suspend and resume on s390
+ *
+ * Copyright IBM Corp. 2009
+ *
+ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com>
+ *
+ */
+
+#include <asm/system.h>
+#include <linux/interrupt.h>
+
+void do_after_copyback(void)
+{
+	mb();
+}
+
diff --git a/arch/s390/power/swsusp_asm64.S b/arch/s390/power/swsusp_asm64.S
new file mode 100644
index 00000000000..3c74e7d827c
--- /dev/null
+++ b/arch/s390/power/swsusp_asm64.S
@@ -0,0 +1,199 @@
+/*
+ * S390 64-bit swsusp implementation
+ *
+ * Copyright IBM Corp. 2009
+ *
+ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com>
+ *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/asm-offsets.h>
+
+/*
+ * Save register context in absolute 0 lowcore and call swsusp_save() to
+ * create in-memory kernel image. The context is saved in the designated
+ * "store status" memory locations (see POP).
+ * We return from this function twice. The first time during the suspend to
+ * disk process. The second time via the swsusp_arch_resume() function
+ * (see below) in the resume process.
+ * This function runs with disabled interrupts.
+ */
+	.section .text
+	.align	2
+	.globl swsusp_arch_suspend
+swsusp_arch_suspend:
+	stmg	%r6,%r15,__SF_GPRS(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+
+	/* Deactivate DAT */
+	stnsm	__SF_EMPTY(%r15),0xfb
+
+	/* Switch off lowcore protection */
+	stctg	%c0,%c0,__SF_EMPTY(%r15)
+	ni	__SF_EMPTY+4(%r15),0xef
+	lctlg	%c0,%c0,__SF_EMPTY(%r15)
+
+	/* Store prefix register on stack */
+	stpx	__SF_EMPTY(%r15)
+
+	/* Setup base register for lowcore (absolute 0) */
+	llgf	%r1,__SF_EMPTY(%r15)
+
+	/* Get pointer to save area */
+	aghi	%r1,0x1000
+
+	/* Store registers */
+	mvc	0x318(4,%r1),__SF_EMPTY(%r15)	/* move prefix to lowcore */
+	stfpc	0x31c(%r1)			/* store fpu control */
+	std	0,0x200(%r1)			/* store f0 */
+	std	1,0x208(%r1)			/* store f1 */
+	std	2,0x210(%r1)			/* store f2 */
+	std	3,0x218(%r1)			/* store f3 */
+	std	4,0x220(%r1)			/* store f4 */
+	std	5,0x228(%r1)			/* store f5 */
+	std	6,0x230(%r1)			/* store f6 */
+	std	7,0x238(%r1)			/* store f7 */
+	std	8,0x240(%r1)			/* store f8 */
+	std	9,0x248(%r1)			/* store f9 */
+	std	10,0x250(%r1)			/* store f10 */
+	std	11,0x258(%r1)			/* store f11 */
+	std	12,0x260(%r1)			/* store f12 */
+	std	13,0x268(%r1)			/* store f13 */
+	std	14,0x270(%r1)			/* store f14 */
+	std	15,0x278(%r1)			/* store f15 */
+	stam	%a0,%a15,0x340(%r1)		/* store access registers */
+	stctg	%c0,%c15,0x380(%r1)		/* store control registers */
+	stmg	%r0,%r15,0x280(%r1)		/* store general registers */
+
+	stpt	0x328(%r1)			/* store timer */
+	stckc	0x330(%r1)			/* store clock comparator */
+
+	/* Activate DAT */
+	stosm	__SF_EMPTY(%r15),0x04
+
+	/* Set prefix page to zero */
+	xc	__SF_EMPTY(4,%r15),__SF_EMPTY(%r15)
+	spx	__SF_EMPTY(%r15)
+
+	/* Setup lowcore */
+	brasl	%r14,setup_lowcore_early
+
+	/* Save image */
+	brasl	%r14,swsusp_save
+
+	/* Switch on lowcore protection */
+	stctg	%c0,%c0,__SF_EMPTY(%r15)
+	oi	__SF_EMPTY+4(%r15),0x10
+	lctlg	%c0,%c0,__SF_EMPTY(%r15)
+
+	/* Restore prefix register and return */
+	lghi	%r1,0x1000
+	spx	0x318(%r1)
+	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
+	lghi	%r2,0
+	br	%r14
+
+/*
+ * Restore saved memory image to correct place and restore register context.
+ * Then we return to the function that called swsusp_arch_suspend().
+ * swsusp_arch_resume() runs with disabled interrupts.
+ */
+	.globl swsusp_arch_resume
+swsusp_arch_resume:
+	stmg	%r6,%r15,__SF_GPRS(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+
+	/* Save boot cpu number */
+	brasl	%r14,smp_get_phys_cpu_id
+	lgr	%r10,%r2
+
+	/* Deactivate DAT */
+	stnsm	__SF_EMPTY(%r15),0xfb
+
+	/* Switch off lowcore protection */
+	stctg	%c0,%c0,__SF_EMPTY(%r15)
+	ni	__SF_EMPTY+4(%r15),0xef
+	lctlg	%c0,%c0,__SF_EMPTY(%r15)
+
+	/* Set prefix page to zero */
+	xc	__SF_EMPTY(4,%r15),__SF_EMPTY(%r15)
+	spx	__SF_EMPTY(%r15)
+
+	/* Restore saved image */
+	larl	%r1,restore_pblist
+	lg	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	2f
+0:
+	lg	%r2,8(%r1)
+	lg	%r4,0(%r1)
+	lghi	%r3,PAGE_SIZE
+	lghi	%r5,PAGE_SIZE
+1:
+	mvcle	%r2,%r4,0
+	jo	1b
+	lg	%r1,16(%r1)
+	ltgr	%r1,%r1
+	jnz	0b
+2:
+	ptlb				/* flush tlb */
+
+	/* Restore registers */
+	lghi	%r13,0x1000		/* %r1 = pointer to save arae */
+
+	spt	0x328(%r13)		/* reprogram timer */
+	//sckc	0x330(%r13)		/* set clock comparator */
+
+	lctlg	%c0,%c15,0x380(%r13)	/* load control registers */
+	lam	%a0,%a15,0x340(%r13)	/* load access registers */
+
+	lfpc	0x31c(%r13)		/* load fpu control */
+	ld	0,0x200(%r13)		/* load f0 */
+	ld	1,0x208(%r13)		/* load f1 */
+	ld	2,0x210(%r13)		/* load f2 */
+	ld	3,0x218(%r13)		/* load f3 */
+	ld	4,0x220(%r13)		/* load f4 */
+	ld	5,0x228(%r13)		/* load f5 */
+	ld	6,0x230(%r13)		/* load f6 */
+	ld	7,0x238(%r13)		/* load f7 */
+	ld	8,0x240(%r13)		/* load f8 */
+	ld	9,0x248(%r13)		/* load f9 */
+	ld	10,0x250(%r13)		/* load f10 */
+	ld	11,0x258(%r13)		/* load f11 */
+	ld	12,0x260(%r13)		/* load f12 */
+	ld	13,0x268(%r13)		/* load f13 */
+	ld	14,0x270(%r13)		/* load f14 */
+	ld	15,0x278(%r13)		/* load f15 */
+
+	/* Load old stack */
+	lg	%r15,0x2f8(%r13)
+
+	/* Pointer to save arae */
+	lghi	%r13,0x1000
+
+	/* Switch CPUs */
+	lgr	%r2,%r10		/* get cpu id */
+	llgf	%r3,0x318(%r13)
+	brasl	%r14,smp_switch_boot_cpu_in_resume
+
+	/* Restore prefix register */
+	spx	0x318(%r13)
+
+	/* Switch on lowcore protection */
+	stctg	%c0,%c0,__SF_EMPTY(%r15)
+	oi	__SF_EMPTY+4(%r15),0x10
+	lctlg	%c0,%c0,__SF_EMPTY(%r15)
+
+	/* Activate DAT */
+	stosm	__SF_EMPTY(%r15),0x04
+
+	/* Return 0 */
+	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
+	lghi	%r2,0
+	br	%r14
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index cc12cd48bbc..3f8b6a92eab 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -37,6 +37,8 @@ config SPARC64
 	select HAVE_KPROBES
 	select HAVE_LMB
 	select HAVE_SYSCALL_WRAPPERS
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select RTC_DRV_CMOS
 	select RTC_DRV_BQ4802
@@ -93,6 +95,9 @@ config AUDIT_ARCH
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y if SPARC64
 
+config HAVE_DYNAMIC_PER_CPU_AREA
+	def_bool y if SPARC64
+
 config GENERIC_HARDIRQS_NO__DO_IRQ
 	bool
 	def_bool y if SPARC64
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index b5d63bd8716..0123a4c596c 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.30-rc2
-# Fri Apr 17 02:03:07 2009
+# Linux kernel version: 2.6.30
+# Tue Jun 16 04:59:36 2009
 #
 CONFIG_64BIT=y
 CONFIG_SPARC=y
@@ -19,6 +19,7 @@ CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_HAVE_LATENCYTOP_SUPPORT=y
 CONFIG_AUDIT_ARCH=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
 CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_MMU=y
 CONFIG_ARCH_NO_VIRT_TO_BUS=y
@@ -82,7 +83,6 @@ CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
-# CONFIG_STRIP_ASM_SYMS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
@@ -95,16 +95,21 @@ CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
 CONFIG_AIO=y
+
+#
+# Performance Counters
+#
 CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_PCI_QUIRKS=y
 CONFIG_SLUB_DEBUG=y
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_COMPAT_BRK is not set
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
 CONFIG_TRACEPOINTS=y
-# CONFIG_MARKERS is not set
+CONFIG_MARKERS=y
 CONFIG_OPROFILE=m
 CONFIG_HAVE_OPROFILE=y
 CONFIG_KPROBES=y
@@ -202,6 +207,7 @@ CONFIG_NR_QUICK=1
 CONFIG_UNEVICTABLE_LRU=y
 CONFIG_HAVE_MLOCK=y
 CONFIG_HAVE_MLOCKED_PAGE_BIT=y
+CONFIG_DEFAULT_MMAP_MIN_ADDR=8192
 CONFIG_SCHED_SMT=y
 CONFIG_SCHED_MC=y
 # CONFIG_PREEMPT_NONE is not set
@@ -321,6 +327,7 @@ CONFIG_VLAN_8021Q=m
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
 # CONFIG_PHONET is not set
+# CONFIG_IEEE802154 is not set
 # CONFIG_NET_SCHED is not set
 # CONFIG_DCB is not set
 
@@ -340,7 +347,11 @@ CONFIG_WIRELESS=y
 CONFIG_WIRELESS_OLD_REGULATORY=y
 # CONFIG_WIRELESS_EXT is not set
 # CONFIG_LIB80211 is not set
-# CONFIG_MAC80211 is not set
+
+#
+# CFG80211 needs to be enabled for MAC80211
+#
+CONFIG_MAC80211_DEFAULT_PS_VALUE=0
 # CONFIG_WIMAX is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
@@ -364,6 +375,7 @@ CONFIG_EXTRA_FIRMWARE=""
 CONFIG_CONNECTOR=m
 # CONFIG_MTD is not set
 CONFIG_OF_DEVICE=y
+CONFIG_OF_MDIO=m
 # CONFIG_PARPORT is not set
 CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_FD is not set
@@ -399,6 +411,7 @@ CONFIG_MISC_DEVICES=y
 # CONFIG_EEPROM_AT24 is not set
 # CONFIG_EEPROM_LEGACY is not set
 # CONFIG_EEPROM_93CX6 is not set
+# CONFIG_CB710_CORE is not set
 CONFIG_HAVE_IDE=y
 CONFIG_IDE=y
 
@@ -477,10 +490,6 @@ CONFIG_BLK_DEV_SR=m
 CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=m
 # CONFIG_CHR_DEV_SCH is not set
-
-#
-# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
-#
 CONFIG_SCSI_MULTI_LUN=y
 CONFIG_SCSI_CONSTANTS=y
 # CONFIG_SCSI_LOGGING is not set
@@ -499,6 +508,7 @@ CONFIG_SCSI_FC_ATTRS=y
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
 # CONFIG_SCSI_CXGB3_ISCSI is not set
+# CONFIG_SCSI_BNX2_ISCSI is not set
 # CONFIG_BLK_DEV_3W_XXXX_RAID is not set
 # CONFIG_SCSI_3W_9XXX is not set
 # CONFIG_SCSI_ACARD is not set
@@ -507,6 +517,7 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_AIC7XXX_OLD is not set
 # CONFIG_SCSI_AIC79XX is not set
 # CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_MVSAS is not set
 # CONFIG_SCSI_ARCMSR is not set
 # CONFIG_MEGARAID_NEWGEN is not set
 # CONFIG_MEGARAID_LEGACY is not set
@@ -521,7 +532,6 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_IPS is not set
 # CONFIG_SCSI_INITIO is not set
 # CONFIG_SCSI_INIA100 is not set
-# CONFIG_SCSI_MVSAS is not set
 # CONFIG_SCSI_STEX is not set
 # CONFIG_SCSI_SYM53C8XX_2 is not set
 # CONFIG_SCSI_QLOGIC_1280 is not set
@@ -569,7 +579,6 @@ CONFIG_DM_ZERO=m
 # CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
 CONFIG_NETDEVICES=y
-CONFIG_COMPAT_NET_DEV_OPS=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
@@ -635,6 +644,7 @@ CONFIG_NET_PCI=y
 # CONFIG_SMSC9420 is not set
 # CONFIG_SUNDANCE is not set
 # CONFIG_TLAN is not set
+# CONFIG_KS8842 is not set
 # CONFIG_VIA_RHINE is not set
 # CONFIG_SC92031 is not set
 # CONFIG_ATL2 is not set
@@ -1127,6 +1137,11 @@ CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_VERBOSE_PRINTK is not set
 # CONFIG_SND_DEBUG is not set
 CONFIG_SND_VMASTER=y
+CONFIG_SND_RAWMIDI_SEQ=m
+# CONFIG_SND_OPL3_LIB_SEQ is not set
+# CONFIG_SND_OPL4_LIB_SEQ is not set
+# CONFIG_SND_SBAWE_SEQ is not set
+# CONFIG_SND_EMU10K1_SEQ is not set
 CONFIG_SND_MPU401_UART=m
 CONFIG_SND_AC97_CODEC=m
 CONFIG_SND_DRIVERS=y
@@ -1153,6 +1168,7 @@ CONFIG_SND_ALI5451=m
 # CONFIG_SND_OXYGEN is not set
 # CONFIG_SND_CS4281 is not set
 # CONFIG_SND_CS46XX is not set
+# CONFIG_SND_CTXFI is not set
 # CONFIG_SND_DARLA20 is not set
 # CONFIG_SND_GINA20 is not set
 # CONFIG_SND_LAYLA20 is not set
@@ -1183,6 +1199,7 @@ CONFIG_SND_ALI5451=m
 # CONFIG_SND_INTEL8X0 is not set
 # CONFIG_SND_INTEL8X0M is not set
 # CONFIG_SND_KORG1212 is not set
+# CONFIG_SND_LX6464ES is not set
 # CONFIG_SND_MAESTRO3 is not set
 # CONFIG_SND_MIXART is not set
 # CONFIG_SND_NM256 is not set
@@ -1229,6 +1246,7 @@ CONFIG_HID_BELKIN=y
 CONFIG_HID_CHERRY=y
 CONFIG_HID_CHICONY=y
 CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
 # CONFIG_DRAGONRISE_FF is not set
 CONFIG_HID_EZKEY=y
 CONFIG_HID_KYE=y
@@ -1246,9 +1264,14 @@ CONFIG_HID_PETALYNX=y
 CONFIG_HID_SAMSUNG=y
 CONFIG_HID_SONY=y
 CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
 # CONFIG_GREENASIA_FF is not set
+CONFIG_HID_SMARTJOYPLUS=y
+# CONFIG_SMARTJOYPLUS_FF is not set
 CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
 # CONFIG_THRUSTMASTER_FF is not set
+CONFIG_HID_ZEROPLUS=y
 # CONFIG_ZEROPLUS_FF is not set
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
@@ -1462,6 +1485,7 @@ CONFIG_FILE_LOCKING=y
 # CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
 # CONFIG_BTRFS_FS is not set
+CONFIG_FSNOTIFY=y
 CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
@@ -1636,25 +1660,28 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y
 # CONFIG_DEBUG_PAGEALLOC is not set
 CONFIG_NOP_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_RING_BUFFER=y
+CONFIG_EVENT_TRACING=y
+CONFIG_CONTEXT_SWITCH_TRACER=y
 CONFIG_TRACING=y
+CONFIG_GENERIC_TRACER=y
 CONFIG_TRACING_SUPPORT=y
-
-#
-# Tracers
-#
+CONFIG_FTRACE=y
 # CONFIG_FUNCTION_TRACER is not set
 # CONFIG_IRQSOFF_TRACER is not set
 # CONFIG_SCHED_TRACER is not set
-# CONFIG_CONTEXT_SWITCH_TRACER is not set
-# CONFIG_EVENT_TRACER is not set
 # CONFIG_BOOT_TRACER is not set
-# CONFIG_TRACE_BRANCH_PROFILING is not set
+CONFIG_BRANCH_PROFILE_NONE=y
+# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
+# CONFIG_PROFILE_ALL_BRANCHES is not set
 # CONFIG_STACK_TRACER is not set
 # CONFIG_KMEMTRACE is not set
 # CONFIG_WORKQUEUE_TRACER is not set
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_FTRACE_STARTUP_TEST is not set
+# CONFIG_RING_BUFFER_BENCHMARK is not set
 # CONFIG_DYNAMIC_DEBUG is not set
 # CONFIG_SAMPLES is not set
 CONFIG_HAVE_ARCH_KGDB=y
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a11b89ee9ef..926397d345f 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -6,9 +6,6 @@
 #ifndef _SPARC64_CPUDATA_H
 #define _SPARC64_CPUDATA_H
 
-#include <asm/hypervisor.h>
-#include <asm/asi.h>
-
 #ifndef __ASSEMBLY__
 
 #include <linux/percpu.h>
@@ -38,202 +35,10 @@ DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
 #define local_cpu_data()	__get_cpu_var(__cpu_data)
 
