Merge branch 'move_extents' of git://oss.oracle.com/git/tye/linux-2.6 into ocfs2-merge-window

Conflicts:
	fs/ocfs2/ioctl.c

100 files changed, 2037 insertions, 2669 deletions

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 3d890a98a08b..f937ad123852 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -39,7 +39,7 @@ SECTIONS
 	__init_begin = ALIGN(PAGE_SIZE);
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 	/* Align to THREAD_SIZE rather than PAGE_SIZE here so any padding page
 	   needed for the THREAD_SIZE aligned init_task gets freed after init */
 	. = ALIGN(THREAD_SIZE);
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b4348e62ef06..e5287f21badc 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -82,7 +82,7 @@ SECTIONS
 #endif
 	}
 
-	PERCPU(32, PAGE_SIZE)
+	PERCPU_SECTION(32)
 
 #ifndef CONFIG_XIP_KERNEL
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/arm/mach-tegra/include/mach/kbc.h b/arch/arm/mach-tegra/include/mach/kbc.h
index 04c779832c78..4f3572a1c684 100644
--- a/arch/arm/mach-tegra/include/mach/kbc.h
+++ b/arch/arm/mach-tegra/include/mach/kbc.h
@@ -50,13 +50,11 @@ struct tegra_kbc_platform_data {
 	unsigned int debounce_cnt;
 	unsigned int repeat_cnt;
 
-	unsigned int wake_cnt; /* 0:wake on any key >1:wake on wake_cfg */
-	const struct tegra_kbc_wake_key *wake_cfg;
-
 	struct tegra_kbc_pin_cfg pin_cfg[KBC_MAX_GPIO];
 	const struct matrix_keymap_data *keymap_data;
 
 	bool wakeup;
 	bool use_fn_map;
+	bool use_ghost_filter;
 };
 #endif
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 6e1907fa94f0..bb26f40493e6 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -204,7 +204,7 @@ static struct i2c_board_info __initdata mop500_i2c2_devices[] = {
 	},
 };
 
-#define U8500_I2C_CONTROLLER(id, _slsu, _tft, _rft, clk, _sm) \
+#define U8500_I2C_CONTROLLER(id, _slsu, _tft, _rft, clk, t_out, _sm)	\
 static struct nmk_i2c_controller u8500_i2c##id##_data = { \
 	/*				\
 	 * slave data setup time, which is	\
@@ -219,19 +219,21 @@ static struct nmk_i2c_controller u8500_i2c##id##_data = { \
 	.rft		= _rft,		\
 	/* std. mode operation */	\
 	.clk_freq	= clk,		\
+	/* Slave response timeout(ms) */\
+	.timeout	= t_out,	\
 	.sm		= _sm,		\
 }
 
 /*
  * The board uses 4 i2c controllers, initialize all of
  * them with slave data setup time of 250 ns,
- * Tx & Rx FIFO threshold values as 1 and standard
+ * Tx & Rx FIFO threshold values as 8 and standard
  * mode of operation
  */
-U8500_I2C_CONTROLLER(0, 0xe, 1, 1, 100000, I2C_FREQ_MODE_STANDARD);
-U8500_I2C_CONTROLLER(1, 0xe, 1, 1, 100000, I2C_FREQ_MODE_STANDARD);
-U8500_I2C_CONTROLLER(2,	0xe, 1, 1, 100000, I2C_FREQ_MODE_STANDARD);
-U8500_I2C_CONTROLLER(3,	0xe, 1, 1, 100000, I2C_FREQ_MODE_STANDARD);
+U8500_I2C_CONTROLLER(0, 0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
+U8500_I2C_CONTROLLER(1, 0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
+U8500_I2C_CONTROLLER(2,	0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
+U8500_I2C_CONTROLLER(3,	0xe, 1, 8, 100000, 200, I2C_FREQ_MODE_FAST);
 
 static void __init mop500_i2c_init(void)
 {
diff --git a/arch/arm/plat-nomadik/include/plat/i2c.h b/arch/arm/plat-nomadik/include/plat/i2c.h
index 1621db67a53d..8ba70ffc31ec 100644
--- a/arch/arm/plat-nomadik/include/plat/i2c.h
+++ b/arch/arm/plat-nomadik/include/plat/i2c.h
@@ -11,8 +11,8 @@
 enum i2c_freq_mode {
 	I2C_FREQ_MODE_STANDARD,		/* up to 100 Kb/s */
 	I2C_FREQ_MODE_FAST,		/* up to 400 Kb/s */
+	I2C_FREQ_MODE_HIGH_SPEED,	/* up to 3.4 Mb/s */
 	I2C_FREQ_MODE_FAST_PLUS,	/* up to 1 Mb/s */
-	I2C_FREQ_MODE_HIGH_SPEED	/* up to 3.4 Mb/s */
 };
 
 /**
@@ -24,13 +24,15 @@ enum i2c_freq_mode {
  *		to the values of 14, 6, 2 for a 48 MHz i2c clk
  * @tft:	Tx FIFO Threshold in bytes
  * @rft:	Rx FIFO Threshold in bytes
+ * @timeout	Slave response timeout(ms)
  * @sm:		speed mode
  */
 struct nmk_i2c_controller {
 	unsigned long	clk_freq;
 	unsigned short	slsu;
-	unsigned char 	tft;
-	unsigned char 	rft;
+	unsigned char	tft;
+	unsigned char	rft;
+	int timeout;
 	enum i2c_freq_mode	sm;
 };
 
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index 854fa49f1c3e..8d85c8c6f857 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -136,7 +136,7 @@ SECTIONS
 
 	. = ALIGN(16);
 	INIT_DATA_SECTION(16)
-	PERCPU(32, PAGE_SIZE)
+	PERCPU_SECTION(32)
 
 	.exit.data :
 	{
diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S
index 728bbd9e7d4c..a6990cb0f098 100644
--- a/arch/cris/kernel/vmlinux.lds.S
+++ b/arch/cris/kernel/vmlinux.lds.S
@@ -102,7 +102,7 @@ SECTIONS
 #endif
 	__vmlinux_end = .;		/* Last address of the physical file. */
 #ifdef CONFIG_ETRAX_ARCH_V32
-	PERCPU(32, PAGE_SIZE)
+	PERCPU_SECTION(32)
 
 	.init.ramfs : {
 		INIT_RAM_FS
diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S
index 0daae8af5787..7e958d829ec9 100644
--- a/arch/frv/kernel/vmlinux.lds.S
+++ b/arch/frv/kernel/vmlinux.lds.S
@@ -37,7 +37,7 @@ SECTIONS
   _einittext = .;
 
   INIT_DATA_SECTION(8)
-  PERCPU(L1_CACHE_BYTES, 4096)
+  PERCPU_SECTION(L1_CACHE_BYTES)
 
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S
index cf95aec77460..018e4a711d79 100644
--- a/arch/m32r/kernel/vmlinux.lds.S
+++ b/arch/m32r/kernel/vmlinux.lds.S
@@ -54,7 +54,7 @@ SECTIONS
   __init_begin = .;
   INIT_TEXT_SECTION(PAGE_SIZE)
   INIT_DATA_SECTION(16)
-  PERCPU(32, PAGE_SIZE)
+  PERCPU_SECTION(32)
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 75531da02a40..d66e34c718d0 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -5,6 +5,7 @@ config M68K
 	select HAVE_AOUT if MMU
 	select GENERIC_ATOMIC64 if MMU
 	select HAVE_GENERIC_HARDIRQS if !MMU
+	select GENERIC_IRQ_SHOW if !MMU
 
 config RWSEM_GENERIC_SPINLOCK
 	bool
diff --git a/arch/m68k/include/asm/bitops_no.h b/arch/m68k/include/asm/bitops_no.h
index 7d3779fdc5b6..6b0e2d349f0e 100644
--- a/arch/m68k/include/asm/bitops_no.h
+++ b/arch/m68k/include/asm/bitops_no.h
@@ -246,23 +246,7 @@ static inline int __test_and_clear_bit_le(int nr, volatile void *addr)
 	return retval;
 }
 
-#define ext2_set_bit_atomic(lock, nr, addr)		\
-	({						\
-		int ret;				\
-		spin_lock(lock);			\
-		ret = __test_and_set_bit_le((nr), (addr));	\
-		spin_unlock(lock);			\
-		ret;					\
-	})
-
-#define ext2_clear_bit_atomic(lock, nr, addr)		\
-	({						\
-		int ret;				\
-		spin_lock(lock);			\
-		ret = __test_and_clear_bit_le((nr), (addr));	\
-		spin_unlock(lock);			\
-		ret;					\
-	})
+#include <asm-generic/bitops/ext2-atomic.h>
 
 static inline int test_bit_le(int nr, const volatile void *addr)
 {
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index cf20f3097af6..353bf754a972 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -144,8 +144,10 @@ static inline void io_insl(unsigned int addr, void *buf, int len)
 #define IOMAP_NOCACHE_NONSER		2
 #define IOMAP_WRITETHROUGH		3
 
-extern void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag);
-
+static inline void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
+{
+	return (void *) physaddr;
+}
 static inline void *ioremap(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
@@ -163,7 +165,7 @@ static inline void *ioremap_fullcache(unsigned long physaddr, unsigned long size
 	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
 }
 
-extern void iounmap(void *addr);
+#define	iounmap(addr)	do { } while(0)
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/m68k/kernel/asm-offsets.c b/arch/m68k/kernel/asm-offsets.c
index 59a69a5c62f2..983fed9d469b 100644
--- a/arch/m68k/kernel/asm-offsets.c
+++ b/arch/m68k/kernel/asm-offsets.c
@@ -1,5 +1,105 @@
-#ifdef CONFIG_MMU
-#include "asm-offsets_mm.c"
+/*
+ * This program is used to generate definitions needed by
+ * assembly language modules.
+ *
+ * We use the technique used in the OSF Mach kernel code:
+ * generate asm statements containing #defines,
+ * compile this file to assembler, and then extract the
+ * #defines from the assembly-language output.
+ */
+
+#define ASM_OFFSETS_C
+
+#include <linux/stddef.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/kbuild.h>
+#include <asm/bootinfo.h>
+#include <asm/irq.h>
+#include <asm/amigahw.h>
+#include <linux/font.h>
+
+int main(void)
+{
+	/* offsets into the task struct */
+	DEFINE(TASK_THREAD, offsetof(struct task_struct, thread));
+	DEFINE(TASK_MM, offsetof(struct task_struct, mm));
+	DEFINE(TASK_INFO, offsetof(struct task_struct, thread.info));
+	DEFINE(TASK_TINFO, offsetof(struct task_struct, thread.info));
+
+	/* offsets into the thread struct */
+	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
+	DEFINE(THREAD_USP, offsetof(struct thread_struct, usp));
+	DEFINE(THREAD_SR, offsetof(struct thread_struct, sr));
+	DEFINE(THREAD_FS, offsetof(struct thread_struct, fs));
+	DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp));
+	DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0));
+	DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp));
+	DEFINE(THREAD_FPCNTL, offsetof(struct thread_struct, fpcntl));
+	DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fpstate));
+
+	/* offsets into the thread_info struct */
+	DEFINE(TINFO_PREEMPT, offsetof(struct thread_info, preempt_count));
+	DEFINE(TINFO_FLAGS, offsetof(struct thread_info, flags));
+
+	/* offsets into the pt_regs */
+	DEFINE(PT_OFF_D0, offsetof(struct pt_regs, d0));
+	DEFINE(PT_OFF_ORIG_D0, offsetof(struct pt_regs, orig_d0));
+	DEFINE(PT_OFF_D1, offsetof(struct pt_regs, d1));
+	DEFINE(PT_OFF_D2, offsetof(struct pt_regs, d2));
+	DEFINE(PT_OFF_D3, offsetof(struct pt_regs, d3));
+	DEFINE(PT_OFF_D4, offsetof(struct pt_regs, d4));
+	DEFINE(PT_OFF_D5, offsetof(struct pt_regs, d5));
+	DEFINE(PT_OFF_A0, offsetof(struct pt_regs, a0));
+	DEFINE(PT_OFF_A1, offsetof(struct pt_regs, a1));
+	DEFINE(PT_OFF_A2, offsetof(struct pt_regs, a2));
+	DEFINE(PT_OFF_PC, offsetof(struct pt_regs, pc));
+	DEFINE(PT_OFF_SR, offsetof(struct pt_regs, sr));
+
+	/* bitfields are a bit difficult */
+#ifdef CONFIG_COLDFIRE
+	DEFINE(PT_OFF_FORMATVEC, offsetof(struct pt_regs, sr) - 2);
 #else
-#include "asm-offsets_no.c"
+	DEFINE(PT_OFF_FORMATVEC, offsetof(struct pt_regs, pc) + 4);
+#endif
+
+	/* offsets into the irq_cpustat_t struct */
+	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
+
+	/* signal defines */
+	DEFINE(LSIGSEGV, SIGSEGV);
+	DEFINE(LSEGV_MAPERR, SEGV_MAPERR);
+	DEFINE(LSIGTRAP, SIGTRAP);
+	DEFINE(LTRAP_TRACE, TRAP_TRACE);
+
+#ifdef CONFIG_MMU
+	/* offsets into the bi_record struct */
+	DEFINE(BIR_TAG, offsetof(struct bi_record, tag));
+	DEFINE(BIR_SIZE, offsetof(struct bi_record, size));
+	DEFINE(BIR_DATA, offsetof(struct bi_record, data));
+
+	/* offsets into font_desc (drivers/video/console/font.h) */
+	DEFINE(FONT_DESC_IDX, offsetof(struct font_desc, idx));
+	DEFINE(FONT_DESC_NAME, offsetof(struct font_desc, name));
+	DEFINE(FONT_DESC_WIDTH, offsetof(struct font_desc, width));
+	DEFINE(FONT_DESC_HEIGHT, offsetof(struct font_desc, height));
+	DEFINE(FONT_DESC_DATA, offsetof(struct font_desc, data));
+	DEFINE(FONT_DESC_PREF, offsetof(struct font_desc, pref));
+
+	/* offsets into the custom struct */
+	DEFINE(CUSTOMBASE, &amiga_custom);
+	DEFINE(C_INTENAR, offsetof(struct CUSTOM, intenar));
+	DEFINE(C_INTREQR, offsetof(struct CUSTOM, intreqr));
+	DEFINE(C_INTENA, offsetof(struct CUSTOM, intena));
+	DEFINE(C_INTREQ, offsetof(struct CUSTOM, intreq));
+	DEFINE(C_SERDATR, offsetof(struct CUSTOM, serdatr));
+	DEFINE(C_SERDAT, offsetof(struct CUSTOM, serdat));
+	DEFINE(C_SERPER, offsetof(struct CUSTOM, serper));
+	DEFINE(CIAABASE, &ciaa);
+	DEFINE(CIABBASE, &ciab);
+	DEFINE(C_PRA, offsetof(struct CIA, pra));
+	DEFINE(ZTWOBASE, zTwoBase);
 #endif
+
+	return 0;
+}
diff --git a/arch/m68k/kernel/asm-offsets_mm.c b/arch/m68k/kernel/asm-offsets_mm.c
deleted file mode 100644
index 78e59b82ebc3..000000000000
--- a/arch/m68k/kernel/asm-offsets_mm.c
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * This program is used to generate definitions needed by
- * assembly language modules.
- *
- * We use the technique used in the OSF Mach kernel code:
- * generate asm statements containing #defines,
- * compile this file to assembler, and then extract the
- * #defines from the assembly-language output.
- */
-
-#define ASM_OFFSETS_C
-
-#include <linux/stddef.h>
-#include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/kbuild.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/amigahw.h>
-#include <linux/font.h>
-
-int main(void)
-{
-	/* offsets into the task struct */
-	DEFINE(TASK_THREAD, offsetof(struct task_struct, thread));
-	DEFINE(TASK_INFO, offsetof(struct task_struct, thread.info));
-	DEFINE(TASK_MM, offsetof(struct task_struct, mm));
-#ifdef CONFIG_MMU
-	DEFINE(TASK_TINFO, offsetof(struct task_struct, thread.info));
-#endif
-
-	/* offsets into the thread struct */
-	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(THREAD_USP, offsetof(struct thread_struct, usp));
-	DEFINE(THREAD_SR, offsetof(struct thread_struct, sr));
-	DEFINE(THREAD_FS, offsetof(struct thread_struct, fs));
-	DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp));
-	DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0));
-	DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp));
-	DEFINE(THREAD_FPCNTL, offsetof(struct thread_struct, fpcntl));
-	DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fpstate));
-
-	/* offsets into the thread_info struct */
-	DEFINE(TINFO_PREEMPT, offsetof(struct thread_info, preempt_count));
-	DEFINE(TINFO_FLAGS, offsetof(struct thread_info, flags));
-
-	/* offsets into the pt_regs */
-	DEFINE(PT_OFF_D0, offsetof(struct pt_regs, d0));
-	DEFINE(PT_OFF_ORIG_D0, offsetof(struct pt_regs, orig_d0));
-	DEFINE(PT_OFF_D1, offsetof(struct pt_regs, d1));
-	DEFINE(PT_OFF_D2, offsetof(struct pt_regs, d2));
-	DEFINE(PT_OFF_D3, offsetof(struct pt_regs, d3));
-	DEFINE(PT_OFF_D4, offsetof(struct pt_regs, d4));
-	DEFINE(PT_OFF_D5, offsetof(struct pt_regs, d5));
-	DEFINE(PT_OFF_A0, offsetof(struct pt_regs, a0));
-	DEFINE(PT_OFF_A1, offsetof(struct pt_regs, a1));
-	DEFINE(PT_OFF_A2, offsetof(struct pt_regs, a2));
-	DEFINE(PT_OFF_PC, offsetof(struct pt_regs, pc));
-	DEFINE(PT_OFF_SR, offsetof(struct pt_regs, sr));
-	/* bitfields are a bit difficult */
-	DEFINE(PT_OFF_FORMATVEC, offsetof(struct pt_regs, pc) + 4);
-
-	/* offsets into the irq_cpustat_t struct */
-	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
-
-	/* offsets into the bi_record struct */
-	DEFINE(BIR_TAG, offsetof(struct bi_record, tag));
-	DEFINE(BIR_SIZE, offsetof(struct bi_record, size));
-	DEFINE(BIR_DATA, offsetof(struct bi_record, data));
-
-	/* offsets into font_desc (drivers/video/console/font.h) */
-	DEFINE(FONT_DESC_IDX, offsetof(struct font_desc, idx));
-	DEFINE(FONT_DESC_NAME, offsetof(struct font_desc, name));
-	DEFINE(FONT_DESC_WIDTH, offsetof(struct font_desc, width));
-	DEFINE(FONT_DESC_HEIGHT, offsetof(struct font_desc, height));
-	DEFINE(FONT_DESC_DATA, offsetof(struct font_desc, data));
-	DEFINE(FONT_DESC_PREF, offsetof(struct font_desc, pref));
-
-	/* signal defines */
-	DEFINE(LSIGSEGV, SIGSEGV);
-	DEFINE(LSEGV_MAPERR, SEGV_MAPERR);
-	DEFINE(LSIGTRAP, SIGTRAP);
-	DEFINE(LTRAP_TRACE, TRAP_TRACE);
-
-	/* offsets into the custom struct */
-	DEFINE(CUSTOMBASE, &amiga_custom);
-	DEFINE(C_INTENAR, offsetof(struct CUSTOM, intenar));
-	DEFINE(C_INTREQR, offsetof(struct CUSTOM, intreqr));
-	DEFINE(C_INTENA, offsetof(struct CUSTOM, intena));
-	DEFINE(C_INTREQ, offsetof(struct CUSTOM, intreq));
-	DEFINE(C_SERDATR, offsetof(struct CUSTOM, serdatr));
-	DEFINE(C_SERDAT, offsetof(struct CUSTOM, serdat));
-	DEFINE(C_SERPER, offsetof(struct CUSTOM, serper));
-	DEFINE(CIAABASE, &ciaa);
-	DEFINE(CIABBASE, &ciab);
-	DEFINE(C_PRA, offsetof(struct CIA, pra));
-	DEFINE(ZTWOBASE, zTwoBase);
-
-	return 0;
-}
diff --git a/arch/m68k/kernel/asm-offsets_no.c b/arch/m68k/kernel/asm-offsets_no.c
deleted file mode 100644
index ffe02f41ad46..000000000000
--- a/arch/m68k/kernel/asm-offsets_no.c
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * This program is used to generate definitions needed by
- * assembly language modules.
- *
- * We use the technique used in the OSF Mach kernel code:
- * generate asm statements containing #defines,
- * compile this file to assembler, and then extract the
- * #defines from the assembly-language output.
- */
-
-#include <linux/stddef.h>
-#include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/ptrace.h>
-#include <linux/hardirq.h>
-#include <linux/kbuild.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/thread_info.h>
-
-int main(void)
-{
-	/* offsets into the task struct */
-	DEFINE(TASK_THREAD, offsetof(struct task_struct, thread));
-	DEFINE(TASK_MM, offsetof(struct task_struct, mm));
-
-	/* offsets into the irq_cpustat_t struct */
-	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
-
-	/* offsets into the thread struct */
-	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(THREAD_USP, offsetof(struct thread_struct, usp));
-	DEFINE(THREAD_SR, offsetof(struct thread_struct, sr));
-	DEFINE(THREAD_FS, offsetof(struct thread_struct, fs));
-	DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp));
-	DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0));
-	DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp));
-	DEFINE(THREAD_FPCNTL, offsetof(struct thread_struct, fpcntl));
-	DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fpstate));
-
-	/* offsets into the pt_regs */
-	DEFINE(PT_OFF_D0, offsetof(struct pt_regs, d0));
-	DEFINE(PT_OFF_ORIG_D0, offsetof(struct pt_regs, orig_d0));
-	DEFINE(PT_OFF_D1, offsetof(struct pt_regs, d1));
-	DEFINE(PT_OFF_D2, offsetof(struct pt_regs, d2));
-	DEFINE(PT_OFF_D3, offsetof(struct pt_regs, d3));
-	DEFINE(PT_OFF_D4, offsetof(struct pt_regs, d4));
-	DEFINE(PT_OFF_D5, offsetof(struct pt_regs, d5));
-	DEFINE(PT_OFF_A0, offsetof(struct pt_regs, a0));
-	DEFINE(PT_OFF_A1, offsetof(struct pt_regs, a1));
-	DEFINE(PT_OFF_A2, offsetof(struct pt_regs, a2));
-	DEFINE(PT_OFF_PC, offsetof(struct pt_regs, pc));
-	DEFINE(PT_OFF_SR, offsetof(struct pt_regs, sr));
-
-#ifdef CONFIG_COLDFIRE
-	/* bitfields are a bit difficult */
-	DEFINE(PT_OFF_FORMATVEC, offsetof(struct pt_regs, sr) - 2);
-#else
-	/* bitfields are a bit difficult */
-	DEFINE(PT_OFF_FORMATVEC, offsetof(struct pt_regs, pc) + 4);
-#endif
-
-	/* signal defines */
-	DEFINE(SIGSEGV, SIGSEGV);
-	DEFINE(SEGV_MAPERR, SEGV_MAPERR);
-	DEFINE(SIGTRAP, SIGTRAP);
-	DEFINE(TRAP_TRACE, TRAP_TRACE);
-
-	DEFINE(PT_PTRACED, PT_PTRACED);
-
-	/* Offsets in thread_info structure */
-	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
-	DEFINE(TI_PREEMPTCOUNT, offsetof(struct thread_info, preempt_count));
-
-	return 0;
-}
diff --git a/arch/m68k/kernel/entry_no.S b/arch/m68k/kernel/entry_no.S
index 2783f25e38bd..5f0f6b598b5a 100644
--- a/arch/m68k/kernel/entry_no.S
+++ b/arch/m68k/kernel/entry_no.S
@@ -24,7 +24,6 @@
  * linux 2.4 support David McCullough <davidm@snapgear.com>
  */
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/setup.h>
diff --git a/arch/m68k/kernel/irq.c b/arch/m68k/kernel/irq.c
index 15dbc3e9d20c..544b8717d499 100644
--- a/arch/m68k/kernel/irq.c
+++ b/arch/m68k/kernel/irq.c
@@ -28,31 +28,3 @@ asmlinkage void do_IRQ(int irq, struct pt_regs *regs)
 