-/* Trap handling code needs to get at a few critical values upon
- * trap entry and to process TSB misses.  These cannot be in the
- * per_cpu() area as we really need to lock them into the TLB and
- * thus make them part of the main kernel image.  As a result we
- * try to make this as small as possible.
- *
- * This is padded out and aligned to 64-bytes to avoid false sharing
- * on SMP.
- */
-
-/* If you modify the size of this structure, please update
- * TRAP_BLOCK_SZ_SHIFT below.
- */
-struct thread_info;
-struct trap_per_cpu {
-/* D-cache line 1: Basic thread information, cpu and device mondo queues */
-	struct thread_info	*thread;
-	unsigned long		pgd_paddr;
-	unsigned long		cpu_mondo_pa;
-	unsigned long		dev_mondo_pa;
-
-/* D-cache line 2: Error Mondo Queue and kernel buffer pointers */
-	unsigned long		resum_mondo_pa;
-	unsigned long		resum_kernel_buf_pa;
-	unsigned long		nonresum_mondo_pa;
-	unsigned long		nonresum_kernel_buf_pa;
-
-/* Dcache lines 3, 4, 5, and 6: Hypervisor Fault Status */
-	struct hv_fault_status	fault_info;
-
-/* Dcache line 7: Physical addresses of CPU send mondo block and CPU list.  */
-	unsigned long		cpu_mondo_block_pa;
-	unsigned long		cpu_list_pa;
-	unsigned long		tsb_huge;
-	unsigned long		tsb_huge_temp;
-
-/* Dcache line 8: IRQ work list, and keep trap_block a power-of-2 in size.  */
-	unsigned long		irq_worklist_pa;
-	unsigned int		cpu_mondo_qmask;
-	unsigned int		dev_mondo_qmask;
-	unsigned int		resum_qmask;
-	unsigned int		nonresum_qmask;
-	void			*hdesc;
-} __attribute__((aligned(64)));
-extern struct trap_per_cpu trap_block[NR_CPUS];
-extern void init_cur_cpu_trap(struct thread_info *);
-extern void setup_tba(void);
-extern int ncpus_probed;
 extern const struct seq_operations cpuinfo_op;
 
-extern unsigned long real_hard_smp_processor_id(void);
-
-struct cpuid_patch_entry {
-	unsigned int	addr;
-	unsigned int	cheetah_safari[4];
-	unsigned int	cheetah_jbus[4];
-	unsigned int	starfire[4];
-	unsigned int	sun4v[4];
-};
-extern struct cpuid_patch_entry __cpuid_patch, __cpuid_patch_end;
-
-struct sun4v_1insn_patch_entry {
-	unsigned int	addr;
-	unsigned int	insn;
-};
-extern struct sun4v_1insn_patch_entry __sun4v_1insn_patch,
-	__sun4v_1insn_patch_end;
-
-struct sun4v_2insn_patch_entry {
-	unsigned int	addr;
-	unsigned int	insns[2];
-};
-extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
-	__sun4v_2insn_patch_end;
-
 #endif /* !(__ASSEMBLY__) */
 
-#define TRAP_PER_CPU_THREAD		0x00
-#define TRAP_PER_CPU_PGD_PADDR		0x08
-#define TRAP_PER_CPU_CPU_MONDO_PA	0x10
-#define TRAP_PER_CPU_DEV_MONDO_PA	0x18
-#define TRAP_PER_CPU_RESUM_MONDO_PA	0x20
-#define TRAP_PER_CPU_RESUM_KBUF_PA	0x28
-#define TRAP_PER_CPU_NONRESUM_MONDO_PA	0x30
-#define TRAP_PER_CPU_NONRESUM_KBUF_PA	0x38
-#define TRAP_PER_CPU_FAULT_INFO		0x40
-#define TRAP_PER_CPU_CPU_MONDO_BLOCK_PA	0xc0
-#define TRAP_PER_CPU_CPU_LIST_PA	0xc8
-#define TRAP_PER_CPU_TSB_HUGE		0xd0
-#define TRAP_PER_CPU_TSB_HUGE_TEMP	0xd8
-#define TRAP_PER_CPU_IRQ_WORKLIST_PA	0xe0
-#define TRAP_PER_CPU_CPU_MONDO_QMASK	0xe8
-#define TRAP_PER_CPU_DEV_MONDO_QMASK	0xec
-#define TRAP_PER_CPU_RESUM_QMASK	0xf0
-#define TRAP_PER_CPU_NONRESUM_QMASK	0xf4
-
-#define TRAP_BLOCK_SZ_SHIFT		8
-
-#include <asm/scratchpad.h>
-
-#define __GET_CPUID(REG)				\
-	/* Spitfire implementation (default). */	\
-661:	ldxa		[%g0] ASI_UPA_CONFIG, REG;	\
-	srlx		REG, 17, REG;			\
-	 and		REG, 0x1f, REG;			\
-	nop;						\
-	.section	.cpuid_patch, "ax";		\
-	/* Instruction location. */			\
-	.word		661b;				\
-	/* Cheetah Safari implementation. */		\
-	ldxa		[%g0] ASI_SAFARI_CONFIG, REG;	\
-	srlx		REG, 17, REG;			\
-	and		REG, 0x3ff, REG;		\
-	nop;						\
-	/* Cheetah JBUS implementation. */		\
-	ldxa		[%g0] ASI_JBUS_CONFIG, REG;	\
-	srlx		REG, 17, REG;			\
-	and		REG, 0x1f, REG;			\
-	nop;						\
-	/* Starfire implementation. */			\
-	sethi		%hi(0x1fff40000d0 >> 9), REG;	\
-	sllx		REG, 9, REG;			\
-	or		REG, 0xd0, REG;			\
-	lduwa		[REG] ASI_PHYS_BYPASS_EC_E, REG;\
-	/* sun4v implementation. */			\
-	mov		SCRATCHPAD_CPUID, REG;		\
-	ldxa		[REG] ASI_SCRATCHPAD, REG;	\
-	nop;						\
-	nop;						\
-	.previous;
-
-#ifdef CONFIG_SMP
-
-#define TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	__GET_CPUID(TMP)			\
-	sethi	%hi(trap_block), DEST;		\
-	sllx	TMP, TRAP_BLOCK_SZ_SHIFT, TMP;	\
-	or	DEST, %lo(trap_block), DEST;	\
-	add	DEST, TMP, DEST;		\
-
-/* Clobbers TMP, current address space PGD phys address into DEST.  */
-#define TRAP_LOAD_PGD_PHYS(DEST, TMP)		\
-	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	ldx	[DEST + TRAP_PER_CPU_PGD_PADDR], DEST;
-
-/* Clobbers TMP, loads local processor's IRQ work area into DEST.  */
-#define TRAP_LOAD_IRQ_WORK_PA(DEST, TMP)	\
-	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	add	DEST, TRAP_PER_CPU_IRQ_WORKLIST_PA, DEST;
-
-/* Clobbers TMP, loads DEST with current thread info pointer.  */
-#define TRAP_LOAD_THREAD_REG(DEST, TMP)		\
-	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	ldx	[DEST + TRAP_PER_CPU_THREAD], DEST;
-
-/* Given the current thread info pointer in THR, load the per-cpu
- * area base of the current processor into DEST.  REG1, REG2, and REG3 are
- * clobbered.
- *
- * You absolutely cannot use DEST as a temporary in this code.  The
- * reason is that traps can happen during execution, and return from
- * trap will load the fully resolved DEST per-cpu base.  This can corrupt
- * the calculations done by the macro mid-stream.
- */
-#define LOAD_PER_CPU_BASE(DEST, THR, REG1, REG2, REG3)	\
-	lduh	[THR + TI_CPU], REG1;			\
-	sethi	%hi(__per_cpu_shift), REG3;		\
-	sethi	%hi(__per_cpu_base), REG2;		\
-	ldx	[REG3 + %lo(__per_cpu_shift)], REG3;	\
-	ldx	[REG2 + %lo(__per_cpu_base)], REG2;	\
-	sllx	REG1, REG3, REG3;			\
-	add	REG3, REG2, DEST;
-
-#else
-
-#define TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	sethi	%hi(trap_block), DEST;		\
-	or	DEST, %lo(trap_block), DEST;	\
-
-/* Uniprocessor versions, we know the cpuid is zero.  */
-#define TRAP_LOAD_PGD_PHYS(DEST, TMP)		\
-	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	ldx	[DEST + TRAP_PER_CPU_PGD_PADDR], DEST;
-
-/* Clobbers TMP, loads local processor's IRQ work area into DEST.  */
-#define TRAP_LOAD_IRQ_WORK_PA(DEST, TMP)	\
-	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	add	DEST, TRAP_PER_CPU_IRQ_WORKLIST_PA, DEST;
-
-#define TRAP_LOAD_THREAD_REG(DEST, TMP)		\
-	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
-	ldx	[DEST + TRAP_PER_CPU_THREAD], DEST;
-
-/* No per-cpu areas on uniprocessor, so no need to load DEST.  */
-#define LOAD_PER_CPU_BASE(DEST, THR, REG1, REG2, REG3)
-
-#endif /* !(CONFIG_SMP) */
+#include <asm/trap_block.h>
 
 #endif /* _SPARC64_CPUDATA_H */
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 0f4150e2661..204e4bf6443 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -1,8 +1,166 @@
 #ifndef ___ASM_SPARC_DMA_MAPPING_H
 #define ___ASM_SPARC_DMA_MAPPING_H
-#if defined(__sparc__) && defined(__arch64__)
-#include <asm/dma-mapping_64.h>
-#else
-#include <asm/dma-mapping_32.h>
-#endif
+
+#include <linux/scatterlist.h>
+#include <linux/mm.h>
+
+#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
+
+extern int dma_supported(struct device *dev, u64 mask);
+extern int dma_set_mask(struct device *dev, u64 dma_mask);
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+#define dma_is_consistent(d, h)	(1)
+
+struct dma_ops {
+	void *(*alloc_coherent)(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t flag);
+	void (*free_coherent)(struct device *dev, size_t size,
+			      void *cpu_addr, dma_addr_t dma_handle);
+	dma_addr_t (*map_page)(struct device *dev, struct page *page,
+			       unsigned long offset, size_t size,
+			       enum dma_data_direction direction);
+	void (*unmap_page)(struct device *dev, dma_addr_t dma_addr,
+			   size_t size,
+			   enum dma_data_direction direction);
+	int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
+		      enum dma_data_direction direction);
+	void (*unmap_sg)(struct device *dev, struct scatterlist *sg,
+			 int nhwentries,
+			 enum dma_data_direction direction);
+	void (*sync_single_for_cpu)(struct device *dev,
+				    dma_addr_t dma_handle, size_t size,
+				    enum dma_data_direction direction);
+	void (*sync_single_for_device)(struct device *dev,
+				       dma_addr_t dma_handle, size_t size,
+				       enum dma_data_direction direction);
+	void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
+				int nelems,
+				enum dma_data_direction direction);
+	void (*sync_sg_for_device)(struct device *dev,
+				   struct scatterlist *sg, int nents,
+				   enum dma_data_direction dir);
+};
+extern const struct dma_ops *dma_ops;
+
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag)
+{
+	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
+{
+	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
+static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
+					size_t size,
+					enum dma_data_direction direction)
+{
+	return dma_ops->map_page(dev, virt_to_page(cpu_addr),
+				 (unsigned long)cpu_addr & ~PAGE_MASK, size,
+				 direction);
+}
+
+static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
+				    size_t size,
+				    enum dma_data_direction direction)
+{
+	dma_ops->unmap_page(dev, dma_addr, size, direction);
+}
+
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+				      unsigned long offset, size_t size,
+				      enum dma_data_direction direction)
+{
+	return dma_ops->map_page(dev, page, offset, size, direction);
+}
+
+static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
+				  size_t size,
+				  enum dma_data_direction direction)
+{
+	dma_ops->unmap_page(dev, dma_address, size, direction);
+}
+
+static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, enum dma_data_direction direction)
+{
+	return dma_ops->map_sg(dev, sg, nents, direction);
+}
+
+static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction direction)
+{
+	dma_ops->unmap_sg(dev, sg, nents, direction);
+}
+
+static inline void dma_sync_single_for_cpu(struct device *dev,
+					   dma_addr_t dma_handle, size_t size,
+					   enum dma_data_direction direction)
+{
+	dma_ops->sync_single_for_cpu(dev, dma_handle, size, direction);
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+					      dma_addr_t dma_handle,
+					      size_t size,
+					      enum dma_data_direction direction)
+{
+	if (dma_ops->sync_single_for_device)
+		dma_ops->sync_single_for_device(dev, dma_handle, size,
+						direction);
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+				       struct scatterlist *sg, int nelems,
+				       enum dma_data_direction direction)
+{
+	dma_ops->sync_sg_for_cpu(dev, sg, nelems, direction);
+}
+
+static inline void dma_sync_sg_for_device(struct device *dev,
+					  struct scatterlist *sg, int nelems,
+					  enum dma_data_direction direction)
+{
+	if (dma_ops->sync_sg_for_device)
+		dma_ops->sync_sg_for_device(dev, sg, nelems, direction);
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+						 dma_addr_t dma_handle,
+						 unsigned long offset,
+						 size_t size,
+						 enum dma_data_direction dir)
+{
+	dma_sync_single_for_cpu(dev, dma_handle+offset, size, dir);
+}
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+						    dma_addr_t dma_handle,
+						    unsigned long offset,
+						    size_t size,
+						    enum dma_data_direction dir)
+{
+	dma_sync_single_for_device(dev, dma_handle+offset, size, dir);
+}
+
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return (dma_addr == DMA_ERROR_CODE);
+}
+
+static inline int dma_get_cache_alignment(void)
+{
+	/*
+	 * no easy way to get cache size on all processors, so return
+	 * the maximum possible, to be safe
+	 */
+	return (1 << INTERNODE_CACHE_SHIFT);
+}
+
 #endif
diff --git a/arch/sparc/include/asm/dma-mapping_32.h b/arch/sparc/include/asm/dma-mapping_32.h
deleted file mode 100644
index 8a57ea0573e..00000000000
--- a/arch/sparc/include/asm/dma-mapping_32.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _ASM_SPARC_DMA_MAPPING_H
-#define _ASM_SPARC_DMA_MAPPING_H
-
-#include <linux/types.h>
-
-struct device;
-struct scatterlist;
-struct page;
-
-#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
-
-extern int dma_supported(struct device *dev, u64 mask);
-extern int dma_set_mask(struct device *dev, u64 dma_mask);
-extern void *dma_alloc_coherent(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag);
-extern void dma_free_coherent(struct device *dev, size_t size,
-			      void *cpu_addr, dma_addr_t dma_handle);
-extern dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-				 size_t size,
-				 enum dma_data_direction direction);
-extern void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-			     size_t size,
-			     enum dma_data_direction direction);
-extern dma_addr_t dma_map_page(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction direction);
-extern void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-			   size_t size, enum dma_data_direction direction);
-extern int dma_map_sg(struct device *dev, struct scatterlist *sg,
-		      int nents, enum dma_data_direction direction);
-extern void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-			 int nents, enum dma_data_direction direction);
-extern void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-				    size_t size,
-				    enum dma_data_direction direction);
-extern void dma_sync_single_for_device(struct device *dev,
-				       dma_addr_t dma_handle,
-				       size_t size,
-				       enum dma_data_direction direction);
-extern void dma_sync_single_range_for_cpu(struct device *dev,
-					  dma_addr_t dma_handle,
-					  unsigned long offset,
-					  size_t size,
-					  enum dma_data_direction direction);
-extern void dma_sync_single_range_for_device(struct device *dev,
-					     dma_addr_t dma_handle,
-					     unsigned long offset, size_t size,
-					     enum dma_data_direction direction);
-extern void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				int nelems, enum dma_data_direction direction);
-extern void dma_sync_sg_for_device(struct device *dev,
-				   struct scatterlist *sg, int nelems,
-				   enum dma_data_direction direction);
-extern int dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-extern int dma_get_cache_alignment(void);
-
-#define dma_alloc_noncoherent	dma_alloc_coherent
-#define dma_free_noncoherent	dma_free_coherent
-
-#endif /* _ASM_SPARC_DMA_MAPPING_H */
diff --git a/arch/sparc/include/asm/dma-mapping_64.h b/arch/sparc/include/asm/dma-mapping_64.h
deleted file mode 100644
index bfa64f9702d..00000000000
--- a/arch/sparc/include/asm/dma-mapping_64.h
+++ /dev/null
@@ -1,154 +0,0 @@
-#ifndef _ASM_SPARC64_DMA_MAPPING_H
-#define _ASM_SPARC64_DMA_MAPPING_H
-
-#include <linux/scatterlist.h>
-#include <linux/mm.h>
-
-#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
-
-struct dma_ops {
-	void *(*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t flag);
-	void (*free_coherent)(struct device *dev, size_t size,
-			      void *cpu_addr, dma_addr_t dma_handle);
-	dma_addr_t (*map_single)(struct device *dev, void *cpu_addr,
-				 size_t size,
-				 enum dma_data_direction direction);
-	void (*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-			     size_t size,
-			     enum dma_data_direction direction);
-	int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
-		      enum dma_data_direction direction);
-	void (*unmap_sg)(struct device *dev, struct scatterlist *sg,
-			 int nhwentries,
-			 enum dma_data_direction direction);
-	void (*sync_single_for_cpu)(struct device *dev,
-				    dma_addr_t dma_handle, size_t size,
-				    enum dma_data_direction direction);
-	void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
-				int nelems,
-				enum dma_data_direction direction);
-};
-extern const struct dma_ops *dma_ops;
-
-extern int dma_supported(struct device *dev, u64 mask);
-extern int dma_set_mask(struct device *dev, u64 dma_mask);
-
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
-{
-	return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
-{
-	dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-					size_t size,
-					enum dma_data_direction direction)
-{
-	return dma_ops->map_single(dev, cpu_addr, size, direction);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				    size_t size,
-				    enum dma_data_direction direction)
-{
-	dma_ops->unmap_single(dev, dma_addr, size, direction);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction direction)
-{
-	return dma_ops->map_single(dev, page_address(page) + offset,
-				   size, direction);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-				  size_t size,
-				  enum dma_data_direction direction)
-{
-	dma_ops->unmap_single(dev, dma_address, size, direction);
-}
-
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction direction)
-{
-	return dma_ops->map_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction direction)
-{
-	dma_ops->unmap_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev,
-					   dma_addr_t dma_handle, size_t size,
-					   enum dma_data_direction direction)
-{
-	dma_ops->sync_single_for_cpu(dev, dma_handle, size, direction);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t dma_handle,
-					      size_t size,
-					      enum dma_data_direction direction)
-{
-	/* No flushing needed to sync cpu writes to the device.  */
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-						 dma_addr_t dma_handle,
-						 unsigned long offset,
-						 size_t size,
-						 enum dma_data_direction direction)
-{
-	dma_sync_single_for_cpu(dev, dma_handle+offset, size, direction);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t dma_handle,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction direction)
-{
-	/* No flushing needed to sync cpu writes to the device.  */
-}
-
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-				       struct scatterlist *sg, int nelems,
-				       enum dma_data_direction direction)
-{
-	dma_ops->sync_sg_for_cpu(dev, sg, nelems, direction);
-}
-
-static inline void dma_sync_sg_for_device(struct device *dev,
-					  struct scatterlist *sg, int nelems,
-					  enum dma_data_direction direction)
-{
-	/* No flushing needed to sync cpu writes to the device.  */
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return (dma_addr == DMA_ERROR_CODE);
-}
-
-static inline int dma_get_cache_alignment(void)
-{
-	/* no easy way to get cache size on all processors, so return
-	 * the maximum possible, to be safe */
-	return (1 << INTERNODE_CACHE_SHIFT);
-}
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_is_consistent(d, h)	(1)
-
-#endif /* _ASM_SPARC64_DMA_MAPPING_H */
diff --git a/arch/sparc/include/asm/errno.h b/arch/sparc/include/asm/errno.h
index a9ef172977d..4e2bc490d71 100644
--- a/arch/sparc/include/asm/errno.h
+++ b/arch/sparc/include/asm/errno.h
@@ -110,4 +110,6 @@
 #define	EOWNERDEAD	132	/* Owner died */
 #define	ENOTRECOVERABLE	133	/* State not recoverable */
 
+#define	ERFKILL		134	/* Operation not possible due to RF-kill */
+
 #endif
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index d27716cd38c..b0f18e9893d 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -11,4 +11,15 @@ extern void _mcount(void);
 
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+/* reloction of mcount call site is the same as the address */
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+struct dyn_arch_ftrace {
+};
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+
 #endif /* _ASM_SPARC64_FTRACE */
diff --git a/arch/sparc/include/asm/mdesc.h b/arch/sparc/include/asm/mdesc.h
index 1acc7272e53..9faa046713f 100644
--- a/arch/sparc/include/asm/mdesc.h
+++ b/arch/sparc/include/asm/mdesc.h
@@ -71,7 +71,8 @@ struct mdesc_notifier_client {
 
 extern void mdesc_register_notifier(struct mdesc_notifier_client *client);
 
-extern void mdesc_fill_in_cpu_data(cpumask_t mask);
+extern void mdesc_fill_in_cpu_data(cpumask_t *mask);
+extern void mdesc_populate_present_mask(cpumask_t *mask);
 
 extern void sun4v_mdesc_init(void);
 
diff --git a/arch/sparc/include/asm/percpu_64.h b/arch/sparc/include/asm/percpu_64.h
index bee64593023..007aafb4ae9 100644
--- a/arch/sparc/include/asm/percpu_64.h
+++ b/arch/sparc/include/asm/percpu_64.h
@@ -7,20 +7,16 @@ register unsigned long __local_per_cpu_offset asm("g5");
 
 #ifdef CONFIG_SMP
 
-extern void real_setup_per_cpu_areas(void);
+#include <asm/trap_block.h>
 
-extern unsigned long __per_cpu_base;
-extern unsigned long __per_cpu_shift;
 #define __per_cpu_offset(__cpu) \
-	(__per_cpu_base + ((unsigned long)(__cpu) << __per_cpu_shift))
+	(trap_block[(__cpu)].__per_cpu_base)
 #define per_cpu_offset(x) (__per_cpu_offset(x))
 
 #define __my_cpu_offset __local_per_cpu_offset
 
 #else /* ! SMP */
 
-#define real_setup_per_cpu_areas()		do { } while (0)
-
 #endif	/* SMP */
 
 #include <asm-generic/percpu.h>
diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index 900d44714f8..be8d7aaeb60 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -86,6 +86,8 @@ extern int of_node_to_nid(struct device_node *dp);
 #endif
 
 extern void prom_build_devicetree(void);
+extern void of_populate_present_mask(void);
+extern void of_fill_in_cpu_data(void);
 
 /* Dummy ref counting routines - to be implemented later */
 static inline struct device_node *of_node_get(struct device_node *node)
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
new file mode 100644
index 00000000000..7e26b2db621
--- /dev/null
+++ b/arch/sparc/include/asm/trap_block.h
@@ -0,0 +1,207 @@
+#ifndef _SPARC_TRAP_BLOCK_H
+#define _SPARC_TRAP_BLOCK_H
+
+#include <asm/hypervisor.h>
+#include <asm/asi.h>
+
+#ifndef __ASSEMBLY__
+
+/* Trap handling code needs to get at a few critical values upon
+ * trap entry and to process TSB misses.  These cannot be in the
+ * per_cpu() area as we really need to lock them into the TLB and
+ * thus make them part of the main kernel image.  As a result we
+ * try to make this as small as possible.
+ *
+ * This is padded out and aligned to 64-bytes to avoid false sharing
+ * on SMP.
+ */
+
+/* If you modify the size of this structure, please update
+ * TRAP_BLOCK_SZ_SHIFT below.
+ */
+struct thread_info;
+struct trap_per_cpu {
+/* D-cache line 1: Basic thread information, cpu and device mondo queues */
+	struct thread_info	*thread;
+	unsigned long		pgd_paddr;
+	unsigned long		cpu_mondo_pa;
+	unsigned long		dev_mondo_pa;
+
+/* D-cache line 2: Error Mondo Queue and kernel buffer pointers */
+	unsigned long		resum_mondo_pa;
+	unsigned long		resum_kernel_buf_pa;
+	unsigned long		nonresum_mondo_pa;
+	unsigned long		nonresum_kernel_buf_pa;
+
+/* Dcache lines 3, 4, 5, and 6: Hypervisor Fault Status */
+	struct hv_fault_status	fault_info;
+
+/* Dcache line 7: Physical addresses of CPU send mondo block and CPU list.  */
+	unsigned long		cpu_mondo_block_pa;
+	unsigned long		cpu_list_pa;
+	unsigned long		tsb_huge;
+	unsigned long		tsb_huge_temp;
+
+/* Dcache line 8: IRQ work list, and keep trap_block a power-of-2 in size.  */
+	unsigned long		irq_worklist_pa;
+	unsigned int		cpu_mondo_qmask;
+	unsigned int		dev_mondo_qmask;
+	unsigned int		resum_qmask;
+	unsigned int		nonresum_qmask;
+	unsigned long		__per_cpu_base;
+} __attribute__((aligned(64)));
+extern struct trap_per_cpu trap_block[NR_CPUS];
+extern void init_cur_cpu_trap(struct thread_info *);
+extern void setup_tba(void);
+extern int ncpus_probed;
+
+extern unsigned long real_hard_smp_processor_id(void);
+
+struct cpuid_patch_entry {
+	unsigned int	addr;
+	unsigned int	cheetah_safari[4];
+	unsigned int	cheetah_jbus[4];
+	unsigned int	starfire[4];
+	unsigned int	sun4v[4];
+};
+extern struct cpuid_patch_entry __cpuid_patch, __cpuid_patch_end;
+
+struct sun4v_1insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insn;
+};
+extern struct sun4v_1insn_patch_entry __sun4v_1insn_patch,
+	__sun4v_1insn_patch_end;
+
+struct sun4v_2insn_patch_entry {
+	unsigned int	addr;
+	unsigned int	insns[2];
+};
+extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
+	__sun4v_2insn_patch_end;
+
+
+#endif /* !(__ASSEMBLY__) */
+
+#define TRAP_PER_CPU_THREAD		0x00
+#define TRAP_PER_CPU_PGD_PADDR		0x08
+#define TRAP_PER_CPU_CPU_MONDO_PA	0x10
+#define TRAP_PER_CPU_DEV_MONDO_PA	0x18
+#define TRAP_PER_CPU_RESUM_MONDO_PA	0x20
+#define TRAP_PER_CPU_RESUM_KBUF_PA	0x28
+#define TRAP_PER_CPU_NONRESUM_MONDO_PA	0x30
+#define TRAP_PER_CPU_NONRESUM_KBUF_PA	0x38
+#define TRAP_PER_CPU_FAULT_INFO		0x40
+#define TRAP_PER_CPU_CPU_MONDO_BLOCK_PA	0xc0
+#define TRAP_PER_CPU_CPU_LIST_PA	0xc8
+#define TRAP_PER_CPU_TSB_HUGE		0xd0
+#define TRAP_PER_CPU_TSB_HUGE_TEMP	0xd8
+#define TRAP_PER_CPU_IRQ_WORKLIST_PA	0xe0
+#define TRAP_PER_CPU_CPU_MONDO_QMASK	0xe8
+#define TRAP_PER_CPU_DEV_MONDO_QMASK	0xec
+#define TRAP_PER_CPU_RESUM_QMASK	0xf0
+#define TRAP_PER_CPU_NONRESUM_QMASK	0xf4
+#define TRAP_PER_CPU_PER_CPU_BASE	0xf8
+
+#define TRAP_BLOCK_SZ_SHIFT		8
+
+#include <asm/scratchpad.h>
+
+#define __GET_CPUID(REG)				\
+	/* Spitfire implementation (default). */	\
+661:	ldxa		[%g0] ASI_UPA_CONFIG, REG;	\
+	srlx		REG, 17, REG;			\
+	 and		REG, 0x1f, REG;			\
+	nop;						\
+	.section	.cpuid_patch, "ax";		\
+	/* Instruction location. */			\
+	.word		661b;				\
+	/* Cheetah Safari implementation. */		\
+	ldxa		[%g0] ASI_SAFARI_CONFIG, REG;	\
+	srlx		REG, 17, REG;			\
+	and		REG, 0x3ff, REG;		\
+	nop;						\
+	/* Cheetah JBUS implementation. */		\
+	ldxa		[%g0] ASI_JBUS_CONFIG, REG;	\
+	srlx		REG, 17, REG;			\
+	and		REG, 0x1f, REG;			\
+	nop;						\
+	/* Starfire implementation. */			\
+	sethi		%hi(0x1fff40000d0 >> 9), REG;	\
+	sllx		REG, 9, REG;			\
+	or		REG, 0xd0, REG;			\
+	lduwa		[REG] ASI_PHYS_BYPASS_EC_E, REG;\
+	/* sun4v implementation. */			\
+	mov		SCRATCHPAD_CPUID, REG;		\
+	ldxa		[REG] ASI_SCRATCHPAD, REG;	\
+	nop;						\
+	nop;						\
+	.previous;
+
+#ifdef CONFIG_SMP
+
+#define TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	__GET_CPUID(TMP)			\
+	sethi	%hi(trap_block), DEST;		\
+	sllx	TMP, TRAP_BLOCK_SZ_SHIFT, TMP;	\
+	or	DEST, %lo(trap_block), DEST;	\
+	add	DEST, TMP, DEST;		\
+
+/* Clobbers TMP, current address space PGD phys address into DEST.  */
+#define TRAP_LOAD_PGD_PHYS(DEST, TMP)		\
+	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	ldx	[DEST + TRAP_PER_CPU_PGD_PADDR], DEST;
+
+/* Clobbers TMP, loads local processor's IRQ work area into DEST.  */
+#define TRAP_LOAD_IRQ_WORK_PA(DEST, TMP)	\
+	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	add	DEST, TRAP_PER_CPU_IRQ_WORKLIST_PA, DEST;
+
+/* Clobbers TMP, loads DEST with current thread info pointer.  */
+#define TRAP_LOAD_THREAD_REG(DEST, TMP)		\
+	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	ldx	[DEST + TRAP_PER_CPU_THREAD], DEST;
+
+/* Given the current thread info pointer in THR, load the per-cpu
+ * area base of the current processor into DEST.  REG1, REG2, and REG3 are
+ * clobbered.
+ *
+ * You absolutely cannot use DEST as a temporary in this code.  The
+ * reason is that traps can happen during execution, and return from
+ * trap will load the fully resolved DEST per-cpu base.  This can corrupt
+ * the calculations done by the macro mid-stream.
+ */
+#define LOAD_PER_CPU_BASE(DEST, THR, REG1, REG2, REG3)	\
+	lduh	[THR + TI_CPU], REG1;			\
+	sethi	%hi(trap_block), REG2;			\
+	sllx	REG1, TRAP_BLOCK_SZ_SHIFT, REG1;	\
+	or	REG2, %lo(trap_block), REG2;		\
+	add	REG2, REG1, REG2;			\
+	ldx	[REG2 + TRAP_PER_CPU_PER_CPU_BASE], DEST;
+
+#else
+
+#define TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	sethi	%hi(trap_block), DEST;		\
+	or	DEST, %lo(trap_block), DEST;	\
+
+/* Uniprocessor versions, we know the cpuid is zero.  */
+#define TRAP_LOAD_PGD_PHYS(DEST, TMP)		\
+	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	ldx	[DEST + TRAP_PER_CPU_PGD_PADDR], DEST;
+
+/* Clobbers TMP, loads local processor's IRQ work area into DEST.  */
+#define TRAP_LOAD_IRQ_WORK_PA(DEST, TMP)	\
+	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	add	DEST, TRAP_PER_CPU_IRQ_WORKLIST_PA, DEST;
+
+#define TRAP_LOAD_THREAD_REG(DEST, TMP)		\
+	TRAP_LOAD_TRAP_BLOCK(DEST, TMP)		\
+	ldx	[DEST + TRAP_PER_CPU_THREAD], DEST;
+
+/* No per-cpu areas on uniprocessor, so no need to load DEST.  */
+#define LOAD_PER_CPU_BASE(DEST, THR, REG1, REG2, REG3)
+
+#endif /* !(CONFIG_SMP) */
+
+#endif /* _SPARC_TRAP_BLOCK_H */
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index b8eb71ef316..b2c406de7d4 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -394,8 +394,9 @@
 #define __NR_accept4		323
 #define __NR_preadv		324
 #define __NR_pwritev		325
+#define __NR_rt_tgsigqueueinfo	326
 
-#define NR_SYSCALLS		326
+#define NR_SYSCALLS		327
 
 #ifdef __32bit_syscall_numbers__
 /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 54742e58831..475ce4696ac 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -37,6 +37,7 @@ obj-y                   += una_asm_$(BITS).o
 obj-$(CONFIG_SPARC32)   += muldiv.o
 obj-y                   += prom_common.o
 obj-y                   += prom_$(BITS).o
+obj-y                   += of_device_common.o
 obj-y                   += of_device_$(BITS).o
 obj-$(CONFIG_SPARC64)   += prom_irqtrans.o
 
@@ -54,6 +55,7 @@ obj-$(CONFIG_SPARC64)   += sstate.o
 obj-$(CONFIG_SPARC64)   += mdesc.o
 obj-$(CONFIG_SPARC64)	+= pcr.o
 obj-$(CONFIG_SPARC64)	+= nmi.o
+obj-$(CONFIG_SPARC64_SMP) += cpumap.o
 