 	set_irq_regs(oldregs);
 }
-
-int show_interrupts(struct seq_file *p, void *v)
-{
-	struct irqaction *ap;
-	int irq = *((loff_t *) v);
-
-	if (irq == 0)
-		seq_puts(p, "           CPU0\n");
-
-	if (irq < NR_IRQS) {
-		struct irq_desc *desc = irq_to_desc(irq);
-
-		ap = desc->action;
-		if (ap) {
-			seq_printf(p, "%3d: ", irq);
-			seq_printf(p, "%10u ", kstat_irqs(irq));
-			seq_printf(p, "%14s  ", irq_desc_get_chip(desc)->name);
-
-			seq_printf(p, "%s", ap->name);
-			for (ap = ap->next; ap; ap = ap->next)
-				seq_printf(p, ", %s", ap->name);
-			seq_putc(p, '\n');
-		}
-	}
-
-	return 0;
-}
-
diff --git a/arch/m68k/kernel/m68k_ksyms.c b/arch/m68k/kernel/m68k_ksyms.c
index 4752c28ce0ac..33f82769547c 100644
--- a/arch/m68k/kernel/m68k_ksyms.c
+++ b/arch/m68k/kernel/m68k_ksyms.c
@@ -1,5 +1,33 @@
-#ifdef CONFIG_MMU
-#include "m68k_ksyms_mm.c"
-#else
-#include "m68k_ksyms_no.c"
+#include <linux/module.h>
+
+asmlinkage long long __ashldi3 (long long, int);
+asmlinkage long long __ashrdi3 (long long, int);
+asmlinkage long long __lshrdi3 (long long, int);
+asmlinkage long long __muldi3 (long long, long long);
+
+/* The following are special because they're not called
+   explicitly (the C compiler generates them).  Fortunately,
+   their interface isn't gonna change any time soon now, so
+   it's OK to leave it out of version control.  */
+EXPORT_SYMBOL(__ashldi3);
+EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__lshrdi3);
+EXPORT_SYMBOL(__muldi3);
+
+#if !defined(__mc68020__) && !defined(__mc68030__) && \
+    !defined(__mc68040__) && !defined(__mc68060__) && !defined(__mcpu32__)
+/*
+ * Simpler 68k and ColdFire parts also need a few other gcc functions.
+ */
+extern long long __divsi3(long long, long long);
+extern long long __modsi3(long long, long long);
+extern long long __mulsi3(long long, long long);
+extern long long __udivsi3(long long, long long);
+extern long long __umodsi3(long long, long long);
+
+EXPORT_SYMBOL(__divsi3);
+EXPORT_SYMBOL(__modsi3);
+EXPORT_SYMBOL(__mulsi3);
+EXPORT_SYMBOL(__udivsi3);
+EXPORT_SYMBOL(__umodsi3);
 #endif
diff --git a/arch/m68k/kernel/m68k_ksyms_mm.c b/arch/m68k/kernel/m68k_ksyms_mm.c
deleted file mode 100644
index d900e77e5363..000000000000
--- a/arch/m68k/kernel/m68k_ksyms_mm.c
+++ /dev/null
@@ -1,16 +0,0 @@
-#include <linux/module.h>
-
-asmlinkage long long __ashldi3 (long long, int);
-asmlinkage long long __ashrdi3 (long long, int);
-asmlinkage long long __lshrdi3 (long long, int);
-asmlinkage long long __muldi3 (long long, long long);
-
-/* The following are special because they're not called
-   explicitly (the C compiler generates them).  Fortunately,
-   their interface isn't gonna change any time soon now, so
-   it's OK to leave it out of version control.  */
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__muldi3);
-
diff --git a/arch/m68k/kernel/m68k_ksyms_no.c b/arch/m68k/kernel/m68k_ksyms_no.c
deleted file mode 100644
index 39fe0a7aec32..000000000000
--- a/arch/m68k/kernel/m68k_ksyms_no.c
+++ /dev/null
@@ -1,78 +0,0 @@
-#include <linux/module.h>
-#include <linux/linkage.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/user.h>
-#include <linux/elfcore.h>
-#include <linux/in6.h>
-#include <linux/interrupt.h>
-
-#include <asm/setup.h>
-#include <asm/machdep.h>
-#include <asm/pgalloc.h>
-#include <asm/irq.h>
-#include <asm/io.h>
-#include <asm/checksum.h>
-#include <asm/current.h>
-
-extern int dump_fpu(struct pt_regs *, elf_fpregset_t *);
-
-/* platform dependent support */
-
-EXPORT_SYMBOL(__ioremap);
-EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(dump_fpu);
-
-EXPORT_SYMBOL(ip_fast_csum);
-
-EXPORT_SYMBOL(kernel_thread);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-
-/* The following are special because they're not called
-   explicitly (the C compiler generates them).  Fortunately,
-   their interface isn't gonna change any time soon now, so
-   it's OK to leave it out of version control.  */
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-
-/*
- * libgcc functions - functions that are used internally by the
- * compiler...  (prototypes are not correct though, but that
- * doesn't really matter since they're not versioned).
- */
-extern void __ashldi3(void);
-extern void __ashrdi3(void);
-extern void __divsi3(void);
-extern void __lshrdi3(void);
-extern void __modsi3(void);
-extern void __muldi3(void);
-extern void __mulsi3(void);
-extern void __udivsi3(void);
-extern void __umodsi3(void);
-
-        /* gcc lib functions */
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__divsi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__muldi3);
-EXPORT_SYMBOL(__mulsi3);
-EXPORT_SYMBOL(__udivsi3);
-EXPORT_SYMBOL(__umodsi3);
-
-#ifdef CONFIG_COLDFIRE
-extern unsigned int *dma_device_address;
-extern unsigned long dma_base_addr, _ramend;
-EXPORT_SYMBOL(dma_base_addr);
-EXPORT_SYMBOL(dma_device_address);
-EXPORT_SYMBOL(_ramend);
-
-extern asmlinkage void trap(void);
-extern void	*_ramvec;
-EXPORT_SYMBOL(trap);
-EXPORT_SYMBOL(_ramvec);
-#endif /* CONFIG_COLDFIRE */
diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c
index e2a63af5d517..9b86ad11c68e 100644
--- a/arch/m68k/kernel/process_no.c
+++ b/arch/m68k/kernel/process_no.c
@@ -151,6 +151,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 	set_fs(fs);
 	return retval;
 }
+EXPORT_SYMBOL(kernel_thread);
 
 void flush_thread(void)
 {
@@ -283,6 +284,7 @@ int dump_fpu(struct pt_regs *regs, struct user_m68kfp_struct *fpu)
 #endif
 	return 1;
 }
+EXPORT_SYMBOL(dump_fpu);
 
 /*
  *	Generic dumping code. Used for panic and debug.
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 63013df33584..8623f8dc16f8 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -1,5 +1,580 @@
+/*
+ * linux/arch/m68k/kernel/sys_m68k.c
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/m68k
+ * platform.
+ */
+
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/ipc.h>
+
+#include <asm/setup.h>
+#include <asm/uaccess.h>
+#include <asm/cachectl.h>
+#include <asm/traps.h>
+#include <asm/page.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+
 #ifdef CONFIG_MMU
-#include "sys_m68k_mm.c"
+
+#include <asm/tlb.h>
+
+asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address,
+			     unsigned long error_code);
+
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+	unsigned long prot, unsigned long flags,
+	unsigned long fd, unsigned long pgoff)
+{
+	/*
+	 * This is wrong for sun3 - there PAGE_SIZE is 8Kb,
+	 * so we need to shift the argument down by 1; m68k mmap64(3)
+	 * (in libc) expects the last argument of mmap2 in 4Kb units.
+	 */
+	return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
+}
+
+/* Convert virtual (user) address VADDR to physical address PADDR */
+#define virt_to_phys_040(vaddr)						\
+({									\
+  unsigned long _mmusr, _paddr;						\
+									\
+  __asm__ __volatile__ (".chip 68040\n\t"				\
+			"ptestr (%1)\n\t"				\
+			"movec %%mmusr,%0\n\t"				\
+			".chip 68k"					\
+			: "=r" (_mmusr)					\
+			: "a" (vaddr));					\
+  _paddr = (_mmusr & MMU_R_040) ? (_mmusr & PAGE_MASK) : 0;		\
+  _paddr;								\
+})
+
+static inline int
+cache_flush_040 (unsigned long addr, int scope, int cache, unsigned long len)
+{
+  unsigned long paddr, i;
+
+  switch (scope)
+    {
+    case FLUSH_SCOPE_ALL:
+      switch (cache)
+	{
+	case FLUSH_CACHE_DATA:
+	  /* This nop is needed for some broken versions of the 68040.  */
+	  __asm__ __volatile__ ("nop\n\t"
+				".chip 68040\n\t"
+				"cpusha %dc\n\t"
+				".chip 68k");
+	  break;
+	case FLUSH_CACHE_INSN:
+	  __asm__ __volatile__ ("nop\n\t"
+				".chip 68040\n\t"
+				"cpusha %ic\n\t"
+				".chip 68k");
+	  break;
+	default:
+	case FLUSH_CACHE_BOTH:
+	  __asm__ __volatile__ ("nop\n\t"
+				".chip 68040\n\t"
+				"cpusha %bc\n\t"
+				".chip 68k");
+	  break;
+	}
+      break;
+
+    case FLUSH_SCOPE_LINE:
+      /* Find the physical address of the first mapped page in the
+	 address range.  */
+      if ((paddr = virt_to_phys_040(addr))) {
+        paddr += addr & ~(PAGE_MASK | 15);
+        len = (len + (addr & 15) + 15) >> 4;
+      } else {
+	unsigned long tmp = PAGE_SIZE - (addr & ~PAGE_MASK);
+
+	if (len <= tmp)
+	  return 0;
+	addr += tmp;
+	len -= tmp;
+	tmp = PAGE_SIZE;
+	for (;;)
+	  {
+	    if ((paddr = virt_to_phys_040(addr)))
+	      break;
+	    if (len <= tmp)
+	      return 0;
+	    addr += tmp;
+	    len -= tmp;
+	  }
+	len = (len + 15) >> 4;
+      }
+      i = (PAGE_SIZE - (paddr & ~PAGE_MASK)) >> 4;
+      while (len--)
+	{
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushl %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushl %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushl %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	  if (!--i && len)
+	    {
+	      /*
+	       * No need to page align here since it is done by
+	       * virt_to_phys_040().
+	       */
+	      addr += PAGE_SIZE;
+	      i = PAGE_SIZE / 16;
+	      /* Recompute physical address when crossing a page
+	         boundary. */
+	      for (;;)
+		{
+		  if ((paddr = virt_to_phys_040(addr)))
+		    break;
+		  if (len <= i)
+		    return 0;
+		  len -= i;
+		  addr += PAGE_SIZE;
+		}
+	    }
+	  else
+	    paddr += 16;
+	}
+      break;
+
+    default:
+    case FLUSH_SCOPE_PAGE:
+      len += (addr & ~PAGE_MASK) + (PAGE_SIZE - 1);
+      for (len >>= PAGE_SHIFT; len--; addr += PAGE_SIZE)
+	{
+	  if (!(paddr = virt_to_phys_040(addr)))
+	    continue;
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushp %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushp %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushp %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	}
+      break;
+    }
+  return 0;
+}
+
+#define virt_to_phys_060(vaddr)				\
+({							\
+  unsigned long paddr;					\
+  __asm__ __volatile__ (".chip 68060\n\t"		\
+			"plpar (%0)\n\t"		\
+			".chip 68k"			\
+			: "=a" (paddr)			\
+			: "0" (vaddr));			\
+  (paddr); /* XXX */					\
+})
+
+static inline int
+cache_flush_060 (unsigned long addr, int scope, int cache, unsigned long len)
+{
+  unsigned long paddr, i;
+
+  /*
+   * 68060 manual says:
+   *  cpush %dc : flush DC, remains valid (with our %cacr setup)
+   *  cpush %ic : invalidate IC
+   *  cpush %bc : flush DC + invalidate IC
+   */
+  switch (scope)
+    {
+    case FLUSH_SCOPE_ALL:
+      switch (cache)
+	{
+	case FLUSH_CACHE_DATA:
+	  __asm__ __volatile__ (".chip 68060\n\t"
+				"cpusha %dc\n\t"
+				".chip 68k");
+	  break;
+	case FLUSH_CACHE_INSN:
+	  __asm__ __volatile__ (".chip 68060\n\t"
+				"cpusha %ic\n\t"
+				".chip 68k");
+	  break;
+	default:
+	case FLUSH_CACHE_BOTH:
+	  __asm__ __volatile__ (".chip 68060\n\t"
+				"cpusha %bc\n\t"
+				".chip 68k");
+	  break;
+	}
+      break;
+
+    case FLUSH_SCOPE_LINE:
+      /* Find the physical address of the first mapped page in the
+	 address range.  */
+      len += addr & 15;
+      addr &= -16;
+      if (!(paddr = virt_to_phys_060(addr))) {
+	unsigned long tmp = PAGE_SIZE - (addr & ~PAGE_MASK);
+
+	if (len <= tmp)
+	  return 0;
+	addr += tmp;
+	len -= tmp;
+	tmp = PAGE_SIZE;
+	for (;;)
+	  {
+	    if ((paddr = virt_to_phys_060(addr)))
+	      break;
+	    if (len <= tmp)
+	      return 0;
+	    addr += tmp;
+	    len -= tmp;
+	  }
+      }
+      len = (len + 15) >> 4;
+      i = (PAGE_SIZE - (paddr & ~PAGE_MASK)) >> 4;
+      while (len--)
+	{
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushl %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushl %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushl %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	  if (!--i && len)
+	    {
+
+	      /*
+	       * We just want to jump to the first cache line
+	       * in the next page.
+	       */
+	      addr += PAGE_SIZE;
+	      addr &= PAGE_MASK;
+
+	      i = PAGE_SIZE / 16;
+	      /* Recompute physical address when crossing a page
+	         boundary. */
+	      for (;;)
+	        {
+	          if ((paddr = virt_to_phys_060(addr)))
+	            break;
+	          if (len <= i)
+	            return 0;
+	          len -= i;
+	          addr += PAGE_SIZE;
+	        }
+	    }
+	  else
+	    paddr += 16;
+	}
+      break;
+
+    default:
+    case FLUSH_SCOPE_PAGE:
+      len += (addr & ~PAGE_MASK) + (PAGE_SIZE - 1);
+      addr &= PAGE_MASK;	/* Workaround for bug in some
+				   revisions of the 68060 */
+      for (len >>= PAGE_SHIFT; len--; addr += PAGE_SIZE)
+	{
+	  if (!(paddr = virt_to_phys_060(addr)))
+	    continue;
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushp %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushp %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushp %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	}
+      break;
+    }
+  return 0;
+}
+
+/* sys_cacheflush -- flush (part of) the processor cache.  */
+asmlinkage int
+sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
+{
+	struct vm_area_struct *vma;
+	int ret = -EINVAL;
+
+	if (scope < FLUSH_SCOPE_LINE || scope > FLUSH_SCOPE_ALL ||
+	    cache & ~FLUSH_CACHE_BOTH)
+		goto out;
+
+	if (scope == FLUSH_SCOPE_ALL) {
+		/* Only the superuser may explicitly flush the whole cache. */
+		ret = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto out;
+	} else {
+		/*
+		 * Verify that the specified address region actually belongs
+		 * to this process.
+		 */
+		vma = find_vma (current->mm, addr);
+		ret = -EINVAL;
+		/* Check for overflow.  */
+		if (addr + len < addr)
+			goto out;
+		if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end)
+			goto out;
+	}
+
+	if (CPU_IS_020_OR_030) {
+		if (scope == FLUSH_SCOPE_LINE && len < 256) {
+			unsigned long cacr;
+			__asm__ ("movec %%cacr, %0" : "=r" (cacr));
+			if (cache & FLUSH_CACHE_INSN)
+				cacr |= 4;
+			if (cache & FLUSH_CACHE_DATA)
+				cacr |= 0x400;
+			len >>= 2;
+			while (len--) {
+				__asm__ __volatile__ ("movec %1, %%caar\n\t"
+						      "movec %0, %%cacr"
+						      : /* no outputs */
+						      : "r" (cacr), "r" (addr));
+				addr += 4;
+			}
+		} else {
+			/* Flush the whole cache, even if page granularity requested. */
+			unsigned long cacr;
+			__asm__ ("movec %%cacr, %0" : "=r" (cacr));
+			if (cache & FLUSH_CACHE_INSN)
+				cacr |= 8;
+			if (cache & FLUSH_CACHE_DATA)
+				cacr |= 0x800;
+			__asm__ __volatile__ ("movec %0, %%cacr" : : "r" (cacr));
+		}
+		ret = 0;
+		goto out;
+	} else {
+	    /*
+	     * 040 or 060: don't blindly trust 'scope', someone could
+	     * try to flush a few megs of memory.
+	     */
+
+	    if (len>=3*PAGE_SIZE && scope<FLUSH_SCOPE_PAGE)
+	        scope=FLUSH_SCOPE_PAGE;
+	    if (len>=10*PAGE_SIZE && scope<FLUSH_SCOPE_ALL)
+	        scope=FLUSH_SCOPE_ALL;
+	    if (CPU_IS_040) {
+		ret = cache_flush_040 (addr, scope, cache, len);
+	    } else if (CPU_IS_060) {
+		ret = cache_flush_060 (addr, scope, cache, len);
+	    }
+	}
+out:
+	return ret;
+}
+
+/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
+   D1 (newval).  */
+asmlinkage int
+sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
+		      unsigned long __user * mem)
+{
+	/* This was borrowed from ARM's implementation.  */
+	for (;;) {
+		struct mm_struct *mm = current->mm;
+		pgd_t *pgd;
+		pmd_t *pmd;
+		pte_t *pte;
+		spinlock_t *ptl;
+		unsigned long mem_value;
+
+		down_read(&mm->mmap_sem);
+		pgd = pgd_offset(mm, (unsigned long)mem);
+		if (!pgd_present(*pgd))
+			goto bad_access;
+		pmd = pmd_offset(pgd, (unsigned long)mem);
+		if (!pmd_present(*pmd))
+			goto bad_access;
+		pte = pte_offset_map_lock(mm, pmd, (unsigned long)mem, &ptl);
+		if (!pte_present(*pte) || !pte_dirty(*pte)
+		    || !pte_write(*pte)) {
+			pte_unmap_unlock(pte, ptl);
+			goto bad_access;
+		}
+
+		mem_value = *mem;
+		if (mem_value == oldval)
+			*mem = newval;
+
+		pte_unmap_unlock(pte, ptl);
+		up_read(&mm->mmap_sem);
+		return mem_value;
+
+	      bad_access:
+		up_read(&mm->mmap_sem);
+		/* This is not necessarily a bad access, we can get here if
+		   a memory we're trying to write to should be copied-on-write.
+		   Make the kernel do the necessary page stuff, then re-iterate.
+		   Simulate a write access fault to do that.  */
+		{
+			/* The first argument of the function corresponds to
+			   D1, which is the first field of struct pt_regs.  */
+			struct pt_regs *fp = (struct pt_regs *)&newval;
+
+			/* '3' is an RMW flag.  */
+			if (do_page_fault(fp, (unsigned long)mem, 3))
+				/* If the do_page_fault() failed, we don't
+				   have anything meaningful to return.
+				   There should be a SIGSEGV pending for
+				   the process.  */
+				return 0xdeadbeef;
+		}
+	}
+}
+
 #else
-#include "sys_m68k_no.c"
-#endif
+
+/* sys_cacheflush -- flush (part of) the processor cache.  */
+asmlinkage int
+sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
+{
+	flush_cache_all();
+	return 0;
+}
+
+/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
+   D1 (newval).  */
+asmlinkage int
+sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
+		      unsigned long __user * mem)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long mem_value;
+
+	down_read(&mm->mmap_sem);
+
+	mem_value = *mem;
+	if (mem_value == oldval)
+		*mem = newval;
+
+	up_read(&mm->mmap_sem);
+	return mem_value;
+}
+
+#endif /* CONFIG_MMU */
+
+asmlinkage int sys_getpagesize(void)
+{
+	return PAGE_SIZE;
+}
+
+/*
+ * Do a system call from kernel instead of calling sys_execve so we
+ * end up with proper pt_regs.
+ */
+int kernel_execve(const char *filename,
+		  const char *const argv[],
+		  const char *const envp[])
+{
+	register long __res asm ("%d0") = __NR_execve;
+	register long __a asm ("%d1") = (long)(filename);
+	register long __b asm ("%d2") = (long)(argv);
+	register long __c asm ("%d3") = (long)(envp);
+	asm volatile ("trap  #0" : "+d" (__res)
+			: "d" (__a), "d" (__b), "d" (__c));
+	return __res;
+}
+
+asmlinkage unsigned long sys_get_thread_area(void)
+{
+	return current_thread_info()->tp_value;
+}
+
+asmlinkage int sys_set_thread_area(unsigned long tp)
+{
+	current_thread_info()->tp_value = tp;
+	return 0;
+}
+
+asmlinkage int sys_atomic_barrier(void)
+{
+	/* no code needed for uniprocs */
+	return 0;
+}
diff --git a/arch/m68k/kernel/sys_m68k_mm.c b/arch/m68k/kernel/sys_m68k_mm.c
deleted file mode 100644
index 3db2e7f902aa..000000000000
--- a/arch/m68k/kernel/sys_m68k_mm.c
+++ /dev/null
@@ -1,546 +0,0 @@
-/*
- * linux/arch/m68k/kernel/sys_m68k.c
- *
- * This file contains various random system calls that
- * have a non-standard calling sequence on the Linux/m68k
- * platform.
- */
-
-#include <linux/capability.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/smp.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/ipc.h>
-
-#include <asm/setup.h>
-#include <asm/uaccess.h>
-#include <asm/cachectl.h>
-#include <asm/traps.h>
-#include <asm/page.h>
-#include <asm/unistd.h>
-#include <linux/elf.h>
-#include <asm/tlb.h>
-
-asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address,
-			     unsigned long error_code);
-
-asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
-	unsigned long prot, unsigned long flags,
-	unsigned long fd, unsigned long pgoff)
-{
-	/*
-	 * This is wrong for sun3 - there PAGE_SIZE is 8Kb,
-	 * so we need to shift the argument down by 1; m68k mmap64(3)
-	 * (in libc) expects the last argument of mmap2 in 4Kb units.
-	 */
-	return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
-}
-
-/* Convert virtual (user) address VADDR to physical address PADDR */
-#define virt_to_phys_040(vaddr)						\
-({									\
-  unsigned long _mmusr, _paddr;						\
-									\
-  __asm__ __volatile__ (".chip 68040\n\t"				\
-			"ptestr (%1)\n\t"				\
-			"movec %%mmusr,%0\n\t"				\
-			".chip 68k"					\
-			: "=r" (_mmusr)					\
-			: "a" (vaddr));					\
-  _paddr = (_mmusr & MMU_R_040) ? (_mmusr & PAGE_MASK) : 0;		\
-  _paddr;								\
-})
-
-static inline int
-cache_flush_040 (unsigned long addr, int scope, int cache, unsigned long len)
-{
-  unsigned long paddr, i;
-
-  switch (scope)
-    {
-    case FLUSH_SCOPE_ALL:
-      switch (cache)
-	{
-	case FLUSH_CACHE_DATA:
-	  /* This nop is needed for some broken versions of the 68040.  */
-	  __asm__ __volatile__ ("nop\n\t"
-				".chip 68040\n\t"
-				"cpusha %dc\n\t"
-				".chip 68k");
-	  break;
-	case FLUSH_CACHE_INSN:
-	  __asm__ __volatile__ ("nop\n\t"
-				".chip 68040\n\t"
-				"cpusha %ic\n\t"
-				".chip 68k");
-	  break;
-	default:
-	case FLUSH_CACHE_BOTH:
-	  __asm__ __volatile__ ("nop\n\t"
-				".chip 68040\n\t"
-				"cpusha %bc\n\t"
-				".chip 68k");
-	  break;
-	}
-      break;
-
-    case FLUSH_SCOPE_LINE:
-      /* Find the physical address of the first mapped page in the
-	 address range.  */
-      if ((paddr = virt_to_phys_040(addr))) {
-        paddr += addr & ~(PAGE_MASK | 15);
-        len = (len + (addr & 15) + 15) >> 4;
-      } else {
-	unsigned long tmp = PAGE_SIZE - (addr & ~PAGE_MASK);
-
-	if (len <= tmp)
-	  return 0;
-	addr += tmp;
-	len -= tmp;
-	tmp = PAGE_SIZE;
-	for (;;)
-	  {
-	    if ((paddr = virt_to_phys_040(addr)))
-	      break;
-	    if (len <= tmp)
-	      return 0;
-	    addr += tmp;
-	    len -= tmp;
-	  }
-	len = (len + 15) >> 4;
-      }
-      i = (PAGE_SIZE - (paddr & ~PAGE_MASK)) >> 4;
-      while (len--)
-	{
-	  switch (cache)
-	    {
-	    case FLUSH_CACHE_DATA:
-	      __asm__ __volatile__ ("nop\n\t"
-				    ".chip 68040\n\t"
-				    "cpushl %%dc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    case FLUSH_CACHE_INSN:
-	      __asm__ __volatile__ ("nop\n\t"
-				    ".chip 68040\n\t"
-				    "cpushl %%ic,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    default:
-	    case FLUSH_CACHE_BOTH:
-	      __asm__ __volatile__ ("nop\n\t"
-				    ".chip 68040\n\t"
-				    "cpushl %%bc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    }
-	  if (!--i && len)
-	    {
-	      /*
-	       * No need to page align here since it is done by
-	       * virt_to_phys_040().
-	       */
-	      addr += PAGE_SIZE;
-	      i = PAGE_SIZE / 16;
-	      /* Recompute physical address when crossing a page
-	         boundary. */
-	      for (;;)
-		{
-		  if ((paddr = virt_to_phys_040(addr)))
-		    break;
-		  if (len <= i)
-		    return 0;
-		  len -= i;
-		  addr += PAGE_SIZE;
-		}
-	    }
-	  else
-	    paddr += 16;
-	}
-      break;
-
-    default:
-    case FLUSH_SCOPE_PAGE:
-      len += (addr & ~PAGE_MASK) + (PAGE_SIZE - 1);
-      for (len >>= PAGE_SHIFT; len--; addr += PAGE_SIZE)
-	{
-	  if (!(paddr = virt_to_phys_040(addr)))
-	    continue;
-	  switch (cache)
-	    {
-	    case FLUSH_CACHE_DATA:
-	      __asm__ __volatile__ ("nop\n\t"
-				    ".chip 68040\n\t"
-				    "cpushp %%dc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    case FLUSH_CACHE_INSN:
-	      __asm__ __volatile__ ("nop\n\t"
-				    ".chip 68040\n\t"
-				    "cpushp %%ic,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    default:
-	    case FLUSH_CACHE_BOTH:
-	      __asm__ __volatile__ ("nop\n\t"
-				    ".chip 68040\n\t"
-				    "cpushp %%bc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    }
-	}
-      break;
-    }
-  return 0;
-}
-
-#define virt_to_phys_060(vaddr)				\
-({							\
-  unsigned long paddr;					\
-  __asm__ __volatile__ (".chip 68060\n\t"		\
-			"plpar (%0)\n\t"		\
-			".chip 68k"			\
-			: "=a" (paddr)			\
-			: "0" (vaddr));			\
-  (paddr); /* XXX */					\
-})
-
-static inline int
-cache_flush_060 (unsigned long addr, int scope, int cache, unsigned long len)
-{
-  unsigned long paddr, i;
-
-  /*
-   * 68060 manual says:
-   *  cpush %dc : flush DC, remains valid (with our %cacr setup)
-   *  cpush %ic : invalidate IC
-   *  cpush %bc : flush DC + invalidate IC
-   */
-  switch (scope)
-    {
-    case FLUSH_SCOPE_ALL:
-      switch (cache)
-	{
-	case FLUSH_CACHE_DATA:
-	  __asm__ __volatile__ (".chip 68060\n\t"
-				"cpusha %dc\n\t"
-				".chip 68k");
-	  break;
-	case FLUSH_CACHE_INSN:
-	  __asm__ __volatile__ (".chip 68060\n\t"
-				"cpusha %ic\n\t"
-				".chip 68k");
-	  break;
-	default:
-	case FLUSH_CACHE_BOTH:
-	  __asm__ __volatile__ (".chip 68060\n\t"
-				"cpusha %bc\n\t"
-				".chip 68k");
-	  break;
-	}
-      break;
-
-    case FLUSH_SCOPE_LINE:
-      /* Find the physical address of the first mapped page in the
-	 address range.  */
-      len += addr & 15;
-      addr &= -16;
-      if (!(paddr = virt_to_phys_060(addr))) {
-	unsigned long tmp = PAGE_SIZE - (addr & ~PAGE_MASK);
-
-	if (len <= tmp)
-	  return 0;
-	addr += tmp;
-	len -= tmp;
-	tmp = PAGE_SIZE;
-	for (;;)
-	  {
-	    if ((paddr = virt_to_phys_060(addr)))
-	      break;
-	    if (len <= tmp)
-	      return 0;
-	    addr += tmp;
-	    len -= tmp;
-	  }
-      }
-      len = (len + 15) >> 4;
-      i = (PAGE_SIZE - (paddr & ~PAGE_MASK)) >> 4;
-      while (len--)
-	{
-	  switch (cache)
-	    {
-	    case FLUSH_CACHE_DATA:
-	      __asm__ __volatile__ (".chip 68060\n\t"
-				    "cpushl %%dc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    case FLUSH_CACHE_INSN:
-	      __asm__ __volatile__ (".chip 68060\n\t"
-				    "cpushl %%ic,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    default:
-	    case FLUSH_CACHE_BOTH:
-	      __asm__ __volatile__ (".chip 68060\n\t"
-				    "cpushl %%bc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    }
-	  if (!--i && len)
-	    {
-
-	      /*
-	       * We just want to jump to the first cache line
-	       * in the next page.
-	       */
-	      addr += PAGE_SIZE;
-	      addr &= PAGE_MASK;
-
-	      i = PAGE_SIZE / 16;
-	      /* Recompute physical address when crossing a page
-	         boundary. */
-	      for (;;)
-	        {
-	          if ((paddr = virt_to_phys_060(addr)))
-	            break;
-	          if (len <= i)
-	            return 0;
-	          len -= i;
-	          addr += PAGE_SIZE;
-	        }
-	    }
-	  else
-	    paddr += 16;
-	}
-      break;
-
-    default:
-    case FLUSH_SCOPE_PAGE:
-      len += (addr & ~PAGE_MASK) + (PAGE_SIZE - 1);
-      addr &= PAGE_MASK;	/* Workaround for bug in some
-				   revisions of the 68060 */
-      for (len >>= PAGE_SHIFT; len--; addr += PAGE_SIZE)
-	{
-	  if (!(paddr = virt_to_phys_060(addr)))
-	    continue;
-	  switch (cache)
-	    {
-	    case FLUSH_CACHE_DATA:
-	      __asm__ __volatile__ (".chip 68060\n\t"
-				    "cpushp %%dc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    case FLUSH_CACHE_INSN:
-	      __asm__ __volatile__ (".chip 68060\n\t"
-				    "cpushp %%ic,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    default:
-	    case FLUSH_CACHE_BOTH:
-	      __asm__ __volatile__ (".chip 68060\n\t"
-				    "cpushp %%bc,(%0)\n\t"
-				    ".chip 68k"
-				    : : "a" (paddr));
-	      break;
-	    }
-	}
-      break;
-    }
-  return 0;
-}
-
-/* sys_cacheflush -- flush (part of) the processor cache.  */
-asmlinkage int
-sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
-{
-	struct vm_area_struct *vma;
-	int ret = -EINVAL;
-
-	if (scope < FLUSH_SCOPE_LINE || scope > FLUSH_SCOPE_ALL ||
-	    cache & ~FLUSH_CACHE_BOTH)
-		goto out;
-
-	if (scope == FLUSH_SCOPE_ALL) {
-		/* Only the superuser may explicitly flush the whole cache. */
-		ret = -EPERM;
-		if (!capable(CAP_SYS_ADMIN))
-			goto out;
-	} else {
-		/*
-		 * Verify that the specified address region actually belongs
-		 * to this process.
-		 */
-		vma = find_vma (current->mm, addr);
-		ret = -EINVAL;
-		/* Check for overflow.  */
-		if (addr + len < addr)
-			goto out;
-		if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end)
-			goto out;
-	}
-
-	if (CPU_IS_020_OR_030) {
-		if (scope == FLUSH_SCOPE_LINE && len < 256) {
-			unsigned long cacr;
-			__asm__ ("movec %%cacr, %0" : "=r" (cacr));
-			if (cache & FLUSH_CACHE_INSN)
-				cacr |= 4;
-			if (cache & FLUSH_CACHE_DATA)
-				cacr |= 0x400;
-			len >>= 2;
-			while (len--) {
-				__asm__ __volatile__ ("movec %1, %%caar\n\t"
-						      "movec %0, %%cacr"
-						      : /* no outputs */
-						      : "r" (cacr), "r" (addr));
-				addr += 4;
-			}
-		} else {
-			/* Flush the whole cache, even if page granularity requested. */
-			unsigned long cacr;
-			__asm__ ("movec %%cacr, %0" : "=r" (cacr));
-			if (cache & FLUSH_CACHE_INSN)
-				cacr |= 8;
-			if (cache & FLUSH_CACHE_DATA)
-				cacr |= 0x800;
-			__asm__ __volatile__ ("movec %0, %%cacr" : : "r" (cacr));
-		}
-		ret = 0;
-		goto out;
-	} else {
-	    /*
-	     * 040 or 060: don't blindly trust 'scope', someone could
-	     * try to flush a few megs of memory.
-	     */
-
-	    if (len>=3*PAGE_SIZE && scope<FLUSH_SCOPE_PAGE)
-	        scope=FLUSH_SCOPE_PAGE;
-	    if (len>=10*PAGE_SIZE && scope<FLUSH_SCOPE_ALL)
-	        scope=FLUSH_SCOPE_ALL;
-	    if (CPU_IS_040) {
-		ret = cache_flush_040 (addr, scope, cache, len);
-	    } else if (CPU_IS_060) {
-		ret = cache_flush_060 (addr, scope, cache, len);
-	    }
-	}
-out:
-	return ret;
-}
-
-asmlinkage int sys_getpagesize(void)
-{
-	return PAGE_SIZE;
-}
-
-/*
- * Do a system call from kernel instead of calling sys_execve so we
- * end up with proper pt_regs.
- */
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	register long __res asm ("%d0") = __NR_execve;
-	register long __a asm ("%d1") = (long)(filename);
-	register long __b asm ("%d2") = (long)(argv);
-	register long __c asm ("%d3") = (long)(envp);
-	asm volatile ("trap  #0" : "+d" (__res)
-			: "d" (__a), "d" (__b), "d" (__c));
-	return __res;
-}
-
-asmlinkage unsigned long sys_get_thread_area(void)
-{
-	return current_thread_info()->tp_value;
-}
-
-asmlinkage int sys_set_thread_area(unsigned long tp)
-{
-	current_thread_info()->tp_value = tp;
-	return 0;
-}
-
-/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
-   D1 (newval).  */
-asmlinkage int
-sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
-		      unsigned long __user * mem)
-{
-	/* This was borrowed from ARM's implementation.  */
-	for (;;) {
-		struct mm_struct *mm = current->mm;
-		pgd_t *pgd;
-		pmd_t *pmd;
-		pte_t *pte;
-		spinlock_t *ptl;
-		unsigned long mem_value;
-
-		down_read(&mm->mmap_sem);
-		pgd = pgd_offset(mm, (unsigned long)mem);
-		if (!pgd_present(*pgd))
-			goto bad_access;
-		pmd = pmd_offset(pgd, (unsigned long)mem);
-		if (!pmd_present(*pmd))
-			goto bad_access;
-		pte = pte_offset_map_lock(mm, pmd, (unsigned long)mem, &ptl);
-		if (!pte_present(*pte) || !pte_dirty(*pte)
-		    || !pte_write(*pte)) {
-			pte_unmap_unlock(pte, ptl);
-			goto bad_access;
-		}
-
-		mem_value = *mem;
-		if (mem_value == oldval)
-			*mem = newval;
-
-		pte_unmap_unlock(pte, ptl);
-		up_read(&mm->mmap_sem);
-		return mem_value;
-
-	      bad_access:
-		up_read(&mm->mmap_sem);
-		/* This is not necessarily a bad access, we can get here if
-		   a memory we're trying to write to should be copied-on-write.
-		   Make the kernel do the necessary page stuff, then re-iterate.
-		   Simulate a write access fault to do that.  */
-		{
-			/* The first argument of the function corresponds to
-			   D1, which is the first field of struct pt_regs.  */
-			struct pt_regs *fp = (struct pt_regs *)&newval;
-
-			/* '3' is an RMW flag.  */
-			if (do_page_fault(fp, (unsigned long)mem, 3))
-				/* If the do_page_fault() failed, we don't
-				   have anything meaningful to return.
-				   There should be a SIGSEGV pending for
-				   the process.  */
-				return 0xdeadbeef;
-		}
-	}
-}
-
-asmlinkage int sys_atomic_barrier(void)
-{
-	/* no code needed for uniprocs */
-	return 0;
-}
diff --git a/arch/m68k/kernel/sys_m68k_no.c b/arch/m68k/kernel/sys_m68k_no.c
deleted file mode 100644
index 68488ae47f0a..000000000000
--- a/arch/m68k/kernel/sys_m68k_no.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * linux/arch/m68knommu/kernel/sys_m68k.c
- *
- * This file contains various random system calls that
- * have a non-standard calling sequence on the Linux/m68k
- * platform.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/ipc.h>
-#include <linux/fs.h>
-
-#include <asm/setup.h>
-#include <asm/uaccess.h>
-#include <asm/cachectl.h>
-#include <asm/traps.h>
-#include <asm/cacheflush.h>
-#include <asm/unistd.h>
-
-/* sys_cacheflush -- flush (part of) the processor cache.  */
-asmlinkage int
-sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
-{
-	flush_cache_all();
-	return(0);
-}
-
-asmlinkage int sys_getpagesize(void)
-{
-	return PAGE_SIZE;
-}
-
-/*
- * Do a system call from kernel instead of calling sys_execve so we
- * end up with proper pt_regs.
- */
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	register long __res asm ("%d0") = __NR_execve;
-	register long __a asm ("%d1") = (long)(filename);
-	register long __b asm ("%d2") = (long)(argv);
-	register long __c asm ("%d3") = (long)(envp);
-	asm volatile ("trap  #0" : "+d" (__res)
-			: "d" (__a), "d" (__b), "d" (__c));
-	return __res;
-}
-
-asmlinkage unsigned long sys_get_thread_area(void)
-{
-	return current_thread_info()->tp_value;
-}
-
-asmlinkage int sys_set_thread_area(unsigned long tp)
-{
-	current_thread_info()->tp_value = tp;
-	return 0;
-}
-
-/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
-   D1 (newval).  */
-asmlinkage int
-sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
-		      unsigned long __user * mem)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long mem_value;
-
-	down_read(&mm->mmap_sem);
-
-	mem_value = *mem;
-	if (mem_value == oldval)
-		*mem = newval;
-
-	up_read(&mm->mmap_sem);
-	return mem_value;
-}
-
-asmlinkage int sys_atomic_barrier(void)
-{
-	/* no code needed for uniprocs */
-	return 0;
-}
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 5909e392cb1e..6f7b09122a00 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -11,7 +11,6 @@
  *  Linux/m68k support by Hamish Macdonald
  */
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 
 #ifndef CONFIG_MMU
diff --git a/arch/m68k/lib/Makefile b/arch/m68k/lib/Makefile
index 1f95881d8437..df421e501436 100644
--- a/arch/m68k/lib/Makefile
+++ b/arch/m68k/lib/Makefile
@@ -1,5 +1,14 @@
+
+#
+# Makefile for m68k-specific library files..
+#
+
+lib-y	:= ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \
+	   memcpy.o memset.o memmove.o
+
 ifdef CONFIG_MMU
-include arch/m68k/lib/Makefile_mm
+lib-y	+= string.o uaccess.o checksum_mm.o
 else
-include arch/m68k/lib/Makefile_no
+lib-y	+= mulsi3.o divsi3.o udivsi3.o modsi3.o umodsi3.o delay.o checksum_no.o
 endif
+
diff --git a/arch/m68k/lib/Makefile_mm b/arch/m68k/lib/Makefile_mm
deleted file mode 100644
index af9abf8d9d98..000000000000
--- a/arch/m68k/lib/Makefile_mm
+++ /dev/null
@@ -1,6 +0,0 @@
-#
-# Makefile for m68k-specific library files..
-#
-
-lib-y	:= ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \
-	   checksum.o string.o uaccess.o
diff --git a/arch/m68k/lib/Makefile_no b/arch/m68k/lib/Makefile_no
deleted file mode 100644
index 32d852e586d7..000000000000
--- a/arch/m68k/lib/Makefile_no
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for m68knommu specific library files..
-#
-
-lib-y	:= ashldi3.o ashrdi3.o lshrdi3.o \
-	   muldi3.o mulsi3.o divsi3.o udivsi3.o modsi3.o umodsi3.o \
-	   checksum.o memcpy.o memmove.o memset.o delay.o
diff --git a/arch/m68k/lib/checksum.c b/arch/m68k/lib/checksum.c
deleted file mode 100644
index 1297536060de..000000000000
--- a/arch/m68k/lib/checksum.c
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_MMU
-#include "checksum_mm.c"
-#else
-#include "checksum_no.c"
-#endif
diff --git a/arch/m68k/lib/checksum_no.c b/arch/m68k/lib/checksum_no.c
index eccf25d3d73e..e4c6354da765 100644
--- a/arch/m68k/lib/checksum_no.c
+++ b/arch/m68k/lib/checksum_no.c
@@ -101,6 +101,7 @@ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
 	return (__force __sum16)~do_csum(iph,ihl*4);
 }
+EXPORT_SYMBOL(ip_fast_csum);
 #endif
 