 # sparc32 do not use GENERIC_HARDIRQS but uses the generic devres implementation
 obj-$(CONFIG_SPARC32)     += devres.o
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
new file mode 100644
index 00000000000..7430ed080b2
--- /dev/null
+++ b/arch/sparc/kernel/cpumap.c
@@ -0,0 +1,431 @@
+/* cpumap.c: used for optimizing CPU assignment
+ *
+ * Copyright (C) 2009 Hong H. Pham <hong.pham@windriver.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/cpumask.h>
+#include <linux/spinlock.h>
+#include <asm/cpudata.h>
+#include "cpumap.h"
+
+
+enum {
+	CPUINFO_LVL_ROOT = 0,
+	CPUINFO_LVL_NODE,
+	CPUINFO_LVL_CORE,
+	CPUINFO_LVL_PROC,
+	CPUINFO_LVL_MAX,
+};
+
+enum {
+	ROVER_NO_OP              = 0,
+	/* Increment rover every time level is visited */
+	ROVER_INC_ON_VISIT       = 1 << 0,
+	/* Increment parent's rover every time rover wraps around */
+	ROVER_INC_PARENT_ON_LOOP = 1 << 1,
+};
+
+struct cpuinfo_node {
+	int id;
+	int level;
+	int num_cpus;    /* Number of CPUs in this hierarchy */
+	int parent_index;
+	int child_start; /* Array index of the first child node */
+	int child_end;   /* Array index of the last child node */
+	int rover;       /* Child node iterator */
+};
+
+struct cpuinfo_level {
+	int start_index; /* Index of first node of a level in a cpuinfo tree */
+	int end_index;   /* Index of last node of a level in a cpuinfo tree */
+	int num_nodes;   /* Number of nodes in a level in a cpuinfo tree */
+};
+
+struct cpuinfo_tree {
+	int total_nodes;
+
+	/* Offsets into nodes[] for each level of the tree */
+	struct cpuinfo_level level[CPUINFO_LVL_MAX];
+	struct cpuinfo_node  nodes[0];
+};
+
+
+static struct cpuinfo_tree *cpuinfo_tree;
+
+static u16 cpu_distribution_map[NR_CPUS];
+static DEFINE_SPINLOCK(cpu_map_lock);
+
+
+/* Niagara optimized cpuinfo tree traversal. */
+static const int niagara_iterate_method[] = {
+	[CPUINFO_LVL_ROOT] = ROVER_NO_OP,
+
+	/* Strands (or virtual CPUs) within a core may not run concurrently
+	 * on the Niagara, as instruction pipeline(s) are shared.  Distribute
+	 * work to strands in different cores first for better concurrency.
+	 * Go to next NUMA node when all cores are used.
+	 */
+	[CPUINFO_LVL_NODE] = ROVER_INC_ON_VISIT|ROVER_INC_PARENT_ON_LOOP,
+
+	/* Strands are grouped together by proc_id in cpuinfo_sparc, i.e.
+	 * a proc_id represents an instruction pipeline.  Distribute work to
+	 * strands in different proc_id groups if the core has multiple
+	 * instruction pipelines (e.g. the Niagara 2/2+ has two).
+	 */
+	[CPUINFO_LVL_CORE] = ROVER_INC_ON_VISIT,
+
+	/* Pick the next strand in the proc_id group. */
+	[CPUINFO_LVL_PROC] = ROVER_INC_ON_VISIT,
+};
+
+/* Generic cpuinfo tree traversal.  Distribute work round robin across NUMA
+ * nodes.
+ */
+static const int generic_iterate_method[] = {
+	[CPUINFO_LVL_ROOT] = ROVER_INC_ON_VISIT,
+	[CPUINFO_LVL_NODE] = ROVER_NO_OP,
+	[CPUINFO_LVL_CORE] = ROVER_INC_PARENT_ON_LOOP,
+	[CPUINFO_LVL_PROC] = ROVER_INC_ON_VISIT|ROVER_INC_PARENT_ON_LOOP,
+};
+
+
+static int cpuinfo_id(int cpu, int level)
+{
+	int id;
+
+	switch (level) {
+	case CPUINFO_LVL_ROOT:
+		id = 0;
+		break;
+	case CPUINFO_LVL_NODE:
+		id = cpu_to_node(cpu);
+		break;
+	case CPUINFO_LVL_CORE:
+		id = cpu_data(cpu).core_id;
+		break;
+	case CPUINFO_LVL_PROC:
+		id = cpu_data(cpu).proc_id;
+		break;
+	default:
+		id = -EINVAL;
+	}
+	return id;
+}
+
+/*
+ * Enumerate the CPU information in __cpu_data to determine the start index,
+ * end index, and number of nodes for each level in the cpuinfo tree.  The
+ * total number of cpuinfo nodes required to build the tree is returned.
+ */
+static int enumerate_cpuinfo_nodes(struct cpuinfo_level *tree_level)
+{
+	int prev_id[CPUINFO_LVL_MAX];
+	int i, n, num_nodes;
+
+	for (i = CPUINFO_LVL_ROOT; i < CPUINFO_LVL_MAX; i++) {
+		struct cpuinfo_level *lv = &tree_level[i];
+
+		prev_id[i] = -1;
+		lv->start_index = lv->end_index = lv->num_nodes = 0;
+	}
+
+	num_nodes = 1; /* Include the root node */
+
+	for (i = 0; i < num_possible_cpus(); i++) {
+		if (!cpu_online(i))
+			continue;
+
+		n = cpuinfo_id(i, CPUINFO_LVL_NODE);
+		if (n > prev_id[CPUINFO_LVL_NODE]) {
+			tree_level[CPUINFO_LVL_NODE].num_nodes++;
+			prev_id[CPUINFO_LVL_NODE] = n;
+			num_nodes++;
+		}
+		n = cpuinfo_id(i, CPUINFO_LVL_CORE);
+		if (n > prev_id[CPUINFO_LVL_CORE]) {
+			tree_level[CPUINFO_LVL_CORE].num_nodes++;
+			prev_id[CPUINFO_LVL_CORE] = n;
+			num_nodes++;
+		}
+		n = cpuinfo_id(i, CPUINFO_LVL_PROC);
+		if (n > prev_id[CPUINFO_LVL_PROC]) {
+			tree_level[CPUINFO_LVL_PROC].num_nodes++;
+			prev_id[CPUINFO_LVL_PROC] = n;
+			num_nodes++;
+		}
+	}
+
+	tree_level[CPUINFO_LVL_ROOT].num_nodes = 1;
+
+	n = tree_level[CPUINFO_LVL_NODE].num_nodes;
+	tree_level[CPUINFO_LVL_NODE].start_index = 1;
+	tree_level[CPUINFO_LVL_NODE].end_index   = n;
+
+	n++;
+	tree_level[CPUINFO_LVL_CORE].start_index = n;
+	n += tree_level[CPUINFO_LVL_CORE].num_nodes;
+	tree_level[CPUINFO_LVL_CORE].end_index   = n - 1;
+
+	tree_level[CPUINFO_LVL_PROC].start_index = n;
+	n += tree_level[CPUINFO_LVL_PROC].num_nodes;
+	tree_level[CPUINFO_LVL_PROC].end_index   = n - 1;
+
+	return num_nodes;
+}
+
+/* Build a tree representation of the CPU hierarchy using the per CPU
+ * information in __cpu_data.  Entries in __cpu_data[0..NR_CPUS] are
+ * assumed to be sorted in ascending order based on node, core_id, and
+ * proc_id (in order of significance).
+ */
+static struct cpuinfo_tree *build_cpuinfo_tree(void)
+{
+	struct cpuinfo_tree *new_tree;
+	struct cpuinfo_node *node;
+	struct cpuinfo_level tmp_level[CPUINFO_LVL_MAX];
+	int num_cpus[CPUINFO_LVL_MAX];
+	int level_rover[CPUINFO_LVL_MAX];
+	int prev_id[CPUINFO_LVL_MAX];
+	int n, id, cpu, prev_cpu, last_cpu, level;
+
+	n = enumerate_cpuinfo_nodes(tmp_level);
+
+	new_tree = kzalloc(sizeof(struct cpuinfo_tree) +
+	                   (sizeof(struct cpuinfo_node) * n), GFP_ATOMIC);
+	if (!new_tree)
+		return NULL;
+
+	new_tree->total_nodes = n;
+	memcpy(&new_tree->level, tmp_level, sizeof(tmp_level));
+
+	prev_cpu = cpu = first_cpu(cpu_online_map);
+
+	/* Initialize all levels in the tree with the first CPU */
+	for (level = CPUINFO_LVL_PROC; level >= CPUINFO_LVL_ROOT; level--) {
+		n = new_tree->level[level].start_index;
+
+		level_rover[level] = n;
+		node = &new_tree->nodes[n];
+
+		id = cpuinfo_id(cpu, level);
+		if (unlikely(id < 0)) {
+			kfree(new_tree);
+			return NULL;
+		}
+		node->id = id;
+		node->level = level;
+		node->num_cpus = 1;
+
+		node->parent_index = (level > CPUINFO_LVL_ROOT)
+		    ? new_tree->level[level - 1].start_index : -1;
+
+		node->child_start = node->child_end = node->rover =
+		    (level == CPUINFO_LVL_PROC)
+		    ? cpu : new_tree->level[level + 1].start_index;
+
+		prev_id[level] = node->id;
+		num_cpus[level] = 1;
+	}
+
+	for (last_cpu = (num_possible_cpus() - 1); last_cpu >= 0; last_cpu--) {
+		if (cpu_online(last_cpu))
+			break;
+	}
+
+	while (++cpu <= last_cpu) {
+		if (!cpu_online(cpu))
+			continue;
+
+		for (level = CPUINFO_LVL_PROC; level >= CPUINFO_LVL_ROOT;
+		     level--) {
+			id = cpuinfo_id(cpu, level);
+			if (unlikely(id < 0)) {
+				kfree(new_tree);
+				return NULL;
+			}
+
+			if ((id != prev_id[level]) || (cpu == last_cpu)) {
+				prev_id[level] = id;
+				node = &new_tree->nodes[level_rover[level]];
+				node->num_cpus = num_cpus[level];
+				num_cpus[level] = 1;
+
+				if (cpu == last_cpu)
+					node->num_cpus++;
+
+				/* Connect tree node to parent */
+				if (level == CPUINFO_LVL_ROOT)
+					node->parent_index = -1;
+				else
+					node->parent_index =
+					    level_rover[level - 1];
+
+				if (level == CPUINFO_LVL_PROC) {
+					node->child_end =
+					    (cpu == last_cpu) ? cpu : prev_cpu;
+				} else {
+					node->child_end =
+					    level_rover[level + 1] - 1;
+				}
+
+				/* Initialize the next node in the same level */
+				n = ++level_rover[level];
+				if (n <= new_tree->level[level].end_index) {
+					node = &new_tree->nodes[n];
+					node->id = id;
+					node->level = level;
+
+					/* Connect node to child */
+					node->child_start = node->child_end =
+					node->rover =
+					    (level == CPUINFO_LVL_PROC)
+					    ? cpu : level_rover[level + 1];
+				}
+			} else
+				num_cpus[level]++;
+		}
+		prev_cpu = cpu;
+	}
+
+	return new_tree;
+}
+
+static void increment_rover(struct cpuinfo_tree *t, int node_index,
+                            int root_index, const int *rover_inc_table)
+{
+	struct cpuinfo_node *node = &t->nodes[node_index];
+	int top_level, level;
+
+	top_level = t->nodes[root_index].level;
+	for (level = node->level; level >= top_level; level--) {
+		node->rover++;
+		if (node->rover <= node->child_end)
+			return;
+
+		node->rover = node->child_start;
+		/* If parent's rover does not need to be adjusted, stop here. */
+		if ((level == top_level) ||
+		    !(rover_inc_table[level] & ROVER_INC_PARENT_ON_LOOP))
+			return;
+
+		node = &t->nodes[node->parent_index];
+	}
+}
+
+static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
+{
+	const int *rover_inc_table;
+	int level, new_index, index = root_index;
+
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_NIAGARA1:
+	case SUN4V_CHIP_NIAGARA2:
+		rover_inc_table = niagara_iterate_method;
+		break;
+	default:
+		rover_inc_table = generic_iterate_method;
+	}
+
+	for (level = t->nodes[root_index].level; level < CPUINFO_LVL_MAX;
+	     level++) {
+		new_index = t->nodes[index].rover;
+		if (rover_inc_table[level] & ROVER_INC_ON_VISIT)
+			increment_rover(t, index, root_index, rover_inc_table);
+
+		index = new_index;
+	}
+	return index;
+}
+
+static void _cpu_map_rebuild(void)
+{
+	int i;
+
+	if (cpuinfo_tree) {
+		kfree(cpuinfo_tree);
+		cpuinfo_tree = NULL;
+	}
+
+	cpuinfo_tree = build_cpuinfo_tree();
+	if (!cpuinfo_tree)
+		return;
+
+	/* Build CPU distribution map that spans all online CPUs.  No need
+	 * to check if the CPU is online, as that is done when the cpuinfo
+	 * tree is being built.
+	 */
+	for (i = 0; i < cpuinfo_tree->nodes[0].num_cpus; i++)
+		cpu_distribution_map[i] = iterate_cpu(cpuinfo_tree, 0);
+}
+
+/* Fallback if the cpuinfo tree could not be built.  CPU mapping is linear
+ * round robin.
+ */
+static int simple_map_to_cpu(unsigned int index)
+{
+	int i, end, cpu_rover;
+
+	cpu_rover = 0;
+	end = index % num_online_cpus();
+	for (i = 0; i < num_possible_cpus(); i++) {
+		if (cpu_online(cpu_rover)) {
+			if (cpu_rover >= end)
+				return cpu_rover;
+
+			cpu_rover++;
+		}
+	}
+
+	/* Impossible, since num_online_cpus() <= num_possible_cpus() */
+	return first_cpu(cpu_online_map);
+}
+
+static int _map_to_cpu(unsigned int index)
+{
+	struct cpuinfo_node *root_node;
+
+	if (unlikely(!cpuinfo_tree)) {
+		_cpu_map_rebuild();
+		if (!cpuinfo_tree)
+			return simple_map_to_cpu(index);
+	}
+
+	root_node = &cpuinfo_tree->nodes[0];
+#ifdef CONFIG_HOTPLUG_CPU
+	if (unlikely(root_node->num_cpus != num_online_cpus())) {
+		_cpu_map_rebuild();
+		if (!cpuinfo_tree)
+			return simple_map_to_cpu(index);
+	}
+#endif
+	return cpu_distribution_map[index % root_node->num_cpus];
+}
+
+int map_to_cpu(unsigned int index)
+{
+	int mapped_cpu;
+	unsigned long flag;
+
+	spin_lock_irqsave(&cpu_map_lock, flag);
+	mapped_cpu = _map_to_cpu(index);
+
+#ifdef CONFIG_HOTPLUG_CPU
+	while (unlikely(!cpu_online(mapped_cpu)))
+		mapped_cpu = _map_to_cpu(index);
+#endif
+	spin_unlock_irqrestore(&cpu_map_lock, flag);
+	return mapped_cpu;
+}
+EXPORT_SYMBOL(map_to_cpu);
+
+void cpu_map_rebuild(void)
+{
+	unsigned long flag;
+
+	spin_lock_irqsave(&cpu_map_lock, flag);
+	_cpu_map_rebuild();
+	spin_unlock_irqrestore(&cpu_map_lock, flag);
+}
diff --git a/arch/sparc/kernel/cpumap.h b/arch/sparc/kernel/cpumap.h
new file mode 100644
index 00000000000..e639880ab86
--- /dev/null
+++ b/arch/sparc/kernel/cpumap.h
@@ -0,0 +1,16 @@
+#ifndef _CPUMAP_H
+#define _CPUMAP_H
+
+#ifdef CONFIG_SMP
+extern void cpu_map_rebuild(void);
+extern int  map_to_cpu(unsigned int index);
+#define cpu_map_init() cpu_map_rebuild()
+#else
+#define cpu_map_init() do {} while (0)
+static inline int map_to_cpu(unsigned int index)
+{
+	return raw_smp_processor_id();
+}
+#endif
+
+#endif
diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c
index ebc8403b035..524c32f97c5 100644
--- a/arch/sparc/kernel/dma.c
+++ b/arch/sparc/kernel/dma.c
@@ -35,8 +35,8 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t flag)
+static void *dma32_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flag)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type)
@@ -44,10 +44,9 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 #endif
 	return sbus_alloc_consistent(dev, size, dma_handle);
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size,
-		       void *cpu_addr, dma_addr_t dma_handle)
+static void dma32_free_coherent(struct device *dev, size_t size,
+				void *cpu_addr, dma_addr_t dma_handle)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -58,38 +57,10 @@ void dma_free_coherent(struct device *dev, size_t size,
 #endif
 	sbus_free_consistent(dev, size, cpu_addr, dma_handle);
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
-dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-			  size_t size, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
-		return pci_map_single(to_pci_dev(dev), cpu_addr,
-				      size, (int)direction);
-#endif
-	return sbus_map_single(dev, cpu_addr, size, (int)direction);
-}
-EXPORT_SYMBOL(dma_map_single);
-
-void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-		      size_t size,
-		      enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		pci_unmap_single(to_pci_dev(dev), dma_addr,
-				 size, (int)direction);
-		return;
-	}
-#endif
-	sbus_unmap_single(dev, dma_addr, size, (int)direction);
-}
-EXPORT_SYMBOL(dma_unmap_single);
-
-dma_addr_t dma_map_page(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction direction)
+static dma_addr_t dma32_map_page(struct device *dev, struct page *page,
+				 unsigned long offset, size_t size,
+				 enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type)
@@ -99,10 +70,9 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page,
 	return sbus_map_single(dev, page_address(page) + offset,
 			       size, (int)direction);
 }
-EXPORT_SYMBOL(dma_map_page);
 
-void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-		    size_t size, enum dma_data_direction direction)
+static void dma32_unmap_page(struct device *dev, dma_addr_t dma_address,
+			     size_t size, enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -113,10 +83,9 @@ void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 #endif
 	sbus_unmap_single(dev, dma_address, size, (int)direction);
 }
-EXPORT_SYMBOL(dma_unmap_page);
 
-int dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction direction)
+static int dma32_map_sg(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type)
@@ -124,10 +93,9 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg,
 #endif
 	return sbus_map_sg(dev, sg, nents, direction);
 }
-EXPORT_SYMBOL(dma_map_sg);
 
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		  int nents, enum dma_data_direction direction)
+void dma32_unmap_sg(struct device *dev, struct scatterlist *sg,
+		    int nents, enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -137,10 +105,10 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 #endif
 	sbus_unmap_sg(dev, sg, nents, (int)direction);
 }
-EXPORT_SYMBOL(dma_unmap_sg);
 
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			     size_t size, enum dma_data_direction direction)
+static void dma32_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+				      size_t size,
+				      enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -151,10 +119,10 @@ void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 #endif
 	sbus_dma_sync_single_for_cpu(dev, dma_handle, size, (int) direction);
 }
-EXPORT_SYMBOL(dma_sync_single_for_cpu);
 
-void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-				size_t size, enum dma_data_direction direction)
+static void dma32_sync_single_for_device(struct device *dev,
+					 dma_addr_t dma_handle, size_t size,
+					 enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -165,28 +133,9 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
 #endif
 	sbus_dma_sync_single_for_device(dev, dma_handle, size, (int) direction);
 }
-EXPORT_SYMBOL(dma_sync_single_for_device);
-
-void dma_sync_single_range_for_cpu(struct device *dev,
-				   dma_addr_t dma_handle,
-				   unsigned long offset,
-				   size_t size,
-				   enum dma_data_direction direction)
-{
-	dma_sync_single_for_cpu(dev, dma_handle+offset, size, direction);
-}
-EXPORT_SYMBOL(dma_sync_single_range_for_cpu);
-
-void dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction direction)
-{
-	dma_sync_single_for_device(dev, dma_handle+offset, size, direction);
-}
-EXPORT_SYMBOL(dma_sync_single_range_for_device);
 
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-			 int nelems, enum dma_data_direction direction)
+static void dma32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+				  int nelems, enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -197,11 +146,10 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 #endif
 	BUG();
 }
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
-void dma_sync_sg_for_device(struct device *dev,
-			    struct scatterlist *sg, int nelems,
-			    enum dma_data_direction direction)
+static void dma32_sync_sg_for_device(struct device *dev,
+				     struct scatterlist *sg, int nelems,
+				     enum dma_data_direction direction)
 {
 #ifdef CONFIG_PCI
 	if (dev->bus == &pci_bus_type) {
@@ -212,16 +160,19 @@ void dma_sync_sg_for_device(struct device *dev,
 #endif
 	BUG();
 }
-EXPORT_SYMBOL(dma_sync_sg_for_device);
 