 /*
@@ -140,6 +141,7 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
 	memcpy(dst, (__force const 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
@@ -151,3 +153,4 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 	memcpy(dst, src, len);
 	return csum_partial(dst, len, sum);
 }
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/m68k/lib/memcpy.c b/arch/m68k/lib/memcpy.c
index b50dbcad4746..62182c81e91c 100644
--- a/arch/m68k/lib/memcpy.c
+++ b/arch/m68k/lib/memcpy.c
@@ -1,62 +1,80 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
 
-#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/string.h>
 
-void * memcpy(void * to, const void * from, size_t n)
+void *memcpy(void *to, const void *from, size_t n)
 {
-#ifdef CONFIG_COLDFIRE
-  void *xto = to;
-  size_t temp;
+	void *xto = to;
+	size_t temp, temp1;
 
-  if (!n)
-    return xto;
-  if ((long) to & 1)
-    {
-      char *cto = to;
-      const char *cfrom = from;
-      *cto++ = *cfrom++;
-      to = cto;
-      from = cfrom;
-      n--;
-    }
-  if (n > 2 && (long) to & 2)
-    {
-      short *sto = to;
-      const short *sfrom = from;
-      *sto++ = *sfrom++;
-      to = sto;
-      from = sfrom;
-      n -= 2;
-    }
-  temp = n >> 2;
-  if (temp)
-    {
-      long *lto = to;
-      const long *lfrom = from;
-      for (; temp; temp--)
-	*lto++ = *lfrom++;
-      to = lto;
-      from = lfrom;
-    }
-  if (n & 2)
-    {
-      short *sto = to;
-      const short *sfrom = from;
-      *sto++ = *sfrom++;
-      to = sto;
-      from = sfrom;
-    }
-  if (n & 1)
-    {
-      char *cto = to;
-      const char *cfrom = from;
-      *cto = *cfrom;
-    }
-  return xto;
+	if (!n)
+		return xto;
+	if ((long)to & 1) {
+		char *cto = to;
+		const char *cfrom = from;
+		*cto++ = *cfrom++;
+		to = cto;
+		from = cfrom;
+		n--;
+	}
+	if (n > 2 && (long)to & 2) {
+		short *sto = to;
+		const short *sfrom = from;
+		*sto++ = *sfrom++;
+		to = sto;
+		from = sfrom;
+		n -= 2;
+	}
+	temp = n >> 2;
+	if (temp) {
+		long *lto = to;
+		const long *lfrom = from;
+#if defined(__mc68020__) || defined(__mc68030__) || \
+    defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__)
+		asm volatile (
+			"	movel %2,%3\n"
+			"	andw  #7,%3\n"
+			"	lsrl  #3,%2\n"
+			"	negw  %3\n"
+			"	jmp   %%pc@(1f,%3:w:2)\n"
+			"4:	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"	movel %0@+,%1@+\n"
+			"1:	dbra  %2,4b\n"
+			"	clrw  %2\n"
+			"	subql #1,%2\n"
+			"	jpl   4b"
+			: "=a" (lfrom), "=a" (lto), "=d" (temp), "=&d" (temp1)
+			: "0" (lfrom), "1" (lto), "2" (temp));
 #else
-  const char *c_from = from;
-  char *c_to = to;
-  while (n-- > 0)
-    *c_to++ = *c_from++;
-  return((void *) to);
+		for (; temp; temp--)
+			*lto++ = *lfrom++;
 #endif
+		to = lto;
+		from = lfrom;
+	}
+	if (n & 2) {
+		short *sto = to;
+		const short *sfrom = from;
+		*sto++ = *sfrom++;
+		to = sto;
+		from = sfrom;
+	}
+	if (n & 1) {
+		char *cto = to;
+		const char *cfrom = from;
+		*cto = *cfrom;
+	}
+	return xto;
 }
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/m68k/lib/memmove.c b/arch/m68k/lib/memmove.c
index b3dcfe9dab7e..6519f7f349f6 100644
--- a/arch/m68k/lib/memmove.c
+++ b/arch/m68k/lib/memmove.c
@@ -4,8 +4,6 @@
  * for more details.
  */
 
-#define __IN_STRING_C
-
 #include <linux/module.h>
 #include <linux/string.h>
 
diff --git a/arch/m68k/lib/memset.c b/arch/m68k/lib/memset.c
index 1389bf455633..f649e6a2e644 100644
--- a/arch/m68k/lib/memset.c
+++ b/arch/m68k/lib/memset.c
@@ -1,47 +1,75 @@
-#include <linux/types.h>
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
 
-void * memset(void * s, int c, size_t count)
+#include <linux/module.h>
+#include <linux/string.h>
+
+void *memset(void *s, int c, size_t count)
 {
-  void *xs = s;
-  size_t temp;
+	void *xs = s;
+	size_t temp;
 