-int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return (dma_addr == DMA_ERROR_CODE);
-}
-EXPORT_SYMBOL(dma_mapping_error);
-
-int dma_get_cache_alignment(void)
-{
-	return 32;
-}
-EXPORT_SYMBOL(dma_get_cache_alignment);
+static const struct dma_ops dma32_dma_ops = {
+	.alloc_coherent		= dma32_alloc_coherent,
+	.free_coherent		= dma32_free_coherent,
+	.map_page		= dma32_map_page,
+	.unmap_page		= dma32_unmap_page,
+	.map_sg			= dma32_map_sg,
+	.unmap_sg		= dma32_unmap_sg,
+	.sync_single_for_cpu	= dma32_sync_single_for_cpu,
+	.sync_single_for_device	= dma32_sync_single_for_device,
+	.sync_sg_for_cpu	= dma32_sync_sg_for_cpu,
+	.sync_sg_for_device	= dma32_sync_sg_for_device,
+};
+
+const struct dma_ops *dma_ops = &dma32_dma_ops;
+EXPORT_SYMBOL(dma_ops);
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 90350f838f0..4a700f4b79c 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -544,7 +544,8 @@ static int __cpuinit dr_cpu_configure(struct ds_info *dp,
 			     resp_len, ncpus, mask,
 			     DR_CPU_STAT_CONFIGURED);
 
-	mdesc_fill_in_cpu_data(*mask);
+	mdesc_populate_present_mask(mask);
+	mdesc_fill_in_cpu_data(mask);
 
 	for_each_cpu_mask(cpu, *mask) {
 		int err;
diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index d0218e73f98..d3b1a307656 100644
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@@ -7,14 +7,10 @@
 
 #include <asm/ftrace.h>
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 static const u32 ftrace_nop = 0x01000000;
 
-unsigned char *ftrace_nop_replace(void)
-{
-	return (char *)&ftrace_nop;
-}
-
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static u32 ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static u32 call;
 	s32 off;
@@ -22,15 +18,11 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	off = ((s32)addr - (s32)ip);
 	call = 0x40000000 | ((u32)off >> 2);
 
-	return (unsigned char *) &call;
+	return call;
 }
 
-int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-		   unsigned char *new_code)
+static int ftrace_modify_code(unsigned long ip, u32 old, u32 new)
 {
-	u32 old = *(u32 *)old_code;
-	u32 new = *(u32 *)new_code;
 	u32 replaced;
 	int faulted;
 
@@ -59,18 +51,43 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	return faulted;
 }
 
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	u32 old, new;
+
+	old = ftrace_call_replace(ip, addr);
+	new = ftrace_nop;
+	return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	u32 old, new;
+
+	old = ftrace_nop;
+	new = ftrace_call_replace(ip, addr);
+	return ftrace_modify_code(ip, old, new);
+}
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	u32 old, new;
 
-	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
+	old = *(u32 *) &ftrace_call;
 	new = ftrace_call_replace(ip, (unsigned long)func);
 	return ftrace_modify_code(ip, old, new);
 }
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	ftrace_mcount_set(data);
+	unsigned long *p = data;
+
+	*p = 0;
+
 	return 0;
 }
+#endif
+
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 91bf4c7f79b..f8f21050448 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -641,28 +641,6 @@ tlb_fixup_done:
 	/* Not reached... */
 
 1:
-	/* If we boot on a non-zero cpu, all of the per-cpu
-	 * variable references we make before setting up the
-	 * per-cpu areas will use a bogus offset.  Put a
-	 * compensating factor into __per_cpu_base to handle
-	 * this cleanly.
-	 *
-	 * What the per-cpu code calculates is:
-	 *
-	 *	__per_cpu_base + (cpu << __per_cpu_shift)
-	 *
-	 * These two variables are zero initially, so to
-	 * make it all cancel out to zero we need to put
-	 * "0 - (cpu << 0)" into __per_cpu_base so that the
-	 * above formula evaluates to zero.
-	 *
-	 * We cannot even perform a printk() until this stuff
-	 * is setup as that calls cpu_clock() which uses
-	 * per-cpu variables.
-	 */
-	sub	%g0, %o0, %o1
-	sethi	%hi(__per_cpu_base), %o2
-	stx	%o1, [%o2 + %lo(__per_cpu_base)]
 #else
 	mov	0, %o0
 #endif
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index d8900e1d5aa..0aeaefe696b 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -351,8 +351,9 @@ static void dma_4u_free_coherent(struct device *dev, size_t size,
 		free_pages((unsigned long)cpu, order);
 }
 
-static dma_addr_t dma_4u_map_single(struct device *dev, void *ptr, size_t sz,
-				    enum dma_data_direction direction)
+static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t sz,
+				  enum dma_data_direction direction)
 {
 	struct iommu *iommu;
 	struct strbuf *strbuf;
@@ -368,7 +369,7 @@ static dma_addr_t dma_4u_map_single(struct device *dev, void *ptr, size_t sz,
 	if (unlikely(direction == DMA_NONE))
 		goto bad_no_ctx;
 
-	oaddr = (unsigned long)ptr;
+	oaddr = (unsigned long)(page_address(page) + offset);
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
@@ -472,8 +473,8 @@ do_flush_sync:
 		       vaddr, ctx, npages);
 }
 
-static void dma_4u_unmap_single(struct device *dev, dma_addr_t bus_addr,
-				size_t sz, enum dma_data_direction direction)
+static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
+			      size_t sz, enum dma_data_direction direction)
 {
 	struct iommu *iommu;
 	struct strbuf *strbuf;
@@ -824,8 +825,8 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 static const struct dma_ops sun4u_dma_ops = {
 	.alloc_coherent		= dma_4u_alloc_coherent,
 	.free_coherent		= dma_4u_free_coherent,
-	.map_single		= dma_4u_map_single,
-	.unmap_single		= dma_4u_unmap_single,
+	.map_page		= dma_4u_map_page,
+	.unmap_page		= dma_4u_unmap_page,
 	.map_sg			= dma_4u_map_sg,
 	.unmap_sg		= dma_4u_unmap_sg,
 	.sync_single_for_cpu	= dma_4u_sync_single_for_cpu,
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index e5e78f9cfc9..bd075054942 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -45,6 +45,7 @@
 #include <asm/cacheflush.h>
 
 #include "entry.h"
+#include "cpumap.h"
 
 #define NUM_IVECS	(IMAP_INR + 1)
 
@@ -256,35 +257,13 @@ static int irq_choose_cpu(unsigned int virt_irq)
 	int cpuid;
 
 	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
-	if (cpus_equal(mask, CPU_MASK_ALL)) {
-		static int irq_rover;
-		static DEFINE_SPINLOCK(irq_rover_lock);
-		unsigned long flags;
-
-		/* Round-robin distribution... */
-	do_round_robin:
-		spin_lock_irqsave(&irq_rover_lock, flags);
-
-		while (!cpu_online(irq_rover)) {
-			if (++irq_rover >= nr_cpu_ids)
-				irq_rover = 0;
-		}
-		cpuid = irq_rover;
-		do {
-			if (++irq_rover >= nr_cpu_ids)
-				irq_rover = 0;
-		} while (!cpu_online(irq_rover));
-
-		spin_unlock_irqrestore(&irq_rover_lock, flags);
+	if (cpus_equal(mask, cpu_online_map)) {
+		cpuid = map_to_cpu(virt_irq);
 	} else {
 		cpumask_t tmp;
 
 		cpus_and(tmp, cpu_online_map, mask);
-
-		if (cpus_empty(tmp))
-			goto do_round_robin;
-
-		cpuid = first_cpu(tmp);
+		cpuid = cpus_empty(tmp) ? map_to_cpu(virt_irq) : first_cpu(tmp);
 	}
 
 	return cpuid;
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index f0e6ed23a46..938da19dc06 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -574,7 +574,7 @@ static void __init report_platform_properties(void)
 	mdesc_release(hp);
 }
 
-static void __devinit fill_in_one_cache(cpuinfo_sparc *c,
+static void __cpuinit fill_in_one_cache(cpuinfo_sparc *c,
 					struct mdesc_handle *hp,
 					u64 mp)
 {
@@ -619,8 +619,7 @@ static void __devinit fill_in_one_cache(cpuinfo_sparc *c,
 	}
 }
 
-static void __devinit mark_core_ids(struct mdesc_handle *hp, u64 mp,
-				    int core_id)
+static void __cpuinit mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
 {
 	u64 a;
 
@@ -653,7 +652,7 @@ static void __devinit mark_core_ids(struct mdesc_handle *hp, u64 mp,
 	}
 }
 
-static void __devinit set_core_ids(struct mdesc_handle *hp)
+static void __cpuinit set_core_ids(struct mdesc_handle *hp)
 {
 	int idx;
 	u64 mp;
@@ -678,8 +677,7 @@ static void __devinit set_core_ids(struct mdesc_handle *hp)
 	}
 }
 
-static void __devinit mark_proc_ids(struct mdesc_handle *hp, u64 mp,
-				    int proc_id)
+static void __cpuinit mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
 {
 	u64 a;
 
@@ -698,8 +696,7 @@ static void __devinit mark_proc_ids(struct mdesc_handle *hp, u64 mp,
 	}
 }
 
-static void __devinit __set_proc_ids(struct mdesc_handle *hp,
-				     const char *exec_unit_name)
+static void __cpuinit __set_proc_ids(struct mdesc_handle *hp, const char *exec_unit_name)
 {
 	int idx;
 	u64 mp;
@@ -720,13 +717,13 @@ static void __devinit __set_proc_ids(struct mdesc_handle *hp,
 	}
 }
 
-static void __devinit set_proc_ids(struct mdesc_handle *hp)
+static void __cpuinit set_proc_ids(struct mdesc_handle *hp)
 {
 	__set_proc_ids(hp, "exec_unit");
 	__set_proc_ids(hp, "exec-unit");
 }
 
-static void __devinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
+static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
 					 unsigned char def)
 {
 	u64 val;
@@ -745,7 +742,7 @@ use_default:
 	*mask = ((1U << def) * 64U) - 1U;
 }
 
-static void __devinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
+static void __cpuinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
 				     struct trap_per_cpu *tb)
 {
 	const u64 *val;
@@ -763,23 +760,15 @@ static void __devinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
 	get_one_mondo_bits(val, &tb->nonresum_qmask, 2);
 }
 
-void __cpuinit mdesc_fill_in_cpu_data(cpumask_t mask)
+static void * __cpuinit mdesc_iterate_over_cpus(void *(*func)(struct mdesc_handle *, u64, int, void *), void *arg, cpumask_t *mask)
 {
 	struct mdesc_handle *hp = mdesc_grab();
+	void *ret = NULL;
 	u64 mp;
 
-	ncpus_probed = 0;
 	mdesc_for_each_node_by_name(hp, mp, "cpu") {
 		const u64 *id = mdesc_get_property(hp, mp, "id", NULL);
-		const u64 *cfreq = mdesc_get_property(hp, mp, "clock-frequency", NULL);
-		struct trap_per_cpu *tb;
-		cpuinfo_sparc *c;
-		int cpuid;
-		u64 a;
-
-		ncpus_probed++;
-
-		cpuid = *id;
+		int cpuid = *id;
 
 #ifdef CONFIG_SMP
 		if (cpuid >= NR_CPUS) {
@@ -788,62 +777,104 @@ void __cpuinit mdesc_fill_in_cpu_data(cpumask_t mask)
 			       cpuid, NR_CPUS);
 			continue;
 		}
-		if (!cpu_isset(cpuid, mask))
+		if (!cpu_isset(cpuid, *mask))
 			continue;
-#else
-		/* On uniprocessor we only want the values for the
-		 * real physical cpu the kernel booted onto, however
-		 * cpu_data() only has one entry at index 0.
-		 */
-		if (cpuid != real_hard_smp_processor_id())
-			continue;
-		cpuid = 0;
 #endif
 
-		c = &cpu_data(cpuid);
-		c->clock_tick = *cfreq;
+		ret = func(hp, mp, cpuid, arg);
+		if (ret)
+			goto out;
+	}
+out:
+	mdesc_release(hp);
+	return ret;
+}
 
-		tb = &trap_block[cpuid];
-		get_mondo_data(hp, mp, tb);
+static void * __cpuinit record_one_cpu(struct mdesc_handle *hp, u64 mp, int cpuid, void *arg)
+{
+	ncpus_probed++;
+#ifdef CONFIG_SMP
+	set_cpu_present(cpuid, true);
+#endif
+	return NULL;
+}
 
-		mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
-			u64 j, t = mdesc_arc_target(hp, a);
-			const char *t_name;
+void __cpuinit mdesc_populate_present_mask(cpumask_t *mask)
+{
+	if (tlb_type != hypervisor)
+		return;
 
-			t_name = mdesc_node_name(hp, t);
-			if (!strcmp(t_name, "cache")) {
-				fill_in_one_cache(c, hp, t);
-				continue;
-			}
+	ncpus_probed = 0;
+	mdesc_iterate_over_cpus(record_one_cpu, NULL, mask);
+}
 
-			mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_FWD) {
-				u64 n = mdesc_arc_target(hp, j);
-				const char *n_name;
+static void * __cpuinit fill_in_one_cpu(struct mdesc_handle *hp, u64 mp, int cpuid, void *arg)
+{
+	const u64 *cfreq = mdesc_get_property(hp, mp, "clock-frequency", NULL);
+	struct trap_per_cpu *tb;
+	cpuinfo_sparc *c;
+	u64 a;
 
-				n_name = mdesc_node_name(hp, n);
-				if (!strcmp(n_name, "cache"))
-					fill_in_one_cache(c, hp, n);
-			}
+#ifndef CONFIG_SMP
+	/* On uniprocessor we only want the values for the
+	 * real physical cpu the kernel booted onto, however
+	 * cpu_data() only has one entry at index 0.
+	 */
+	if (cpuid != real_hard_smp_processor_id())
+		return NULL;
+	cpuid = 0;
+#endif
+
+	c = &cpu_data(cpuid);
+	c->clock_tick = *cfreq;
+
+	tb = &trap_block[cpuid];
+	get_mondo_data(hp, mp, tb);
+
+	mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+		u64 j, t = mdesc_arc_target(hp, a);
+		const char *t_name;
+
+		t_name = mdesc_node_name(hp, t);
+		if (!strcmp(t_name, "cache")) {
+			fill_in_one_cache(c, hp, t);
+			continue;
 		}
 
-#ifdef CONFIG_SMP
-		cpu_set(cpuid, cpu_present_map);
-#endif
+		mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_FWD) {
+			u64 n = mdesc_arc_target(hp, j);
+			const char *n_name;
 
-		c->core_id = 0;
-		c->proc_id = -1;
+			n_name = mdesc_node_name(hp, n);
+			if (!strcmp(n_name, "cache"))
+				fill_in_one_cache(c, hp, n);
+		}
 	}
 
+	c->core_id = 0;
+	c->proc_id = -1;
+
+	return NULL;
+}
+
+void __cpuinit mdesc_fill_in_cpu_data(cpumask_t *mask)
+{
+	struct mdesc_handle *hp;
+
+	mdesc_iterate_over_cpus(fill_in_one_cpu, NULL, mask);
+
 #ifdef CONFIG_SMP
 	sparc64_multi_core = 1;
 #endif
 
+	hp = mdesc_grab();
+
 	set_core_ids(hp);
 	set_proc_ids(hp);
 
-	smp_fill_in_sib_core_maps();
-
 	mdesc_release(hp);
+
+	smp_fill_in_sib_core_maps();
 }
 
 static ssize_t mdesc_read(struct file *file, char __user *buf,
@@ -887,7 +918,6 @@ void __init sun4v_mdesc_init(void)
 {
 	struct mdesc_handle *hp;
 	unsigned long len, real_len, status;
-	cpumask_t mask;
 
 	(void) sun4v_mach_desc(0UL, 0UL, &len);
 
@@ -911,7 +941,4 @@ void __init sun4v_mdesc_init(void)
 	cur_mdesc = hp;
 
 	report_platform_properties();
-
-	cpus_setall(mask);
-	mdesc_fill_in_cpu_data(mask);
 }
diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c
index c8f14c1dc52..90396702ea2 100644
--- a/arch/sparc/kernel/of_device_32.c
+++ b/arch/sparc/kernel/of_device_32.c
@@ -6,159 +6,11 @@
 #include <linux/mod_devicetable.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
+#include <linux/irq.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
 
-static int node_match(struct device *dev, void *data)
-{
-	struct of_device *op = to_of_device(dev);
-	struct device_node *dp = data;
-
-	return (op->node == dp);
-}
-
-struct of_device *of_find_device_by_node(struct device_node *dp)
-{
-	struct device *dev = bus_find_device(&of_platform_bus_type, NULL,
-					     dp, node_match);
-
-	if (dev)
-		return to_of_device(dev);
-
-	return NULL;
-}
-EXPORT_SYMBOL(of_find_device_by_node);
-
-unsigned int irq_of_parse_and_map(struct device_node *node, int index)
-{
-	struct of_device *op = of_find_device_by_node(node);
-
-	if (!op || index >= op->num_irqs)
-		return 0;
-
-	return op->irqs[index];
-}
-EXPORT_SYMBOL(irq_of_parse_and_map);
-
-/* Take the archdata values for IOMMU, STC, and HOSTDATA found in
- * BUS and propagate to all child of_device objects.
- */
-void of_propagate_archdata(struct of_device *bus)
-{
-	struct dev_archdata *bus_sd = &bus->dev.archdata;
-	struct device_node *bus_dp = bus->node;
-	struct device_node *dp;
-
-	for (dp = bus_dp->child; dp; dp = dp->sibling) {
-		struct of_device *op = of_find_device_by_node(dp);
-
-		op->dev.archdata.iommu = bus_sd->iommu;
-		op->dev.archdata.stc = bus_sd->stc;
-		op->dev.archdata.host_controller = bus_sd->host_controller;
-		op->dev.archdata.numa_node = bus_sd->numa_node;
-
-		if (dp->child)
-			of_propagate_archdata(op);
-	}
-}
-
-struct bus_type of_platform_bus_type;
-EXPORT_SYMBOL(of_platform_bus_type);
-
-static inline u64 of_read_addr(const u32 *cell, int size)
-{
-	u64 r = 0;
-	while (size--)
-		r = (r << 32) | *(cell++);
-	return r;
-}
-
-static void __init get_cells(struct device_node *dp,
-			     int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = of_n_addr_cells(dp);
-	if (sizec)
-		*sizec = of_n_size_cells(dp);
-}
-
-/* Max address size we deal with */
-#define OF_MAX_ADDR_CELLS	4
-
-struct of_bus {
-	const char	*name;
-	const char	*addr_prop_name;
-	int		(*match)(struct device_node *parent);
-	void		(*count_cells)(struct device_node *child,
-				       int *addrc, int *sizec);
-	int		(*map)(u32 *addr, const u32 *range,
-			       int na, int ns, int pna);
-	unsigned long	(*get_flags)(const u32 *addr, unsigned long);
-};
-
-/*
- * Default translator (generic bus)
- */
-
-static void of_bus_default_count_cells(struct device_node *dev,
-				       int *addrc, int *sizec)
-{
-	get_cells(dev, addrc, sizec);
-}
-
-/* Make sure the least significant 64-bits are in-range.  Even
- * for 3 or 4 cell values it is a good enough approximation.
- */
-static int of_out_of_range(const u32 *addr, const u32 *base,
-			   const u32 *size, int na, int ns)
-{
-	u64 a = of_read_addr(addr, na);
-	u64 b = of_read_addr(base, na);
-
-	if (a < b)
-		return 1;
-
-	b += of_read_addr(size, ns);
-	if (a >= b)
-		return 1;
-
-	return 0;
-}
-
-static int of_bus_default_map(u32 *addr, const u32 *range,
-			      int na, int ns, int pna)
-{
-	u32 result[OF_MAX_ADDR_CELLS];
-	int i;
-
-	if (ns > 2) {
-		printk("of_device: Cannot handle size cells (%d) > 2.", ns);
-		return -EINVAL;
-	}
-
-	if (of_out_of_range(addr, range, range + na + pna, na, ns))
-		return -EINVAL;
-
-	/* Start with the parent range base.  */
-	memcpy(result, range + na, pna * 4);
-
-	/* Add in the child address offset.  */
-	for (i = 0; i < na; i++)
-		result[pna - 1 - i] +=
-			(addr[na - 1 - i] -
-			 range[na - 1 - i]);
-
-	memcpy(addr, result, pna * 4);
-
-	return 0;
-}
-
-static unsigned long of_bus_default_get_flags(const u32 *addr, unsigned long flags)
-{
-	if (flags)
-		return flags;
-	return IORESOURCE_MEM;
-}
+#include "of_device_common.h"
 