-  if (!count)
-    return xs;
-  c &= 0xff;
-  c |= c << 8;
-  c |= c << 16;
-  if ((long) s & 1)
-    {
-      char *cs = s;
-      *cs++ = c;
-      s = cs;
-      count--;
-    }
-  if (count > 2 && (long) s & 2)
-    {
-      short *ss = s;
-      *ss++ = c;
-      s = ss;
-      count -= 2;
-    }
-  temp = count >> 2;
-  if (temp)
-    {
-      long *ls = s;
-      for (; temp; temp--)
-	*ls++ = c;
-      s = ls;
-    }
-  if (count & 2)
-    {
-      short *ss = s;
-      *ss++ = c;
-      s = ss;
-    }
-  if (count & 1)
-    {
-      char *cs = s;
-      *cs = c;
-    }
-  return xs;
+	if (!count)
+		return xs;
+	c &= 0xff;
+	c |= c << 8;
+	c |= c << 16;
+	if ((long)s & 1) {
+		char *cs = s;
+		*cs++ = c;
+		s = cs;
+		count--;
+	}
+	if (count > 2 && (long)s & 2) {
+		short *ss = s;
+		*ss++ = c;
+		s = ss;
+		count -= 2;
+	}
+	temp = count >> 2;
+	if (temp) {
+		long *ls = s;
+#if defined(__mc68020__) || defined(__mc68030__) || \
+    defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__)
+		size_t temp1;
+		asm volatile (
+			"	movel %1,%2\n"
+			"	andw  #7,%2\n"
+			"	lsrl  #3,%1\n"
+			"	negw  %2\n"
+			"	jmp   %%pc@(2f,%2:w:2)\n"
+			"1:	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"	movel %3,%0@+\n"
+			"2:	dbra  %1,1b\n"
+			"	clrw  %1\n"
+			"	subql #1,%1\n"
+			"	jpl   1b"
+			: "=a" (ls), "=d" (temp), "=&d" (temp1)
+			: "d" (c), "0" (ls), "1" (temp));
+#else
+		for (; temp; temp--)
+			*ls++ = c;
+#endif
+		s = ls;
+	}
+	if (count & 2) {
+		short *ss = s;
+		*ss++ = c;
+		s = ss;
+	}
+	if (count & 1) {
+		char *cs = s;
+		*cs = c;
+	}
+	return xs;
 }
+EXPORT_SYMBOL(memset);
diff --git a/arch/m68k/lib/muldi3.c b/arch/m68k/lib/muldi3.c
index 16e0eb338ee0..079bafca073e 100644
--- a/arch/m68k/lib/muldi3.c
+++ b/arch/m68k/lib/muldi3.c
@@ -1,5 +1,98 @@
-#ifdef CONFIG_MMU
-#include "muldi3_mm.c"
+/* muldi3.c extracted from gcc-2.7.2.3/libgcc2.c and 
+			   gcc-2.7.2.3/longlong.h which is: */
+/* Copyright (C) 1989, 1992, 1993, 1994, 1995 Free Software Foundation, Inc.
+
+This file is part of GNU CC.
+
+GNU CC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 2, or (at your option)
+any later version.
+
+GNU CC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNU CC; see the file COPYING.  If not, write to
+the Free Software Foundation, 59 Temple Place - Suite 330,
+Boston, MA 02111-1307, USA.  */
+
+#if defined(__mc68020__) || defined(__mc68030__) || \
+    defined(__mc68040__) || defined(__mc68060__) || defined(__mcpu32__)
+
+#define umul_ppmm(w1, w0, u, v) \
+  __asm__ ("mulu%.l %3,%1:%0"						\
+           : "=d" ((USItype)(w0)),					\
+             "=d" ((USItype)(w1))					\
+           : "%0" ((USItype)(u)),					\
+             "dmi" ((USItype)(v)))
+
 #else
-#include "muldi3_no.c"
+
+#define SI_TYPE_SIZE 32
+#define __BITS4 (SI_TYPE_SIZE / 4)
+#define __ll_B (1L << (SI_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((USItype) (t) % __ll_B)
+#define __ll_highpart(t) ((USItype) (t) / __ll_B)
+
+#define umul_ppmm(w1, w0, u, v)						\
+  do {									\
+    USItype __x0, __x1, __x2, __x3;					\
+    USItype __ul, __vl, __uh, __vh;					\
+									\
+    __ul = __ll_lowpart (u);						\
+    __uh = __ll_highpart (u);						\
+    __vl = __ll_lowpart (v);						\
+    __vh = __ll_highpart (v);						\
+									\
+    __x0 = (USItype) __ul * __vl;					\
+    __x1 = (USItype) __ul * __vh;					\
+    __x2 = (USItype) __uh * __vl;					\
+    __x3 = (USItype) __uh * __vh;					\
+									\
+    __x1 += __ll_highpart (__x0);/* this can't give carry */		\
+    __x1 += __x2;		/* but this indeed can */		\
+    if (__x1 < __x2)		/* did we get it? */			\
+      __x3 += __ll_B;		/* yes, add it in the proper pos. */	\
+									\
+    (w1) = __x3 + __ll_highpart (__x1);					\
+    (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0);		\
+  } while (0)
+
 #endif
+
+#define __umulsidi3(u, v) \
+  ({DIunion __w;							\
+    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
+    __w.ll; })
+
+typedef 	 int SItype	__attribute__ ((mode (SI)));
+typedef unsigned int USItype	__attribute__ ((mode (SI)));
+typedef		 int DItype	__attribute__ ((mode (DI)));
+typedef int word_type __attribute__ ((mode (__word__)));
+
+struct DIstruct {SItype high, low;};
+
+typedef union
+{
+  struct DIstruct s;
+  DItype ll;
+} DIunion;
+
+DItype
+__muldi3 (DItype u, DItype v)
+{
+  DIunion w;
+  DIunion uu, vv;
+
+  uu.ll = u,
+  vv.ll = v;
+
+  w.ll = __umulsidi3 (uu.s.low, vv.s.low);
+  w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high
+	       + (USItype) uu.s.high * (USItype) vv.s.low);
+
+  return w.ll;
+}
diff --git a/arch/m68k/lib/muldi3_mm.c b/arch/m68k/lib/muldi3_mm.c
deleted file mode 100644
index be4f275649e3..000000000000
--- a/arch/m68k/lib/muldi3_mm.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/* muldi3.c extracted from gcc-2.7.2.3/libgcc2.c and
-			   gcc-2.7.2.3/longlong.h which is: */
-/* Copyright (C) 1989, 1992, 1993, 1994, 1995 Free Software Foundation, Inc.
-
-This file is part of GNU CC.
-
-GNU CC is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2, or (at your option)
-any later version.
-
-GNU CC is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with GNU CC; see the file COPYING.  If not, write to
-the Free Software Foundation, 59 Temple Place - Suite 330,
-Boston, MA 02111-1307, USA.  */
-
-#define BITS_PER_UNIT 8
-
-#define umul_ppmm(w1, w0, u, v) \
-  __asm__ ("mulu%.l %3,%1:%0"						\
-           : "=d" ((USItype)(w0)),					\
-             "=d" ((USItype)(w1))					\
-           : "%0" ((USItype)(u)),					\
-             "dmi" ((USItype)(v)))
-
-#define __umulsidi3(u, v) \
-  ({DIunion __w;							\
-    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
-    __w.ll; })
-
-typedef		 int SItype	__attribute__ ((mode (SI)));
-typedef unsigned int USItype	__attribute__ ((mode (SI)));
-typedef		 int DItype	__attribute__ ((mode (DI)));
-typedef int word_type __attribute__ ((mode (__word__)));
-
-struct DIstruct {SItype high, low;};
-
-typedef union
-{
-  struct DIstruct s;
-  DItype ll;
-} DIunion;
-
-DItype
-__muldi3 (DItype u, DItype v)
-{
-  DIunion w;
-  DIunion uu, vv;
-
-  uu.ll = u,
-  vv.ll = v;
-
-  w.ll = __umulsidi3 (uu.s.low, vv.s.low);
-  w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high
-	       + (USItype) uu.s.high * (USItype) vv.s.low);
-
-  return w.ll;
-}
diff --git a/arch/m68k/lib/muldi3_no.c b/arch/m68k/lib/muldi3_no.c
deleted file mode 100644
index 34af72c30303..000000000000
--- a/arch/m68k/lib/muldi3_no.c
+++ /dev/null
@@ -1,86 +0,0 @@
-/* muldi3.c extracted from gcc-2.7.2.3/libgcc2.c and 
-			   gcc-2.7.2.3/longlong.h which is: */
-/* Copyright (C) 1989, 1992, 1993, 1994, 1995 Free Software Foundation, Inc.
-
-This file is part of GNU CC.
-
-GNU CC is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2, or (at your option)
-any later version.
-
-GNU CC is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with GNU CC; see the file COPYING.  If not, write to
-the Free Software Foundation, 59 Temple Place - Suite 330,
-Boston, MA 02111-1307, USA.  */
-
-#define BITS_PER_UNIT 8
-#define SI_TYPE_SIZE 32
-
-#define __BITS4 (SI_TYPE_SIZE / 4)
-#define __ll_B (1L << (SI_TYPE_SIZE / 2))
-#define __ll_lowpart(t) ((USItype) (t) % __ll_B)
-#define __ll_highpart(t) ((USItype) (t) / __ll_B)
-
-#define umul_ppmm(w1, w0, u, v)						\
-  do {									\
-    USItype __x0, __x1, __x2, __x3;					\
-    USItype __ul, __vl, __uh, __vh;					\
-									\
-    __ul = __ll_lowpart (u);						\
-    __uh = __ll_highpart (u);						\
-    __vl = __ll_lowpart (v);						\
-    __vh = __ll_highpart (v);						\
-									\
-    __x0 = (USItype) __ul * __vl;					\
-    __x1 = (USItype) __ul * __vh;					\
-    __x2 = (USItype) __uh * __vl;					\
-    __x3 = (USItype) __uh * __vh;					\
-									\
-    __x1 += __ll_highpart (__x0);/* this can't give carry */		\
-    __x1 += __x2;		/* but this indeed can */		\
-    if (__x1 < __x2)		/* did we get it? */			\
-      __x3 += __ll_B;		/* yes, add it in the proper pos. */	\
-									\
-    (w1) = __x3 + __ll_highpart (__x1);					\
-    (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0);		\
-  } while (0)
-
-#define __umulsidi3(u, v) \
-  ({DIunion __w;							\
-    umul_ppmm (__w.s.high, __w.s.low, u, v);				\
-    __w.ll; })
-
-typedef 	 int SItype	__attribute__ ((mode (SI)));
-typedef unsigned int USItype	__attribute__ ((mode (SI)));
-typedef		 int DItype	__attribute__ ((mode (DI)));
-typedef int word_type __attribute__ ((mode (__word__)));
-
-struct DIstruct {SItype high, low;};
-
-typedef union
-{
-  struct DIstruct s;
-  DItype ll;
-} DIunion;
-
-DItype
-__muldi3 (DItype u, DItype v)
-{
-  DIunion w;
-  DIunion uu, vv;
-
-  uu.ll = u,
-  vv.ll = v;
-
-  w.ll = __umulsidi3 (uu.s.low, vv.s.low);
-  w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high
-	       + (USItype) uu.s.high * (USItype) vv.s.low);
-
-  return w.ll;
-}
diff --git a/arch/m68k/lib/string.c b/arch/m68k/lib/string.c
index d399c5f25636..b9a57abfad08 100644
--- a/arch/m68k/lib/string.c
+++ b/arch/m68k/lib/string.c
@@ -20,226 +20,3 @@ char *strcat(char *dest, const char *src)
 	return __kernel_strcpy(dest + __kernel_strlen(dest), src);
 }
 EXPORT_SYMBOL(strcat);
-
-void *memset(void *s, int c, size_t count)
-{
-	void *xs = s;
-	size_t temp, temp1;
-
-	if (!count)
-		return xs;
-	c &= 0xff;
-	c |= c << 8;
-	c |= c << 16;
-	if ((long)s & 1) {
-		char *cs = s;
-		*cs++ = c;
-		s = cs;
-		count--;
-	}
-	if (count > 2 && (long)s & 2) {
-		short *ss = s;
-		*ss++ = c;
-		s = ss;
-		count -= 2;
-	}
-	temp = count >> 2;
-	if (temp) {
-		long *ls = s;
-
-		asm volatile (
-			"	movel %1,%2\n"
-			"	andw  #7,%2\n"
-			"	lsrl  #3,%1\n"
-			"	negw  %2\n"
-			"	jmp   %%pc@(2f,%2:w:2)\n"
-			"1:	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"	movel %3,%0@+\n"
-			"2:	dbra  %1,1b\n"
-			"	clrw  %1\n"
-			"	subql #1,%1\n"
-			"	jpl   1b"
-			: "=a" (ls), "=d" (temp), "=&d" (temp1)
-			: "d" (c), "0" (ls), "1" (temp));
-		s = ls;
-	}
-	if (count & 2) {
-		short *ss = s;
-		*ss++ = c;
-		s = ss;
-	}
-	if (count & 1) {
-		char *cs = s;
-		*cs = c;
-	}
-	return xs;
-}
-EXPORT_SYMBOL(memset);
-
-void *memcpy(void *to, const void *from, size_t n)
-{
-	void *xto = to;
-	size_t temp, temp1;
-
-	if (!n)
-		return xto;
-	if ((long)to & 1) {
-		char *cto = to;
-		const char *cfrom = from;
-		*cto++ = *cfrom++;
-		to = cto;
-		from = cfrom;
-		n--;
-	}
-	if (n > 2 && (long)to & 2) {
-		short *sto = to;
-		const short *sfrom = from;
-		*sto++ = *sfrom++;
-		to = sto;
-		from = sfrom;
-		n -= 2;
-	}
-	temp = n >> 2;
-	if (temp) {
-		long *lto = to;
-		const long *lfrom = from;
-
-		asm volatile (
-			"	movel %2,%3\n"
-			"	andw  #7,%3\n"
-			"	lsrl  #3,%2\n"
-			"	negw  %3\n"
-			"	jmp   %%pc@(1f,%3:w:2)\n"
-			"4:	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"	movel %0@+,%1@+\n"
-			"1:	dbra  %2,4b\n"
-			"	clrw  %2\n"
-			"	subql #1,%2\n"
-			"	jpl   4b"
-			: "=a" (lfrom), "=a" (lto), "=d" (temp), "=&d" (temp1)
-			: "0" (lfrom), "1" (lto), "2" (temp));
-		to = lto;
-		from = lfrom;
-	}
-	if (n & 2) {
-		short *sto = to;
-		const short *sfrom = from;
-		*sto++ = *sfrom++;
-		to = sto;
-		from = sfrom;
-	}
-	if (n & 1) {
-		char *cto = to;
-		const char *cfrom = from;
-		*cto = *cfrom;
-	}
-	return xto;
-}
-EXPORT_SYMBOL(memcpy);
-
-void *memmove(void *dest, const void *src, size_t n)
-{
-	void *xdest = dest;
-	size_t temp;
-
-	if (!n)
-		return xdest;
-
-	if (dest < src) {
-		if ((long)dest & 1) {
-			char *cdest = dest;
-			const char *csrc = src;
-			*cdest++ = *csrc++;
-			dest = cdest;
-			src = csrc;
-			n--;
-		}
-		if (n > 2 && (long)dest & 2) {
-			short *sdest = dest;
-			const short *ssrc = src;
-			*sdest++ = *ssrc++;
-			dest = sdest;
-			src = ssrc;
-			n -= 2;
-		}
-		temp = n >> 2;
-		if (temp) {
-			long *ldest = dest;
-			const long *lsrc = src;
-			temp--;
-			do
-				*ldest++ = *lsrc++;
-			while (temp--);
-			dest = ldest;
-			src = lsrc;
-		}
-		if (n & 2) {
-			short *sdest = dest;
-			const short *ssrc = src;
-			*sdest++ = *ssrc++;
-			dest = sdest;
-			src = ssrc;
-		}
-		if (n & 1) {
-			char *cdest = dest;
-			const char *csrc = src;
-			*cdest = *csrc;
-		}
-	} else {
-		dest = (char *)dest + n;
-		src = (const char *)src + n;
-		if ((long)dest & 1) {
-			char *cdest = dest;
-			const char *csrc = src;
-			*--cdest = *--csrc;
-			dest = cdest;
-			src = csrc;
-			n--;
-		}
-		if (n > 2 && (long)dest & 2) {
-			short *sdest = dest;
-			const short *ssrc = src;
-			*--sdest = *--ssrc;
-			dest = sdest;
-			src = ssrc;
-			n -= 2;
-		}
-		temp = n >> 2;
-		if (temp) {
-			long *ldest = dest;
-			const long *lsrc = src;
-			temp--;
-			do
-				*--ldest = *--lsrc;
-			while (temp--);
-			dest = ldest;
-			src = lsrc;
-		}
-		if (n & 2) {
-			short *sdest = dest;
-			const short *ssrc = src;
-			*--sdest = *--ssrc;
-			dest = sdest;
-			src = ssrc;
-		}
-		if (n & 1) {
-			char *cdest = dest;
-			const char *csrc = src;
-			*--cdest = *--csrc;
-		}
-	}
-	return xdest;
-}
-EXPORT_SYMBOL(memmove);
diff --git a/arch/m68k/mm/Makefile b/arch/m68k/mm/Makefile
index b60270e4954b..09cadf1058d5 100644
--- a/arch/m68k/mm/Makefile
+++ b/arch/m68k/mm/Makefile
@@ -1,5 +1,9 @@
-ifdef CONFIG_MMU
-include arch/m68k/mm/Makefile_mm
-else
-include arch/m68k/mm/Makefile_no
-endif
+#
+# Makefile for the linux m68k-specific parts of the memory manager.
+#
+
+obj-y	:= init.o
+
+obj-$(CONFIG_MMU)		+= cache.o fault.o hwtest.o
+obj-$(CONFIG_MMU_MOTOROLA)	+= kmap.o memory.o motorola.o
+obj-$(CONFIG_MMU_SUN3)		+= sun3kmap.o sun3mmu.o
diff --git a/arch/m68k/mm/Makefile_mm b/arch/m68k/mm/Makefile_mm
deleted file mode 100644
index 5eaa43c4cb3c..000000000000
--- a/arch/m68k/mm/Makefile_mm
+++ /dev/null
@@ -1,8 +0,0 @@
-#
-# Makefile for the linux m68k-specific parts of the memory manager.
-#
-
-obj-y		:= cache.o init.o fault.o hwtest.o
-
-obj-$(CONFIG_MMU_MOTOROLA)	+= kmap.o memory.o motorola.o
-obj-$(CONFIG_MMU_SUN3)		+= sun3kmap.o sun3mmu.o
diff --git a/arch/m68k/mm/Makefile_no b/arch/m68k/mm/Makefile_no
deleted file mode 100644
index b54ab6b4b523..000000000000
--- a/arch/m68k/mm/Makefile_no
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux m68knommu specific parts of the memory manager.
-#
-
-obj-y += init.o kmap.o
diff --git a/arch/m68k/mm/init_no.c b/arch/m68k/mm/init_no.c
index 8a6653f56bd8..7cbd7bd1f8bc 100644
--- a/arch/m68k/mm/init_no.c
+++ b/arch/m68k/mm/init_no.c
@@ -38,28 +38,10 @@
 #include <asm/system.h>
 #include <asm/machdep.h>
 
-#undef DEBUG
-
-extern void die_if_kernel(char *,struct pt_regs *,long);
-extern void free_initmem(void);
-
 /*
- * BAD_PAGE is the page that is used for page faults when linux
- * is out-of-memory. Older versions of linux just did a
- * do_exit(), but using this instead means there is less risk
- * for a process dying in kernel mode, possibly leaving a inode
- * unused etc..
- *
- * BAD_PAGETABLE is the accompanying page-table: it is initialized
- * to point to BAD_PAGE entries.
- *
  * ZERO_PAGE is a special page that is used for zero-initialized
  * data and COW.
  */
-static unsigned long empty_bad_page_table;
-
-static unsigned long empty_bad_page;
-
 unsigned long empty_zero_page;
 
 extern unsigned long memory_start;
@@ -77,22 +59,9 @@ void __init paging_init(void)
 	 * Make sure start_mem is page aligned, otherwise bootmem and
 	 * page_alloc get different views of the world.
 	 */
-#ifdef DEBUG
-	unsigned long start_mem = PAGE_ALIGN(memory_start);
-#endif
 	unsigned long end_mem   = memory_end & PAGE_MASK;
+	unsigned long zones_size[MAX_NR_ZONES] = {0, };
 
-#ifdef DEBUG
-	printk (KERN_DEBUG "start_mem is %#lx\nvirtual_end is %#lx\n",
-		start_mem, end_mem);
-#endif
-
-	/*
-	 * Initialize the bad page table and bad page to point
-	 * to a couple of allocated pages.
-	 */
-	empty_bad_page_table = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
-	empty_bad_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
 	empty_zero_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
 	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 
@@ -101,19 +70,8 @@ void __init paging_init(void)
 	 */
 	set_fs (USER_DS);
 
-#ifdef DEBUG
-	printk (KERN_DEBUG "before free_area_init\n");
-
-	printk (KERN_DEBUG "free_area_init -> start_mem is %#lx\nvirtual_end is %#lx\n",
-		start_mem, end_mem);
-#endif
-
-	{
-		unsigned long zones_size[MAX_NR_ZONES] = {0, };
-
-		zones_size[ZONE_DMA] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
-		free_area_init(zones_size);
-	}
+	zones_size[ZONE_DMA] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
+	free_area_init(zones_size);
 }
 