 /*
  * PCI bus specific translator
@@ -240,47 +92,6 @@ static unsigned long of_bus_pci_get_flags(const u32 *addr, unsigned long flags)
 	return flags;
 }
 
-/*
- * SBUS bus specific translator
- */
-
-static int of_bus_sbus_match(struct device_node *np)
-{
-	struct device_node *dp = np;
-
-	while (dp) {
-		if (!strcmp(dp->name, "sbus") ||
-		    !strcmp(dp->name, "sbi"))
-			return 1;
-
-		/* Have a look at use_1to1_mapping().  We're trying
-		 * to match SBUS if that's the top-level bus and we
-		 * don't have some intervening real bus that provides
-		 * ranges based translations.
-		 */
-		if (of_find_property(dp, "ranges", NULL) != NULL)
-			break;
-
-		dp = dp->parent;
-	}
-
-	return 0;
-}
-
-static void of_bus_sbus_count_cells(struct device_node *child,
-				   int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = 2;
-	if (sizec)
-		*sizec = 1;
-}
-
-static int of_bus_sbus_map(u32 *addr, const u32 *range, int na, int ns, int pna)
-{
-	return of_bus_default_map(addr, range, na, ns, pna);
-}
-
 static unsigned long of_bus_sbus_get_flags(const u32 *addr, unsigned long flags)
 {
 	return IORESOURCE_MEM;
@@ -307,7 +118,7 @@ static struct of_bus of_busses[] = {
 		.addr_prop_name = "reg",
 		.match = of_bus_sbus_match,
 		.count_cells = of_bus_sbus_count_cells,
-		.map = of_bus_sbus_map,
+		.map = of_bus_default_map,
 		.get_flags = of_bus_sbus_get_flags,
 	},
 	/* Default */
diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c
index 5ac287ac03d..881947e59e9 100644
--- a/arch/sparc/kernel/of_device_64.c
+++ b/arch/sparc/kernel/of_device_64.c
@@ -10,6 +10,8 @@
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
 
+#include "of_device_common.h"
+
 void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name)
 {
 	unsigned long ret = res->start + offset;
@@ -35,156 +37,6 @@ void of_iounmap(struct resource *res, void __iomem *base, unsigned long size)
 }
 EXPORT_SYMBOL(of_iounmap);
 
-static int node_match(struct device *dev, void *data)
-{
-	struct of_device *op = to_of_device(dev);
-	struct device_node *dp = data;
-
-	return (op->node == dp);
-}
-
-struct of_device *of_find_device_by_node(struct device_node *dp)
-{
-	struct device *dev = bus_find_device(&of_platform_bus_type, NULL,
-					     dp, node_match);
-
-	if (dev)
-		return to_of_device(dev);
-
-	return NULL;
-}
-EXPORT_SYMBOL(of_find_device_by_node);
-
-unsigned int irq_of_parse_and_map(struct device_node *node, int index)
-{
-	struct of_device *op = of_find_device_by_node(node);
-
-	if (!op || index >= op->num_irqs)
-		return 0;
-
-	return op->irqs[index];
-}
-EXPORT_SYMBOL(irq_of_parse_and_map);
-
-/* Take the archdata values for IOMMU, STC, and HOSTDATA found in
- * BUS and propagate to all child of_device objects.
- */
-void of_propagate_archdata(struct of_device *bus)
-{
-	struct dev_archdata *bus_sd = &bus->dev.archdata;
-	struct device_node *bus_dp = bus->node;
-	struct device_node *dp;
-
-	for (dp = bus_dp->child; dp; dp = dp->sibling) {
-		struct of_device *op = of_find_device_by_node(dp);
-
-		op->dev.archdata.iommu = bus_sd->iommu;
-		op->dev.archdata.stc = bus_sd->stc;
-		op->dev.archdata.host_controller = bus_sd->host_controller;
-		op->dev.archdata.numa_node = bus_sd->numa_node;
-
-		if (dp->child)
-			of_propagate_archdata(op);
-	}
-}
-
-struct bus_type of_platform_bus_type;
-EXPORT_SYMBOL(of_platform_bus_type);
-
-static inline u64 of_read_addr(const u32 *cell, int size)
-{
-	u64 r = 0;
-	while (size--)
-		r = (r << 32) | *(cell++);
-	return r;
-}
-
-static void get_cells(struct device_node *dp, int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = of_n_addr_cells(dp);
-	if (sizec)
-		*sizec = of_n_size_cells(dp);
-}
-
-/* Max address size we deal with */
-#define OF_MAX_ADDR_CELLS	4
-
-struct of_bus {
-	const char	*name;
-	const char	*addr_prop_name;
-	int		(*match)(struct device_node *parent);
-	void		(*count_cells)(struct device_node *child,
-				       int *addrc, int *sizec);
-	int		(*map)(u32 *addr, const u32 *range,
-			       int na, int ns, int pna);
-	unsigned long	(*get_flags)(const u32 *addr, unsigned long);
-};
-
-/*
- * Default translator (generic bus)
- */
-
-static void of_bus_default_count_cells(struct device_node *dev,
-				       int *addrc, int *sizec)
-{
-	get_cells(dev, addrc, sizec);
-}
-
-/* Make sure the least significant 64-bits are in-range.  Even
- * for 3 or 4 cell values it is a good enough approximation.
- */
-static int of_out_of_range(const u32 *addr, const u32 *base,
-			   const u32 *size, int na, int ns)
-{
-	u64 a = of_read_addr(addr, na);
-	u64 b = of_read_addr(base, na);
-
-	if (a < b)
-		return 1;
-
-	b += of_read_addr(size, ns);
-	if (a >= b)
-		return 1;
-
-	return 0;
-}
-
-static int of_bus_default_map(u32 *addr, const u32 *range,
-			      int na, int ns, int pna)
-{
-	u32 result[OF_MAX_ADDR_CELLS];
-	int i;
-
-	if (ns > 2) {
-		printk("of_device: Cannot handle size cells (%d) > 2.", ns);
-		return -EINVAL;
-	}
-
-	if (of_out_of_range(addr, range, range + na + pna, na, ns))
-		return -EINVAL;
-
-	/* Start with the parent range base.  */
-	memcpy(result, range + na, pna * 4);
-
-	/* Add in the child address offset.  */
-	for (i = 0; i < na; i++)
-		result[pna - 1 - i] +=
-			(addr[na - 1 - i] -
-			 range[na - 1 - i]);
-
-	memcpy(addr, result, pna * 4);
-
-	return 0;
-}
-
-static unsigned long of_bus_default_get_flags(const u32 *addr, unsigned long flags)
-{
-	if (flags)
-		return flags;
-	return IORESOURCE_MEM;
-}
-
 /*
  * PCI bus specific translator
  */
@@ -295,42 +147,6 @@ static unsigned long of_bus_pci_get_flags(const u32 *addr, unsigned long flags)
 }
 
 /*
- * SBUS bus specific translator
- */
-
-static int of_bus_sbus_match(struct device_node *np)
-{
-	struct device_node *dp = np;
-
-	while (dp) {
-		if (!strcmp(dp->name, "sbus") ||
-		    !strcmp(dp->name, "sbi"))
-			return 1;
-
-		/* Have a look at use_1to1_mapping().  We're trying
-		 * to match SBUS if that's the top-level bus and we
-		 * don't have some intervening real bus that provides
-		 * ranges based translations.
-		 */
-		if (of_find_property(dp, "ranges", NULL) != NULL)
-			break;
-
-		dp = dp->parent;
-	}
-
-	return 0;
-}
-
-static void of_bus_sbus_count_cells(struct device_node *child,
-				   int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = 2;
-	if (sizec)
-		*sizec = 1;
-}
-
-/*
  * FHC/Central bus specific translator.
  *
  * This is just needed to hard-code the address and size cell
diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c
new file mode 100644
index 00000000000..cb8eb799bb6
--- /dev/null
+++ b/arch/sparc/kernel/of_device_common.c
@@ -0,0 +1,174 @@
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/irq.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+
+#include "of_device_common.h"
+
+static int node_match(struct device *dev, void *data)
+{
+	struct of_device *op = to_of_device(dev);
+	struct device_node *dp = data;
+
+	return (op->node == dp);
+}
+
+struct of_device *of_find_device_by_node(struct device_node *dp)
+{
+	struct device *dev = bus_find_device(&of_platform_bus_type, NULL,
+					     dp, node_match);
+
+	if (dev)
+		return to_of_device(dev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(of_find_device_by_node);
+
+unsigned int irq_of_parse_and_map(struct device_node *node, int index)
+{
+	struct of_device *op = of_find_device_by_node(node);
+
+	if (!op || index >= op->num_irqs)
+		return 0;
+
+	return op->irqs[index];
+}
+EXPORT_SYMBOL(irq_of_parse_and_map);
+
+/* Take the archdata values for IOMMU, STC, and HOSTDATA found in
+ * BUS and propagate to all child of_device objects.
+ */
+void of_propagate_archdata(struct of_device *bus)
+{
+	struct dev_archdata *bus_sd = &bus->dev.archdata;
+	struct device_node *bus_dp = bus->node;
+	struct device_node *dp;
+
+	for (dp = bus_dp->child; dp; dp = dp->sibling) {
+		struct of_device *op = of_find_device_by_node(dp);
+
+		op->dev.archdata.iommu = bus_sd->iommu;
+		op->dev.archdata.stc = bus_sd->stc;
+		op->dev.archdata.host_controller = bus_sd->host_controller;
+		op->dev.archdata.numa_node = bus_sd->numa_node;
+
+		if (dp->child)
+			of_propagate_archdata(op);
+	}
+}
+
+struct bus_type of_platform_bus_type;
+EXPORT_SYMBOL(of_platform_bus_type);
+
+static void get_cells(struct device_node *dp, int *addrc, int *sizec)
+{
+	if (addrc)
+		*addrc = of_n_addr_cells(dp);
+	if (sizec)
+		*sizec = of_n_size_cells(dp);
+}
+
+/*
+ * Default translator (generic bus)
+ */
+
+void of_bus_default_count_cells(struct device_node *dev, int *addrc, int *sizec)
+{
+	get_cells(dev, addrc, sizec);
+}
+
+/* Make sure the least significant 64-bits are in-range.  Even
+ * for 3 or 4 cell values it is a good enough approximation.
+ */
+int of_out_of_range(const u32 *addr, const u32 *base,
+		    const u32 *size, int na, int ns)
+{
+	u64 a = of_read_addr(addr, na);
+	u64 b = of_read_addr(base, na);
+
+	if (a < b)
+		return 1;
+
+	b += of_read_addr(size, ns);
+	if (a >= b)
+		return 1;
+
+	return 0;
+}
+
+int of_bus_default_map(u32 *addr, const u32 *range, int na, int ns, int pna)
+{
+	u32 result[OF_MAX_ADDR_CELLS];
+	int i;
+
+	if (ns > 2) {
+		printk("of_device: Cannot handle size cells (%d) > 2.", ns);
+		return -EINVAL;
+	}
+
+	if (of_out_of_range(addr, range, range + na + pna, na, ns))
+		return -EINVAL;
+
+	/* Start with the parent range base.  */
+	memcpy(result, range + na, pna * 4);
+
+	/* Add in the child address offset.  */
+	for (i = 0; i < na; i++)
+		result[pna - 1 - i] +=
+			(addr[na - 1 - i] -
+			 range[na - 1 - i]);
+
+	memcpy(addr, result, pna * 4);
+
+	return 0;
+}
+
+unsigned long of_bus_default_get_flags(const u32 *addr, unsigned long flags)
+{
+	if (flags)
+		return flags;
+	return IORESOURCE_MEM;
+}
+
+/*
+ * SBUS bus specific translator
+ */
+
+int of_bus_sbus_match(struct device_node *np)
+{
+	struct device_node *dp = np;
+
+	while (dp) {
+		if (!strcmp(dp->name, "sbus") ||
+		    !strcmp(dp->name, "sbi"))
+			return 1;
+
+		/* Have a look at use_1to1_mapping().  We're trying
+		 * to match SBUS if that's the top-level bus and we
+		 * don't have some intervening real bus that provides
+		 * ranges based translations.
+		 */
+		if (of_find_property(dp, "ranges", NULL) != NULL)
+			break;
+
+		dp = dp->parent;
+	}
+
+	return 0;
+}
+
+void of_bus_sbus_count_cells(struct device_node *child, int *addrc, int *sizec)
+{
+	if (addrc)
+		*addrc = 2;
+	if (sizec)
+		*sizec = 1;
+}
diff --git a/arch/sparc/kernel/of_device_common.h b/arch/sparc/kernel/of_device_common.h
new file mode 100644
index 00000000000..cdfd2399284
--- /dev/null
+++ b/arch/sparc/kernel/of_device_common.h
@@ -0,0 +1,36 @@
+#ifndef _OF_DEVICE_COMMON_H
+#define _OF_DEVICE_COMMON_H
+
+static inline u64 of_read_addr(const u32 *cell, int size)
+{
+	u64 r = 0;
+	while (size--)
+		r = (r << 32) | *(cell++);
+	return r;
+}
+
+void of_bus_default_count_cells(struct device_node *dev, int *addrc,
+				int *sizec);
+int of_out_of_range(const u32 *addr, const u32 *base,
+		    const u32 *size, int na, int ns);
+int of_bus_default_map(u32 *addr, const u32 *range, int na, int ns, int pna);
+unsigned long of_bus_default_get_flags(const u32 *addr, unsigned long flags);
+
+int of_bus_sbus_match(struct device_node *np);
+void of_bus_sbus_count_cells(struct device_node *child, int *addrc, int *sizec);
+
+/* Max address size we deal with */
+#define OF_MAX_ADDR_CELLS	4
+
+struct of_bus {
+	const char	*name;
+	const char	*addr_prop_name;
+	int		(*match)(struct device_node *parent);
+	void		(*count_cells)(struct device_node *child,
+				       int *addrc, int *sizec);
+	int		(*map)(u32 *addr, const u32 *range,
+			       int na, int ns, int pna);
+	unsigned long	(*get_flags)(const u32 *addr, unsigned long);
+};
+
+#endif /* _OF_DEVICE_COMMON_H */
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 5db5ebed35d..2485eaa2310 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -230,8 +230,9 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 		free_pages((unsigned long)cpu, order);
 }
 
-static dma_addr_t dma_4v_map_single(struct device *dev, void *ptr, size_t sz,
-				    enum dma_data_direction direction)
+static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t sz,
+				  enum dma_data_direction direction)
 {
 	struct iommu *iommu;
 	unsigned long flags, npages, oaddr;
@@ -245,7 +246,7 @@ static dma_addr_t dma_4v_map_single(struct device *dev, void *ptr, size_t sz,
 	if (unlikely(direction == DMA_NONE))
 		goto bad;
 
-	oaddr = (unsigned long)ptr;
+	oaddr = (unsigned long)(page_address(page) + offset);
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
@@ -294,8 +295,8 @@ iommu_map_fail:
 	return DMA_ERROR_CODE;
 }
 
-static void dma_4v_unmap_single(struct device *dev, dma_addr_t bus_addr,
-				size_t sz, enum dma_data_direction direction)
+static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
+			      size_t sz, enum dma_data_direction direction)
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
@@ -537,8 +538,8 @@ static void dma_4v_sync_sg_for_cpu(struct device *dev,
 static const struct dma_ops sun4v_dma_ops = {
 	.alloc_coherent			= dma_4v_alloc_coherent,
 	.free_coherent			= dma_4v_free_coherent,
-	.map_single			= dma_4v_map_single,
-	.unmap_single			= dma_4v_unmap_single,
+	.map_page			= dma_4v_map_page,
+	.unmap_page			= dma_4v_unmap_page,
 	.map_sg				= dma_4v_map_sg,
 	.unmap_sg			= dma_4v_unmap_sg,
 	.sync_single_for_cpu		= dma_4v_sync_single_for_cpu,
diff --git a/arch/sparc/kernel/prom.h b/arch/sparc/kernel/prom.h
index bb0f0fda6ca..453397fe5e1 100644
--- a/arch/sparc/kernel/prom.h
+++ b/arch/sparc/kernel/prom.h
@@ -22,7 +22,6 @@ static inline int is_root_node(const struct device_node *dp)
 
 extern char *build_path_component(struct device_node *dp);
 extern void of_console_init(void);
-extern void of_fill_in_cpu_data(void);
 
 extern unsigned int prom_early_allocated;
 
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index ca55c7012f7..fb06ac2bd38 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -374,75 +374,26 @@ static const char *get_mid_prop(void)
 	return (tlb_type == spitfire ? "upa-portid" : "portid");
 }
 
-struct device_node *of_find_node_by_cpuid(int cpuid)
-{
-	struct device_node *dp;
-	const char *mid_prop = get_mid_prop();
-
-	for_each_node_by_type(dp, "cpu") {
-		int id = of_getintprop_default(dp, mid_prop, -1);
-		const char *this_mid_prop = mid_prop;
-
-		if (id < 0) {
-			this_mid_prop = "cpuid";
-			id = of_getintprop_default(dp, this_mid_prop, -1);
-		}
-
-		if (id < 0) {
-			prom_printf("OF: Serious problem, cpu lacks "
-				    "%s property", this_mid_prop);
-			prom_halt();
-		}
-		if (cpuid == id)
-			return dp;
-	}
-	return NULL;
-}
-
-void __init of_fill_in_cpu_data(void)
+static void *of_iterate_over_cpus(void *(*func)(struct device_node *, int, int), int arg)
 {
 	struct device_node *dp;
 	const char *mid_prop;
 
-	if (tlb_type == hypervisor)
-		return;
-
 	mid_prop = get_mid_prop();
-	ncpus_probed = 0;
 	for_each_node_by_type(dp, "cpu") {
 		int cpuid = of_getintprop_default(dp, mid_prop, -1);
 		const char *this_mid_prop = mid_prop;
-		struct device_node *portid_parent;
-		int portid = -1;
+		void *ret;
 
-		portid_parent = NULL;
 		if (cpuid < 0) {
 			this_mid_prop = "cpuid";
 			cpuid = of_getintprop_default(dp, this_mid_prop, -1);
-			if (cpuid >= 0) {
-				int limit = 2;
-
-				portid_parent = dp;
-				while (limit--) {
-					portid_parent = portid_parent->parent;
-					if (!portid_parent)
-						break;
-					portid = of_getintprop_default(portid_parent,
-								       "portid", -1);
-					if (portid >= 0)
-						break;
-				}
-			}
 		}
-
 		if (cpuid < 0) {
 			prom_printf("OF: Serious problem, cpu lacks "
 				    "%s property", this_mid_prop);
 			prom_halt();
 		}
-
-		ncpus_probed++;
-
 #ifdef CONFIG_SMP
 		if (cpuid >= NR_CPUS) {
 			printk(KERN_WARNING "Ignoring CPU %d which is "
@@ -450,79 +401,142 @@ void __init of_fill_in_cpu_data(void)
 			       cpuid, NR_CPUS);
 			continue;
 		}
-#else
-		/* On uniprocessor we only want the values for the
-		 * real physical cpu the kernel booted onto, however
-		 * cpu_data() only has one entry at index 0.
-		 */
-		if (cpuid != real_hard_smp_processor_id())
-			continue;
-		cpuid = 0;
 #endif
+		ret = func(dp, cpuid, arg);
+		if (ret)
+			return ret;
+	}
+	return NULL;
+}
 
-		cpu_data(cpuid).clock_tick =
-			of_getintprop_default(dp, "clock-frequency", 0);
-
-		if (portid_parent) {
-			cpu_data(cpuid).dcache_size =
-				of_getintprop_default(dp, "l1-dcache-size",
-						      16 * 1024);
-			cpu_data(cpuid).dcache_line_size =
-				of_getintprop_default(dp, "l1-dcache-line-size",
-						      32);
-			cpu_data(cpuid).icache_size =
-				of_getintprop_default(dp, "l1-icache-size",
-						      8 * 1024);
-			cpu_data(cpuid).icache_line_size =
-				of_getintprop_default(dp, "l1-icache-line-size",
-						      32);
-			cpu_data(cpuid).ecache_size =
-				of_getintprop_default(dp, "l2-cache-size", 0);
-			cpu_data(cpuid).ecache_line_size =
-				of_getintprop_default(dp, "l2-cache-line-size", 0);
-			if (!cpu_data(cpuid).ecache_size ||
-			    !cpu_data(cpuid).ecache_line_size) {
-				cpu_data(cpuid).ecache_size =
-					of_getintprop_default(portid_parent,
-							      "l2-cache-size",
-							      (4 * 1024 * 1024));
-				cpu_data(cpuid).ecache_line_size =
-					of_getintprop_default(portid_parent,
-							      "l2-cache-line-size", 64);
-			}
-
-			cpu_data(cpuid).core_id = portid + 1;
-			cpu_data(cpuid).proc_id = portid;
+static void *check_cpu_node(struct device_node *dp, int cpuid, int id)
+{
+	if (id == cpuid)
+		return dp;
+	return NULL;
+}
+
+struct device_node *of_find_node_by_cpuid(int cpuid)
+{
+	return of_iterate_over_cpus(check_cpu_node, cpuid);
+}
+
+static void *record_one_cpu(struct device_node *dp, int cpuid, int arg)
+{
+	ncpus_probed++;
 #ifdef CONFIG_SMP
-			sparc64_multi_core = 1;
+	set_cpu_present(cpuid, true);
+	set_cpu_possible(cpuid, true);
 #endif
-		} else {
-			cpu_data(cpuid).dcache_size =
-				of_getintprop_default(dp, "dcache-size", 16 * 1024);
-			cpu_data(cpuid).dcache_line_size =
-				of_getintprop_default(dp, "dcache-line-size", 32);
+	return NULL;
+}
 
-			cpu_data(cpuid).icache_size =
-				of_getintprop_default(dp, "icache-size", 16 * 1024);
-			cpu_data(cpuid).icache_line_size =
-				of_getintprop_default(dp, "icache-line-size", 32);
+void __init of_populate_present_mask(void)
+{
+	if (tlb_type == hypervisor)
+		return;
+
+	ncpus_probed = 0;
+	of_iterate_over_cpus(record_one_cpu, 0);
+}
 
+static void *fill_in_one_cpu(struct device_node *dp, int cpuid, int arg)
+{
+	struct device_node *portid_parent = NULL;
+	int portid = -1;
+
+	if (of_find_property(dp, "cpuid", NULL)) {
+		int limit = 2;
+
+		portid_parent = dp;
+		while (limit--) {
+			portid_parent = portid_parent->parent;
+			if (!portid_parent)
+				break;
+			portid = of_getintprop_default(portid_parent,
+						       "portid", -1);
+			if (portid >= 0)
+				break;
+		}
+	}
+
+#ifndef CONFIG_SMP
+	/* On uniprocessor we only want the values for the
+	 * real physical cpu the kernel booted onto, however
+	 * cpu_data() only has one entry at index 0.
+	 */
+	if (cpuid != real_hard_smp_processor_id())
+		return NULL;
+	cpuid = 0;
+#endif
+
+	cpu_data(cpuid).clock_tick =
+		of_getintprop_default(dp, "clock-frequency", 0);
+
+	if (portid_parent) {
+		cpu_data(cpuid).dcache_size =
+			of_getintprop_default(dp, "l1-dcache-size",
+					      16 * 1024);
+		cpu_data(cpuid).dcache_line_size =
+			of_getintprop_default(dp, "l1-dcache-line-size",
+					      32);
+		cpu_data(cpuid).icache_size =
+			of_getintprop_default(dp, "l1-icache-size",
+					      8 * 1024);
+		cpu_data(cpuid).icache_line_size =
+			of_getintprop_default(dp, "l1-icache-line-size",
+					      32);
+		cpu_data(cpuid).ecache_size =
+			of_getintprop_default(dp, "l2-cache-size", 0);
+		cpu_data(cpuid).ecache_line_size =
+			of_getintprop_default(dp, "l2-cache-line-size", 0);
+		if (!cpu_data(cpuid).ecache_size ||
+		    !cpu_data(cpuid).ecache_line_size) {
 			cpu_data(cpuid).ecache_size =
-				of_getintprop_default(dp, "ecache-size",
+				of_getintprop_default(portid_parent,
+						      "l2-cache-size",
 						      (4 * 1024 * 1024));
 			cpu_data(cpuid).ecache_line_size =
-				of_getintprop_default(dp, "ecache-line-size", 64);
-
-			cpu_data(cpuid).core_id = 0;
-			cpu_data(cpuid).proc_id = -1;
+				of_getintprop_default(portid_parent,
+						      "l2-cache-line-size", 64);
 		}
 
+		cpu_data(cpuid).core_id = portid + 1;
+		cpu_data(cpuid).proc_id = portid;
 #ifdef CONFIG_SMP
-		set_cpu_present(cpuid, true);
-		set_cpu_possible(cpuid, true);
+		sparc64_multi_core = 1;
 #endif
+	} else {
+		cpu_data(cpuid).dcache_size =
+			of_getintprop_default(dp, "dcache-size", 16 * 1024);
+		cpu_data(cpuid).dcache_line_size =
+			of_getintprop_default(dp, "dcache-line-size", 32);
+
+		cpu_data(cpuid).icache_size =
+			of_getintprop_default(dp, "icache-size", 16 * 1024);
+		cpu_data(cpuid).icache_line_size =
+			of_getintprop_default(dp, "icache-line-size", 32);
+
+		cpu_data(cpuid).ecache_size =
+			of_getintprop_default(dp, "ecache-size",
+					      (4 * 1024 * 1024));
+		cpu_data(cpuid).ecache_line_size =
+			of_getintprop_default(dp, "ecache-line-size", 64);
+
+		cpu_data(cpuid).core_id = 0;
+		cpu_data(cpuid).proc_id = -1;
 	}
 
+	return NULL;
+}
+
+void __init of_fill_in_cpu_data(void)
+{
+	if (tlb_type == hypervisor)
+		return;
+
+	of_iterate_over_cpus(fill_in_one_cpu, 0);
+
 	smp_fill_in_sib_core_maps();
 }
 
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
index ff7b591c894..0fb5789d43c 100644
--- a/arch/sparc/kernel/prom_common.c
+++ b/arch/sparc/kernel/prom_common.c
@@ -313,6 +313,4 @@ void __init prom_build_devicetree(void)
 
 	printk("PROM: Built device tree with %u bytes of memory.\n",
 	       prom_early_allocated);
-
-	of_fill_in_cpu_data();
 }
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index f7642e5a94d..fa44eaf8d89 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -20,7 +20,8 @@
 #include <linux/cache.h>
 #include <linux/jiffies.h>
 #include <linux/profile.h>
-#include <linux/lmb.h>
+#include <linux/bootmem.h>
+#include <linux/vmalloc.h>
 #include <linux/cpu.h>
 
 #include <asm/head.h>
@@ -47,6 +48,8 @@
 #include <asm/ldc.h>
 #include <asm/hypervisor.h>
 
+#include "cpumap.h"
+
 int sparc64_multi_core __read_mostly;
 
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
@@ -278,7 +281,7 @@ static unsigned long kimage_addr_to_ra(void *p)
 	return kern_base + (val - KERNBASE);
 }
 
-static void __cpuinit ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread_reg)
+static void __cpuinit ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread_reg, void **descrp)
 {
 	extern unsigned long sparc64_ttable_tl0;
 	extern unsigned long kern_locked_tte_data;
@@ -298,12 +301,12 @@ static void __cpuinit ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread
 		       "hvtramp_descr.\n");
 		return;
 	}
+	*descrp = hdesc;
 
 	hdesc->cpu = cpu;
 	hdesc->num_mappings = num_kernel_image_mappings;
 
 	tb = &trap_block[cpu];
-	tb->hdesc = hdesc;
 
 	hdesc->fault_info_va = (unsigned long) &tb->fault_info;
 	hdesc->fault_info_pa = kimage_addr_to_ra(&tb->fault_info);
@@ -341,12 +344,12 @@ static struct thread_info *cpu_new_thread = NULL;
 
 static int __cpuinit smp_boot_one_cpu(unsigned int cpu)
 {
-	struct trap_per_cpu *tb = &trap_block[cpu];
 	unsigned long entry =
 		(unsigned long)(&sparc64_cpu_startup);
 	unsigned long cookie =
 		(unsigned long)(&cpu_new_thread);
 	struct task_struct *p;
+	void *descr = NULL;
 	int timeout, ret;
 
 	p = fork_idle(cpu);
@@ -359,7 +362,8 @@ static int __cpuinit smp_boot_one_cpu(unsigned int cpu)
 #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
 		if (ldom_domaining_enabled)
 			ldom_startcpu_cpuid(cpu,
-					    (unsigned long) cpu_new_thread);
+					    (unsigned long) cpu_new_thread,
+					    &descr);
 		else
 #endif
 			prom_startcpu_cpuid(cpu, entry, cookie);
@@ -383,10 +387,7 @@ static int __cpuinit smp_boot_one_cpu(unsigned int cpu)
 	}
 	cpu_new_thread = NULL;
 
-	if (tb->hdesc) {
-		kfree(tb->hdesc);
-		tb->hdesc = NULL;
-	}
+	kfree(descr);
 
 	return ret;
 }
@@ -1315,6 +1316,8 @@ int __cpu_disable(void)
 	cpu_clear(cpu, cpu_online_map);
 	ipi_call_unlock();
 
+	cpu_map_rebuild();
+
 	return 0;
 }
 
@@ -1373,36 +1376,171 @@ void smp_send_stop(void)
 {
 }
 
-unsigned long __per_cpu_base __read_mostly;
-unsigned long __per_cpu_shift __read_mostly;
+/**
+ * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
+ * @cpu: cpu to allocate for
+ * @size: size allocation in bytes
+ * @align: alignment
+ *
+ * Allocate @size bytes aligned at @align for cpu @cpu.  This wrapper
+ * does the right thing for NUMA regardless of the current
+ * configuration.
+ *
+ * RETURNS:
+ * Pointer to the allocated area on success, NULL on failure.
+ */
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
+					unsigned long align)
+{
+	const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	int node = cpu_to_node(cpu);
+	void *ptr;
+
+	if (!node_online(node) || !NODE_DATA(node)) {
+		ptr = __alloc_bootmem(size, align, goal);
+		pr_info("cpu %d has no node %d or node-local memory\n",
+			cpu, node);
+		pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
+			 cpu, size, __pa(ptr));
+	} else {
+		ptr = __alloc_bootmem_node(NODE_DATA(node),
+					   size, align, goal);
+		pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
+			 "%016lx\n", cpu, size, node, __pa(ptr));
+	}
+	return ptr;
+#else
+	return __alloc_bootmem(size, align, goal);
+#endif
+}
 
-EXPORT_SYMBOL(__per_cpu_base);
-EXPORT_SYMBOL(__per_cpu_shift);
+static size_t pcpur_size __initdata;
+static void **pcpur_ptrs __initdata;
 
-void __init real_setup_per_cpu_areas(void)
+static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
 {
-	unsigned long paddr, goal, size, i;
-	char *ptr;
+	size_t off = (size_t)pageno << PAGE_SHIFT;
 
-	/* Copy section for each CPU (we discard the original) */
-	goal = PERCPU_ENOUGH_ROOM;
+	if (off >= pcpur_size)
+		return NULL;
 
-	__per_cpu_shift = PAGE_SHIFT;
-	for (size = PAGE_SIZE; size < goal; size <<= 1UL)
-		__per_cpu_shift++;
+	return virt_to_page(pcpur_ptrs[cpu] + off);
+}
+
+#define PCPU_CHUNK_SIZE (4UL * 1024UL * 1024UL)
+
+static void __init pcpu_map_range(unsigned long start, unsigned long end,
+				  struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long pte_base;
+
+	BUG_ON((pfn<<PAGE_SHIFT)&(PCPU_CHUNK_SIZE - 1UL));
+
+	pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U |
+		    _PAGE_CP_4U | _PAGE_CV_4U |
+		    _PAGE_P_4U | _PAGE_W_4U);
+	if (tlb_type == hypervisor)
+		pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
+			    _PAGE_CP_4V | _PAGE_CV_4V |
+			    _PAGE_P_4V | _PAGE_W_4V);
+
+	while (start < end) {
+		pgd_t *pgd = pgd_offset_k(start);
+		unsigned long this_end;
+		pud_t *pud;
+		pmd_t *pmd;
+		pte_t *pte;
+
+		pud = pud_offset(pgd, start);
+		if (pud_none(*pud)) {
+			pmd_t *new;
+
+			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+			pud_populate(&init_mm, pud, new);
+		}
+
+		pmd = pmd_offset(pud, start);
+		if (!pmd_present(*pmd)) {
+			pte_t *new;
+
+			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+			pmd_populate_kernel(&init_mm, pmd, new);
+		}
 
-	paddr = lmb_alloc(size * NR_CPUS, PAGE_SIZE);
-	if (!paddr) {
-		prom_printf("Cannot allocate per-cpu memory.\n");
-		prom_halt();
+		pte = pte_offset_kernel(pmd, start);
+		this_end = (start + PMD_SIZE) & PMD_MASK;
+		if (this_end > end)
+			this_end = end;
+
+		while (start < this_end) {
+			unsigned long paddr = pfn << PAGE_SHIFT;
+
+			pte_val(*pte) = (paddr | pte_base);
+
+			start += PAGE_SIZE;
+			pte++;
+			pfn++;
+		}
+	}
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	size_t dyn_size, static_size = __per_cpu_end - __per_cpu_start;
+	static struct vm_struct vm;
+	unsigned long delta, cpu;
+	size_t pcpu_unit_size;
+	size_t ptrs_size;
+
+	pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
+			       PERCPU_DYNAMIC_RESERVE);
+	dyn_size = pcpur_size - static_size - PERCPU_MODULE_RESERVE;
+
+
+	ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0]));
+	pcpur_ptrs = alloc_bootmem(ptrs_size);
+
+	for_each_possible_cpu(cpu) {
+		pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PCPU_CHUNK_SIZE,
+						     PCPU_CHUNK_SIZE);
+
+		free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size),
+			     PCPU_CHUNK_SIZE - pcpur_size);
+
+		memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size);
 	}
 