 void __init mem_init(void)
@@ -166,8 +124,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-void
-free_initmem()
+void free_initmem(void)
 {
 #ifdef CONFIG_RAMKERNEL
 	unsigned long addr;
diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index a373d136b2b2..69345849454b 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -1,5 +1,367 @@
-#ifdef CONFIG_MMU
-#include "kmap_mm.c"
+/*
+ *  linux/arch/m68k/mm/kmap.c
+ *
+ *  Copyright (C) 1997 Roman Hodek
+ *
+ *  10/01/99 cleaned up the code and changing to the same interface
+ *	     used by other architectures		/Roman Zippel
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include <asm/setup.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/io.h>
+#include <asm/system.h>
+
+#undef DEBUG
+
+#define PTRTREESIZE	(256*1024)
+
+/*
+ * For 040/060 we can use the virtual memory area like other architectures,
+ * but for 020/030 we want to use early termination page descriptor and we
+ * can't mix this with normal page descriptors, so we have to copy that code
+ * (mm/vmalloc.c) and return appriorate aligned addresses.
+ */
+
+#ifdef CPU_M68040_OR_M68060_ONLY
+
+#define IO_SIZE		PAGE_SIZE
+
+static inline struct vm_struct *get_io_area(unsigned long size)
+{
+	return get_vm_area(size, VM_IOREMAP);
+}
+
+
+static inline void free_io_area(void *addr)
+{
+	vfree((void *)(PAGE_MASK & (unsigned long)addr));
+}
+
 #else
-#include "kmap_no.c"
+
+#define IO_SIZE		(256*1024)
+
+static struct vm_struct *iolist;
+
+static struct vm_struct *get_io_area(unsigned long size)
+{
+	unsigned long addr;
+	struct vm_struct **p, *tmp, *area;
+
+	area = kmalloc(sizeof(*area), GFP_KERNEL);
+	if (!area)
+		return NULL;
+	addr = KMAP_START;
+	for (p = &iolist; (tmp = *p) ; p = &tmp->next) {
+		if (size + addr < (unsigned long)tmp->addr)
+			break;
+		if (addr > KMAP_END-size) {
+			kfree(area);
+			return NULL;
+		}
+		addr = tmp->size + (unsigned long)tmp->addr;
+	}
+	area->addr = (void *)addr;
+	area->size = size + IO_SIZE;
+	area->next = *p;
+	*p = area;
+	return area;
+}
+
+static inline void free_io_area(void *addr)
+{
+	struct vm_struct **p, *tmp;
+
+	if (!addr)
+		return;
+	addr = (void *)((unsigned long)addr & -IO_SIZE);
+	for (p = &iolist ; (tmp = *p) ; p = &tmp->next) {
+		if (tmp->addr == addr) {
+			*p = tmp->next;
+			__iounmap(tmp->addr, tmp->size);
+			kfree(tmp);
+			return;
+		}
+	}
+}
+
 #endif
+
+/*
+ * Map some physical address range into the kernel address space.
+ */
+/* Rewritten by Andreas Schwab to remove all races. */
+
+void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
+{
+	struct vm_struct *area;
+	unsigned long virtaddr, retaddr;
+	long offset;
+	pgd_t *pgd_dir;
+	pmd_t *pmd_dir;
+	pte_t *pte_dir;
+
+	/*
+	 * Don't allow mappings that wrap..
+	 */
+	if (!size || physaddr > (unsigned long)(-size))
+		return NULL;
+
+#ifdef CONFIG_AMIGA
+	if (MACH_IS_AMIGA) {
+		if ((physaddr >= 0x40000000) && (physaddr + size < 0x60000000)
+		    && (cacheflag == IOMAP_NOCACHE_SER))
+			return (void __iomem *)physaddr;
+	}
+#endif
+
+#ifdef DEBUG
+	printk("ioremap: 0x%lx,0x%lx(%d) - ", physaddr, size, cacheflag);
+#endif
+	/*
+	 * Mappings have to be aligned
+	 */
+	offset = physaddr & (IO_SIZE - 1);
+	physaddr &= -IO_SIZE;
+	size = (size + offset + IO_SIZE - 1) & -IO_SIZE;
+
+	/*
+	 * Ok, go for it..
+	 */
+	area = get_io_area(size);
+	if (!area)
+		return NULL;
+
+	virtaddr = (unsigned long)area->addr;
+	retaddr = virtaddr + offset;
+#ifdef DEBUG
+	printk("0x%lx,0x%lx,0x%lx", physaddr, virtaddr, retaddr);
+#endif
+
+	/*
+	 * add cache and table flags to physical address
+	 */
+	if (CPU_IS_040_OR_060) {
+		physaddr |= (_PAGE_PRESENT | _PAGE_GLOBAL040 |
+			     _PAGE_ACCESSED | _PAGE_DIRTY);
+		switch (cacheflag) {
+		case IOMAP_FULL_CACHING:
+			physaddr |= _PAGE_CACHE040;
+			break;
+		case IOMAP_NOCACHE_SER:
+		default:
+			physaddr |= _PAGE_NOCACHE_S;
+			break;
+		case IOMAP_NOCACHE_NONSER:
+			physaddr |= _PAGE_NOCACHE;
+			break;
+		case IOMAP_WRITETHROUGH:
+			physaddr |= _PAGE_CACHE040W;
+			break;
+		}
+	} else {
+		physaddr |= (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_DIRTY);
+		switch (cacheflag) {
+		case IOMAP_NOCACHE_SER:
+		case IOMAP_NOCACHE_NONSER:
+		default:
+			physaddr |= _PAGE_NOCACHE030;
+			break;
+		case IOMAP_FULL_CACHING:
+		case IOMAP_WRITETHROUGH:
+			break;
+		}
+	}
+
+	while ((long)size > 0) {
+#ifdef DEBUG
+		if (!(virtaddr & (PTRTREESIZE-1)))
+			printk ("\npa=%#lx va=%#lx ", physaddr, virtaddr);
+#endif
+		pgd_dir = pgd_offset_k(virtaddr);
+		pmd_dir = pmd_alloc(&init_mm, pgd_dir, virtaddr);
+		if (!pmd_dir) {
+			printk("ioremap: no mem for pmd_dir\n");
+			return NULL;
+		}
+
+		if (CPU_IS_020_OR_030) {
+			pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr;
+			physaddr += PTRTREESIZE;
+			virtaddr += PTRTREESIZE;
+			size -= PTRTREESIZE;
+		} else {
+			pte_dir = pte_alloc_kernel(pmd_dir, virtaddr);
+			if (!pte_dir) {
+				printk("ioremap: no mem for pte_dir\n");
+				return NULL;
+			}
+
+			pte_val(*pte_dir) = physaddr;
+			virtaddr += PAGE_SIZE;
+			physaddr += PAGE_SIZE;
+			size -= PAGE_SIZE;
+		}
+	}
+#ifdef DEBUG
+	printk("\n");
+#endif
+	flush_tlb_all();
+
+	return (void __iomem *)retaddr;
+}
+EXPORT_SYMBOL(__ioremap);
+
+/*
+ * Unmap a ioremap()ed region again
+ */
+void iounmap(void __iomem *addr)
+{
+#ifdef CONFIG_AMIGA
+	if ((!MACH_IS_AMIGA) ||
+	    (((unsigned long)addr < 0x40000000) ||
+	     ((unsigned long)addr > 0x60000000)))
+			free_io_area((__force void *)addr);
+#else
+	free_io_area((__force void *)addr);
+#endif
+}
+EXPORT_SYMBOL(iounmap);
+
+/*
+ * __iounmap unmaps nearly everything, so be careful
+ * it doesn't free currently pointer/page tables anymore but it
+ * wans't used anyway and might be added later.
+ */
+void __iounmap(void *addr, unsigned long size)
+{
+	unsigned long virtaddr = (unsigned long)addr;
+	pgd_t *pgd_dir;
+	pmd_t *pmd_dir;
+	pte_t *pte_dir;
+
+	while ((long)size > 0) {
+		pgd_dir = pgd_offset_k(virtaddr);
+		if (pgd_bad(*pgd_dir)) {
+			printk("iounmap: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
+			pgd_clear(pgd_dir);
+			return;
+		}
+		pmd_dir = pmd_offset(pgd_dir, virtaddr);
+
+		if (CPU_IS_020_OR_030) {
+			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
+			int pmd_type = pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK;
+
+			if (pmd_type == _PAGE_PRESENT) {
+				pmd_dir->pmd[pmd_off] = 0;
+				virtaddr += PTRTREESIZE;
+				size -= PTRTREESIZE;
+				continue;
+			} else if (pmd_type == 0)
+				continue;
+		}
+
+		if (pmd_bad(*pmd_dir)) {
+			printk("iounmap: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
+			pmd_clear(pmd_dir);
+			return;
+		}
+		pte_dir = pte_offset_kernel(pmd_dir, virtaddr);
+
+		pte_val(*pte_dir) = 0;
+		virtaddr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+
+	flush_tlb_all();
+}
+
+/*
+ * Set new cache mode for some kernel address space.
+ * The caller must push data for that range itself, if such data may already
+ * be in the cache.
+ */
+void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
+{
+	unsigned long virtaddr = (unsigned long)addr;
+	pgd_t *pgd_dir;
+	pmd_t *pmd_dir;
+	pte_t *pte_dir;
+
+	if (CPU_IS_040_OR_060) {
+		switch (cmode) {
+		case IOMAP_FULL_CACHING:
+			cmode = _PAGE_CACHE040;
+			break;
+		case IOMAP_NOCACHE_SER:
+		default:
+			cmode = _PAGE_NOCACHE_S;
+			break;
+		case IOMAP_NOCACHE_NONSER:
+			cmode = _PAGE_NOCACHE;
+			break;
+		case IOMAP_WRITETHROUGH:
+			cmode = _PAGE_CACHE040W;
+			break;
+		}
+	} else {
+		switch (cmode) {
+		case IOMAP_NOCACHE_SER:
+		case IOMAP_NOCACHE_NONSER:
+		default:
+			cmode = _PAGE_NOCACHE030;
+			break;
+		case IOMAP_FULL_CACHING:
+		case IOMAP_WRITETHROUGH:
+			cmode = 0;
+		}
+	}
+
+	while ((long)size > 0) {
+		pgd_dir = pgd_offset_k(virtaddr);
+		if (pgd_bad(*pgd_dir)) {
+			printk("iocachemode: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
+			pgd_clear(pgd_dir);
+			return;
+		}
+		pmd_dir = pmd_offset(pgd_dir, virtaddr);
+
+		if (CPU_IS_020_OR_030) {
+			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
+
+			if ((pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK) == _PAGE_PRESENT) {
+				pmd_dir->pmd[pmd_off] = (pmd_dir->pmd[pmd_off] &
+							 _CACHEMASK040) | cmode;
+				virtaddr += PTRTREESIZE;
+				size -= PTRTREESIZE;
+				continue;
+			}
+		}
+
+		if (pmd_bad(*pmd_dir)) {
+			printk("iocachemode: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
+			pmd_clear(pmd_dir);
+			return;
+		}
+		pte_dir = pte_offset_kernel(pmd_dir, virtaddr);
+
+		pte_val(*pte_dir) = (pte_val(*pte_dir) & _CACHEMASK040) | cmode;
+		virtaddr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+
+	flush_tlb_all();
+}
+EXPORT_SYMBOL(kernel_set_cachemode);
diff --git a/arch/m68k/mm/kmap_mm.c b/arch/m68k/mm/kmap_mm.c
deleted file mode 100644
index 69345849454b..000000000000
--- a/arch/m68k/mm/kmap_mm.c
+++ /dev/null
@@ -1,367 +0,0 @@
-/*
- *  linux/arch/m68k/mm/kmap.c
- *
- *  Copyright (C) 1997 Roman Hodek
- *
- *  10/01/99 cleaned up the code and changing to the same interface
- *	     used by other architectures		/Roman Zippel
- */
-
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-
-#include <asm/setup.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-#include <asm/io.h>
-#include <asm/system.h>
-
-#undef DEBUG
-
-#define PTRTREESIZE	(256*1024)
-
-/*
- * For 040/060 we can use the virtual memory area like other architectures,
- * but for 020/030 we want to use early termination page descriptor and we
- * can't mix this with normal page descriptors, so we have to copy that code
- * (mm/vmalloc.c) and return appriorate aligned addresses.
- */
-
-#ifdef CPU_M68040_OR_M68060_ONLY
-
-#define IO_SIZE		PAGE_SIZE
-
-static inline struct vm_struct *get_io_area(unsigned long size)
-{
-	return get_vm_area(size, VM_IOREMAP);
-}
-
-
-static inline void free_io_area(void *addr)
-{
-	vfree((void *)(PAGE_MASK & (unsigned long)addr));
-}
-
-#else
-
-#define IO_SIZE		(256*1024)
-
-static struct vm_struct *iolist;
-
-static struct vm_struct *get_io_area(unsigned long size)
-{
-	unsigned long addr;
-	struct vm_struct **p, *tmp, *area;
-
-	area = kmalloc(sizeof(*area), GFP_KERNEL);
-	if (!area)
-		return NULL;
-	addr = KMAP_START;
-	for (p = &iolist; (tmp = *p) ; p = &tmp->next) {
-		if (size + addr < (unsigned long)tmp->addr)
-			break;
-		if (addr > KMAP_END-size) {
-			kfree(area);
-			return NULL;
-		}
-		addr = tmp->size + (unsigned long)tmp->addr;
-	}
-	area->addr = (void *)addr;
-	area->size = size + IO_SIZE;
-	area->next = *p;
-	*p = area;
-	return area;
-}
-
-static inline void free_io_area(void *addr)
-{
-	struct vm_struct **p, *tmp;
-
-	if (!addr)
-		return;
-	addr = (void *)((unsigned long)addr & -IO_SIZE);
-	for (p = &iolist ; (tmp = *p) ; p = &tmp->next) {
-		if (tmp->addr == addr) {
-			*p = tmp->next;
-			__iounmap(tmp->addr, tmp->size);
-			kfree(tmp);
-			return;
-		}
-	}
-}
-
-#endif
-
-/*
- * Map some physical address range into the kernel address space.
- */
-/* Rewritten by Andreas Schwab to remove all races. */
-
-void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
-{
-	struct vm_struct *area;
-	unsigned long virtaddr, retaddr;
-	long offset;
-	pgd_t *pgd_dir;
-	pmd_t *pmd_dir;
-	pte_t *pte_dir;
-
-	/*
-	 * Don't allow mappings that wrap..
-	 */
-	if (!size || physaddr > (unsigned long)(-size))
-		return NULL;
-
-#ifdef CONFIG_AMIGA
-	if (MACH_IS_AMIGA) {
-		if ((physaddr >= 0x40000000) && (physaddr + size < 0x60000000)
-		    && (cacheflag == IOMAP_NOCACHE_SER))
-			return (void __iomem *)physaddr;
-	}
-#endif
-
-#ifdef DEBUG
-	printk("ioremap: 0x%lx,0x%lx(%d) - ", physaddr, size, cacheflag);
-#endif
-	/*
-	 * Mappings have to be aligned
-	 */
-	offset = physaddr & (IO_SIZE - 1);
-	physaddr &= -IO_SIZE;
-	size = (size + offset + IO_SIZE - 1) & -IO_SIZE;
-
-	/*
-	 * Ok, go for it..
-	 */
-	area = get_io_area(size);
-	if (!area)
-		return NULL;
-
-	virtaddr = (unsigned long)area->addr;
-	retaddr = virtaddr + offset;
-#ifdef DEBUG
-	printk("0x%lx,0x%lx,0x%lx", physaddr, virtaddr, retaddr);
-#endif
-
-	/*
-	 * add cache and table flags to physical address
-	 */
-	if (CPU_IS_040_OR_060) {
-		physaddr |= (_PAGE_PRESENT | _PAGE_GLOBAL040 |
-			     _PAGE_ACCESSED | _PAGE_DIRTY);
-		switch (cacheflag) {
-		case IOMAP_FULL_CACHING:
-			physaddr |= _PAGE_CACHE040;
-			break;
-		case IOMAP_NOCACHE_SER:
-		default:
-			physaddr |= _PAGE_NOCACHE_S;
-			break;
-		case IOMAP_NOCACHE_NONSER:
-			physaddr |= _PAGE_NOCACHE;
-			break;
-		case IOMAP_WRITETHROUGH:
-			physaddr |= _PAGE_CACHE040W;
-			break;
-		}
-	} else {
-		physaddr |= (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_DIRTY);
-		switch (cacheflag) {
-		case IOMAP_NOCACHE_SER:
-		case IOMAP_NOCACHE_NONSER:
-		default:
-			physaddr |= _PAGE_NOCACHE030;
-			break;
-		case IOMAP_FULL_CACHING:
-		case IOMAP_WRITETHROUGH:
-			break;
-		}
-	}
-
-	while ((long)size > 0) {
-#ifdef DEBUG
-		if (!(virtaddr & (PTRTREESIZE-1)))
-			printk ("\npa=%#lx va=%#lx ", physaddr, virtaddr);
-#endif
-		pgd_dir = pgd_offset_k(virtaddr);
-		pmd_dir = pmd_alloc(&init_mm, pgd_dir, virtaddr);
-		if (!pmd_dir) {
-			printk("ioremap: no mem for pmd_dir\n");
-			return NULL;
-		}
-
-		if (CPU_IS_020_OR_030) {
-			pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr;
-			physaddr += PTRTREESIZE;
-			virtaddr += PTRTREESIZE;
-			size -= PTRTREESIZE;
-		} else {
-			pte_dir = pte_alloc_kernel(pmd_dir, virtaddr);
-			if (!pte_dir) {
-				printk("ioremap: no mem for pte_dir\n");
-				return NULL;
-			}
-
-			pte_val(*pte_dir) = physaddr;
-			virtaddr += PAGE_SIZE;
-			physaddr += PAGE_SIZE;
-			size -= PAGE_SIZE;
-		}
-	}
-#ifdef DEBUG
-	printk("\n");
-#endif
-	flush_tlb_all();
-
-	return (void __iomem *)retaddr;
-}
-EXPORT_SYMBOL(__ioremap);
-
-/*
- * Unmap a ioremap()ed region again
- */
-void iounmap(void __iomem *addr)
-{
-#ifdef CONFIG_AMIGA
-	if ((!MACH_IS_AMIGA) ||
-	    (((unsigned long)addr < 0x40000000) ||
-	     ((unsigned long)addr > 0x60000000)))
-			free_io_area((__force void *)addr);
-#else
-	free_io_area((__force void *)addr);
-#endif
-}
-EXPORT_SYMBOL(iounmap);
-
-/*
- * __iounmap unmaps nearly everything, so be careful
- * it doesn't free currently pointer/page tables anymore but it
- * wans't used anyway and might be added later.
- */
-void __iounmap(void *addr, unsigned long size)
-{
-	unsigned long virtaddr = (unsigned long)addr;
-	pgd_t *pgd_dir;
-	pmd_t *pmd_dir;
-	pte_t *pte_dir;
-
-	while ((long)size > 0) {
-		pgd_dir = pgd_offset_k(virtaddr);
-		if (pgd_bad(*pgd_dir)) {
-			printk("iounmap: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
-			pgd_clear(pgd_dir);
-			return;
-		}
-		pmd_dir = pmd_offset(pgd_dir, virtaddr);
-
-		if (CPU_IS_020_OR_030) {
-			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
-			int pmd_type = pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK;
-
-			if (pmd_type == _PAGE_PRESENT) {
-				pmd_dir->pmd[pmd_off] = 0;
-				virtaddr += PTRTREESIZE;
-				size -= PTRTREESIZE;
-				continue;
-			} else if (pmd_type == 0)
-				continue;
-		}
-
-		if (pmd_bad(*pmd_dir)) {
-			printk("iounmap: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
-			pmd_clear(pmd_dir);
-			return;
-		}
-		pte_dir = pte_offset_kernel(pmd_dir, virtaddr);
-
-		pte_val(*pte_dir) = 0;
-		virtaddr += PAGE_SIZE;
-		size -= PAGE_SIZE;
-	}
-
-	flush_tlb_all();
-}
-
-/*
- * Set new cache mode for some kernel address space.
- * The caller must push data for that range itself, if such data may already
- * be in the cache.
- */
-void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
-{
-	unsigned long virtaddr = (unsigned long)addr;
-	pgd_t *pgd_dir;
-	pmd_t *pmd_dir;
-	pte_t *pte_dir;
-
-	if (CPU_IS_040_OR_060) {
-		switch (cmode) {
-		case IOMAP_FULL_CACHING:
-			cmode = _PAGE_CACHE040;
-			break;
-		case IOMAP_NOCACHE_SER:
-		default:
-			cmode = _PAGE_NOCACHE_S;
-			break;
-		case IOMAP_NOCACHE_NONSER:
-			cmode = _PAGE_NOCACHE;
-			break;
-		case IOMAP_WRITETHROUGH:
-			cmode = _PAGE_CACHE040W;
-			break;
-		}
-	} else {
-		switch (cmode) {
-		case IOMAP_NOCACHE_SER:
-		case IOMAP_NOCACHE_NONSER:
-		default:
-			cmode = _PAGE_NOCACHE030;
-			break;
-		case IOMAP_FULL_CACHING:
-		case IOMAP_WRITETHROUGH:
-			cmode = 0;
-		}
-	}
-
-	while ((long)size > 0) {
-		pgd_dir = pgd_offset_k(virtaddr);
-		if (pgd_bad(*pgd_dir)) {
-			printk("iocachemode: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
-			pgd_clear(pgd_dir);
-			return;
-		}
-		pmd_dir = pmd_offset(pgd_dir, virtaddr);
-
-		if (CPU_IS_020_OR_030) {
-			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
-
-			if ((pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK) == _PAGE_PRESENT) {
-				pmd_dir->pmd[pmd_off] = (pmd_dir->pmd[pmd_off] &
-							 _CACHEMASK040) | cmode;
-				virtaddr += PTRTREESIZE;
-				size -= PTRTREESIZE;
-				continue;
-			}
-		}
-
-		if (pmd_bad(*pmd_dir)) {
-			printk("iocachemode: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
-			pmd_clear(pmd_dir);
-			return;
-		}
-		pte_dir = pte_offset_kernel(pmd_dir, virtaddr);
-
-		pte_val(*pte_dir) = (pte_val(*pte_dir) & _CACHEMASK040) | cmode;
-		virtaddr += PAGE_SIZE;
-		size -= PAGE_SIZE;
-	}
-
-	flush_tlb_all();
-}
-EXPORT_SYMBOL(kernel_set_cachemode);
diff --git a/arch/m68k/mm/kmap_no.c b/arch/m68k/mm/kmap_no.c
deleted file mode 100644
index ece8d5ad4e6c..000000000000
--- a/arch/m68k/mm/kmap_no.c
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- *  linux/arch/m68knommu/mm/kmap.c
- *
- *  Copyright (C) 2000 Lineo, <davidm@snapgear.com>
- *  Copyright (C) 2000-2002 David McCullough <davidm@snapgear.com>
- */
-
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/vmalloc.h>
-
-#include <asm/setup.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-#include <asm/io.h>
-#include <asm/system.h>
-
-#undef DEBUG
-
-/*
- * Map some physical address range into the kernel address space.
- */
-void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
-{
-	return (void *)physaddr;
-}
-
-/*
- * Unmap a ioremap()ed region again.
- */
-void iounmap(void *addr)
-{
-}
-
-/*
- * Set new cache mode for some kernel address space.
- * The caller must push data for that range itself, if such data may already
- * be in the cache.
- */
-void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
-{
-}
diff --git a/arch/m68k/platform/68328/entry.S b/arch/m68k/platform/68328/entry.S
index 676960cf022a..f68dce766c0a 100644
--- a/arch/m68k/platform/68328/entry.S
+++ b/arch/m68k/platform/68328/entry.S
@@ -10,7 +10,6 @@
  * Linux/m68k support by Hamish Macdonald
  */
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
@@ -80,7 +79,7 @@ ENTRY(system_call)
 	movel	%sp,%d1			/* get thread_info pointer */
 	andl	#-THREAD_SIZE,%d1
 	movel	%d1,%a2
-	btst	#(TIF_SYSCALL_TRACE%8),%a2@(TI_FLAGS+(31-TIF_SYSCALL_TRACE)/8)
+	btst	#(TIF_SYSCALL_TRACE%8),%a2@(TINFO_FLAGS+(31-TIF_SYSCALL_TRACE)/8)
 	jne	do_trace
 	cmpl	#NR_syscalls,%d0
 	jcc	badsys
@@ -107,12 +106,12 @@ Luser_return:
 	andl	#-THREAD_SIZE,%d1
 	movel	%d1,%a2
 1:
-	move	%a2@(TI_FLAGS),%d1	/* thread_info->flags */
+	move	%a2@(TINFO_FLAGS),%d1	/* thread_info->flags */
 	jne	Lwork_to_do
 	RESTORE_ALL
 
 Lwork_to_do:
-	movel	%a2@(TI_FLAGS),%d1	/* thread_info->flags */
+	movel	%a2@(TINFO_FLAGS),%d1	/* thread_info->flags */
 	btst	#TIF_NEED_RESCHED,%d1
 	jne	reschedule
 
diff --git a/arch/m68k/platform/68360/entry.S b/arch/m68k/platform/68360/entry.S
index 46c1b18c9dcb..a07b14feed92 100644
--- a/arch/m68k/platform/68360/entry.S
+++ b/arch/m68k/platform/68360/entry.S
@@ -12,7 +12,6 @@
  * M68360 Port by SED Systems, and Lineo.
  */
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
@@ -76,7 +75,7 @@ ENTRY(system_call)
 	movel	%sp,%d1			/* get thread_info pointer */
 	andl	#-THREAD_SIZE,%d1
 	movel	%d1,%a2
-	btst	#(TIF_SYSCALL_TRACE%8),%a2@(TI_FLAGS+(31-TIF_SYSCALL_TRACE)/8)
+	btst	#(TIF_SYSCALL_TRACE%8),%a2@(TINFO_FLAGS+(31-TIF_SYSCALL_TRACE)/8)
 	jne	do_trace
 	cmpl	#NR_syscalls,%d0
 	jcc	badsys
@@ -103,12 +102,12 @@ Luser_return:
 	andl	#-THREAD_SIZE,%d1
 	movel	%d1,%a2
 1:
-	move	%a2@(TI_FLAGS),%d1	/* thread_info->flags */
+	move	%a2@(TINFO_FLAGS),%d1	/* thread_info->flags */
 	jne	Lwork_to_do
 	RESTORE_ALL
 
 Lwork_to_do:
-	movel	%a2@(TI_FLAGS),%d1	/* thread_info->flags */
+	movel	%a2@(TINFO_FLAGS),%d1	/* thread_info->flags */
 	btst	#TIF_NEED_RESCHED,%d1
 	jne	reschedule
 
diff --git a/arch/m68k/platform/coldfire/dma.c b/arch/m68k/platform/coldfire/dma.c
index e88b95e2cc62..df5ce20d181c 100644
--- a/arch/m68k/platform/coldfire/dma.c
+++ b/arch/m68k/platform/coldfire/dma.c
@@ -9,6 +9,7 @@
 /***************************************************************************/
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <asm/dma.h>
 #include <asm/coldfire.h>
 #include <asm/mcfsim.h>
@@ -33,7 +34,9 @@ unsigned int dma_base_addr[MAX_M68K_DMA_CHANNELS] = {
 	MCFDMA_BASE3,
 #endif
 };
+EXPORT_SYMBOL(dma_base_addr);
 
 unsigned int dma_device_address[MAX_M68K_DMA_CHANNELS];
+EXPORT_SYMBOL(dma_device_address);
 
 /***************************************************************************/
diff --git a/arch/m68k/platform/coldfire/entry.S b/arch/m68k/platform/coldfire/entry.S
index eab63f09965b..27c2b001161e 100644
--- a/arch/m68k/platform/coldfire/entry.S
+++ b/arch/m68k/platform/coldfire/entry.S
@@ -26,7 +26,6 @@
  * Bug, speed and maintainability fixes by Philippe De Muyter <phdm@macqel.be>
  */
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
@@ -78,7 +77,7 @@ ENTRY(system_call)
 	movel	%d2,%a0
 	movel	%a0@,%a1		/* save top of frame */
 	movel	%sp,%a1@(TASK_THREAD+THREAD_ESP0)
-	btst	#(TIF_SYSCALL_TRACE%8),%a0@(TI_FLAGS+(31-TIF_SYSCALL_TRACE)/8)
+	btst	#(TIF_SYSCALL_TRACE%8),%a0@(TINFO_FLAGS+(31-TIF_SYSCALL_TRACE)/8)
 	bnes	1f
 
 	movel	%d3,%a0
@@ -113,11 +112,11 @@ ret_from_exception:
 	movel	%sp,%d1			/* get thread_info pointer */
 	andl	#-THREAD_SIZE,%d1	/* at base of kernel stack */
 	movel	%d1,%a0
-	movel	%a0@(TI_FLAGS),%d1	/* get thread_info->flags */
+	movel	%a0@(TINFO_FLAGS),%d1	/* get thread_info->flags */
 	andl	#(1<<TIF_NEED_RESCHED),%d1
 	jeq	Lkernel_return
 
-	movel	%a0@(TI_PREEMPTCOUNT),%d1
+	movel	%a0@(TINFO_PREEMPT),%d1
 	cmpl	#0,%d1
 	jne	Lkernel_return
 
@@ -137,14 +136,14 @@ Luser_return:
 	movel	%sp,%d1			/* get thread_info pointer */
 	andl	#-THREAD_SIZE,%d1	/* at base of kernel stack */
 	movel	%d1,%a0
-	movel	%a0@(TI_FLAGS),%d1	/* get thread_info->flags */
+	movel	%a0@(TINFO_FLAGS),%d1	/* get thread_info->flags */
 	jne	Lwork_to_do		/* still work to do */
 
 Lreturn:
 	RESTORE_USER
 
 Lwork_to_do:
-	movel	%a0@(TI_FLAGS),%d1	/* get thread_info->flags */
+	movel	%a0@(TINFO_FLAGS),%d1	/* get thread_info->flags */
 	move	#0x2000,%sr		/* enable intrs again */
 	btst	#TIF_NEED_RESCHED,%d1
 	jne	reschedule
diff --git a/arch/m68k/platform/coldfire/head.S b/arch/m68k/platform/coldfire/head.S
index 6ae91a499184..c33483824a2e 100644
--- a/arch/m68k/platform/coldfire/head.S
+++ b/arch/m68k/platform/coldfire/head.S
@@ -8,7 +8,6 @@
 
 /*****************************************************************************/
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 01af3876cf90..a81176f44c74 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -118,7 +118,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU(1 << CONFIG_MIPS_L1_CACHE_SHIFT, PAGE_SIZE)
+	PERCPU_SECTION(1 << CONFIG_MIPS_L1_CACHE_SHIFT)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index 968bcd2cb022..6f702a6ab395 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -70,7 +70,7 @@ SECTIONS
 	.exit.text : { EXIT_TEXT; }
 	.exit.data : { EXIT_DATA; }
 
-  PERCPU(32, PAGE_SIZE)
+  PERCPU_SECTION(32)
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
   /* freed after init ends here */
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index e1a55849bfa7..fa6f2b8163e0 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -149,7 +149,7 @@ SECTIONS
 		EXIT_DATA
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index b9150f07d266..920276c0f6a1 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -160,7 +160,7 @@ SECTIONS
 		INIT_RAM_FS
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4a7f14079e03..ff2d2371b2e9 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -230,17 +230,6 @@ config SYSVIPC_COMPAT
 config AUDIT_ARCH
 	def_bool y
 
-config S390_EXEC_PROTECT
-	def_bool y
-	prompt "Data execute protection"
-	help
-	  This option allows to enable a buffer overflow protection for user
-	  space programs and it also selects the addressing mode option above.
-	  The kernel parameter noexec=on will enable this feature and also
-	  switch the addressing modes, default is disabled. Enabling this (via
-	  kernel parameter) on machines earlier than IBM System z9 this will
-	  reduce system performance.
-
 comment "Code generation options"
 
 choice
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 5c91995b74e4..24bff4f1cc52 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -130,9 +130,7 @@ static void appldata_work_fn(struct work_struct *work)
 {
 	struct list_head *lh;
 	struct appldata_ops *ops;
-	int i;
 
-	i = 0;
 	get_online_cpus();
 	mutex_lock(&appldata_ops_mutex);
 	list_for_each(lh, &appldata_ops_list) {
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 7488e52efa97..81d7908416cf 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -167,7 +167,6 @@ static inline unsigned long __cmpxchg(void *ptr, unsigned long old,
 #ifdef CONFIG_64BIT
 #define cmpxchg64(ptr, o, n)						\
 ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
 	cmpxchg((ptr), (o), (n));					\
 })
 #else /* CONFIG_64BIT */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 10c029cfcc7d..64b61bf72e93 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -196,18 +196,6 @@ do {								\
 } while (0)
 #endif /* __s390x__ */
 
-/*
- * An executable for which elf_read_implies_exec() returns TRUE will
- * have the READ_IMPLIES_EXEC personality flag set automatically.
- */
-#define elf_read_implies_exec(ex, executable_stack)	\
-({							\
-	if (current->mm->context.noexec &&		\
-	    executable_stack != EXSTACK_DISABLE_X)	\
-		disable_noexec(current->mm, current);	\
-	current->mm->context.noexec == 0;		\
-})
-
 #define STACK_RND_MASK	0x7ffUL
 
 #define ARCH_DLINFO							    \
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index b56403c2df28..799ed0f1643d 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -111,21 +111,10 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm,
 {
 	pmd_t *pmdp = (pmd_t *) ptep;
 
-	if (!MACHINE_HAS_IDTE) {
-		__pmd_csp(pmdp);
-		if (mm->context.noexec) {
-			pmdp = get_shadow_table(pmdp);
-			__pmd_csp(pmdp);
-		}
-		return;
-	}
-
-	__pmd_idte(address, pmdp);
-	if (mm->context.noexec) {
-		pmdp = get_shadow_table(pmdp);
+	if (MACHINE_HAS_IDTE)
 		__pmd_idte(address, pmdp);
-	}
-	return;
+	else
+		__pmd_csp(pmdp);
 }
 
 #define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index db14a311f1d2..1544b90bd6d6 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -15,6 +15,7 @@ enum interruption_class {
 	EXTINT_VRT,
 	EXTINT_SCP,
 	EXTINT_IUC,
+	EXTINT_CPM,
 	IOINT_QAI,
 	IOINT_QDI,
 	IOINT_DAS,
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 65e172f8209d..228cf0b295db 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -124,7 +124,7 @@ struct _lowcore {
 	/* Address space pointer. */
 	__u32	kernel_asce;			/* 0x02ac */
 	__u32	user_asce;			/* 0x02b0 */
-	__u32	user_exec_asce;			/* 0x02b4 */
+	__u32	current_pid;			/* 0x02b4 */
 
 	/* SMP info area */
 	__u32	cpu_nr;				/* 0x02b8 */
@@ -255,7 +255,7 @@ struct _lowcore {
 	/* Address space pointer. */
 	__u64	kernel_asce;			/* 0x0310 */
 	__u64	user_asce;			/* 0x0318 */
-	__u64	user_exec_asce;			/* 0x0320 */
+	__u64	current_pid;			/* 0x0320 */
 
 	/* SMP info area */
 	__u32	cpu_nr;				/* 0x0328 */
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 78522cdefdd4..82d0847896a0 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -5,19 +5,18 @@ typedef struct {
 	atomic_t attach_count;
 	unsigned int flush_mm;
 	spinlock_t list_lock;
-	struct list_head crst_list;
 	struct list_head pgtable_list;
 	unsigned long asce_bits;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
-	int noexec;
-	int has_pgste;	 /* The mmu context has extended page tables */
-	int alloc_pgste; /* cloned contexts will have extended page tables */
+	/* Cloned contexts will be created with extended page tables. */
+	unsigned int alloc_pgste:1;
+	/* The mmu context has extended page tables. */
+	unsigned int has_pgste:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						      \
 	.context.list_lock    = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \
-	.context.crst_list    = LIST_HEAD_INIT(name.context.crst_list),	      \
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),
 
 #endif
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 8c277caa8d3a..5682f160ff82 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -35,11 +35,9 @@ static inline int init_new_context(struct task_struct *tsk,
 		 * and if has_pgste is set, it will create extended page
 		 * tables.
 		 */
-		mm->context.noexec = 0;
 		mm->context.has_pgste = 1;
 		mm->context.alloc_pgste = 1;
 	} else {
-		mm->context.noexec = (user_mode == SECONDARY_SPACE_MODE);
 		mm->context.has_pgste = 0;
 		mm->context.alloc_pgste = 0;
 	}
@@ -63,10 +61,8 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
 	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
 	if (user_mode != HOME_SPACE_MODE) {
 		/* Load primary space page table origin. */
-		pgd = mm->context.noexec ? get_shadow_table(pgd) : pgd;
-		S390_lowcore.user_exec_asce = mm->context.asce_bits | __pa(pgd);
 		asm volatile(LCTL_OPCODE" 1,1,%0\n"
-			     : : "m" (S390_lowcore.user_exec_asce) );
+			     : : "m" (S390_lowcore.user_asce) );
 	} else
 		/* Load home space page table origin. */
 		asm volatile(LCTL_OPCODE" 13,13,%0"
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 3c987e9ec8d6..accb372ddc7e 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -90,6 +90,7 @@ static inline void copy_page(void *to, void *from)
  */
 
 typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct { unsigned long pgste; } pgste_t;
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pud; } pud_t;
@@ -97,18 +98,21 @@ typedef struct { unsigned long pgd; } pgd_t;
 typedef pte_t *pgtable_t;
 