-	ptr = __va(paddr);
-	__per_cpu_base = ptr - __per_cpu_start;
+	/* allocate address and map */
+	vm.flags = VM_ALLOC;
+	vm.size = num_possible_cpus() * PCPU_CHUNK_SIZE;
+	vm_area_register_early(&vm, PCPU_CHUNK_SIZE);
+
+	for_each_possible_cpu(cpu) {
+		unsigned long start = (unsigned long) vm.addr;
+		unsigned long end;
+
+		start += cpu * PCPU_CHUNK_SIZE;
+		end = start + PCPU_CHUNK_SIZE;
+		pcpu_map_range(start, end, virt_to_page(pcpur_ptrs[cpu]));
+	}
 
-	for (i = 0; i < NR_CPUS; i++, ptr += size)
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+	pcpu_unit_size = pcpu_setup_first_chunk(pcpur_get_page, static_size,
+						PERCPU_MODULE_RESERVE, dyn_size,
+						PCPU_CHUNK_SIZE, vm.addr, NULL);
+
+	free_bootmem(__pa(pcpur_ptrs), ptrs_size);
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu) {
+		__per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
+	}
 
 	/* Setup %g5 for the boot cpu.  */
 	__local_per_cpu_offset = __per_cpu_offset(smp_processor_id());
+
+	of_fill_in_cpu_data();
+	if (tlb_type == hypervisor)
+		mdesc_fill_in_cpu_data(cpu_all_mask);
 }
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 00ec3b15f38..69090165729 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -81,4 +81,6 @@ sys_call_table:
 /*305*/	.long sys_set_mempolicy, sys_kexec_load, sys_move_pages, sys_getcpu, sys_epoll_pwait
 /*310*/	.long sys_utimensat, sys_signalfd, sys_timerfd_create, sys_eventfd, sys_fallocate
 /*315*/	.long sys_timerfd_settime, sys_timerfd_gettime, sys_signalfd4, sys_eventfd2, sys_epoll_create1
-/*320*/	.long sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv, sys_pwritev
+/*320*/	.long sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
+/*325*/	.long sys_pwritev, sys_rt_tgsigqueueinfo
+
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 82b5bf85b9d..6b3ee88e253 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -82,7 +82,8 @@ sys_call_table32:
 	.word compat_sys_set_mempolicy, compat_sys_kexec_load, compat_sys_move_pages, sys_getcpu, compat_sys_epoll_pwait
 /*310*/	.word compat_sys_utimensat, compat_sys_signalfd, sys_timerfd_create, sys_eventfd, compat_sys_fallocate
 	.word compat_sys_timerfd_settime, compat_sys_timerfd_gettime, compat_sys_signalfd4, sys_eventfd2, sys_epoll_create1
-/*320*/	.word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, compat_sys_preadv, compat_sys_pwritev
+/*320*/	.word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, compat_sys_preadv
+	.word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo
 
 #endif /* CONFIG_COMPAT */
 
@@ -156,4 +157,5 @@ sys_call_table:
 	.word sys_set_mempolicy, sys_kexec_load, sys_move_pages, sys_getcpu, sys_epoll_pwait
 /*310*/	.word sys_utimensat, sys_signalfd, sys_timerfd_create, sys_eventfd, sys_fallocate
 	.word sys_timerfd_settime, sys_timerfd_gettime, sys_signalfd4, sys_eventfd2, sys_epoll_create1
-/*320*/	.word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv, sys_pwritev
+/*320*/	.word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
+	.word sys_pwritev, sys_rt_tgsigqueueinfo
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index d809c4ebb48..10f7bb9fc14 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2509,6 +2509,7 @@ void do_getpsr(struct pt_regs *regs)
 }
 
 struct trap_per_cpu trap_block[NR_CPUS];
+EXPORT_SYMBOL(trap_block);
 
 /* This can get invoked before sched_init() so play it super safe
  * and use hard_smp_processor_id().
@@ -2530,84 +2531,97 @@ extern void tsb_config_offsets_are_bolixed_dave(void);
 void __init trap_init(void)
 {
 	/* Compile time sanity check. */
-	if (TI_TASK != offsetof(struct thread_info, task) ||
-	    TI_FLAGS != offsetof(struct thread_info, flags) ||
-	    TI_CPU != offsetof(struct thread_info, cpu) ||
-	    TI_FPSAVED != offsetof(struct thread_info, fpsaved) ||
-	    TI_KSP != offsetof(struct thread_info, ksp) ||
-	    TI_FAULT_ADDR != offsetof(struct thread_info, fault_address) ||
-	    TI_KREGS != offsetof(struct thread_info, kregs) ||
-	    TI_UTRAPS != offsetof(struct thread_info, utraps) ||
-	    TI_EXEC_DOMAIN != offsetof(struct thread_info, exec_domain) ||
-	    TI_REG_WINDOW != offsetof(struct thread_info, reg_window) ||
-	    TI_RWIN_SPTRS != offsetof(struct thread_info, rwbuf_stkptrs) ||
-	    TI_GSR != offsetof(struct thread_info, gsr) ||
-	    TI_XFSR != offsetof(struct thread_info, xfsr) ||
-	    TI_USER_CNTD0 != offsetof(struct thread_info, user_cntd0) ||
-	    TI_USER_CNTD1 != offsetof(struct thread_info, user_cntd1) ||
-	    TI_KERN_CNTD0 != offsetof(struct thread_info, kernel_cntd0) ||
-	    TI_KERN_CNTD1 != offsetof(struct thread_info, kernel_cntd1) ||
-	    TI_PCR != offsetof(struct thread_info, pcr_reg) ||
-	    TI_PRE_COUNT != offsetof(struct thread_info, preempt_count) ||
-	    TI_NEW_CHILD != offsetof(struct thread_info, new_child) ||
-	    TI_SYS_NOERROR != offsetof(struct thread_info, syscall_noerror) ||
-	    TI_RESTART_BLOCK != offsetof(struct thread_info, restart_block) ||
-	    TI_KUNA_REGS != offsetof(struct thread_info, kern_una_regs) ||
-	    TI_KUNA_INSN != offsetof(struct thread_info, kern_una_insn) ||
-	    TI_FPREGS != offsetof(struct thread_info, fpregs) ||
-	    (TI_FPREGS & (64 - 1)))
-		thread_info_offsets_are_bolixed_dave();
-
-	if (TRAP_PER_CPU_THREAD != offsetof(struct trap_per_cpu, thread) ||
-	    (TRAP_PER_CPU_PGD_PADDR !=
-	     offsetof(struct trap_per_cpu, pgd_paddr)) ||
-	    (TRAP_PER_CPU_CPU_MONDO_PA !=
-	     offsetof(struct trap_per_cpu, cpu_mondo_pa)) ||
-	    (TRAP_PER_CPU_DEV_MONDO_PA !=
-	     offsetof(struct trap_per_cpu, dev_mondo_pa)) ||
-	    (TRAP_PER_CPU_RESUM_MONDO_PA !=
-	     offsetof(struct trap_per_cpu, resum_mondo_pa)) ||
-	    (TRAP_PER_CPU_RESUM_KBUF_PA !=
-	     offsetof(struct trap_per_cpu, resum_kernel_buf_pa)) ||
-	    (TRAP_PER_CPU_NONRESUM_MONDO_PA !=
-	     offsetof(struct trap_per_cpu, nonresum_mondo_pa)) ||
-	    (TRAP_PER_CPU_NONRESUM_KBUF_PA !=
-	     offsetof(struct trap_per_cpu, nonresum_kernel_buf_pa)) ||
-	    (TRAP_PER_CPU_FAULT_INFO !=
-	     offsetof(struct trap_per_cpu, fault_info)) ||
-	    (TRAP_PER_CPU_CPU_MONDO_BLOCK_PA !=
-	     offsetof(struct trap_per_cpu, cpu_mondo_block_pa)) ||
-	    (TRAP_PER_CPU_CPU_LIST_PA !=
-	     offsetof(struct trap_per_cpu, cpu_list_pa)) ||
-	    (TRAP_PER_CPU_TSB_HUGE !=
-	     offsetof(struct trap_per_cpu, tsb_huge)) ||
-	    (TRAP_PER_CPU_TSB_HUGE_TEMP !=
-	     offsetof(struct trap_per_cpu, tsb_huge_temp)) ||
-	    (TRAP_PER_CPU_IRQ_WORKLIST_PA !=
-	     offsetof(struct trap_per_cpu, irq_worklist_pa)) ||
-	    (TRAP_PER_CPU_CPU_MONDO_QMASK !=
-	     offsetof(struct trap_per_cpu, cpu_mondo_qmask)) ||
-	    (TRAP_PER_CPU_DEV_MONDO_QMASK !=
-	     offsetof(struct trap_per_cpu, dev_mondo_qmask)) ||
-	    (TRAP_PER_CPU_RESUM_QMASK !=
-	     offsetof(struct trap_per_cpu, resum_qmask)) ||
-	    (TRAP_PER_CPU_NONRESUM_QMASK !=
-	     offsetof(struct trap_per_cpu, nonresum_qmask)))
-		trap_per_cpu_offsets_are_bolixed_dave();
-
-	if ((TSB_CONFIG_TSB !=
-	     offsetof(struct tsb_config, tsb)) ||
-	    (TSB_CONFIG_RSS_LIMIT !=
-	     offsetof(struct tsb_config, tsb_rss_limit)) ||
-	    (TSB_CONFIG_NENTRIES !=
-	     offsetof(struct tsb_config, tsb_nentries)) ||
-	    (TSB_CONFIG_REG_VAL !=
-	     offsetof(struct tsb_config, tsb_reg_val)) ||
-	    (TSB_CONFIG_MAP_VADDR !=
-	     offsetof(struct tsb_config, tsb_map_vaddr)) ||
-	    (TSB_CONFIG_MAP_PTE !=
-	     offsetof(struct tsb_config, tsb_map_pte)))
-		tsb_config_offsets_are_bolixed_dave();
+	BUILD_BUG_ON(TI_TASK != offsetof(struct thread_info, task) ||
+		     TI_FLAGS != offsetof(struct thread_info, flags) ||
+		     TI_CPU != offsetof(struct thread_info, cpu) ||
+		     TI_FPSAVED != offsetof(struct thread_info, fpsaved) ||
+		     TI_KSP != offsetof(struct thread_info, ksp) ||
+		     TI_FAULT_ADDR != offsetof(struct thread_info,
+					       fault_address) ||
+		     TI_KREGS != offsetof(struct thread_info, kregs) ||
+		     TI_UTRAPS != offsetof(struct thread_info, utraps) ||
+		     TI_EXEC_DOMAIN != offsetof(struct thread_info,
+						exec_domain) ||
+		     TI_REG_WINDOW != offsetof(struct thread_info,
+					       reg_window) ||
+		     TI_RWIN_SPTRS != offsetof(struct thread_info,
+					       rwbuf_stkptrs) ||
+		     TI_GSR != offsetof(struct thread_info, gsr) ||
+		     TI_XFSR != offsetof(struct thread_info, xfsr) ||
+		     TI_USER_CNTD0 != offsetof(struct thread_info,
+					       user_cntd0) ||
+		     TI_USER_CNTD1 != offsetof(struct thread_info,
+					       user_cntd1) ||
+		     TI_KERN_CNTD0 != offsetof(struct thread_info,
+					       kernel_cntd0) ||
+		     TI_KERN_CNTD1 != offsetof(struct thread_info,
+					       kernel_cntd1) ||
+		     TI_PCR != offsetof(struct thread_info, pcr_reg) ||
+		     TI_PRE_COUNT != offsetof(struct thread_info,
+					      preempt_count) ||
+		     TI_NEW_CHILD != offsetof(struct thread_info, new_child) ||
+		     TI_SYS_NOERROR != offsetof(struct thread_info,
+						syscall_noerror) ||
+		     TI_RESTART_BLOCK != offsetof(struct thread_info,
+						  restart_block) ||
+		     TI_KUNA_REGS != offsetof(struct thread_info,
+					      kern_una_regs) ||
+		     TI_KUNA_INSN != offsetof(struct thread_info,
+					      kern_una_insn) ||
+		     TI_FPREGS != offsetof(struct thread_info, fpregs) ||
+		     (TI_FPREGS & (64 - 1)));
+
+	BUILD_BUG_ON(TRAP_PER_CPU_THREAD != offsetof(struct trap_per_cpu,
+						     thread) ||
+		     (TRAP_PER_CPU_PGD_PADDR !=
+		      offsetof(struct trap_per_cpu, pgd_paddr)) ||
+		     (TRAP_PER_CPU_CPU_MONDO_PA !=
+		      offsetof(struct trap_per_cpu, cpu_mondo_pa)) ||
+		     (TRAP_PER_CPU_DEV_MONDO_PA !=
+		      offsetof(struct trap_per_cpu, dev_mondo_pa)) ||
+		     (TRAP_PER_CPU_RESUM_MONDO_PA !=
+		      offsetof(struct trap_per_cpu, resum_mondo_pa)) ||
+		     (TRAP_PER_CPU_RESUM_KBUF_PA !=
+		      offsetof(struct trap_per_cpu, resum_kernel_buf_pa)) ||
+		     (TRAP_PER_CPU_NONRESUM_MONDO_PA !=
+		      offsetof(struct trap_per_cpu, nonresum_mondo_pa)) ||
+		     (TRAP_PER_CPU_NONRESUM_KBUF_PA !=
+		      offsetof(struct trap_per_cpu, nonresum_kernel_buf_pa)) ||
+		     (TRAP_PER_CPU_FAULT_INFO !=
+		      offsetof(struct trap_per_cpu, fault_info)) ||
+		     (TRAP_PER_CPU_CPU_MONDO_BLOCK_PA !=
+		      offsetof(struct trap_per_cpu, cpu_mondo_block_pa)) ||
+		     (TRAP_PER_CPU_CPU_LIST_PA !=
+		      offsetof(struct trap_per_cpu, cpu_list_pa)) ||
+		     (TRAP_PER_CPU_TSB_HUGE !=
+		      offsetof(struct trap_per_cpu, tsb_huge)) ||
+		     (TRAP_PER_CPU_TSB_HUGE_TEMP !=
+		      offsetof(struct trap_per_cpu, tsb_huge_temp)) ||
+		     (TRAP_PER_CPU_IRQ_WORKLIST_PA !=
+		      offsetof(struct trap_per_cpu, irq_worklist_pa)) ||
+		     (TRAP_PER_CPU_CPU_MONDO_QMASK !=
+		      offsetof(struct trap_per_cpu, cpu_mondo_qmask)) ||
+		     (TRAP_PER_CPU_DEV_MONDO_QMASK !=
+		      offsetof(struct trap_per_cpu, dev_mondo_qmask)) ||
+		     (TRAP_PER_CPU_RESUM_QMASK !=
+		      offsetof(struct trap_per_cpu, resum_qmask)) ||
+		     (TRAP_PER_CPU_NONRESUM_QMASK !=
+		      offsetof(struct trap_per_cpu, nonresum_qmask)) ||
+		     (TRAP_PER_CPU_PER_CPU_BASE !=
+		      offsetof(struct trap_per_cpu, __per_cpu_base)));
+
+	BUILD_BUG_ON((TSB_CONFIG_TSB !=
+		      offsetof(struct tsb_config, tsb)) ||
+		     (TSB_CONFIG_RSS_LIMIT !=
+		      offsetof(struct tsb_config, tsb_rss_limit)) ||
+		     (TSB_CONFIG_NENTRIES !=
+		      offsetof(struct tsb_config, tsb_nentries)) ||
+		     (TSB_CONFIG_REG_VAL !=
+		      offsetof(struct tsb_config, tsb_reg_val)) ||
+		     (TSB_CONFIG_MAP_VADDR !=
+		      offsetof(struct tsb_config, tsb_map_vaddr)) ||
+		     (TSB_CONFIG_MAP_PTE !=
+		      offsetof(struct tsb_config, tsb_map_pte)));
 
 	/* Attach to the address space of init_task.  On SMP we
 	 * do this in smp.c:smp_callin for other cpus.
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index cbb282dab5a..26bb3919ff1 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -358,6 +358,7 @@ void __init paging_init(void)
 	protection_map[15] = PAGE_SHARED;
 	btfixup();
 	prom_build_devicetree();
+	of_fill_in_cpu_data();
 	device_scan();
 }
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index f26a352c08a..ca92e2f54e4 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1679,11 +1679,6 @@ pgd_t swapper_pg_dir[2048];
 static void sun4u_pgprot_init(void);
 static void sun4v_pgprot_init(void);
 
-/* Dummy function */
-void __init setup_per_cpu_areas(void)
-{
-}
-
 void __init paging_init(void)
 {
 	unsigned long end_pfn, shift, phys_base;
@@ -1799,16 +1794,13 @@ void __init paging_init(void)
 	if (tlb_type == hypervisor)
 		sun4v_ktsb_register();
 
-	/* We must setup the per-cpu areas before we pull in the
-	 * PROM and the MDESC.  The code there fills in cpu and
-	 * other information into per-cpu data structures.
-	 */
-	real_setup_per_cpu_areas();
-
 	prom_build_devicetree();
+	of_populate_present_mask();
 
-	if (tlb_type == hypervisor)
+	if (tlb_type == hypervisor) {
 		sun4v_mdesc_init();
+		mdesc_populate_present_mask(cpu_all_mask);
+	}
 
 	/* Once the OF device tree and MDESC have been setup, we know
 	 * the list of possible cpus.  Therefore we can allocate the
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 06c9a7d9820..ade4eb373bd 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -19,6 +19,7 @@
 #include <linux/fs.h>
 #include <linux/seq_file.h>
 #include <linux/kdebug.h>
+#include <linux/log2.h>
 
 #include <asm/bitext.h>
 #include <asm/page.h>
@@ -349,7 +350,7 @@ static void srmmu_free_nocache(unsigned long vaddr, int size)
 		    vaddr, srmmu_nocache_end);
 		BUG();
 	}
-	if (size & (size-1)) {
+	if (!is_power_of_2(size)) {
 		printk("Size 0x%x is not a power of 2\n", size);
 		BUG();
 	}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index ef0ae207a7c..096d19aea2f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -463,7 +463,7 @@ static void uv_heartbeat(unsigned long ignored)
 	uv_set_scir_bits(bits);
 
 	/* enable next timer period */
-	mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
+	mod_timer_pinned(timer, jiffies + SCIR_CPU_HB_INTERVAL);
 }
 
 static void __cpuinit uv_heartbeat_enable(int cpu)