 #define pgprot_val(x)	((x).pgprot)
+#define pgste_val(x)	((x).pgste)
 #define pte_val(x)	((x).pte)
 #define pmd_val(x)	((x).pmd)
 #define pud_val(x)	((x).pud)
 #define pgd_val(x)      ((x).pgd)
 
+#define __pgste(x)	((pgste_t) { (x) } )
 #define __pte(x)        ((pte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
+#define __pud(x)	((pud_t) { (x) } )
 #define __pgd(x)        ((pgd_t) { (x) } )
 #define __pgprot(x)     ((pgprot_t) { (x) } )
 
-static inline void
-page_set_storage_key(unsigned long addr, unsigned int skey, int mapped)
+static inline void page_set_storage_key(unsigned long addr,
+					unsigned char skey, int mapped)
 {
 	if (!mapped)
 		asm volatile(".insn rrf,0xb22b0000,%0,%1,8,0"
@@ -117,15 +121,59 @@ page_set_storage_key(unsigned long addr, unsigned int skey, int mapped)
 		asm volatile("sske %0,%1" : : "d" (skey), "a" (addr));
 }
 
-static inline unsigned int
-page_get_storage_key(unsigned long addr)
+static inline unsigned char page_get_storage_key(unsigned long addr)
 {
-	unsigned int skey;
+	unsigned char skey;
 
-	asm volatile("iske %0,%1" : "=d" (skey) : "a" (addr), "0" (0));
+	asm volatile("iske %0,%1" : "=d" (skey) : "a" (addr));
 	return skey;
 }
 
+static inline int page_reset_referenced(unsigned long addr)
+{
+	unsigned int ipm;
+
+	asm volatile(
+		"	rrbe	0,%1\n"
+		"	ipm	%0\n"
+		: "=d" (ipm) : "a" (addr) : "cc");
+	return !!(ipm & 0x20000000);
+}
+
+/* Bits int the storage key */
+#define _PAGE_CHANGED		0x02	/* HW changed bit		*/
+#define _PAGE_REFERENCED	0x04	/* HW referenced bit		*/
+#define _PAGE_FP_BIT		0x08	/* HW fetch protection bit	*/
+#define _PAGE_ACC_BITS		0xf0	/* HW access control bits	*/
+
+/*
+ * Test and clear dirty bit in storage key.
+ * We can't clear the changed bit atomically. This is a potential
+ * race against modification of the referenced bit. This function
+ * should therefore only be called if it is not mapped in any
+ * address space.
+ */
+#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
+static inline int page_test_and_clear_dirty(unsigned long pfn, int mapped)
+{
+	unsigned char skey;
+
+	skey = page_get_storage_key(pfn << PAGE_SHIFT);
+	if (!(skey & _PAGE_CHANGED))
+		return 0;
+	page_set_storage_key(pfn << PAGE_SHIFT, skey & ~_PAGE_CHANGED, mapped);
+	return 1;
+}
+
+/*
+ * Test and clear referenced bit in storage key.
+ */
+#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
+static inline int page_test_and_clear_young(unsigned long pfn)
+{
+	return page_reset_referenced(pfn << PAGE_SHIFT);
+}
+
 struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index f7ad8719d02d..5325c89a5843 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -1,6 +1,9 @@
 #ifndef __ARCH_S390_PERCPU__
 #define __ARCH_S390_PERCPU__
 
+#include <linux/preempt.h>
+#include <asm/cmpxchg.h>
+
 /*
  * s390 uses its own implementation for per cpu data, the offset of
  * the cpu local data area is cached in the cpu's lowcore memory.
@@ -16,6 +19,71 @@
 #define ARCH_NEEDS_WEAK_PER_CPU
 #endif
 
+#define arch_irqsafe_cpu_to_op(pcp, val, op)				\
+do {									\
+	typedef typeof(pcp) pcp_op_T__;					\
+	pcp_op_T__ old__, new__, prev__;				\
+	pcp_op_T__ *ptr__;						\
+	preempt_disable();						\
+	ptr__ = __this_cpu_ptr(&(pcp));					\
+	prev__ = *ptr__;						\
+	do {								\
+		old__ = prev__;						\
+		new__ = old__ op (val);					\
+		switch (sizeof(*ptr__)) {				\
+		case 8:							\
+			prev__ = cmpxchg64(ptr__, old__, new__);	\
+			break;						\
+		default:						\
+			prev__ = cmpxchg(ptr__, old__, new__);		\
+		}							\
+	} while (prev__ != old__);					\
+	preempt_enable();						\
+} while (0)
+
+#define irqsafe_cpu_add_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
+#define irqsafe_cpu_add_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
+#define irqsafe_cpu_add_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
+#define irqsafe_cpu_add_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
+
+#define irqsafe_cpu_and_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
+#define irqsafe_cpu_and_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
+#define irqsafe_cpu_and_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
+#define irqsafe_cpu_and_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
+
+#define irqsafe_cpu_or_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
+#define irqsafe_cpu_or_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
+#define irqsafe_cpu_or_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
+#define irqsafe_cpu_or_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
+
+#define irqsafe_cpu_xor_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
+#define irqsafe_cpu_xor_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
+#define irqsafe_cpu_xor_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
+#define irqsafe_cpu_xor_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
+
+#define arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)			\
+({									\
+	typedef typeof(pcp) pcp_op_T__;					\
+	pcp_op_T__ ret__;						\
+	pcp_op_T__ *ptr__;						\
+	preempt_disable();						\
+	ptr__ = __this_cpu_ptr(&(pcp));					\
+	switch (sizeof(*ptr__)) {					\
+	case 8:								\
+		ret__ = cmpxchg64(ptr__, oval, nval);			\
+		break;							\
+	default:							\
+		ret__ = cmpxchg(ptr__, oval, nval);			\
+	}								\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#define irqsafe_cpu_cmpxchg_1(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_2(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_4(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_8(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ARCH_S390_PERCPU__ */
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 082eb4e50e8b..f6314af3b354 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -19,14 +19,13 @@
 
 #define check_pgt_cache()	do {} while (0)
 
-unsigned long *crst_table_alloc(struct mm_struct *, int);
+unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
 void crst_table_free_rcu(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mm_struct *, unsigned long *);
-void disable_noexec(struct mm_struct *, struct task_struct *);
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
@@ -50,9 +49,6 @@ static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 {
 	clear_table(crst, entry, sizeof(unsigned long)*2048);
-	crst = get_shadow_table(crst);
-	if (crst)
-		clear_table(crst, entry, sizeof(unsigned long)*2048);
 }
 
 #ifndef __s390x__
@@ -69,10 +65,7 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 #define pmd_free(mm, x)				do { } while (0)
 
 #define pgd_populate(mm, pgd, pud)		BUG()
-#define pgd_populate_kernel(mm, pgd, pud)	BUG()
-
 #define pud_populate(mm, pud, pmd)		BUG()
-#define pud_populate_kernel(mm, pud, pmd)	BUG()
 
 #else /* __s390x__ */
 
@@ -90,7 +83,7 @@ void crst_table_downgrade(struct mm_struct *, unsigned long limit);
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	unsigned long *table = crst_table_alloc(mm, mm->context.noexec);
+	unsigned long *table = crst_table_alloc(mm);
 	if (table)
 		crst_table_init(table, _REGION3_ENTRY_EMPTY);
 	return (pud_t *) table;
@@ -99,43 +92,21 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *table = crst_table_alloc(mm, mm->context.noexec);
+	unsigned long *table = crst_table_alloc(mm);
 	if (table)
 		crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
 	return (pmd_t *) table;
 }
 #define pmd_free(mm, pmd) crst_table_free(mm, (unsigned long *) pmd)
 
-static inline void pgd_populate_kernel(struct mm_struct *mm,
-				       pgd_t *pgd, pud_t *pud)
-{
-	pgd_val(*pgd) = _REGION2_ENTRY | __pa(pud);
-}
-
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 {
-	pgd_populate_kernel(mm, pgd, pud);
-	if (mm->context.noexec) {
-		pgd = get_shadow_table(pgd);
-		pud = get_shadow_table(pud);
-		pgd_populate_kernel(mm, pgd, pud);
-	}
-}
-
-static inline void pud_populate_kernel(struct mm_struct *mm,
-				       pud_t *pud, pmd_t *pmd)
-{
-	pud_val(*pud) = _REGION3_ENTRY | __pa(pmd);
+	pgd_val(*pgd) = _REGION2_ENTRY | __pa(pud);
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pud_populate_kernel(mm, pud, pmd);
-	if (mm->context.noexec) {
-		pud = get_shadow_table(pud);
-		pmd = get_shadow_table(pmd);
-		pud_populate_kernel(mm, pud, pmd);
-	}
+	pud_val(*pud) = _REGION3_ENTRY | __pa(pmd);
 }
 
 #endif /* __s390x__ */
@@ -143,29 +114,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	spin_lock_init(&mm->context.list_lock);
-	INIT_LIST_HEAD(&mm->context.crst_list);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
-	return (pgd_t *)
-		crst_table_alloc(mm, user_mode == SECONDARY_SPACE_MODE);
+	return (pgd_t *) crst_table_alloc(mm);
 }
 #define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
 
-static inline void pmd_populate_kernel(struct mm_struct *mm,
-				       pmd_t *pmd, pte_t *pte)
-{
-	pmd_val(*pmd) = _SEGMENT_ENTRY + __pa(pte);
-}
-
 static inline void pmd_populate(struct mm_struct *mm,
 				pmd_t *pmd, pgtable_t pte)
 {
-	pmd_populate_kernel(mm, pmd, pte);
-	if (mm->context.noexec) {
-		pmd = get_shadow_table(pmd);
-		pmd_populate_kernel(mm, pmd, pte + PTRS_PER_PTE);
-	}
+	pmd_val(*pmd) = _SEGMENT_ENTRY + __pa(pte);
 }
 
+#define pmd_populate_kernel(mm, pmd, pte) pmd_populate(mm, pmd, pte)
+
 #define pmd_pgtable(pmd) \
 	(pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 02ace3491c51..c4773a2ef3d3 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -31,9 +31,8 @@
 #ifndef __ASSEMBLY__
 #include <linux/sched.h>
 #include <linux/mm_types.h>
-#include <asm/bitops.h>
 #include <asm/bug.h>
-#include <asm/processor.h>
+#include <asm/page.h>
 
 extern pgd_t swapper_pg_dir[] __attribute__ ((aligned (4096)));
 extern void paging_init(void);
@@ -243,11 +242,13 @@ extern unsigned long VMALLOC_START;
 /* Software bits in the page table entry */
 #define _PAGE_SWT	0x001		/* SW pte type bit t */
 #define _PAGE_SWX	0x002		/* SW pte type bit x */
-#define _PAGE_SPECIAL	0x004		/* SW associated with special page */
+#define _PAGE_SWC	0x004		/* SW pte changed bit (for KVM) */
+#define _PAGE_SWR	0x008		/* SW pte referenced bit (for KVM) */
+#define _PAGE_SPECIAL	0x010		/* SW associated with special page */
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_SPECIAL)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_SPECIAL | _PAGE_SWC | _PAGE_SWR)
 
 /* Six different types of pages. */
 #define _PAGE_TYPE_EMPTY	0x400
@@ -256,8 +257,6 @@ extern unsigned long VMALLOC_START;
 #define _PAGE_TYPE_FILE		0x601	/* bit 0x002 is used for offset !! */
 #define _PAGE_TYPE_RO		0x200
 #define _PAGE_TYPE_RW		0x000
-#define _PAGE_TYPE_EX_RO	0x202
-#define _PAGE_TYPE_EX_RW	0x002
 
 /*
  * Only four types for huge pages, using the invalid bit and protection bit
@@ -287,8 +286,6 @@ extern unsigned long VMALLOC_START;
  * _PAGE_TYPE_FILE	11?1   ->   11?1
  * _PAGE_TYPE_RO	0100   ->   1100
  * _PAGE_TYPE_RW	0000   ->   1000
- * _PAGE_TYPE_EX_RO	0110   ->   1110
- * _PAGE_TYPE_EX_RW	0010   ->   1010
  *
  * pte_none is true for bits combinations 1000, 1010, 1100, 1110
  * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001
@@ -297,14 +294,17 @@ extern unsigned long VMALLOC_START;
  */
 
 /* Page status table bits for virtualization */
-#define RCP_PCL_BIT	55
-#define RCP_HR_BIT	54
-#define RCP_HC_BIT	53
-#define RCP_GR_BIT	50
-#define RCP_GC_BIT	49
-
-/* User dirty bit for KVM's migration feature */
-#define KVM_UD_BIT	47
+#define RCP_ACC_BITS	0xf000000000000000UL
+#define RCP_FP_BIT	0x0800000000000000UL
+#define RCP_PCL_BIT	0x0080000000000000UL
+#define RCP_HR_BIT	0x0040000000000000UL
+#define RCP_HC_BIT	0x0020000000000000UL
+#define RCP_GR_BIT	0x0004000000000000UL
+#define RCP_GC_BIT	0x0002000000000000UL
+
+/* User dirty / referenced bit for KVM's migration feature */
+#define KVM_UR_BIT	0x0000800000000000UL
+#define KVM_UC_BIT	0x0000400000000000UL
 
 #ifndef __s390x__
 
@@ -377,85 +377,54 @@ extern unsigned long VMALLOC_START;
 #define _ASCE_USER_BITS		(_ASCE_SPACE_SWITCH | _ASCE_PRIVATE_SPACE | \
 				 _ASCE_ALT_EVENT)
 
-/* Bits int the storage key */
-#define _PAGE_CHANGED    0x02          /* HW changed bit                   */
-#define _PAGE_REFERENCED 0x04          /* HW referenced bit                */
-
 /*
  * Page protection definitions.
  */
 #define PAGE_NONE	__pgprot(_PAGE_TYPE_NONE)
 #define PAGE_RO		__pgprot(_PAGE_TYPE_RO)
 #define PAGE_RW		__pgprot(_PAGE_TYPE_RW)
-#define PAGE_EX_RO	__pgprot(_PAGE_TYPE_EX_RO)
-#define PAGE_EX_RW	__pgprot(_PAGE_TYPE_EX_RW)
 
 #define PAGE_KERNEL	PAGE_RW
 #define PAGE_COPY	PAGE_RO
 
 /*
- * Dependent on the EXEC_PROTECT option s390 can do execute protection.
- * Write permission always implies read permission. In theory with a
- * primary/secondary page table execute only can be implemented but
- * it would cost an additional bit in the pte to distinguish all the
- * different pte types. To avoid that execute permission currently
- * implies read permission as well.
+ * On s390 the page table entry has an invalid bit and a read-only bit.
+ * Read permission implies execute permission and write permission
+ * implies read permission.
  */
          /*xwr*/
 #define __P000	PAGE_NONE
 #define __P001	PAGE_RO
 #define __P010	PAGE_RO
 #define __P011	PAGE_RO
-#define __P100	PAGE_EX_RO
-#define __P101	PAGE_EX_RO
-#define __P110	PAGE_EX_RO
-#define __P111	PAGE_EX_RO
+#define __P100	PAGE_RO
+#define __P101	PAGE_RO
+#define __P110	PAGE_RO
+#define __P111	PAGE_RO
 
 #define __S000	PAGE_NONE
 #define __S001	PAGE_RO
 #define __S010	PAGE_RW
 #define __S011	PAGE_RW
-#define __S100	PAGE_EX_RO
-#define __S101	PAGE_EX_RO
-#define __S110	PAGE_EX_RW
-#define __S111	PAGE_EX_RW
-
-#ifndef __s390x__
-# define PxD_SHADOW_SHIFT	1
-#else /* __s390x__ */
-# define PxD_SHADOW_SHIFT	2
-#endif /* __s390x__ */
+#define __S100	PAGE_RO
+#define __S101	PAGE_RO
+#define __S110	PAGE_RW
+#define __S111	PAGE_RW
 
-static inline void *get_shadow_table(void *table)
+static inline int mm_exclusive(struct mm_struct *mm)
 {
-	unsigned long addr, offset;
-	struct page *page;
-
-	addr = (unsigned long) table;
-	offset = addr & ((PAGE_SIZE << PxD_SHADOW_SHIFT) - 1);
-	page = virt_to_page((void *)(addr ^ offset));
-	return (void *)(addr_t)(page->index ? (page->index | offset) : 0UL);
+	return likely(mm == current->active_mm &&
+		      atomic_read(&mm->context.attach_count) <= 1);
 }
 
-/*
- * Certain architectures need to do special things when PTEs
- * within a page table are directly modified.  Thus, the following
- * hook is made available.
- */
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t entry)
+static inline int mm_has_pgste(struct mm_struct *mm)
 {
-	*ptep = entry;
-	if (mm->context.noexec) {
-		if (!(pte_val(entry) & _PAGE_INVALID) &&
-		    (pte_val(entry) & _PAGE_SWX))
-			pte_val(entry) |= _PAGE_RO;
-		else
-			pte_val(entry) = _PAGE_TYPE_EMPTY;
-		ptep[PTRS_PER_PTE] = entry;
-	}
+#ifdef CONFIG_PGSTE
+	if (unlikely(mm->context.has_pgste))
+		return 1;
+#endif
+	return 0;
 }
-
 /*
  * pgd/pmd/pte query functions
  */
@@ -568,52 +537,127 @@ static inline int pte_special(pte_t pte)
 }
 
 #define __HAVE_ARCH_PTE_SAME
-#define pte_same(a,b)  (pte_val(a) == pte_val(b))
+static inline int pte_same(pte_t a, pte_t b)
+{
+	return pte_val(a) == pte_val(b);
+}
 
-static inline void rcp_lock(pte_t *ptep)
+static inline pgste_t pgste_get_lock(pte_t *ptep)
 {
+	unsigned long new = 0;
 #ifdef CONFIG_PGSTE
-	unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
+	unsigned long old;
+
 	preempt_disable();
-	while (test_and_set_bit(RCP_PCL_BIT, pgste))
-		;
+	asm(
+		"	lg	%0,%2\n"
+		"0:	lgr	%1,%0\n"
+		"	nihh	%0,0xff7f\n"	/* clear RCP_PCL_BIT in old */
+		"	oihh	%1,0x0080\n"	/* set RCP_PCL_BIT in new */
+		"	csg	%0,%1,%2\n"
+		"	jl	0b\n"
+		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
+		: "Q" (ptep[PTRS_PER_PTE]) : "cc");
 #endif
+	return __pgste(new);
 }
 
-static inline void rcp_unlock(pte_t *ptep)
+static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
-	clear_bit(RCP_PCL_BIT, pgste);
+	asm(
+		"	nihh	%1,0xff7f\n"	/* clear RCP_PCL_BIT */
+		"	stg	%1,%0\n"
+		: "=Q" (ptep[PTRS_PER_PTE])
+		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) : "cc");
 	preempt_enable();
 #endif
 }
 
-/* forward declaration for SetPageUptodate in page-flags.h*/
-static inline void page_clear_dirty(struct page *page, int mapped);
-#include <linux/page-flags.h>
-
-static inline void ptep_rcp_copy(pte_t *ptep)
+static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-	struct page *page = virt_to_page(pte_val(*ptep));
-	unsigned int skey;
-	unsigned long *pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
-
-	skey = page_get_storage_key(page_to_phys(page));
-	if (skey & _PAGE_CHANGED) {
-		set_bit_simple(RCP_GC_BIT, pgste);
-		set_bit_simple(KVM_UD_BIT, pgste);
+	unsigned long pfn, bits;
+	unsigned char skey;
+
+	pfn = pte_val(*ptep) >> PAGE_SHIFT;
+	skey = page_get_storage_key(pfn);
+	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
+	/* Clear page changed & referenced bit in the storage key */
+	if (bits) {
+		skey ^= bits;
+		page_set_storage_key(pfn, skey, 1);
 	}
-	if (skey & _PAGE_REFERENCED)
-		set_bit_simple(RCP_GR_BIT, pgste);
-	if (test_and_clear_bit_simple(RCP_HC_BIT, pgste)) {
-		SetPageDirty(page);
-		set_bit_simple(KVM_UD_BIT, pgste);
-	}
-	if (test_and_clear_bit_simple(RCP_HR_BIT, pgste))
-		SetPageReferenced(page);
+	/* Transfer page changed & referenced bit to guest bits in pgste */
+	pgste_val(pgste) |= bits << 48;		/* RCP_GR_BIT & RCP_GC_BIT */
+	/* Get host changed & referenced bits from pgste */
+	bits |= (pgste_val(pgste) & (RCP_HR_BIT | RCP_HC_BIT)) >> 52;
+	/* Clear host bits in pgste. */
+	pgste_val(pgste) &= ~(RCP_HR_BIT | RCP_HC_BIT);
+	pgste_val(pgste) &= ~(RCP_ACC_BITS | RCP_FP_BIT);
+	/* Copy page access key and fetch protection bit to pgste */
+	pgste_val(pgste) |=
+		(unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
+	/* Transfer changed and referenced to kvm user bits */
+	pgste_val(pgste) |= bits << 45;		/* KVM_UR_BIT & KVM_UC_BIT */
+	/* Transfer changed & referenced to pte sofware bits */
+	pte_val(*ptep) |= bits << 1;		/* _PAGE_SWR & _PAGE_SWC */
 #endif
+	return pgste;
+
+}
+
+static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
+{
+#ifdef CONFIG_PGSTE
+	int young;
+
+	young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+	/* Transfer page referenced bit to pte software bit (host view) */
+	if (young || (pgste_val(pgste) & RCP_HR_BIT))
+		pte_val(*ptep) |= _PAGE_SWR;
+	/* Clear host referenced bit in pgste. */
+	pgste_val(pgste) &= ~RCP_HR_BIT;
+	/* Transfer page referenced bit to guest bit in pgste */
+	pgste_val(pgste) |= (unsigned long) young << 50; /* set RCP_GR_BIT */
+#endif
+	return pgste;
+
+}
+
+static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
+{
+#ifdef CONFIG_PGSTE
+	unsigned long pfn;
+	unsigned long okey, nkey;
+
+	pfn = pte_val(*ptep) >> PAGE_SHIFT;
+	okey = nkey = page_get_storage_key(pfn);
+	nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
+	/* Set page access key and fetch protection bit from pgste */
+	nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
+	if (okey != nkey)
+		page_set_storage_key(pfn, nkey, 1);
+#endif
+}
+
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t entry)
+{
+	pgste_t pgste;
+
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_get_lock(ptep);
+		pgste_set_pte(ptep, pgste);
+		*ptep = entry;
+		pgste_set_unlock(ptep, pgste);
+	} else
+		*ptep = entry;
 }
 
 /*
@@ -627,19 +671,19 @@ static inline int pte_write(pte_t pte)
 
 static inline int pte_dirty(pte_t pte)
 {
-	/* A pte is neither clean nor dirty on s/390. The dirty bit
-	 * is in the storage key. See page_test_and_clear_dirty for
-	 * details.
-	 */
+#ifdef CONFIG_PGSTE
+	if (pte_val(pte) & _PAGE_SWC)
+		return 1;
+#endif
 	return 0;
 }
 
 static inline int pte_young(pte_t pte)
 {
-	/* A pte is neither young nor old on s/390. The young bit
-	 * is in the storage key. See page_test_and_clear_young for
-	 * details.
-	 */
+#ifdef CONFIG_PGSTE
+	if (pte_val(pte) & _PAGE_SWR)
+		return 1;
+#endif
 	return 0;
 }
 
@@ -647,64 +691,30 @@ static inline int pte_young(pte_t pte)
  * pgd/pmd/pte modification functions
  */
 
-#ifndef __s390x__
-
-#define pgd_clear(pgd)		do { } while (0)
-#define pud_clear(pud)		do { } while (0)
-
-#else /* __s390x__ */
-
-static inline void pgd_clear_kernel(pgd_t * pgd)
+static inline void pgd_clear(pgd_t *pgd)
 {
+#ifdef __s390x__
 	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
 		pgd_val(*pgd) = _REGION2_ENTRY_EMPTY;
+#endif
 }
 
-static inline void pgd_clear(pgd_t * pgd)
-{
-	pgd_t *shadow = get_shadow_table(pgd);
-
-	pgd_clear_kernel(pgd);
-	if (shadow)
-		pgd_clear_kernel(shadow);
-}
-
-static inline void pud_clear_kernel(pud_t *pud)
+static inline void pud_clear(pud_t *pud)
 {
+#ifdef __s390x__
 	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
 		pud_val(*pud) = _REGION3_ENTRY_EMPTY;
+#endif
 }
 
-static inline void pud_clear(pud_t *pud)
-{
-	pud_t *shadow = get_shadow_table(pud);
-
-	pud_clear_kernel(pud);
-	if (shadow)
-		pud_clear_kernel(shadow);
-}
-
-#endif /* __s390x__ */
-
-static inline void pmd_clear_kernel(pmd_t * pmdp)
+static inline void pmd_clear(pmd_t *pmdp)
 {
 	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
 }
 
-static inline void pmd_clear(pmd_t *pmd)
-{
-	pmd_t *shadow = get_shadow_table(pmd);
-
-	pmd_clear_kernel(pmd);
-	if (shadow)
-		pmd_clear_kernel(shadow);
-}
-
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
-	if (mm->context.noexec)
-		pte_val(ptep[PTRS_PER_PTE]) = _PAGE_TYPE_EMPTY;
 }
 
 /*
@@ -734,35 +744,27 @@ static inline pte_t pte_mkwrite(pte_t pte)
 
 static inline pte_t pte_mkclean(pte_t pte)
 {
-	/* The only user of pte_mkclean is the fork() code.
-	   We must *not* clear the *physical* page dirty bit
-	   just because fork() wants to clear the dirty bit in
-	   *one* of the page's mappings.  So we just do nothing. */
+#ifdef CONFIG_PGSTE
+	pte_val(pte) &= ~_PAGE_SWC;
+#endif
 	return pte;
 }
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	/* We do not explicitly set the dirty bit because the
-	 * sske instruction is slow. It is faster to let the
-	 * next instruction set the dirty bit.
-	 */
 	return pte;
 }
 
 static inline pte_t pte_mkold(pte_t pte)
 {
-	/* S/390 doesn't keep its dirty/referenced bit in the pte.
-	 * There is no point in clearing the real referenced bit.
-	 */
+#ifdef CONFIG_PGSTE
+	pte_val(pte) &= ~_PAGE_SWR;
+#endif
 	return pte;
 }
 
 static inline pte_t pte_mkyoung(pte_t pte)
 {
-	/* S/390 doesn't keep its dirty/referenced bit in the pte.
-	 * There is no point in setting the real referenced bit.
-	 */
 	return pte;
 }
 
@@ -800,62 +802,60 @@ static inline pte_t pte_mkhuge(pte_t pte)
 }
 #endif
 
-#ifdef CONFIG_PGSTE
 /*
- * Get (and clear) the user dirty bit for a PTE.
+ * Get (and clear) the user dirty bit for a pte.
  */
-static inline int kvm_s390_test_and_clear_page_dirty(struct mm_struct *mm,
-						     pte_t *ptep)
+static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
+						 pte_t *ptep)
 {
-	int dirty;
-	unsigned long *pgste;
-	struct page *page;
-	unsigned int skey;
-
-	if (!mm->context.has_pgste)
-		return -EINVAL;
-	rcp_lock(ptep);
-	pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
-	page = virt_to_page(pte_val(*ptep));
-	skey = page_get_storage_key(page_to_phys(page));
-	if (skey & _PAGE_CHANGED) {
-		set_bit_simple(RCP_GC_BIT, pgste);
-		set_bit_simple(KVM_UD_BIT, pgste);
+	pgste_t pgste;
+	int dirty = 0;
+
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_get_lock(ptep);
+		pgste = pgste_update_all(ptep, pgste);
+		dirty = !!(pgste_val(pgste) & KVM_UC_BIT);
+		pgste_val(pgste) &= ~KVM_UC_BIT;
+		pgste_set_unlock(ptep, pgste);
+		return dirty;
 	}
-	if (test_and_clear_bit_simple(RCP_HC_BIT, pgste)) {
-		SetPageDirty(page);
-		set_bit_simple(KVM_UD_BIT, pgste);
-	}
-	dirty = test_and_clear_bit_simple(KVM_UD_BIT, pgste);
-	if (skey & _PAGE_CHANGED)
-		page_clear_dirty(page, 1);
-	rcp_unlock(ptep);
 	return dirty;
 }
-#endif
+
+/*
+ * Get (and clear) the user referenced bit for a pte.
+ */
+static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
+						 pte_t *ptep)
+{
+	pgste_t pgste;
+	int young = 0;
+
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_get_lock(ptep);
+		pgste = pgste_update_young(ptep, pgste);
+		young = !!(pgste_val(pgste) & KVM_UR_BIT);
+		pgste_val(pgste) &= ~KVM_UR_BIT;
+		pgste_set_unlock(ptep, pgste);
+	}
+	return young;
+}
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
 {
-#ifdef CONFIG_PGSTE
-	unsigned long physpage;
-	int young;
-	unsigned long *pgste;
+	pgste_t pgste;
+	pte_t pte;
 
-	if (!vma->vm_mm->context.has_pgste)
-		return 0;
-	physpage = pte_val(*ptep) & PAGE_MASK;
-	pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
-
-	young = ((page_get_storage_key(physpage) & _PAGE_REFERENCED) != 0);
-	rcp_lock(ptep);
-	if (young)
-		set_bit_simple(RCP_GR_BIT, pgste);
-	young |= test_and_clear_bit_simple(RCP_HR_BIT, pgste);
-	rcp_unlock(ptep);
-	return young;
-#endif
+	if (mm_has_pgste(vma->vm_mm)) {
+		pgste = pgste_get_lock(ptep);
+		pgste = pgste_update_young(ptep, pgste);
+		pte = *ptep;
+		*ptep = pte_mkold(pte);
+		pgste_set_unlock(ptep, pgste);
+		return pte_young(pte);
+	}
 	return 0;
 }
 
@@ -867,10 +867,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 	 * On s390 reference bits are in storage key and never in TLB
 	 * With virtualization we handle the reference bit, without we
 	 * we can simply return */
-#ifdef CONFIG_PGSTE
 	return ptep_test_and_clear_young(vma, address, ptep);
-#endif
-	return 0;
 }
 
 static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
@@ -890,25 +887,6 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 	}
 }
 
-static inline void ptep_invalidate(struct mm_struct *mm,
-				   unsigned long address, pte_t *ptep)
-{
-	if (mm->context.has_pgste) {
-		rcp_lock(ptep);
-		__ptep_ipte(address, ptep);
-		ptep_rcp_copy(ptep);
-		pte_val(*ptep) = _PAGE_TYPE_EMPTY;
-		rcp_unlock(ptep);
-		return;
-	}
-	__ptep_ipte(address, ptep);
-	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
-	if (mm->context.noexec) {
-		__ptep_ipte(address, ptep + PTRS_PER_PTE);
-		pte_val(*(ptep + PTRS_PER_PTE)) = _PAGE_TYPE_EMPTY;
-	}
-}
-
 /*
  * This is hard to understand. ptep_get_and_clear and ptep_clear_flush
  * both clear the TLB for the unmapped pte. The reason is that
@@ -923,24 +901,72 @@ static inline void ptep_invalidate(struct mm_struct *mm,
  * is a nop.
  */
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-#define ptep_get_and_clear(__mm, __address, __ptep)			\
-({									\
-	pte_t __pte = *(__ptep);					\
-	(__mm)->context.flush_mm = 1;					\
-	if (atomic_read(&(__mm)->context.attach_count) > 1 ||		\
-	    (__mm) != current->active_mm)				\
-		ptep_invalidate(__mm, __address, __ptep);		\
-	else								\
-		pte_clear((__mm), (__address), (__ptep));		\
-	__pte;								\
-})
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	pgste_t pgste;
+	pte_t pte;
+
+	mm->context.flush_mm = 1;
+	if (mm_has_pgste(mm))
+		pgste = pgste_get_lock(ptep);
+
+	pte = *ptep;
+	if (!mm_exclusive(mm))
+		__ptep_ipte(address, ptep);
+	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_update_all(&pte, pgste);
+		pgste_set_unlock(ptep, pgste);
+	}
+	return pte;
+}
+
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
+					   unsigned long address,
+					   pte_t *ptep)
+{
+	pte_t pte;
+
+	mm->context.flush_mm = 1;
+	if (mm_has_pgste(mm))
+		pgste_get_lock(ptep);
+
+	pte = *ptep;
+	if (!mm_exclusive(mm))
+		__ptep_ipte(address, ptep);
+	return pte;
+}
+
+static inline void ptep_modify_prot_commit(struct mm_struct *mm,
+					   unsigned long address,
+					   pte_t *ptep, pte_t pte)
+{
+	*ptep = pte;
+	if (mm_has_pgste(mm))
+		pgste_set_unlock(ptep, *(pgste_t *)(ptep + PTRS_PER_PTE));
+}
 
 #define __HAVE_ARCH_PTEP_CLEAR_FLUSH
 static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 				     unsigned long address, pte_t *ptep)
 {
-	pte_t pte = *ptep;
-	ptep_invalidate(vma->vm_mm, address, ptep);
+	pgste_t pgste;
+	pte_t pte;
+
+	if (mm_has_pgste(vma->vm_mm))
+		pgste = pgste_get_lock(ptep);
+
+	pte = *ptep;
+	__ptep_ipte(address, ptep);
+	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+
+	if (mm_has_pgste(vma->vm_mm)) {
+		pgste = pgste_update_all(&pte, pgste);
+		pgste_set_unlock(ptep, pgste);
+	}
 	return pte;
 }
 
@@ -953,76 +979,67 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
  */
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long addr,
+					    unsigned long address,
 					    pte_t *ptep, int full)
 {
-	pte_t pte = *ptep;
+	pgste_t pgste;
+	pte_t pte;
+
+	if (mm_has_pgste(mm))
+		pgste = pgste_get_lock(ptep);
+
+	pte = *ptep;
+	if (!full)
+		__ptep_ipte(address, ptep);
+	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
 
-	if (full)
-		pte_clear(mm, addr, ptep);
-	else
-		ptep_invalidate(mm, addr, ptep);
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_update_all(&pte, pgste);
+		pgste_set_unlock(ptep, pgste);
+	}
 	return pte;
 }
 
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
-#define ptep_set_wrprotect(__mm, __addr, __ptep)			\
-({									\
-	pte_t __pte = *(__ptep);					\
-	if (pte_write(__pte)) {						\
-		(__mm)->context.flush_mm = 1;				\
-		if (atomic_read(&(__mm)->context.attach_count) > 1 ||	\
-		    (__mm) != current->active_mm)			\
-			ptep_invalidate(__mm, __addr, __ptep);		\
-		set_pte_at(__mm, __addr, __ptep, pte_wrprotect(__pte));	\
-	}								\
-})
+static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	pgste_t pgste;
+	pte_t pte = *ptep;
 
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-#define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty)	\
-({									\
-	int __changed = !pte_same(*(__ptep), __entry);			\
-	if (__changed) {						\
-		ptep_invalidate((__vma)->vm_mm, __addr, __ptep);	\
-		set_pte_at((__vma)->vm_mm, __addr, __ptep, __entry);	\
-	}								\
-	__changed;							\
-})
+	if (pte_write(pte)) {
+		mm->context.flush_mm = 1;
+		if (mm_has_pgste(mm))
+			pgste = pgste_get_lock(ptep);
 
-/*
- * Test and clear dirty bit in storage key.
- * We can't clear the changed bit atomically. This is a potential
- * race against modification of the referenced bit. This function
- * should therefore only be called if it is not mapped in any
- * address space.
- */
-#define __HAVE_ARCH_PAGE_TEST_DIRTY
-static inline int page_test_dirty(struct page *page)
-{
-	return (page_get_storage_key(page_to_phys(page)) & _PAGE_CHANGED) != 0;
-}
+		if (!mm_exclusive(mm))
+			__ptep_ipte(address, ptep);
+		*ptep = pte_wrprotect(pte);
 
-#define __HAVE_ARCH_PAGE_CLEAR_DIRTY
-static inline void page_clear_dirty(struct page *page, int mapped)
-{
-	page_set_storage_key(page_to_phys(page), PAGE_DEFAULT_KEY, mapped);
+		if (mm_has_pgste(mm))
+			pgste_set_unlock(ptep, pgste);
+	}
+	return pte;
 }
 
-/*
- * Test and clear referenced bit in storage key.
- */
-#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
-static inline int page_test_and_clear_young(struct page *page)
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+static inline int ptep_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pte_t *ptep,
+					pte_t entry, int dirty)
 {
-	unsigned long physpage = page_to_phys(page);
-	int ccode;
-
-	asm volatile(
-		"	rrbe	0,%1\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (ccode) : "a" (physpage) : "cc" );
-	return ccode & 2;
+	pgste_t pgste;
+
+	if (pte_same(*ptep, entry))
+		return 0;
+	if (mm_has_pgste(vma->vm_mm))
+		pgste = pgste_get_lock(ptep);
+
+	__ptep_ipte(address, ptep);
+	*ptep = entry;
+
+	if (mm_has_pgste(vma->vm_mm))
+		pgste_set_unlock(ptep, pgste);
+	return 1;
 }
 
 /*
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 2c79b6416271..1300c3025334 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -84,6 +84,7 @@ struct thread_struct {
 	struct per_event per_event;	/* Cause of the last PER trap */
         /* pfault_wait is used to block the process on a pfault event */
 	unsigned long pfault_wait;
+	struct list_head list;
 };
 
 typedef struct thread_struct thread_struct;
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 29d5d6d4becc..b7a4f2eb0057 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -50,7 +50,7 @@ static inline void __tlb_flush_full(struct mm_struct *mm)
 	/*
 	 * If the process only ran on the local cpu, do a local flush.
 	 */
-	local_cpumask = cpumask_of_cpu(smp_processor_id());
+	cpumask_copy(&local_cpumask, cpumask_of(smp_processor_id()));
 	if (cpumask_equal(mm_cpumask(mm), &local_cpumask))
 		__tlb_flush_local();
 	else
@@ -80,16 +80,11 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * on all cpus instead of doing a local flush if the mm
 	 * only ran on the local cpu.
 	 */
-	if (MACHINE_HAS_IDTE) {
-		if (mm->context.noexec)
-			__tlb_flush_idte((unsigned long)
-					 get_shadow_table(mm->pgd) |
-					 mm->context.asce_bits);
+	if (MACHINE_HAS_IDTE)
 		__tlb_flush_idte((unsigned long) mm->pgd |
 				 mm->context.asce_bits);
-		return;
-	}
-	__tlb_flush_full(mm);
+	else
+		__tlb_flush_full(mm);
 }
 
 static inline void __tlb_flush_mm_cond(struct mm_struct * mm)
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index e82152572377..9208e69245a0 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -385,6 +385,7 @@
 
 /* Ignore system calls that are also reachable via sys_socket */
 #define __IGNORE_recvmmsg
+#define __IGNORE_sendmmsg
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index fe03c140002a..edfbd17d7082 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -124,13 +124,11 @@ int main(void)
 	DEFINE(__LC_LAST_UPDATE_TIMER, offsetof(struct _lowcore, last_update_timer));
 	DEFINE(__LC_LAST_UPDATE_CLOCK, offsetof(struct _lowcore, last_update_clock));
 	DEFINE(__LC_CURRENT, offsetof(struct _lowcore, current_task));
+	DEFINE(__LC_CURRENT_PID, offsetof(struct _lowcore, current_pid));
 	DEFINE(__LC_THREAD_INFO, offsetof(struct _lowcore, thread_info));
 	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
 	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
 	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
-	DEFINE(__LC_KERNEL_ASCE, offsetof(struct _lowcore, kernel_asce));
-	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
-	DEFINE(__LC_USER_EXEC_ASCE, offsetof(struct _lowcore, user_exec_asce));
 	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 1b67fc6ebdc2..0476174dfff5 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -212,6 +212,7 @@ __switch_to:
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	lm	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	st	%r3,__LC_CURRENT		# store task struct of next
+	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3)	# store pid of next
 	st	%r5,__LC_THREAD_INFO		# store thread info of next
 	ahi	%r5,STACK_SIZE			# end of kernel stack of next
 	st	%r5,__LC_KERNEL_STACK		# store end of kernel stack
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 9fd864563499..d61967e2eab0 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -220,6 +220,7 @@ __switch_to:
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	stg	%r3,__LC_CURRENT		# store task struct of next
+	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
 	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	aghi	%r5,STACK_SIZE			# end of kernel stack of next
 	stg	%r5,__LC_KERNEL_STACK		# store end of kernel stack
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index ea5099c9709c..e204f9597aaf 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -32,6 +32,7 @@ static const struct irq_class intrclass_names[] = {
 	{.name = "VRT", .desc = "[EXT] Virtio" },
 	{.name = "SCP", .desc = "[EXT] Service Call" },
 	{.name = "IUC", .desc = "[EXT] IUCV" },
+	{.name = "CPM", .desc = "[EXT] CPU Measurement" },
 	{.name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt" },
 	{.name = "QDI", .desc = "[I/O] QDIO Interrupt" },
 	{.name = "DAS", .desc = "[I/O] DASD" },
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index a895e69379f7..541a7509faeb 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -9,41 +9,26 @@
 
 #include <linux/compiler.h>
 #include <linux/cpu.h>
-#include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/fs.h>
 #include <linux/smp.h>
-#include <linux/stddef.h>
 #include <linux/slab.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/vmalloc.h>
-#include <linux/user.h>
 #include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/notifier.h>
 #include <linux/tick.h>
-#include <linux/elfcore.h>
-#include <linux/kernel_stat.h>
 #include <linux/personality.h>
 #include <linux/syscalls.h>
 #include <linux/compat.h>
 #include <linux/kprobes.h>
 #include <linux/random.h>
-#include <asm/compat.h>
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
+#include <linux/module.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <asm/timer.h>
 #include <asm/nmi.h>
+#include <asm/compat.h>
 #include <asm/smp.h>
 #include "entry.h"
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f5434d1ecb31..0c35dee10b00 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -305,8 +305,7 @@ static int set_amode_and_uaccess(unsigned long user_amode,
  */
 static int __init early_parse_switch_amode(char *p)
 {
-	if (user_mode != SECONDARY_SPACE_MODE)
-		user_mode = PRIMARY_SPACE_MODE;
+	user_mode = PRIMARY_SPACE_MODE;
 	return 0;
 }
 early_param("switch_amode", early_parse_switch_amode);
@@ -315,10 +314,6 @@ static int __init early_parse_user_mode(char *p)
 {
 	if (p && strcmp(p, "primary") == 0)
 		user_mode = PRIMARY_SPACE_MODE;
-#ifdef CONFIG_S390_EXEC_PROTECT
-	else if (p && strcmp(p, "secondary") == 0)
-		user_mode = SECONDARY_SPACE_MODE;
-#endif
 	else if (!p || strcmp(p, "home") == 0)
 		user_mode = HOME_SPACE_MODE;
 	else
@@ -327,31 +322,9 @@ static int __init early_parse_user_mode(char *p)
 }
 early_param("user_mode", early_parse_user_mode);
 
-#ifdef CONFIG_S390_EXEC_PROTECT
-/*
- * Enable execute protection?
- */
-static int __init early_parse_noexec(char *p)
-{
-	if (!strncmp(p, "off", 3))
-		return 0;
-	user_mode = SECONDARY_SPACE_MODE;
-	return 0;
-}
-early_param("noexec", early_parse_noexec);
-#endif /* CONFIG_S390_EXEC_PROTECT */
-
 static void setup_addressing_mode(void)
 {
-	if (user_mode == SECONDARY_SPACE_MODE) {
-		if (set_amode_and_uaccess(PSW_ASC_SECONDARY,
-					  PSW32_ASC_SECONDARY))
-			pr_info("Execute protection active, "
-				"mvcos available\n");
-		else
-			pr_info("Execute protection active, "
-				"mvcos not available\n");
-	} else if (user_mode == PRIMARY_SPACE_MODE) {
+	if (user_mode == PRIMARY_SPACE_MODE) {
 		if (set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY))
 			pr_info("Address spaces switched, "
 				"mvcos available\n");
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 63c7d9ff220d..f8e85ecbc459 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -335,7 +335,7 @@ static int smp_rescan_cpus_sigp(cpumask_t avail)
 		smp_cpu_polarization[logical_cpu] = POLARIZATION_UNKNWN;
 		if (!cpu_stopped(logical_cpu))
 			continue;
-		cpu_set(logical_cpu, cpu_present_map);
+		set_cpu_present(logical_cpu, true);
 		smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
 		logical_cpu = cpumask_next(logical_cpu, &avail);
 		if (logical_cpu >= nr_cpu_ids)
@@ -367,7 +367,7 @@ static int smp_rescan_cpus_sclp(cpumask_t avail)
 			continue;
 		__cpu_logical_map[logical_cpu] = cpu_id;
 		smp_cpu_polarization[logical_cpu] = POLARIZATION_UNKNWN;
-		cpu_set(logical_cpu, cpu_present_map);
+		set_cpu_present(logical_cpu, true);
 		if (cpu >= info->configured)
 			smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY;
 		else
@@ -385,7 +385,7 @@ static int __smp_rescan_cpus(void)
 {
 	cpumask_t avail;
 
-	cpus_xor(avail, cpu_possible_map, cpu_present_map);
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
 	if (smp_use_sigp_detection)
 		return smp_rescan_cpus_sigp(avail);
 	else
@@ -467,7 +467,7 @@ int __cpuinit start_secondary(void *cpuvoid)
 	notify_cpu_starting(smp_processor_id());
 	/* Mark this cpu as online */
 	ipi_call_lock();
-	cpu_set(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), true);
 	ipi_call_unlock();
 	/* Switch on interrupts */
 	local_irq_enable();
@@ -644,7 +644,7 @@ int __cpu_disable(void)
 	struct ec_creg_mask_parms cr_parms;
 	int cpu = smp_processor_id();
 
-	cpu_clear(cpu, cpu_online_map);
+	set_cpu_online(cpu, false);
 
 	/* Disable pfault pseudo page faults on this cpu. */
 	pfault_fini();
@@ -654,8 +654,8 @@ int __cpu_disable(void)
 
 	/* disable all external interrupts */
 	cr_parms.orvals[0] = 0;
-	cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 12 |
-				1 << 11 | 1 << 10 | 1 <<  6 | 1 <<  4);
+	cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 11 |
+				1 << 10 | 1 <<	9 | 1 <<  6 | 1 <<  4);
 	/* disable all I/O interrupts */
 	cr_parms.orvals[6] = 0;
 	cr_parms.andvals[6] = ~(1 << 31 | 1 << 30 | 1 << 29 | 1 << 28 |
@@ -681,7 +681,7 @@ void __cpu_die(unsigned int cpu)
 	atomic_dec(&init_mm.context.attach_count);
 }
 
-void cpu_die(void)
+void __noreturn cpu_die(void)
 {
 	idle_task_exit();
 	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
@@ -738,8 +738,8 @@ void __init smp_prepare_boot_cpu(void)
 	BUG_ON(smp_processor_id() != 0);
 
 	current_thread_info()->cpu = 0;
-	cpu_set(0, cpu_present_map);
-	cpu_set(0, cpu_online_map);
+	set_cpu_present(0, true);
+	set_cpu_online(0, true);
 	S390_lowcore.percpu_offset = __per_cpu_offset[0];
 	current_set[0] = current;
 	smp_cpu_state[0] = CPU_STATE_CONFIGURED;
@@ -1016,21 +1016,21 @@ int __ref smp_rescan_cpus(void)
 
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	newcpus = cpu_present_map;
+	cpumask_copy(&newcpus, cpu_present_mask);
 	rc = __smp_rescan_cpus();
 	if (rc)
 		goto out;
-	cpus_andnot(newcpus, cpu_present_map, newcpus);
-	for_each_cpu_mask(cpu, newcpus) {
+	cpumask_andnot(&newcpus, cpu_present_mask, &newcpus);
+	for_each_cpu(cpu, &newcpus) {
 		rc = smp_add_present_cpu(cpu);
 		if (rc)
-			cpu_clear(cpu, cpu_present_map);
+			set_cpu_present(cpu, false);
 	}
 	rc = 0;
 out:
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
-	if (!cpus_empty(newcpus))
+	if (!cpumask_empty(&newcpus))
 		topology_schedule_update();
 	return rc;
 }
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 87be655557aa..a59557f1fb5f 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -810,7 +810,7 @@ static int etr_sync_clock_stop(struct etr_aib *aib, int port)
 	etr_sync.etr_port = port;
 	get_online_cpus();
 	atomic_set(&etr_sync.cpus, num_online_cpus() - 1);
-	rc = stop_machine(etr_sync_clock, &etr_sync, &cpu_online_map);
+	rc = stop_machine(etr_sync_clock, &etr_sync, cpu_online_mask);
 	put_online_cpus();
 	return rc;
 }
@@ -1579,7 +1579,7 @@ static void stp_work_fn(struct work_struct *work)
 	memset(&stp_sync, 0, sizeof(stp_sync));
 	get_online_cpus();
 	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
-	stop_machine(stp_sync_clock, &stp_sync, &cpu_online_map);
+	stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
 	put_online_cpus();
 
 	if (!check_sync_clock())
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 94b06c31fc8a..2eafb8c7a746 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -52,20 +52,20 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
 	cpumask_t mask;
 
-	cpus_clear(mask);
+	cpumask_clear(&mask);
 	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY) {
 		cpumask_copy(&mask, cpumask_of(cpu));
 		return mask;
 	}
 	while (info) {
-		if (cpu_isset(cpu, info->mask)) {
+		if (cpumask_test_cpu(cpu, &info->mask)) {
 			mask = info->mask;
 			break;
 		}
 		info = info->next;
 	}
-	if (cpus_empty(mask))
-		mask = cpumask_of_cpu(cpu);
+	if (cpumask_empty(&mask))
+		cpumask_copy(&mask, cpumask_of(cpu));
 	return mask;
 }
 
@@ -85,10 +85,10 @@ static void add_cpus_to_mask(struct topology_cpu *tl_cpu,
 			if (cpu_logical_map(lcpu) != rcpu)
 				continue;
 #ifdef CONFIG_SCHED_BOOK
-			cpu_set(lcpu, book->mask);
+			cpumask_set_cpu(lcpu, &book->mask);
 			cpu_book_id[lcpu] = book->id;
 #endif
-			cpu_set(lcpu, core->mask);
+			cpumask_set_cpu(lcpu, &core->mask);
 			cpu_core_id[lcpu] = core->id;
 			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
@@ -101,13 +101,13 @@ static void clear_masks(void)
 
 	info = &core_info;
 	while (info) {
-		cpus_clear(info->mask);
+		cpumask_clear(&info->mask);
 		info = info->next;
 	}
 #ifdef CONFIG_SCHED_BOOK
 	info = &book_info;
 	while (info) {
-		cpus_clear(info->mask);
+		cpumask_clear(&info->mask);
 		info = info->next;
 	}
 #endif
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index d13e8755a8cc..8ad2b34ad151 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -22,6 +22,9 @@ obj-y += vdso32_wrapper.o
 extra-y += vdso32.lds
 CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
 
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+
 # Force dependency (incbin is bad)
 $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
 
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 449352dda9cd..2a8ddfd12a5b 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -22,6 +22,9 @@ obj-y += vdso64_wrapper.o
 extra-y += vdso64.lds
 CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
 
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+
 # Force dependency (incbin is bad)
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
 
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 1bc18cdb525b..56fe6bc81fee 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -77,7 +77,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)
 
-	PERCPU(0x100, PAGE_SIZE)
+	PERCPU_SECTION(0x100)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 3cc95dd0a3a6..075ddada4911 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -412,6 +412,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 	struct dcss_segment *seg;
 	int rc, diag_cc;
 
+	start_addr = end_addr = 0;
 	seg = kmalloc(sizeof(*seg), GFP_KERNEL | GFP_DMA);
 	if (seg == NULL) {
 		rc = -ENOMEM;
@@ -573,6 +574,7 @@ segment_modify_shared (char *name, int do_nonshared)
 	unsigned long start_addr, end_addr, dummy;
 	int rc, diag_cc;
 
+	start_addr = end_addr = 0;
 	mutex_lock(&dcss_lock);
 	seg = segment_by_name (name);
 	if (seg == NULL) {
@@ -681,8 +683,6 @@ void
 segment_save(char *name)
 {
 	struct dcss_segment *seg;
-	int startpfn = 0;
-	int endpfn = 0;
 	char cmd1[160];
 	char cmd2[80];
 	int i, response;
@@ -698,8 +698,6 @@ segment_save(char *name)
 		goto out;
 	}
 
-	startpfn = seg->start_addr >> PAGE_SHIFT;
-	endpfn = (seg->end) >> PAGE_SHIFT;
 	sprintf(cmd1, "DEFSEG %s", name);
 	for (i=0; i<seg->segcnt; i++) {
 		sprintf(cmd1+strlen(cmd1), " %lX-%lX %s",
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index ab988135e5c6..a0f9e730f26a 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -225,33 +225,6 @@ static noinline void do_sigbus(struct pt_regs *regs, long int_code,
 	force_sig_info(SIGBUS, &si, tsk);
 }
 
-#ifdef CONFIG_S390_EXEC_PROTECT
-static noinline int signal_return(struct pt_regs *regs, long int_code,
-				  unsigned long trans_exc_code)
-{
-	u16 instruction;
-	int rc;
-
-	rc = __get_user(instruction, (u16 __user *) regs->psw.addr);
-
-	if (!rc && instruction == 0x0a77) {
-		clear_tsk_thread_flag(current, TIF_PER_TRAP);
-		if (is_compat_task())
-			sys32_sigreturn();
-		else
-			sys_sigreturn();
-	} else if (!rc && instruction == 0x0aad) {
-		clear_tsk_thread_flag(current, TIF_PER_TRAP);
-		if (is_compat_task())
-			sys32_rt_sigreturn();
-		else
-			sys_rt_sigreturn();
-	} else
-		do_sigsegv(regs, int_code, SEGV_MAPERR, trans_exc_code);
-	return 0;
-}
-#endif /* CONFIG_S390_EXEC_PROTECT */
-
 static noinline void do_fault_error(struct pt_regs *regs, long int_code,
 				    unsigned long trans_exc_code, int fault)
 {
@@ -259,13 +232,6 @@ static noinline void do_fault_error(struct pt_regs *regs, long int_code,
 
 	switch (fault) {
 	case VM_FAULT_BADACCESS:
-#ifdef CONFIG_S390_EXEC_PROTECT
-		if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY &&
-		    (trans_exc_code & 3) == 0) {
-			signal_return(regs, int_code, trans_exc_code);
-			break;
-		}
-#endif /* CONFIG_S390_EXEC_PROTECT */
 	case VM_FAULT_BADMAP:
 		/* Bad memory access. Check if it is kernel or user space. */
 		if (regs->psw.mask & PSW_MASK_PSTATE) {
@@ -414,11 +380,6 @@ void __kprobes do_dat_exception(struct pt_regs *regs, long pgm_int_code,
 	int access, fault;
 
 	access = VM_READ | VM_EXEC | VM_WRITE;
-#ifdef CONFIG_S390_EXEC_PROTECT
-	if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY &&
-	    (trans_exc_code & 3) == 0)
-		access = VM_EXEC;
-#endif
 	fault = do_exception(regs, access, trans_exc_code);
 	if (unlikely(fault))
 		do_fault_error(regs, pgm_int_code & 255, trans_exc_code, fault);
@@ -491,22 +452,28 @@ static int __init nopfault(char *str)
 
 __setup("nopfault", nopfault);
 
-typedef struct {
-	__u16 refdiagc;
-	__u16 reffcode;
-	__u16 refdwlen;
-	__u16 refversn;
-	__u64 refgaddr;
-	__u64 refselmk;
-	__u64 refcmpmk;
-	__u64 reserved;
-} __attribute__ ((packed, aligned(8))) pfault_refbk_t;
+struct pfault_refbk {
+	u16 refdiagc;
+	u16 reffcode;
+	u16 refdwlen;
+	u16 refversn;
+	u64 refgaddr;
+	u64 refselmk;
+	u64 refcmpmk;
+	u64 reserved;
+} __attribute__ ((packed, aligned(8)));
 
 int pfault_init(void)
 {
-	pfault_refbk_t refbk =
-		{ 0x258, 0, 5, 2, __LC_CURRENT, 1ULL << 48, 1ULL << 48,
-		  __PF_RES_FIELD };
+	struct pfault_refbk refbk = {
+		.refdiagc = 0x258,
+		.reffcode = 0,
+		.refdwlen = 5,
+		.refversn = 2,
+		.refgaddr = __LC_CURRENT_PID,
+		.refselmk = 1ULL << 48,
+		.refcmpmk = 1ULL << 48,
+		.reserved = __PF_RES_FIELD };
         int rc;
 
 	if (!MACHINE_IS_VM || pfault_disable)
@@ -524,8 +491,12 @@ int pfault_init(void)
 
 void pfault_fini(void)
 {
-	pfault_refbk_t refbk =
-	{ 0x258, 1, 5, 2, 0ULL, 0ULL, 0ULL, 0ULL };
+	struct pfault_refbk refbk = {
+		.refdiagc = 0x258,
+		.reffcode = 1,
+		.refdwlen = 5,
+		.refversn = 2,
+	};
 
 	if (!MACHINE_IS_VM || pfault_disable)
 		return;
@@ -537,11 +508,15 @@ void pfault_fini(void)
 		: : "a" (&refbk), "m" (refbk) : "cc");
 }
 
+static DEFINE_SPINLOCK(pfault_lock);
+static LIST_HEAD(pfault_list);
+
 static void pfault_interrupt(unsigned int ext_int_code,
 			     unsigned int param32, unsigned long param64)
 {
 	struct task_struct *tsk;
 	__u16 subcode;
+	pid_t pid;
 
 	/*
 	 * Get the external interruption subcode & pfault
@@ -553,44 +528,79 @@ static void pfault_interrupt(unsigned int ext_int_code,
 	if ((subcode & 0xff00) != __SUBCODE_MASK)
 		return;
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_PFL]++;
-
-	/*
-	 * Get the token (= address of the task structure of the affected task).
-	 */
-#ifdef CONFIG_64BIT
-	tsk = (struct task_struct *) param64;
-#else
-	tsk = (struct task_struct *) param32;
-#endif
-
+	if (subcode & 0x0080) {
+		/* Get the token (= pid of the affected task). */
+		pid = sizeof(void *) == 4 ? param32 : param64;
+		rcu_read_lock();
+		tsk = find_task_by_pid_ns(pid, &init_pid_ns);
+		if (tsk)
+			get_task_struct(tsk);
+		rcu_read_unlock();
+		if (!tsk)
+			return;
+	} else {
+		tsk = current;
+	}
+	spin_lock(&pfault_lock);
 	if (subcode & 0x0080) {
 		/* signal bit is set -> a page has been swapped in by VM */
-		if (xchg(&tsk->thread.pfault_wait, -1) != 0) {
+		if (tsk->thread.pfault_wait == 1) {
 			/* Initial interrupt was faster than the completion
 			 * interrupt. pfault_wait is valid. Set pfault_wait
 			 * back to zero and wake up the process. This can
 			 * safely be done because the task is still sleeping
 			 * and can't produce new pfaults. */
 			tsk->thread.pfault_wait = 0;
+			list_del(&tsk->thread.list);
 			wake_up_process(tsk);
-			put_task_struct(tsk);
+		} else {
+			/* Completion interrupt was faster than initial
+			 * interrupt. Set pfault_wait to -1 so the initial
+			 * interrupt doesn't put the task to sleep. */
+			tsk->thread.pfault_wait = -1;
 		}
+		put_task_struct(tsk);
 	} else {
 		/* signal bit not set -> a real page is missing. */
-		get_task_struct(tsk);
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
-		if (xchg(&tsk->thread.pfault_wait, 1) != 0) {
+		if (tsk->thread.pfault_wait == -1) {
 			/* Completion interrupt was faster than the initial
-			 * interrupt (swapped in a -1 for pfault_wait). Set
-			 * pfault_wait back to zero and exit. This can be
-			 * done safely because tsk is running in kernel 
-			 * mode and can't produce new pfaults. */
+			 * interrupt (pfault_wait == -1). Set pfault_wait
+			 * back to zero and exit. */
 			tsk->thread.pfault_wait = 0;
-			set_task_state(tsk, TASK_RUNNING);
-			put_task_struct(tsk);
-		} else
+		} else {
+			/* Initial interrupt arrived before completion
+			 * interrupt. Let the task sleep. */
+			tsk->thread.pfault_wait = 1;
+			list_add(&tsk->thread.list, &pfault_list);
+			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 			set_tsk_need_resched(tsk);
+		}
+	}
+	spin_unlock(&pfault_lock);
+}
+
+static int __cpuinit pfault_cpu_notify(struct notifier_block *self,
+				       unsigned long action, void *hcpu)
+{
+	struct thread_struct *thread, *next;
+	struct task_struct *tsk;
+
+	switch (action) {
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		spin_lock_irq(&pfault_lock);
+		list_for_each_entry_safe(thread, next, &pfault_list, list) {
+			thread->pfault_wait = 0;
+			list_del(&thread->list);
+			tsk = container_of(thread, struct task_struct, thread);
+			wake_up_process(tsk);
+		}
+		spin_unlock_irq(&pfault_lock);
+		break;
+	default:
+		break;
 	}
+	return NOTIFY_OK;
 }
 
 static int __init pfault_irq_init(void)
@@ -599,22 +609,21 @@ static int __init pfault_irq_init(void)
 
 	if (!MACHINE_IS_VM)
 		return 0;
-	/*
-	 * Try to get pfault pseudo page faults going.
-	 */
 	rc = register_external_interrupt(0x2603, pfault_interrupt);
-	if (rc) {
-		pfault_disable = 1;
-		return rc;
-	}
-	if (pfault_init() == 0)
-		return 0;
+	if (rc)
+		goto out_extint;
+	rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
+	if (rc)
+		goto out_pfault;
+	hotcpu_notifier(pfault_cpu_notify, 0);
+	return 0;
 
-	/* Tough luck, no pfault. */
-	pfault_disable = 1;
+out_pfault:
 	unregister_external_interrupt(0x2603, pfault_interrupt);
-	return 0;
+out_extint:
+	pfault_disable = 1;
+	return rc;
 }
 early_initcall(pfault_irq_init);
 
-#endif
+#endif /* CONFIG_PFAULT */
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 639cd21f2218..a4d856db9154 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -13,7 +13,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *pteptr, pte_t pteval)
 {
 	pmd_t *pmdp = (pmd_t *) pteptr;
-	pte_t shadow_pteval = pteval;
 	unsigned long mask;
 
 	if (!MACHINE_HAS_HPAGE) {
@@ -21,18 +20,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		mask = pte_val(pteval) &
 				(_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
 		pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask;
-		if (mm->context.noexec) {
-			pteptr += PTRS_PER_PTE;
-			pte_val(shadow_pteval) =
-					(_SEGMENT_ENTRY + __pa(pteptr)) | mask;
-		}
 	}
 
 	pmd_val(*pmdp) = pte_val(pteval);
-	if (mm->context.noexec) {
-		pmdp = get_shadow_table(pmdp);
-		pmd_val(*pmdp) = pte_val(shadow_pteval);
-	}
 }
 
 int arch_prepare_hugepage(struct page *page)
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index bb409332a484..dfefc2171691 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -175,7 +175,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 		pmd = pmd_offset(pud, address);
 		pte = pte_offset_kernel(pmd, address);
 		if (!enable) {
-			ptep_invalidate(&init_mm, address, pte);
+			__ptep_ipte(address, pte);
+			pte_val(*pte) = _PAGE_TYPE_EMPTY;
 			continue;
 		}
 		*pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW));
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index f05edcc3beff..d013ed39743b 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -28,7 +28,7 @@ static void change_page_attr(unsigned long addr, int numpages,
 
 		pte = *ptep;
 		pte = set(pte);
-		ptep_invalidate(&init_mm, addr, ptep);
+		__ptep_ipte(addr, ptep);
 		*ptep = pte;
 		addr += PAGE_SIZE;
 	}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index e1850c28cd68..8d4330642512 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -40,7 +40,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 static DEFINE_PER_CPU(struct rcu_table_freelist *, rcu_table_freelist);
 
 static void __page_table_free(struct mm_struct *mm, unsigned long *table);
-static void __crst_table_free(struct mm_struct *mm, unsigned long *table);
 
 static struct rcu_table_freelist *rcu_table_freelist_get(struct mm_struct *mm)
 {
@@ -67,7 +66,7 @@ static void rcu_table_freelist_callback(struct rcu_head *head)
 	while (batch->pgt_index > 0)
 		__page_table_free(batch->mm, batch->table[--batch->pgt_index]);
 	while (batch->crst_index < RCU_FREELIST_SIZE)
-		__crst_table_free(batch->mm, batch->table[batch->crst_index++]);
+		crst_table_free(batch->mm, batch->table[batch->crst_index++]);
 	free_page((unsigned long) batch);
 }
 
@@ -125,63 +124,33 @@ static int __init parse_vmalloc(char *arg)
 }
 early_param("vmalloc", parse_vmalloc);
 
-unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
+unsigned long *crst_table_alloc(struct mm_struct *mm)
 {
 	struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
 
 	if (!page)
 		return NULL;
-	page->index = 0;
-	if (noexec) {
-		struct page *shadow = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
-		if (!shadow) {
-			__free_pages(page, ALLOC_ORDER);
-			return NULL;
-		}
-		page->index = page_to_phys(shadow);
-	}
-	spin_lock_bh(&mm->context.list_lock);
-	list_add(&page->lru, &mm->context.crst_list);
-	spin_unlock_bh(&mm->context.list_lock);
 	return (unsigned long *) page_to_phys(page);
 }
 
-static void __crst_table_free(struct mm_struct *mm, unsigned long *table)
-{
-	unsigned long *shadow = get_shadow_table(table);
-
-	if (shadow)
-		free_pages((unsigned long) shadow, ALLOC_ORDER);
-	free_pages((unsigned long) table, ALLOC_ORDER);
-}
-
 void crst_table_free(struct mm_struct *mm, unsigned long *table)
 {
-	struct page *page = virt_to_page(table);
-
-	spin_lock_bh(&mm->context.list_lock);
-	list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
-	__crst_table_free(mm, table);
+	free_pages((unsigned long) table, ALLOC_ORDER);
 }
 
 void crst_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 {
 	struct rcu_table_freelist *batch;
-	struct page *page = virt_to_page(table);
 
-	spin_lock_bh(&mm->context.list_lock);
-	list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
 	if (atomic_read(&mm->mm_users) < 2 &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		__crst_table_free(mm, table);
+		crst_table_free(mm, table);
 		return;
 	}
 	batch = rcu_table_freelist_get(mm);
 	if (!batch) {
 		smp_call_function(smp_sync, NULL, 1);
-		__crst_table_free(mm, table);
+		crst_table_free(mm, table);
 		return;
 	}
 	batch->table[--batch->crst_index] = table;
@@ -197,7 +166,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
 
 	BUG_ON(limit > (1UL << 53));
 repeat:
-	table = crst_table_alloc(mm, mm->context.noexec);
+	table = crst_table_alloc(mm);
 	if (!table)
 		return -ENOMEM;
 	spin_lock_bh(&mm->page_table_lock);
@@ -273,7 +242,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	unsigned long *table;
 	unsigned long bits;
 
-	bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+	bits = (mm->context.has_pgste) ? 3UL : 1UL;
 	spin_lock_bh(&mm->context.list_lock);
 	page = NULL;
 	if (!list_empty(&mm->context.pgtable_list)) {
@@ -329,7 +298,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	struct page *page;
 	unsigned long bits;
 
-	bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+	bits = (mm->context.has_pgste) ? 3UL : 1UL;
 	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
@@ -366,7 +335,7 @@ void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 		page_table_free(mm, table);
 		return;
 	}
-	bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+	bits = (mm->context.has_pgste) ? 3UL : 1UL;
 	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
@@ -379,25 +348,6 @@ void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 		rcu_table_freelist_finish();
 }
 
-void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
-{
-	struct page *page;
-
-	spin_lock_bh(&mm->context.list_lock);
-	/* Free shadow region and segment tables. */
-	list_for_each_entry(page, &mm->context.crst_list, lru)
-		if (page->index) {
-			free_pages((unsigned long) page->index, ALLOC_ORDER);
-			page->index = 0;
-		}
-	/* "Free" second halves of page tables. */
-	list_for_each_entry(page, &mm->context.pgtable_list, lru)
-		page->flags &= ~SECOND_HALVES;
-	spin_unlock_bh(&mm->context.list_lock);
-	mm->context.noexec = 0;
-	update_mm(mm, tsk);
-}
-
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 34c43f23b28c..8c1970d1dd91 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -95,7 +95,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			pu_dir = vmem_pud_alloc();
 			if (!pu_dir)
 				goto out;
-			pgd_populate_kernel(&init_mm, pg_dir, pu_dir);
+			pgd_populate(&init_mm, pg_dir, pu_dir);
 		}
 
 		pu_dir = pud_offset(pg_dir, address);
@@ -103,7 +103,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			pm_dir = vmem_pmd_alloc();
 			if (!pm_dir)
 				goto out;
-			pud_populate_kernel(&init_mm, pu_dir, pm_dir);
+			pud_populate(&init_mm, pu_dir, pm_dir);
 		}
 
 		pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0));
@@ -123,7 +123,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			pt_dir = vmem_pte_alloc();
 			if (!pt_dir)
 				goto out;
-			pmd_populate_kernel(&init_mm, pm_dir, pt_dir);
+			pmd_populate(&init_mm, pm_dir, pt_dir);
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
@@ -159,7 +159,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size)
 			continue;
 
 		if (pmd_huge(*pm_dir)) {
-			pmd_clear_kernel(pm_dir);
+			pmd_clear(pm_dir);
 			address += HPAGE_SIZE - PAGE_SIZE;
 			continue;
 		}
@@ -192,7 +192,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 			pu_dir = vmem_pud_alloc();
 			if (!pu_dir)
 				goto out;
-			pgd_populate_kernel(&init_mm, pg_dir, pu_dir);
+			pgd_populate(&init_mm, pg_dir, pu_dir);
 		}
 
 		pu_dir = pud_offset(pg_dir, address);
@@ -200,7 +200,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 			pm_dir = vmem_pmd_alloc();
 			if (!pm_dir)
 				goto out;
-			pud_populate_kernel(&init_mm, pu_dir, pm_dir);
+			pud_populate(&init_mm, pu_dir, pm_dir);
 		}
 
 		pm_dir = pmd_offset(pu_dir, address);
@@ -208,7 +208,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 			pt_dir = vmem_pte_alloc();
 			if (!pt_dir)
 				goto out;
-			pmd_populate_kernel(&init_mm, pm_dir, pt_dir);
+			pmd_populate(&init_mm, pm_dir, pt_dir);
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index 33cbd373cce4..053caa0fd276 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -5,6 +5,7 @@
  * Author: Heinz Graalfs <graalfs@de.ibm.com>
  */
 
+#include <linux/kernel_stat.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/smp.h>
@@ -674,17 +675,11 @@ int hwsampler_activate(unsigned int cpu)
 static void hws_ext_handler(unsigned int ext_int_code,
 			    unsigned int param32, unsigned long param64)
 {
-	int cpu;
 	struct hws_cpu_buffer *cb;
 
-	cpu = smp_processor_id();
-	cb = &per_cpu(sampler_cpu_buffer, cpu);
-
-	atomic_xchg(
-			&cb->ext_params,
-			atomic_read(&cb->ext_params)
-				| S390_lowcore.ext_params);
-
+	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
+	cb = &__get_cpu_var(sampler_cpu_buffer);
+	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
 	if (hws_wq)
 		queue_work(hws_wq, &cb->worker);
 }
@@ -764,7 +759,7 @@ static int worker_check_error(unsigned int cpu, int ext_params)
 	if (!sdbt || !*sdbt)
 		return -EINVAL;
 
-	if (ext_params & EI_IEA)
+	if (ext_params & EI_PRA)
 		cb->req_alert++;
 
 	if (ext_params & EI_LSDA)
@@ -1009,7 +1004,7 @@ int hwsampler_deallocate()
 	if (hws_state != HWS_STOPPED)
 		goto deallocate_exit;
 
-	smp_ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+	ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
 	deallocate_sdbt();
 
 	hws_state = HWS_DEALLOCATED;
@@ -1123,7 +1118,7 @@ int hwsampler_shutdown()
 		mutex_lock(&hws_sem);
 
 		if (hws_state == HWS_STOPPED) {
-			smp_ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+			ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
 			deallocate_sdbt();
 		}
 		if (hws_wq) {
@@ -1198,7 +1193,7 @@ start_all_exit:
 	hws_oom = 1;
 	hws_flush_all = 0;
 	/* now let them in, 1407 CPUMF external interrupts */
-	smp_ctl_set_bit(0, 5); /* set CR0 bit 58 */
+	ctl_set_bit(0, 5); /* set CR0 bit 58 */
 
 	return 0;
 }
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index af4d46187a79..731c10ce67b5 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -66,7 +66,7 @@ SECTIONS
 		__machvec_end = .;
 	}
 
-	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	/*
 	 * .exit.text is discarded at runtime, not link time, to deal with
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 92b557afe535..c0220759003e 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -108,7 +108,7 @@ SECTIONS
 		__sun4v_2insn_patch_end = .;
 	}
 
-	PERCPU(SMP_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
diff --git a/arch/tile/kernel/vmlinux.lds.S b/arch/tile/kernel/vmlinux.lds.S
index 38f64fafdc10..631f10de12fe 100644
--- a/arch/tile/kernel/vmlinux.lds.S
+++ b/arch/tile/kernel/vmlinux.lds.S
@@ -60,7 +60,7 @@ SECTIONS
   . = ALIGN(PAGE_SIZE);
   VMLINUX_SYMBOL(_sinitdata) = .;
   INIT_DATA_SECTION(16) :data =0
-  PERCPU(L2_CACHE_BYTES, PAGE_SIZE)
+  PERCPU_SECTION(L2_CACHE_BYTES)
   . = ALIGN(PAGE_SIZE);
   VMLINUX_SYMBOL(_einitdata) = .;
 
diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86
index a9da516a5274..795ea8e869f4 100644
--- a/arch/um/Kconfig.x86
+++ b/arch/um/Kconfig.x86
@@ -29,10 +29,10 @@ config X86_64
 	def_bool 64BIT
 
 config RWSEM_XCHGADD_ALGORITHM
-	def_bool X86_XADD
+	def_bool X86_XADD && 64BIT
 
 config RWSEM_GENERIC_SPINLOCK
-	def_bool !X86_XADD
+	def_bool !RWSEM_XCHGADD_ALGORITHM
 
 config 3_LEVEL_PGTABLES
 	bool "Three-level pagetables (EXPERIMENTAL)" if !64BIT
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
index 34bede8aad4a..4938de5512d2 100644
--- a/arch/um/include/asm/common.lds.S
+++ b/arch/um/include/asm/common.lds.S
@@ -42,7 +42,7 @@
 	INIT_SETUP(0)
   }
 
-  PERCPU(32, 32)
+  PERCPU_SECTION(32)
 	
   .initcall.init : {
 	INIT_CALLS
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 12d55e773eb6..48142971b25d 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,11 +8,6 @@
 
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
-/*
- * For 32-bit UML - mark functions implemented in assembly that use
- * regparm input parameters:
- */
-#define asmregparm __attribute__((regparm(3)))
 
 /*
  * Make sure the compiler doesn't do anything stupid with the
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 53278b0dfdf6..a0a9779084d1 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -509,6 +509,11 @@ do {									\
  * it in software.  The address used in the cmpxchg16 instruction must be
  * aligned to a 16 byte boundary.
  */
+#ifdef CONFIG_SMP
+#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP3
+#else
+#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP2
+#endif
 #define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)			\
 ({									\
 	char __ret;							\
@@ -517,7 +522,7 @@ do {									\
 	typeof(o2) __o2 = o2;						\
 	typeof(o2) __n2 = n2;						\
 	typeof(o2) __dummy;						\
-	alternative_io("call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP4,	\
+	alternative_io(CMPXCHG16B_EMU_CALL,				\
 		       "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",	\
 		       X86_FEATURE_CX16,				\
 		       ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),		\
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9488dcff7aec..e5293394b548 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -676,7 +676,7 @@ void mask_ioapic_entries(void)
 	int apic, pin;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		if (ioapics[apic].saved_registers)
+		if (!ioapics[apic].saved_registers)
 			continue;
 
 		for (pin = 0; pin < ioapics[apic].nr_registers; pin++) {
@@ -699,7 +699,7 @@ int restore_ioapic_entries(void)
 	int apic, pin;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		if (ioapics[apic].saved_registers)
+		if (!ioapics[apic].saved_registers)
 			continue;
 
 		for (pin = 0; pin < ioapics[apic].nr_registers; pin++)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index f65e5b521dbd..807c2a2b80f1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1363,7 +1363,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
  * We must return the syscall number to actually look up in the table.
  * This can be -1L to skip running any syscall at all.
  */
-asmregparm long syscall_trace_enter(struct pt_regs *regs)
+long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
@@ -1408,7 +1408,7 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
 	return ret ?: regs->orig_ax;
 }
 
-asmregparm void syscall_trace_leave(struct pt_regs *regs)
+void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 49927a863cc1..61682f0ac264 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -326,7 +326,7 @@ SECTIONS
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE)
+	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index a2820065927e..88ecea3facb4 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -155,7 +155,7 @@ SECTIONS
     INIT_RAM_FS
   }
 
-  PERCPU(XCHAL_ICACHE_LINESIZE, PAGE_SIZE)
+  PERCPU_SECTION(XCHAL_ICACHE_LINESIZE)
 
   /* We need this dummy segment here */